Using Natural Language Processing to Explore Differences in Healthcare Professionals’ Language On Functional Neurological Disorders: A Comparative Topic and Sentiment Analysis Study

Using Natural Language Processing to Explore Differences in Healthcare Professionals’ Language On Functional Neurological Disorders: A Comparative Topic and Sentiment Analysis Study | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Using Natural Language Processing to Explore Differences in Healthcare Professionals’ Language On Functional Neurological Disorders: A Comparative Topic and Sentiment Analysis Study Md Shadab Mashuk, Yang Lu, Lana YH Lai, Matthew Shardlow, Shumit Saha, and 5 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6018381/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 14 Jan, 2026 Read the published version in Frontiers in Digital Health → Version 1 posted You are reading this latest preprint version Abstract Background Effective communication is essential for delivering quality healthcare, particularly for individuals with Functional Neurological Disorders (FND), who are often subject to misdiagnosis and stigmatising language that implies symptom fabrication. Variability in communication styles among healthcare professionals may contribute to these challenges, affecting patient understanding and care outcomes. Methods This study employed natural language processing (NLP) to analyse clinician-to-clinician and clinician-to-patient communication regarding FND. A total of 869 electronic health records (EHRs) were examined to assess differences in language use and emotional tone across various professionals—specifically, neurologists and psychologists—and different document types, such as discharge summaries and letters to general practitioners (GPs). Sentiment analysis was also applied to evaluate the emotional tone of communications. Results Findings revealed distinct communication patterns between neurologists and psychologists. Psychologists frequently used terms related to subjective experiences, such as ‘trauma’ and ‘awareness,’ aiming to help patients understand their diagnosis. In contrast, neurologists focused on medicalised narratives, emphasising symptoms like ‘seizures’ and clinical interventions, including assessment (‘telemetry’) and treatment (‘medication’). Sentiment analysis indicated that psychologists tended to use more positive and proactive language, whereas neurologists generally adopted a neutral or cautious tone. Conclusions These findings highlight significant differences in communication styles and emotional tones among professionals involved in FND care. The study underscores the importance of fostering integrated, multidisciplinary care pathways and developing standardised guidelines for clinical terminology in FND to improve communication and patient outcomes. Future research should explore how these communication patterns influence patient experiences and treatment adherence. Functional Neurological Disorders (FND) Natural Language Processing (NLP) Topic modelling Sentiment analysis Healthcare Professionals Electronic Medical Records Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 Figure 7 1. INTRODUCTION 1.1 Functional Neurological Disorder (FND) and the importance of clinician-patient communication Functional Neurological Disorder (FND) is a neurological condition caused by a functional rather than a structural disorder, i.e., by changes in the brain network, rather than in the brain structure [ 1 , 2 ]. Symptoms of FND, which include tremor, paralysis, dystonia, sensory disturbances, speech difficulties, and dissociative seizures, are genuine and often likely to interfere with how a person functions and copes with daily life [ 1 , 3 ]. The burden of this disease is remarkable as FND is associated with high rates of distress and disability [ 2 , 4 – 6 ] and a substantial reduction in quality of life, as well as impairments across multiple life domains, such as employment, socialisation, ability to be independent and experience of social stigma [ 7 – 9 ]. Furthermore, evidence indicates that FND is the second most common reason for neurological consultations after headaches [ 6 , 10 ] and is linked to substantial healthcare costs for both individuals and services [ 11 ], with estimated costs exceeding US $ 1 billion/year in the United States [ 12 ] and £3 billion/year in England alone [ 13 ]. Healthcare costs may be further enhanced by the frequent misdiagnosis of this disorder [ 14 ] and an average diagnostic delay of 7.2 years [ 15 ], which contributed to FND being labelled as medicine’s “silent epidemic,” psychiatry’s “blind spot” and a “demonised diagnosis” [ 16 – 19 ]. Fundamental to an individual’s understanding and management of their FND diagnosis is the communication and therapeutic relationship with healthcare professionals [ 20 , 21 ]. Literature on FND highlighted that relationships with clinical professionals can, at times, entail negative interactions with FND patients [ 22 – 25 ]. More specifically, studies on this topic highlighted that healthcare professionals in different roles, e.g., neurologists, general practitioners (GPs) and nurses, often express stigmatising views of FND patients as feigning their symptoms and pretending not to have control over them [ 26 , 27 ]. Additionally, they can perceive FND patients as ‘difficult’ and frustrating, which in turn can lead patients to feel misunderstood, disbelieved, and rejected by their physicians [ 22 ]. Professionals’ negative attitudes are often conveyed via the language they use in routine interactions with FND patients, and some studies shed light on professionals’ use of stigmatising language concerning FND, including terms such as “fake” or “hysterical seizure” [ 27 ] and disparaging phrases such as “it’s all in your head” [ 16 ]. A recent review [ 28 ] reported how common ways used by healthcare professionals to describe individuals with FND included “attention-seeking”, “manipulative”, “annoying”, “impossible to help”, “troublesome”, “challenging”, and “frustrating” [ 13 , 25 , 26 , 29 – 31 ]. In contrast, FND patients reported being made to feel as if they were feigning or exaggerating their symptoms [ 32 , 33 ]. This highlights the need to develop a shared consensus on FND terminologies through standardising vocabulary across clinical professionals, in order to improve patient-clinician communication and reduce patient stigmatisation [ 34 – 36 ]. The necessity for shared vocabularies supporting multidisciplinary work in FND is also underscored by existing literature, which reveals both distinct and overlapping realms of expertise between the two types of professionals most frequently involved with the treatment of FND patients, i.e., neurologists and psychologists [ 37 , 38 ]. Neurologists’ proficiency in diagnosing FND and identifying its symptoms through its distinguishing physiological features is well-documented [ 38 , 39 ]. Psychologists, conversely, are often described in FND literature as focusing on the more intrinsic ‘root factors’, behaviours, personality traits and psychosocial sequelae that are linked to FND [ 40 ]. The need for complex, multidisciplinary approaches to treating FND has often been outlined as necessary [ 41 , 42 ], although challenges persist in adopting clear, standardised guidelines to communicate with patients and in sharing information across services and healthcare professionals [ 43 , 44 ]. One key factor in building collaborative, multidisciplinary approaches lies in the need to analyse the language used by healthcare professionals who support people with FND, to understand their vocabulary and the ‘emotional tone’ underpinning their communications. This would allow for a better understanding of their core beliefs and conceptualisation of FND, and how these might influence both their relationships with patients and the overall quality of the support offered. 1.2 The application of Artificial Intelligence (AI) and Natural Language Processing (NLP) to the analysis of clinician-patient interactions Natural Language Processing (NLP) is a technique within the broader field of Artificial Intelligence (AI) that draws from linguistics and machine learning and aims at quantifying written language as vectors that can be statistically evaluated. It offers to broaden the reach of computational analysis to include human experience, emotion, and relationships [ 45 , 46 ], and its application in the mental health domain has broadened exponentially in the past two decades [ 47 – 50 ]. NLP is commonly applied to electronic health records (EHRs) to process large quantities of unstructured (human-authored) text, in order to return information about different text aspects, such as syntactic processing, semantic analysis (e.g., capturing meanings from single words or groups of words), and detecting relationships among terms and concepts [ 51 – 54 ]. Electronic health records are a rich source of data in the analysis and treatment of patients [ 55 , 56 ], and NLP has proven to be effective in analysing and extracting information from clinical text data [ 57 – 59 ]. NLP applied to EHRs might be particularly useful in exploring health professionals’ vocabularies, as written text is likely to reflect the specific variations in their knowledge and expertise and their use of lay and professional vocabularies [ 58 ]. NLP analysis on healthcare professionals’ vocabularies has been applied in a variety of settings, for example, to explore and bridge the gap in vocabularies between healthcare professionals and their patients as well as people looking for health information online [ 60 – 63 ]. A specific NLP-related technique, known as ‘topic modelling’, has been increasingly used over the past few years to analyse textual data in EHRs to identify recurrent keywords and discussion themes [ 64 ] and identify people’s perspectives on their mental health issues [ 65 ]. Increasing interest in the healthcare domain has also been given to another NLP-derived technique, sentiment analysis, which has also been utilised to understand the general tone and emotion of clinical narratives [ 66 ]. In other studies [ 67 ], EHRs such as hospital discharge notes were analysed to determine potential readmission and mortality risk from the ‘sentiment’ of the notes, highlighting the multifaceted potential value of capturing ‘emotional tones’ from EHRs to inform improvement in care pathways. 1.3. Identifying gaps and opportunities While existing studies highlight the potential of NLP in healthcare research, its role in the FND domain has received little consideration. Moreover, the comparative analysis of professional discourse between neurologists and psychologists on FND through topic modelling and sentiment analysis remains unexplored. By applying these techniques on written documents produced by neurologists and psychologists supporting patients with FND, the present study sought to understand how different professionals communicate about and perceive FND. In turn, understanding clinical narratives, as well as their differences across care professionals, can inform training, clinical practice, and interdisciplinary collaboration, ultimately fostering a healthcare environment where the nuances of FND are more deeply understood and addressed with greater effectiveness. To the authors’ knowledge, this is the first study employing well-known NLP techniques to comparatively analyse the narratives and underlying emotional tones of different healthcare professionals working in FND care. 2. METHODOLOGY The current study aimed to leverage the potential of NLP to conduct an in-depth analysis of the vocabularies used and emotional tones expressed by different groups of healthcare professionals supporting individuals with FND. Two NLP techniques, topic modelling and sentiment analysis, were used to extract and classify electronic clinical documents from the outpatient services of the Salford Royal Hospital (Northern Care Alliance NHS Group Trust), a large hospital located in the Northwest of the UK. Ethical approval to extract clinical documents from hospital records was obtained from the R&I department of the Northern Care Alliance NHS Group Trust (approval number 22HIP47). 2.1. Data Source More than a thousand clinical documents written by clinical professionals from 2011 to 2022 were extracted from EHRs. These documents were produced by healthcare professionals supporting people with FND in different roles, which, for analysis purposes, were divided into three categories: neurologists, psychologists and ‘others’ (e.g., physiologists, GPs and pain experts). The retrieved documents were independently checked for quality and completeness by four research group members (two research assistants, a clinical psychologist and a neurologist). Incomplete documents or records that were deemed uninformative (e.g., documents only containing very short information) were excluded. All documents were manually anonymised by research assistants employed at the Salford Royal Hospital, by removing any identifiable information before study commencement. The date, type of document (i.e., letter type), professional group category (i.e., neurologists, psychologists or others) and raw unstructured text were preserved and provided as a Word file to researchers. A Python script was written to parse the document, retrieve, and store the relevant information of each letter into a csv file, and create a structured corpus containing the ‘document type’, ‘professional group’, ‘date’ and ‘text’. The corpus was further cleaned for missing values, replacements, and misspelled medical terminologies, which were identified through manual observation. Of the 978 documents identified for analysis, 550 were written by neurologists, 319 by psychologists, and 108 were unlabelled, hence they were categorised as “others”. The total word count per document ranged between 200 and 1200 words. Focus was given to the labelled professional groups (i.e. neurologists and psychologists), giving a total sample size of 869 documents. The documents were also categorised by types: i.e. referrals, clinic letters, GP letters, assessments and discharge letters. Details of the different letter types and contents are provided in Appendix 1. 2.2. Framework of Exploratory Analysis In this section, the general framework of the exploratory analysis is presented in Fig. 1 . In addition to the steps discussed above, NLP preprocessing steps such as tokenization, bigrams, trigrams, lemmatization and removal of stop words were also applied. Then, the state-of-the-art topic modelling and sentiment analysis techniques were used to identify differences in the usage of words, topics of discussion, and tone/sentiment across healthcare professionals (i.e. psychologists and neurologists), as well as by document types. 2.2.1. Preprocessing To identify the topic of discussion, preprocessing of the data was carried out (Fig. 1 ). The stages of data processing included the following: Tokenisation; Texts are lower cased and nltks’ word tokenise library was used to tokenise sentences into tokens of words. Custom tags such as titles (ms, mrs, mr, miss), date and time, special characters and a minimum word length (4) were also applied to ensure that only the most relevant tokens were left. Parts of speech (POS) tags (NOUN) were also applied. Noun-only POS tags were used as we were only interested in identifying important keywords. Ngrams; Bigram and Trigram models were also created and applied using Gensim’s Phrases library for any tokens that can be combined as bigram or trigram. Lemmatisation; Lemmatisation was applied using nltks’ wordnet/morphy library as appropriate. Stop words; Stop words were removed using Gensim’s simple preprocess library. To optimise the quality of topic keywords, some common and high-frequency junk terms found across both psychologists’ and neurologists’ records were removed during tokenisation. This was done based on empirical observation by running the topic model several times and identifying keywords that commonly occurred within the topics. The clean data was then passed on to the topic modelling algorithm. 2.2.2. Topic Modeling To understand the differences in how psychologists and neurologists approach FND patients, it is important to identify common discussion topics and the words associated with each topic. To do so, topic modelling, a form of computational text mining based on word co-occurrence within a corpus, was used. Topic modelling algorithms take a collection of documents as input, discover recurring ‘themes’ discussed within the collection (topics), and then determine the degree to which each document presents each of the topics identified [ 68 ]. One of the most widely used unsupervised document modelling techniques, Latent Dirichlet Allocation (LDA), was applied. LDA is a generative probabilistic Bayesian model providing a representation of a document in the form of topics and topic probabilities, and it is claimed to be the simplest and most widely used topic modeling technique in fields outside of computer science [ 68 , 69 ]. Further details related to the underlying mathematical principles can be found in the original paper [ 70 ]. In our study, Gensim’s LDA model for Python was used to generate the topics of discussion. Before generating the topics, the optimal topic number was estimated by tuning the hyperparameter α, which is the Dirichlet prior to the per-document topic distribution and determines theta (θ). θ is the distribution of words per topic that, in turn, determines the shape of the overall distribution of topics. The model rearranges the topic distribution within the documents and keyword distribution within the topics to achieve good probabilities of topic-keywords distribution. For different values of α, the corresponding coherence plots were generated and used to estimate the optimal topic number. The final LDA model was then configured accordingly and used to generate the topics for each set of documents. Figure 2 shows that the coherence metric started with a value closer to zero before falling sharply approximately between topics 6 and 4 and then flattening out for α = 0.001 and 0.01 for psychology and neurology records, respectively. The higher coherence value signifies dominance and importance of topic within the analysed data set. When α = 5, the coherence plot does not show a clear distinction between dominant topics and shows a gradual fall; similarly, when α = 1000, it again shows a reasonably gradual fall from topic 8 onward. In addition, the coherence value is close to zero for the neurology and psychology data when α = 1000 but they do not seem to be converging quickly enough as is the case with α = 5 values. As such, there is the need to achieve a right balance between the topic distribution not being too widely spread across the document, and a topic number which has a coherence value reasonably closer to zero. Hence, it can be concluded that it is reasonable and safe to choose the optimal topic number as 5 as it is more dominant and coherent in both the neurology and psychology dataset and also choose the value α = 0.01 as the optimal value for creating the final model. Based on the discussion above, the following hyperparameter configuration was used in the final model for both scenarios: 2.2.3. Sentiment Analysis Sentiment analysis is a computational method for determining the emotional tone behind words. It is essential for understanding the attitudes, opinions, and emotions expressed in textual data. In this study, sentiment analysis was conducted to explore the sentiment levels of neurologists and psychologists as reflected in various types of clinical documentation and also verify the topics and themes of discussion observed from the topic modelling analysis. Two pre-trained sentiment models, VADER and Flair, were implemented. VADER is a lexicon and rule-based sentiment analysis tool [ 72 ] deployed to assess sentiment levels across different file types within the clinical documentation of each professional group. Its efficiency and sensitivity to subtle linguistic cues make it particularly suitable for analysing the structured format and concise language often found in such documents. However, it does not examine the context-dependent nuances of the sentences. Therefore, while VADER’s lexicon-based may be a fast and effective tool for processing large volumes of documents, it may not fully capture the context-dependent nuances of sentiment. Flair’s deep learning approach fills this gap by analysing sentences in their entirety, considering the context to provide a nuanced understanding of sentiment. This is crucial for understanding complex narratives found in referral letters or discharge summaries, where the sentiment may be influenced by medical conditions, treatment outcomes, or patient experiences. Also, clinical documents present a unique challenge due to their use of specialised medical terminology. Together, these models offer a comprehensive sentiment analysis that can be used to cross-validate each other's output since the models are not specifically trained with medical terminologies. This tailored application can enhance the reliability of sentiment analysis and contribute valuable perspectives on the emotional and professional dynamics within clinical settings. 3. RESULTS 3.1 Topic modeling The topic analysis was divided into two stages. In the first stage, words and themes of topic discussions between psychologists and neurologists were compared. In the second stage, a detailed analysis was conducted on psychology and neurology records according to letter types. 3.1.1 Professional group comparison: identifying main differences in communication between neurologists and psychologists Firstly, the main differences between the two professional groups were considered across all documents (regardless of the document type – e.g., discharge letter). Figures 3 a and 3 b below show the most salient terms used by neurologists and psychology professionals in all clinical documents. Additionally, they also show inter-topic distribution plots, which demonstrate the ‘importance’ of each topic (i.e., the frequency with which that topic was addressed in clinical documents). Both psychological and neurological medical records had evenly distributed and similar-sized topics of discussion, with some contributing less to the discussion. Most of the topics were distinct from one another, although there were some overlaps between topics 1 and 2 in the psychology records. To maintain the quality of topic distribution, some common terms widely used by both professional groups, such as “diagnosis”, “session”, “therapy”, “service”, “attack”, and “episode”, were removed before generating the topics. Figure 3 . Inter-topic distribution plot showing the uniqueness, spread and size of the topics The top thirty salient terms across all the psychology documents – as seen in the inter-topic distribution plots (Fig. 3 a above)- highlighted the frequent use of terms related to inner/subjective experiences of people with FND (e.g., ‘experience’, ‘stress’ and ‘awareness’) and the emotional and psychological correlates of living with their symptoms (e.g., ‘feeling’, ‘impact’, ‘control’ [or lack of thereof] and ‘pressure’). It is also worth noticing that the most commonly used terms include positive and proactive language, such as ‘action’, ‘progress’ and ‘opportunity’. Overall, in psychology professionals’ language, there seems to be a well-balanced importance given to patients’ treatment (including aspects such as medication, care approaches and intervention planning) as well as more personal dimensions, such as the psychological sequelae of living with FND. Table 1 below shows the important keywords for psychology documents based on topics of discussion. Although the topic modelling algorithm produced five topics, as seen in Fig. 3 , Table 1 only showed the four most relevant topics of discussion as these were deemed to be the most representative of relevant aspects in clinicians’ communication with and about patients. For each topic, some of the most relevant keywords are reported, together with a topic name based on the semantic commonalities among topic keywords. Following the identification of topics through topic modelling, a human-led process of interpretation was applied to the topics retrieved. As several authors pointed out [ 55 , 73 – 75 ], the topics retrieved by topic modelling techniques need to undergo a process of sense-making based on the researcher’s understanding of words reported as strongly associated with each topic. To do this, an interpretation process was performed independently by the study principal investigator (MSM) and a researcher team member with clinical expertise (DDB). Interpretations and themes were compared, and discrepancies were resolved by consensus. Table 1 Keywords and topics: Psychology documents Psychology Documents Topic No. Topic Name Selected keywords 1 Psychoeducation about FND approach, information, change, exercise, compassion, respect, health, body, trauma 2 Diagnosis and prognosis assessment, disorder, symptom, progress, stress, year, appointment, history, treatment 3 Pragmatic support for symptom management appointment, telephone, letter, strategy, treatment, support, health, medication, breathing 4 Emotional and social support for symptom management feeling, pressure, anxiety, management, family, emotion, sensation, awareness, communication Topic 1 (Psychoeducation about FND): The dominant terms revolved around discussions of factors and experiences related to seizures, access to information, and approaches to managing FND (e.g., adopting self-compassion, and taking care of one’s mental and physical health). Topic 2 (Diagnosis and prognosis): This theme focused on the diagnostic process both from a medical perspective (with related keywords such as ‘assessment’ and ‘disorder’) and from a more subjective one, with terms such as ‘stress’ that suggest a consideration of how the diagnosis of FND can impact on people’s wellbeing and personal experiences in different areas of their lives. Topic 3 (Pragmatic support): The dominant terms referred to objective ways of obtaining support for FND symptoms, including appointments, receiving clinical letters, adopting different strategies for treatment and using medication. Topic 4 (Emotional/personal support): Although similar to the previous topic in its focus on long-term management strategies (e.g., ‘management and ‘review’), this topic also seemed to stress a social and emotional component that may play a key role in coping with FND in the long term. Indeed, there were terms such as ‘family’, ‘emotion’, ‘sensation’ and ‘feeling’ that seemed to refer to the importance of emphasising relational and emotional components of symptomatic management in FND. Neurologists’ conversations, on the other hand, seemed to show different patterns in their communications with and about clients (Fig. 3 b). More specifically, the 30 most salient terms across all neurology documents showed that their discussion mostly revolved around seizure attacks, admission and potential actions taken during those episodes. The focus was also on patients’ health and their treatment, history and medication, as well as the duration of attacks, due to using terms such as ‘month’, ‘night’, ‘minute’, and ‘today’. A closer look at the topic distribution in Table 2 showed topic-wise discussion themes mentioned by neurologists. Table 2 Keywords and topics - Neurology documents Neurology Documents Topic No. Topic Name Selected keywords 1 Assessment of FND and contributing/maintaining factors medication, seizure, assessment, patient, admission, management, clinic, stress, sleep, neuropsychology 2 Treatment planning seizure, telemetry, treatment, medication, admission, discharge 3 Management of FND symptoms medication, today, year, appointment, week, attendance, management 4 Recommendations for support and long-term management citalopram, behaviour, health, husband, disturbance, awareness, management Topic 1 (Assessment of FND and contributing/maintaining factors): The dominant theme revolved around discussions about the assessment of FND symptoms (‘seizure’ and ‘assessment’), medication, and characteristics of service provision (‘e.g., admission’ and ‘neuropsychology’). Topic 2 (Treatment planning) – The second theme placed an emphasis on strategies for ongoing monitoring aimed at establishing best treatment options (e.g., ‘telemetry’, ‘video’, ‘treatment’ and ‘medication’) according to both patient symptoms (‘seizure’) and other conditions (‘pregnancy’). It also contained a reference to different stages of the patient journey, such as ‘admission’ and ‘discharge’. Topic 3 (Management of FND symptoms) – Quite similar to the previous theme, this third theme focused on different aspects of managing FND, including taking ‘medication’, attending ‘appointments’ and adopting strategies for ongoing ‘management’ of this condition. Topic 4 (Recommendations for support and long-term management) – this theme included terms related to modifications in ‘behaviour’ and ‘health’ attitudes to manage FND symptoms in the long term. Interestingly, though, there were some terms related to key aspects that neurologists appear to consider as crucial in FND management: the involvement of patients’ family and close network (‘father’, ‘husband’ and ‘friend’), attention to the person overall mental health (‘citalopram’) and psychological wellbeing (‘awareness’ and ‘disturbance’). Following these analyses, a further set was performed to gain a more granular understanding of communication differences between the two professional groups (psychologists and neurologists) across different document types (referral letters, clinic letters, GP letters, assessment and discharge letters). The topics retrieved and the related most relevant keywords topic-wise are illustrated in Appendices 2–6, and the main differences that emerged are presented descriptively below. 3.1.2. Group comparisons across document ‘types’: exploring document types separately better to understand differences in communications between neurologists and psychologists Once the main language differences between psychologists and neurologists had been outlined, our analyses progressed toward further investigating the granularity of these differences by analysing their communication patterns and topics, focusing on each document type (referral letters, clinic letters, GP letters, assessment letters, and discharge letters) separately. 3.1.2.1. Referral letters Both referral letters written by neurologists and by psychologists showed some commonly recurring topics, such as the reference to FND symptoms (‘seizure’, [alteration in] ‘consciousness’) and mention of assessment, intervention planning and management of FND (‘assessment’, ‘intervention’, ‘hospital’, ‘outpatient’ and ‘clinic’). Another important commonality between the two groups is the reference to aetiological and maintaining factors of FND, such as ‘trauma’ and ‘stress’). The main differences between the two professional categories were reflected in the use of medical terminology (e.g., ‘disorder’), which was more frequent in neurologists’ referral letters as compared to psychologists’. On this note, neurologists also seemed to refer more often to other medical conditions (e.g., ‘epilepsy’ and ‘autism’, ‘drug’ [abuse] comorbid to FND, that they may have considered and/or assessed for during patient visits. They also mentioned a broader list of FND-related medical terms, such as ‘convulsions’, [lack/loss of] ‘consciousness’ and ‘myoclonus’. Interestingly, psychologists, but not neurologists, mentioned that patients were usually women, therefore giving relevance to personal characteristics such as their gender. They also placed great importance on the overall quality of patients’ lives by frequently paying attention to pain (‘painkillers’, ‘headaches’) and quality of ‘sleep’. They also mentioned the term ‘goal’, which in their referral letters was often used to indicate the goals agreed upon with the patient and to achieve which a referral to another service might have been needed (e.g., psychological services offering trauma-focused therapy). Neurologists showed appreciation of the ‘burden’ that FND can represent on patients’ lives and mentioned this term in a few of their referral letters, mostly to indicate the need and/or urgency for a patient to receive support. 3.1.2.2 Clinic letters The split between a ‘medical focus’ versus a more comprehensive attention to a range of factors influencing FND in the two professional groups is perhaps even more evident in the topics retrieved in the clinic letters. Whilst neurologists’ discussions revolved around the ‘brain’ and physiological manifestations of FND such as ‘myokymia’, ‘seizure’ and ‘memory’, psychologists’ vocabulary encompassed a range of terms that showcased their appreciation for different FND-related and personal aspects of people's lives. Among these, there were ‘childhood’ experiences, ‘feeling[s] and emotions[s]’ reported in clinical appointments, and an appreciation for the subjective experience of FND-related ‘stress’, ‘overwhelm’ and ‘pressure’ experienced by patients. There was also a reference to psychological correlates of FND, such as ‘dissociation’, and a mention of cognitive, emotional and behavioural coping strategies (e.g., ‘belief’, ‘habit’, ‘commitment’), representing a unique feature in psychologists’ communication. Although terms such as ‘partners’ and ‘family’ - referring to personal dimensions of people’s lives- were also present in neurologists’ communication, these terms were used in a more factual/descriptive way, e.g., to describe the caregiver(s) accompanying patients to neurology appointments, rather than to convey an appreciation of patients’ social/family network and the role they might play in FND management. 3.1.2.3 GP letters The trend described above (using a medical vocabulary vs a more holistic one) was once again evident in the topics retrieved from letters sent to GPs. All the five topics that were more relevant in neurologists’ communications with other medical professionals (GPs) contained a reference to symptoms, diagnostic and prognostic processes (‘NEAD’, ‘recovery’) and types of support and services (e.g., ‘neurology’ and ‘community’ services, ‘letter’ and ‘telephone’) that may be part of the patient journey. Words such as ‘friend’ were present, but as above, they were mostly used to provide contextual information, as exemplified by the following excerpt from a neurologist’s letter to a GP: “ Her friend (…) says that (…) was at her home and was about to sleep on her couch when she started staring into space ”. 3.1.2.4 Assessment letters The topics retrieved in assessment letters showed the different conceptualisations of the assessment processes in the two professional groups considered, with once again a medical and a biopsychosocial model emerging from clinicians’ written communications. The primary dimensions considered in neurologists’ assessments are physiological ‘signs’ such as ‘tremor’, service engagement (‘treatment, ‘attendance’, ‘history, ‘month’), medication (‘lamotrigine’, ’risperidone’) and comorbidities that may be present or warrant further exploration (‘anxiety’ and ‘depression’). The term ’childhood’, indicating a consideration for early traumatic experiences influencing FND, was present but was retrieved as part of topic five, meaning its use was not so frequent. Conversely, psychologists’ assessment letters offered proof of the importance of many factors when considering the best care options for patients. More specifically, a set of medical/physiological aspects was considered (‘stress’, ‘seizure’, ‘medication’), but this was in conjunction with psychosocial aspects (‘exercise’, ‘emotion’, ‘relaxation’, ‘awareness’) that showed how psychologists think of FND patients from a perspective of complexity, encompassing disorder-related dimensions but also opportunities for symptomatic management through engagement in activities that can improve psychosomatic wellbeing. In this regard, it was worth noticing the presence of positive and encouraging terms in their vocabulary, such as ‘opportunity’, ‘strategy’ and ‘development’. 3.1.2.5 Discharge letters In line with previous considerations, the analysis of discharge letters evidenced the presence of a communicative approach in neurologists’ written text that favoured objective/factual information to motivate patient discharge, as evidenced, for example, by salient terms composing topic one (e.g., ‘discharge’, ‘admission’, ‘neurology’, ‘assessment’, ‘gynaecology’, ‘medication’, ‘history’, ‘telemetry’, ‘haemoglobin’, ‘pregnancy’). Psychologists, instead, tended to use terms referring to a more general appraisal of patients’ conditions as characterised by ‘deterioration’, ‘alcohol consumption’ leading to a feeling of ‘concern’, but also by the appreciation for ‘progress’ and ‘goals’ that patients were pursuing in their journey. Further to this point, psychologists’ discharge letters tended to refer to ‘goals’ and future directions when informing suggestions or more direct requests for patients to access additional support upon discharge. 3.2 Sentiment Analysis Based on the results from topic modelling, the next step was to use sentiment analysis to investigate how the two health professional groups' different choices of words and approaches signaled the ‘emotional tone’ underpinning their interactions. The section below presents the tone variation between professional groups (psychologists and neurologists) and among document types. The previously mentioned pre-trained sentiment analysis models (VADER and Flair) were used to cross-validate the sentiment scores. A subset of patient records was analysed by domain experts to validate the tone of the patient records, and the results across letter types were implemented to further verify the model’s sentiment output. It is important to note, in this regard, that the terms ‘positive’, ‘neutral’ and ‘negative’ emotional tone are used to refer to the overall emotional tone expressed within the text, essentially analysing whether the general sentiment conveyed by healthcare professionals in their letters is favourable, unfavourable, or neutral [ 76 ]. 3.2.1 VADER sentiment analysis The compound sentiment scores across the two professional groups according to letter types are presented in Fig. 4 . Based on the plots, it can be inferred that neurologists’ interactions with patients across all the stages of care tend to be quite cautious, which could explain the pronounced negative score. For psychologists, assessments and clinic letters tend to be more positive compared to GP letters and referral letters, with discharge letters showing a high level of positivity. This was reflected when looking at the compound sentiment score distribution of the professional groups through the violin plots in Fig. 5 . Psychologists seemed to take a more positive, friendly, and informal approach than neurologists, with the bulk of their records leaning towards the positive side. Looking at the non-compound sentiment scores, it seemed that both psychologists and neurologists tended to use neutral sentiment keywords, with similar distributions of positive and negative sentiment keywords. 3.2.2 Flair sentiment analysis To cross-validate our sentiment results from VADER, the Flair model was also used to generate sentiment scores, as seen in Figs. 6 and 7 . The results showed similar outcomes to our findings derived from the VADER model. As seen in Fig. 7 , neurologists’ sentiment scores were clearly situated at the negative end across all the letter types except for referral letters. Psychologists, instead, seemed to show a more positive and friendly approach when dealing with patients. This is further reflected in Fig. 6 , referring to the analyses of patient records across the two professional groups. Overall, neurologists tend to be more critical and reserved in their approach when dealing with FND patients. 3.3 Expert Review To evaluate the performance of the sentiment model for medical notes analysis, an expert review was conducted to compare the analysis results with the domain expert’s opinions. Approximately 100 medical records were first selected from the neutral, positive, and negative groups (34, 33, 33, respectively) as the ground truth. Then, a healthcare professional (expert clinical psychologist) who was ‘blind’ to the results of the sentiment analysis was asked to rate the records selected, classifying them as positive, negative, and neutral. The results obtained were then compared with the sentiment classification results of VADER using the compound sentiment score and the non-compound percentage score of negative, positive, and neutral words in each record. The results are tabulated below (Table 3 ). There was a 61% match using the compound sentiment score. For the remaining 39%, a high percentage of the records not matching was mostly one-degree differences, e.g., model rated negative, but expert rated neutral, or model rated positive, expert rated neutral, or vice versa. In total, 17 nonmatching records were falling into the ‘negative to neutral/neutral to negative’ labels, with the majority being from neurology records (11/17). Looking at the ‘positive to neutral/neutral to positive’ group, there were 13 nonmatching records, with the majority being from the neurology records (11/13). There were only nine records showing two-degree differences, i.e., model rated positive, expert rated negative (or vice versa), with eight of such cases showing the expert assigned negative sentiment labels, with most of them being neurology records (8/9). There are different possible explanations for the presence of these expert/model divergences. One lies in the VADER model not being trained with medical terminologies related to FND patients and not considering the context in which clinician-patient conversations take place. This might help to explain why the expert, and more widely, healthcare professionals, might tend to have more neutral or pessimistic views of the ‘sentiment’ underlying a conversation. In other words, whilst the model might render a ‘positive’ label based on the presence of positive terms in the document analysed, clinical professionals are likely to consider the content of that document in light of wider dimensions – e.g., the severity of patient’s symptoms (despite possible positive events or improvements occurring) or whether a patient is experiencing pivotal life changes that might bear a negative influence on their overall mental health. Furthermore, it appears evident that most ‘mismatches’ are present in documents produced by neurologists, which calls into question whether a more medicalised language could lead to greater difficulties for AI models to capture the underlying ‘sentiment’ of the conversation. Table 3 Expert review results Metric Observation Compound sentiment score 61 matches One-degree difference (neg to neutral or neutral to neg) 17 One-degree difference (pos to neutral or neutral to pos) 13 Two-degree difference (pos to neg or neg to pos) 9 4. DISCUSSION The results of this study provide significant insights into the linguistic and tonal differences between neurologists and psychologists when addressing FND patients in written clinical documents. By leveraging NLP techniques and sentiment analysis, the study highlighted how these professional groups differed in their clinical discourse, which may have direct implications for patient care, communication, and treatment approaches. This discussion will interpret these findings in light of their clinical relevance, theoretical implications, and potential for future research and practice. 4.1. Topic modeling: Thematic differences between psychologists and neurologists The topic modeling analysis revealed clear distinctions in the focus of communication between psychologists and neurologists, which underscores the different professional orientations of these two groups. Psychologists predominantly focused on themes related to emotional and subjective experiences, personal care, and the long-term management of symptoms. This is evident in the frequent use of words like ‘stress’, ‘awareness’, ‘feeling’ and ‘support’, which reflect a holistic and patient-centred approach. This finding aligns with the role of psychology in FND, which is not only to diagnose and treat this condition, but also to address how patients manage their symptoms in their everyday life, help them to improve their overall mental health and quality of life, and decrease medical service utilisation [ 77 – 81 ]. On the other hand, neurologists used more medical and technical language, with their communication centring on clinical and diagnostic terms such as ‘seizure’, ‘medication’, ‘assessment’ and ‘history’. This is reflective of the medical model that neurologists employ in their treatment of FND, where the emphasis is on identifying physiological abnormalities and managing symptoms through clinical interventions [ 82 ]. This also aligns with evidence on neurologists’ pivotal role in diagnosing FND, explaining its mechanisms to patients and suggesting appropriate medical treatment to reduce the burden of FND symptoms [ 83 , 84 ]. In other words, the findings of the present study seem to suggest that neurologists’ communications are more likely to emphasise the patient’s immediate clinical state and medical treatment, while psychologists take a broader view that encompasses emotional, psychological, and social factors. Importantly, this divergence in focus may reflect differences in training, professional responsibilities, and expectations placed upon these healthcare professionals. This finding has implications for interdisciplinary collaboration, as it suggests that optimal care for FND patients requires the integration of both perspectives: the neurological focus on symptom management and the psychological attention to emotional support and coping mechanisms. 4.2. Document types and professional communication styles The analysis of specific document types (referral letters, clinic letters, GP letters, assessment letters, and discharge letters) shed further light on the granularity of communication differences between the two groups. Across all document types, psychologists tended to focus on a broad array of factors influencing FND patients, including psychosocial aspects such as childhood trauma, quality of life, and emotional coping strategies. Neurologists focused more narrowly on clinical symptoms, diagnosis, and medical treatment plans. For example, in referral letters, neurologists' communications were more clinical and diagnostic, with references to seizure types, medical history, and medications. Psychologists, by contrast, incorporated a broader understanding of the patient’s life, discussing personal goals and emotional factors such as pain, stress, and sleep quality. This suggests that psychologists may be more likely to take a holistic view of the patient when communicating with other professionals, while neurologists may focus on ensuring that other clinicians are aware of the patient’s medical condition and treatment needs. More generally, the neurologists’ tendency to use medical and diagnostic-centred communication and psychologists’ proclivity to adopt a biopsychosocial perspective on assessment and care for FND was evident across all types of documents analysed. This calls for effective interdisciplinary collaboration to ensure that patients receive comprehensive care that addresses both their medical and psychological needs [ 85 , 86 ]. A failure to appreciate the complementary nature of these communication styles could lead to fragmented care, with one aspect of the patient’s experience being overlooked [ 87 ]. This integration in domain knowledge and communication styles appears to be even more relevant when considering that for the past half-century, the clinical management of FND has been subject to a great deal of fragmentation, with a paucity of care pathways mutually agreed upon between neurologists and psychiatrists [ 88 ]. Besides being potentially detrimental to FND patients, this fragmentation often leads to poor outcomes and frustrations for both patients and professionals [ 89 ]. In light of these considerations, studies such as the current one offer support for the need for a more substantial shift in these care models and the consequent recognition of the need for truly multidisciplinary and integrated care [ 90 , 91 ]. 4.3. Sentiment analysis: Tone and emotional engagement The sentiment analysis results provided another layer of insight into how psychologists and neurologists differ in their interactions with FND patients. Across all stages of care, neurologists tended to have a more cautious and often negative tone, while psychologists exhibited a more positive and emotionally supportive tone. This difference is particularly salient in the context of patient care, as the tone of communication can significantly impact a patient’s experience, trust, and engagement with their treatment plan [ 92 – 94 ]. The positive language in psychological documents, such as ‘opportunity’, ‘progress’ and ‘support’, may help to foster a more hopeful and proactive patient mindset, which evidence increasingly suggests can be particularly important in the management of chronic conditions like FND [ 95 , 96 ]. Conversely, the more negative tone found in neurologists’ documents may reflect the cautious and often uncertain nature of medical diagnosis and treatment in FND, a condition that is still not fully understood and can be challenging to treat [ 21 , 97 ]. Neurologists may also focus more on risk factors, complications, and the need for medical interventions, which could explain the prevalence of negative sentiment. While this cautious tone is likely a reflection of the complexities and challenges of managing FND, it may also have unintended consequences for patient engagement and satisfaction. For instance, patients may feel discouraged or less hopeful if their interactions with neurologists are perceived as overly negative or detached. This datum appears to be even more important when applied to FND, as there is abundant evidence regarding the role that problematic conversations and stigmatising attitudes from clinicians can have on FND patients’ disease management, access and experiences of care[ 98 – 100 ]. The differences in sentiment between the two professional groups also raise important questions about how tone influences patient outcomes. Research in healthcare communication has shown that positive, supportive language can improve patient satisfaction, adherence to treatment, and even health outcomes [ 101 – 103 ]. In contrast, negative or overly cautious language may contribute to patient anxiety, dissatisfaction, and disengagement [ 100 , 104 , 105 ]. Therefore, these findings suggest that neurologists may benefit from incorporating more positive and empathetic language into their communications, particularly when discussing treatment options and prognosis with patients. 4.4. Expert review and model validation The expert review of the sentiment analysis provides a critical reflection on the limitations of using NLP models like VADER and Flair in clinical contexts. The relatively low match (61%) between the model’s sentiment classification and the expert’s ratings highlights the challenges of applying general sentiment analysis tools to specialised medical documents. One key issue is that these models are not trained to understand medical terminology or the nuanced ways in which healthcare professionals discuss patients’ conditions. For example, terms that the model may interpret as negative, such as ‘seizure’ or ‘disorder’ may not necessarily carry a negative connotation in the context of a clinical document, where they are part of the routine language used to describe medical conditions. Likewise, positive terms like ‘progress’ might not fully capture the severity or complexity of a patient’s condition, leading to potential discrepancies between the model’s output and the expert’s interpretation. There is increasing interest in using NLP to analyse textual information from clinical records. NLP has been successfully implemented in the FND domain, for example, to aid in accurately differentiating epileptic seizures from psychogenic seizures [ 106 , 107 ]. Nonetheless, subsequent manual analyses are often required to supplement the NLP-generated outcomes with essential details and context, as NLP can fail to detect all nuances in text [ 108 ]. This suggests the need to develop specialised NLP models specifically trained on medical documents and to account for the need for expert input to provide details and interpretations that NLP analyses alone may not be able to capture, thus improving the accuracy of NLP output and its effectiveness to aid clinical practice and clinical decision-making processes. Lastly, future NLP applications in clinical practice (including, but not limited to, FND) would need to account for the specific context in which clinical language is used and understand the implicit meanings that healthcare professionals attribute to certain terms and phrases. Additionally, further research could explore how integrating domain-specific knowledge into NLP models might enhance their ability to capture not just sentiment, but also the intent and nuance of clinical communications. 4.5. Implications for practice and future research The findings of this study have several important implications for clinical practice and future research. First, the clear differences in communication styles between psychologists and neurologists suggest that interdisciplinary teams must be mindful of these differences when coordinating patient care. Neurologists and psychologists should aim to communicate more effectively, ensuring that both the medical and psychosocial aspects of a patient’s care are given equal attention. Regular interdisciplinary meetings and joint case discussions could help bridge this gap and ensure that patients receive holistic, integrated care [ 41 , 109 , 110 ]. Second, the sentiment analysis results suggest that neurologists could benefit from adopting more positive and supportive language when interacting with patients. This could be particularly important in cases where patients are struggling with the emotional and psychological burden of FND, and where a more empathetic and hopeful approach may improve patient engagement and outcomes. Future research should explore how these communication differences and sentiment patterns may influence patient outcomes. For example, it would be useful to determine whether patients who receive more positive and supportive communications from their healthcare providers report higher levels of satisfaction or adherence to treatment or if different communication styles may lead to differences in clinical outcomes. More generally, understanding the impact of communication on patient care in more detail could provide valuable insights for improving interdisciplinary collaboration and enhancing patient outcomes in FND management. 5. Conclusion In conclusion, this study demonstrates that neurologists and psychologists use distinct communication styles when interacting with FND patients, with neurologists adopting a more clinical and cautious approach. In contrast, psychologists focus on emotional support and holistic care. These differences are also reflected in the sentiment analysis, with neurologists exhibiting a more negative tone and psychologists taking a more positive and supportive approach. These findings have important implications for interdisciplinary collaboration and patient care, highlighting the need for integrated approaches that address both the medical and psychosocial dimensions of FND. Further research is needed to explore how these communication differences affect patient outcomes and to develop more specialised NLP models that can accurately capture the nuances of medical discourse. Declarations CONFLICT OF INTEREST STATEMENT The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest. AUTHOR CONTRIBUTIONS All authors have contributed to the study conceptualisation and the write-up of the current manuscript. The first and second authors (MSM and YL) processed, analysed and interpreted the findings. LHYL and DDB had a steering role in study management and extraction of clinical documents from clinical records, helped by research assistants (AL and SL). DDB also provided clinical insights informing the interpretations of the clinical significance of the findings and the recommendations deriving from the study. MS, SS and AW assisted in writing and reviewing the manuscript and RJ, as a clinical expert in the field of neurology and FND, provided feedback on the relevance and informativeness of the findings obtained. FUNDING This work was supported by the Alan Turing Institute - Manchester Sandpit Project Grant, 2022. ETHICS STATEMENT This study was approved by the Northern Care Alliance NHS Group Trust. This study was performed with Ethical approval to extract clinical documents from hospital records, which was obtained with relevant guidelines from the R&I department of the Northern Care Alliance NHS Group Trust (approval number 22HIP47). CONSENT STATEMENT (PERMISSION TO ACCESS CLINICAL RECORDS) Permission to access and analyse these records was granted by the Trust following Research and Development (R&D) approval. The study was conducted in compliance with applicable legal and ethical frameworks governing the use of patient data for research, including the principles of lawful access to healthcare data for research purposes. All data processing adhered to institutional and national guidelines for data protection and confidentiality, ensuring that patient anonymity and privacy were maintained throughout the study. DATA AVAILABILITY The data that support the findings of this study are available from Northern Care Alliance NHS Group Trust (approval number 22HIP47) but restrictions apply to the availability of these data due to the nature and sensitivity related to patient records, which were obtained and used with relevant guidelines from the R&I department of the Northern Care Alliance NHS Group Trust for the current study, and so are not publicly available. CLINICAL TRIAL NUMBER : not applicable. References Bennett, K., Diamond, C., Hoeritzauer, I., Gardiner, P., McWhirter, L., Carson, A., Stone, J.: A practical review of functional neurological disorder (FND) for the general physician. Clin. Med. 21, 28 (2021). https://doi.org/10.7861/clinmed.2020-0987. Oriuwa, C., Mollica, A., Feinstein, A., Giacobbe, P., Lipsman, N., Perez, D.L., Burke, M.J.: Neuromodulation for the treatment of functional neurological disorder and somatic symptom disorder: a systematic review. J. Neurol. Neurosurg. Amp Psychiatry. 93, 280 (2022). https://doi.org/10.1136/jnnp-2021-327025. Stone, J., Campbell, K., Sharma, N., Carson, A., Warlow, C.P., Sharpe, M.: What should we call pseudoseizures? Seizure. 12, 568–572 (2003). https://doi.org/10.1016/s1059-1311(03)00055-4. Carson, A., Stone, J., Hibberd, C., Murray, G., Duncan, R., R Coleman, C Warlow, R Roberts, A Pelosi, J Cavanagh, K Matthews, R Goldbeck, C Hansen, M Sharpe: Disability, distress and unemployment in neurology outpatients with symptoms ‘unexplained by organic disease.’ J. Neurol. Neurosurg. Amp Psychiatry. 82, 810 (2011). https://doi.org/10.1136/jnnp.2010.220640. Gelauff, J., Stone, J., Edwards, M., Carson, A.: The prognosis of functional (psychogenic) motor symptoms: a systematic review. J. Neurol. Neurosurg. Amp Psychiatry. 85, 220 (2014). https://doi.org/10.1136/jnnp-2013-305321. Stone, J., Burton, C., Carson, A.: Recognising and explaining functional neurological disorder. BMJ. 371, m3745 (2020). https://doi.org/10.1136/bmj.m3745. Asadi-Pooya, A.A.: Psychogenic nonepileptic seizures: a concise review. Neurol. Sci. 38, 935–940 (2017). https://doi.org/10.1007/s10072-017-2887-8. Jones, B., Reuber, M., Norman, P.: Correlates of health‐related quality of life in adults with psychogenic nonepileptic seizures: a systematic review. Epilepsia. 57, 171–181 (2016). Rawlings, G.H., Brown, I., Reuber, M.: Predictors of health-related quality of life in patients with epilepsy and psychogenic nonepileptic seizures. Epilepsy Behav. 68, 153–158 (2017). Carson, A., Lehn, A.: Chapter 5 - Epidemiology. In: Hallett, M., Stone, J., and Carson, A. (eds.) Handbook of Clinical Neurology. pp. 47–60. Elsevier (2016). https://doi.org/10.1016/B978-0-12-801772-2.00005-9. Watson, M., Woodward, J., Strom, L.A.: The Financial Burden of Functional Neurological Disorders. Curr. Neurol. Neurosci. Rep. 23, 637–643 (2023). https://doi.org/10.1007/s11910-023-01298-8. Stephen, C.D., Fung, V., Lungu, C.I., Espay, A.J.: Assessment of Emergency Department and Inpatient Use and Costs in Adult and Pediatric Functional Neurological Disorders. JAMA Neurol. 78, 88–101 (2021). https://doi.org/10.1001/jamaneurol.2020.3753. FND Hope: FND 2021 impact report. (2022). Cuoco, S., Scannapieco, S., Carotenuto, I., Picillo, M., Pellecchia, M.T., Barone, P., Erro, R.: Higher Health Service Costs Associated With Delayed Diagnosis of Functional Neurological Disorder. J. Neuropsychiatry Clin. Neurosci. 35, 86–91 (2023). https://doi.org/10.1176/appi.neuropsych.21110288. El-Naggar, H., Moloney, P., Widdess-Walsh, P., Kilbride, R., Delanty, N., Mullins, G.: Simultaneous occurrence of nonepileptic and epileptic seizures during a single period of in-patient video-electroencephalographic monitoring. Epilepsia Open. 2, 467–471 (2017). https://doi.org/10.1002/epi4.12071. Burke, M.J.: “It’s All in Your Head”—Medicine’s Silent Epidemic. JAMA Neurol. 76, 1417–1418 (2019). https://doi.org/10.1001/jamaneurol.2019.3043. Dickson, B.E., Hay-Smith, E.J.C., Dean, S.G.: Demonised diagnosis: the influence of stigma on interdisciplinary rehabilitation of somatoform disorder. N. Z. J. Physiother. 37, (2009). Keynejad, R.C., Carson, A.J., David, A.S., Nicholson, T.R.: Functional neurological disorder: psychiatry’s blind spot. Lancet Psychiatry. 4, e2–e3 (2017). https://doi.org/10.1016/S2215-0366(17)30036-6. Onofrj, M., Ajdinaj, P., Digiovanni, A., Malek, N., Martinotti, G., Ferro, F.M., Russo, M., Thomas, A., Sensi, S.L.: Functional Neurologic Disorders, disorders to be managed by neurologists, or are neurologists wandering in a dangerous field with inadequate resources? Front. Psychiatry. 14, (2023). Pretorius, C.: Barriers and facilitators to reaching a diagnosis of PNES from the patients’ perspective: Preliminary findings. Seizure. 38, 1–6 (2016). https://doi.org/10.1016/j.seizure.2016.03.007. Varley, D., Sweetman, J., Brabyn, S., Lagos, D., van der Feltz-Cornelis, C.: The clinical management of functional neurological disorder: A scoping review of the literature. J. Psychosom. Res. 165, 111121 (2023). https://doi.org/10.1016/j.jpsychores.2022.111121. Brownell, A.K.W., Atkins, C., Whiteley, A., Woollard, R.F., Kornelsen, J.: Clinical practitioners’ views on the management of patients with medically unexplained physical symptoms (MUPS): a qualitative study. BMJ Open. 6, e012379 (2016). https://doi.org/10.1136/bmjopen-2016-012379. Dickson, J.M., Peacock, M., Grünewald, R.A., Howlett, S., Bissell, P., Reuber, M.: Non-epileptic attack disorder: the importance of diagnosis and treatment. BMJ Case Rep. bcr2016218278 (2017). https://doi.org/10.1136/bcr-2016-218278. McNicholas, O., Pryce, H.: Clinical physiologists’ experiences of working with people with nonepileptic attack disorder: A qualitative study. Epilepsy Behav. 127, 108501 (2022). https://doi.org/10.1016/j.yebeh.2021.108501. Yon, K., Nettleton, S., Walters, K., Lamahewa, K., Buszewicz, M.: Junior doctors’ experiences of managing patients with medically unexplained symptoms: a qualitative study. BMJ Open. 5, e009593 (2015). https://doi.org/10.1136/bmjopen-2015-009593. Kanaan, R.A., Armstrong, D., Wessely, S.C.: Neurologists’ understanding and management of conversion disorder. J. Neurol. Neurosurg. Amp Psychiatry. 82, 961 (2011). https://doi.org/10.1136/jnnp.2010.233114. Sahaya, K., Dholakia, S.A., Lardizabal, D., Sahota, P.K.: Opinion survey of health care providers towards psychogenic non epileptic seizures. Clin. Neurol. Neurosurg. 114, 1304–1307 (2012). https://doi.org/10.1016/j.clineuro.2012.03.047. Barnett, C., Davis, R., Mitchell, C., Tyson, S.: The vicious cycle of functional neurological disorders: a synthesis of healthcare professionals’ views on working with patients with functional neurological disorder. Disabil. Rehabil. 44, 1802–1811 (2022). https://doi.org/10.1080/09638288.2020.1822935. Ahern, L., Stone, J., Sharpe, M.C.: Attitudes of Neuroscience Nurses Toward Patients With Conversion Symptoms. Psychosomatics. 50, 336–339 (2009). https://doi.org/10.1176/appi.psy.50.4.336. McMillan, K.K., Pugh, M.J., Hamid, H., Salinsky, M., Pugh, J., Noël, P.H., Finley, E.P., Leykum, L.K., Lanham, H.J., LaFrance, W.C., Jr.: Providers’ perspectives on treating psychogenic nonepileptic seizures: Frustration and hope. Epilepsy Behav. 37, 276–281 (2014). https://doi.org/10.1016/j.yebeh.2014.07.001. Robson, C., Lian, O.S.: “Blaming, shaming, humiliation”: Stigmatising medical interactions among people with non-epileptic seizures. Wellcome Open Res. 2, 55 (2017). https://doi.org/10.12688/wellcomeopenres.12133.2. Edwards, M.J., Yogarajah, M., Stone, J.: Why functional neurological disorder is not feigning or malingering. Nat. Rev. Neurol. 19, 246–256 (2023). https://doi.org/10.1038/s41582-022-00765-z. McLoughlin, C., McGhie-Fraser, B., Carson, A., Olde Hartman, T., Stone, J.: How stigma unfolds for patients with Functional Neurological Disorder. J. Psychosom. Res. 181, 111667 (2024). https://doi.org/10.1016/j.jpsychores.2024.111667. Asadi-Pooya, A.A., Brigo, F., Mildon, B., Nicholson, T.R.: Terminology for psychogenic nonepileptic seizures: Making the case for “functional seizures.” Epilepsy Behav. 104, 106895 (2020). https://doi.org/10.1016/j.yebeh.2019.106895. Brigo, F., Igwe, S.C., Ausserer, H., Nardone, R., Tezzon, F., Bongiovanni, L.G., Tinazzi, M., Trinka, E.: Terminology of psychogenic nonepileptic seizures. Epilepsia. 56, e21–e25 (2015). https://doi.org/10.1111/epi.12911. Brigo, F., Tinazzi, M., Trinka, E.: In Response: Terminology of psychogenic nonepileptic seizures—a Babel of different names? Epilepsia. 56, 1179–1180 (2015). https://doi.org/10.1111/epi.13028. Carson, A., Lehn, A., Ludwig, L., Stone, J.: Explaining functional disorders in the neurology clinic: a photo story. Pract. Neurol. 16, 56 (2016). https://doi.org/10.1136/practneurol-2015-001242. Marotta, A., Lasalvia, A., Fiorio, M., Zanalda, E., Di Sciascio, G., Palumbo, C., Papola, D., Barbui, C., Tinazzi, M.: Psychiatrists’ attitudes towards functional neurological disorders: results from a national survey. Front. Psychiatry. 14, (2023). https://doi.org/10.3389/fpsyt.2023.1216756. Stone, J.: Functional neurological disorders: the neurological assessment as treatment. Pract. Neurol. 16, 7–17 (2016). https://doi.org/10.1136/practneurol-2015-001241. Keatley, E., Molton, I.: A shift in approach: assessment and treatment of adults with functional neurological disorder. J. Health Serv. Psychol. 48, 79–87 (2022). Palmer, D.D.G., Gamble, M., Higgins, M., Maley, J., Watson, E.: Outcomes of an Integrated Multidisciplinary Clinic for People with Functional Neurological Disorder. Mov. Disord. Clin. Pract. 10, 967–973 (2023). https://doi.org/10.1002/mdc3.13757. Jimenez, X.F., Aboussouan, A., Johnson, J.: Functional neurological disorder responds favorably to interdisciplinary rehabilitation models. Psychosomatics. 60, 556–562 (2019). LaFaver, K., LaFrance, W.C., Price, M.E., Rosen, P.B., Rapaport, M.: Treatment of functional neurological disorder: current state, future directions, and a research agenda. CNS Spectr. 26, 607–613 (2021). https://doi.org/10.1017/S1092852920002138. Velazquez-Rodriquez, Y., Fehily, B.: Functional Neurological Disorder: Historical Trends and Urgent Directions. J. Neurol. Res. 13, 12–32 (2023). https://doi.org/10.14740/jnr754. Levis, M., Leonard Westgate, C., Gui, J., Watts, B.V., Shiner, B.: Natural language processing of clinical mental health notes may add predictive value to existing suicide risk models. Psychol. Med. 51, 1382–1391 (2021). https://doi.org/10.1017/S0033291720000173. Locke, S., Bashall, A., Al-Adely, S., Moore, J., Wilson, A., Kitchen, G.B.: Natural language processing in medicine: A review. Trends Anaesth. Crit. Care. 38, 4–9 (2021). https://doi.org/10.1016/j.tacc.2021.02.007. Le Glaz, A., Haralambous, Y., Kim-Dufor, D.-H., Lenca, P., Billot, R., Ryan, T.C., Marsh, J., DeVylder, J., Walter, M., Berrouiguet, S., Lemey, C.: Machine Learning and Natural Language Processing in Mental Health: Systematic Review. J Med Internet Res. 23, e15708 (2021). https://doi.org/10.2196/15708. Malgaroli, M., Hull, T.D., Zech, J.M., Althoff, T.: Natural language processing for mental health interventions: a systematic review and research framework. Transl. Psychiatry. 13, 309 (2023). Mukherjee, S.S., Yu, J., Won, Y., McClay, M.J., Wang, L., Rush, A.J., Sarkar, J.: Natural language processing-based quantification of the mental state of psychiatric patients. Comput. Psychiatry. 4, (2020). Zhang, T., Schoene, A.M., Ji, S., Ananiadou, S.: Natural language processing applied to mental illness detection: a narrative review. Npj Digit. Med. 5, 46 (2022). https://doi.org/10.1038/s41746-022-00589-7. Fleuren, W.W.M., Alkema, W.: Application of text mining in the biomedical domain. Text Min. Biomed. Lit. 74, 97–106 (2015). https://doi.org/10.1016/j.ymeth.2015.01.015. Jackson, R.G., Patel, R., Jayatilleke, N., Kolliakou, A., Ball, M., Genevieve Gorrell, Angus Roberts, Richard J Dobson, Robert Stewart: Natural language processing to extract symptoms of severe mental illness from clinical text: the Clinical Record Interactive Search Comprehensive Data Extraction (CRIS-CODE) project. BMJ Open. 7, e012012 (2017). https://doi.org/10.1136/bmjopen-2016-012012. Koleck, T.A., Dreisbach, C., Bourne, P.E., Bakken, S.: Natural language processing of symptoms documented in free-text narratives of electronic health records: a systematic review. J. Am. Med. Inform. Assoc. 26, 364–379 (2019). https://doi.org/10.1093/jamia/ocy173. Wang, Y., Wang, L., Rastegar-Mojarad, M., Moon, S., Shen, F., Afzal, N., Liu, S., Zeng, Y., Mehrabi, S., Sohn, S.: Clinical information extraction applications: a literature review. J. Biomed. Inform. 77, 34–49 (2018). Roberts, A.: Language, structure, and reuse in the electronic health record. AMA J. Ethics. 19, 281–288 (2017). Velupillai, S., Suominen, H., Liakata, M., Roberts, A., Shah, A.D., Morley, K., Osborn, D., Hayes, J., Stewart, R., Downs, J., Chapman, W., Dutta, R.: Using clinical Natural Language Processing for health outcomes research: Overview and actionable suggestions for future advances. J. Biomed. Inform. 88, 11–19 (2018). https://doi.org/10.1016/j.jbi.2018.10.005. Ford, E., Carroll, J.A., Smith, H.E., Scott, D., Cassell, J.A.: Extracting information from the text of electronic medical records to improve case detection: a systematic review. J. Am. Med. Inform. Assoc. 23, 1007–1015 (2016). https://doi.org/10.1093/jamia/ocv180. Le, D.V., Montgomery, J., Kirkby, K.C., Scanlan, J.: Risk prediction using natural language processing of electronic mental health records in an inpatient forensic psychiatry setting. J. Biomed. Inform. 86, 49–58 (2018). https://doi.org/10.1016/j.jbi.2018.08.007. Sohn, S., Kocher, J.-P.A., Chute, C.G., Savova, G.K.: Drug side effect extraction from clinical narratives of psychiatry and psychology patients. J. Am. Med. Inform. Assoc. 18, i144–i149 (2011). https://doi.org/10.1136/amiajnl-2011-000351. Boden, C.: Overcoming the linguistic divide: a barrier to consumer health information. J. Can. Health Libr. Assoc. Assoc. Bibl. Santé Can. 30, 75–80 (2009). He, Z.: Understanding and Bridging the Language and Terminology Gap Between Health Professionals and Consumers Using Social Media. In: Bian, J., Guo, Y., He, Z., and Hu, X. (eds.) Social Web and Health Research: Benefits, Limitations, and Best Practices. pp. 103–121. Springer International Publishing, Cham (2019). https://doi.org/10.1007/978-3-030-14714-3_6. Nie, L., Zhao, Y.-L., Akbari, M., Shen, J., Chua, T.-S.: Bridging the vocabulary gap between health seekers and healthcare knowledge. IEEE Trans. Knowl. Data Eng. 27, 396–409 (2014). Varma, J.B., Deeba, K.: Mapping of terms between healthcare providers and patients. In: 2017 International Conference on Trends in Electronics and Informatics (ICEI). pp. 773–776 (2017). https://doi.org/10.1109/ICOEI.2017.8300808. Puerari, I., Duarte, D., Dal Bianco, G., Felipette Lima, J.: Exploratory Analysis of Electronic Health Records using Topic Modeling. J. Inf. Data Manag. 11, (2021). https://doi.org/10.5753/jidm.2020.2024. Carron-Arthur, B., Reynolds, J., Bennett, K., Bennett, A., Griffiths, K.M.: What’s all the talk about? Topic modelling in a mental health Internet support group. BMC Psychiatry. 16, (2016). https://doi.org/10.1186/s12888-016-1073-5. Denecke, K., Reichenpfader, D.: Sentiment analysis of clinical narratives: A scoping review. J. Biomed. Inform. 140, 104336 (2023). https://doi.org/10.1016/j.jbi.2023.104336. Mccoy, T.H., Castro, V.M., Cagan, A., Roberson, A.M., Kohane, I.S., Perlis, R.H.: Sentiment Measured in Hospital Discharge Notes Is Associated with Readmission and Mortality Risk: An Electronic Health Record Study. PLOS ONE. 10, e0136341 (2015). https://doi.org/10.1371/journal.pone.0136341. Blei, D.M.: Probabilistic topic models. Commun. ACM. 55, 77–84 (2012). https://doi.org/10.1145/2133806.2133826. Gillings, M., Hardie, A.: The interpretation of topic models for scholarly analysis: An evaluation and critique of current practice. Digit. Scholarsh. Humanit. 38, 530–543 (2023). https://doi.org/10.1093/llc/fqac075. Blei, D., Ng, A., Jordan, M.: Latent Dirichlet Allocation. J. Mach. Learn. Res. 3, 993–1022 (2003). Syed, S., Spruit, M.: Full-Text or Abstract? Examining Topic Coherence Scores Using Latent Dirichlet Allocation. (2017). https://doi.org/10.1109/DSAA.2017.61. Hutto, C., Gilbert, E.: VADER: A Parsimonious Rule-Based Model for Sentiment Analysis of Social Media Text. Proc. Int. AAAI Conf. Web Soc. Media. 8, 216–225 (2014). https://doi.org/10.1609/icwsm.v8i1.14550. Rhody, L.M.: Topic modeling and figurative language. (2012). Giannoulakis, S., Tsapatsoulis, N.: Topic Identification via Human Interpretation of Word Clouds: The Case of Instagram Hashtags. In: Maglogiannis, I., Macintyre, J., and Iliadis, L. (eds.) Artificial Intelligence Applications and Innovations. pp. 283–294. Springer International Publishing, Cham (2021). Arnold, C.W., Oh, A., Chen, S., Speier, W.: Evaluating topic model interpretability from a primary care physician perspective. Comput. Methods Programs Biomed. 124, 67–75 (2016). Cambria, E., Das, D., Bandyopadhyay, S., Feraco, A.: A practical guide to sentiment analysis. Springer (2017). Espay, A.J., Aybek, S., Carson, A., Edwards, M.J., Goldstein, L.H., Hallett, M., Lafaver, K., Lafrance, W.C., Lang, A.E., Nicholson, T., Nielsen, G., Reuber, M., Voon, V., Stone, J., Morgante, F.: Current Concepts in Diagnosis and Treatment of Functional Neurological Disorders. JAMA Neurol. 75, 1132 (2018). https://doi.org/10.1001/jamaneurol.2018.1264. Goldstein, L.H., Mellers, J.D.C.: Chapter 46 - Psychologic treatment of functional neurologic disorders. In: Hallett, M., Stone, J., and Carson, A. (eds.) Handbook of Clinical Neurology. pp. 571–583. Elsevier (2016). https://doi.org/10.1016/B978-0-12-801772-2.00046-1. LaFrance Jr., W.C., Miller, I.W., Ryan, C.E., Blum, A.S., Solomon, D.A., Kelley, J.E., Keitner, G.I.: Cognitive behavioral therapy for psychogenic nonepileptic seizures. Epilepsy Behav. 14, 591–596 (2009). https://doi.org/10.1016/j.yebeh.2009.02.016. Myers, L., Sarudiansky, M., Korman, G., Baslet, G.: Using evidence-based psychotherapy to tailor treatment for patients with functional neurological disorders. Epilepsy Behav. Rep. 16, 100478 (2021). https://doi.org/10.1016/j.ebr.2021.100478. Goldstein, L.H., Chalder, T., Chigwedere, C., Khondoker, M.R., Moriarty, J., Toone, B.K., Mellers, J.D.C.: Cognitive-behavioral therapy for psychogenic nonepileptic seizures: A pilot RCT. Neurology. 74, 1986–1994 (2010). https://doi.org/10.1212/wnl.0b013e3181e39658. Perez, D.L., Haller, A.L., Espay, A.J.: Should neurologists diagnose and manage functional neurologic disorders? It is complicated. Neurol. Clin. Pract. 9, 165–167 (2019). https://doi.org/10.1212/cpj.0000000000000573. Gilmour, G.S., Nielsen, G., Teodoro, T., Yogarajah, M., Coebergh, J.A., Dilley, M.D., Martino, D., Edwards, M.J.: Management of functional neurological disorder. J. Neurol. 267, 2164–2172 (2020). https://doi.org/10.1007/s00415-020-09772-w. Tinazzi, M., Fiorio, M., Berardelli, A., Bonetti, B., Bonifati, D.M., Burlina, A., Cagnin, A., Calabria, F., Corbetta, M., Cortelli, P., Giometto, B., Guidoni, S.V., Lopiano, L., Mancardi, G., Marchioretto, F., Pellegrini, M., Teatini, F., Tedeschi, G., Tesolin, L., Turinese, E., Zappia, M., Marotta, A.: Opinion, knowledge, and clinical experience with functional neurological disorders among Italian neurologists: results from an online survey. J Neurol. 269, 2549–2559 (2022). https://doi.org/10.1007/s00415-021-10840-y. McKee, K., Glass, S., Adams, C., Stephen, C.D., King, F., Parlman, K., Perez, D.L., Kontos, N.: The Inpatient Assessment and Management of Motor Functional Neurological Disorders: An Interdisciplinary Perspective. Psychosomatics. 59, 358–368 (2018). https://doi.org/10.1016/j.psym.2017.12.006. Sireci, F., Moretti, V., Cavallieri, F., Ferrari, S., Minardi, V., Ferrari, F., Balestra, G.L., Ghirotto, L., Valzania, F.: “Somewhere Between an Actual Disease and a Disease”: A Grounded Theory Study on Diagnosing Functional Neurological Disorders From a Multi-Informant Perspective. Qual. Health Res. 10497323231216346 (2023). https://doi.org/10.1177/10497323231216346. Winton-Brown, T., Wilson, S.J., Felmingham, K., Rayner, G., O’Brien, T.J., O’Brien, P., Mohan, A., Velakoulis, D., Kanaan, R.: Principles for delivering improved care of people with functional seizures: Closing the treatment gap. Aust. N. Z. J. Psychiatry. 57, 1511–1517 (2023). https://doi.org/10.1177/00048674231180509. Pepper, E., Mohan, A., Butcher, K., Parsons, M., Curtis, J.: Functional neurological disorders: an Australian interdisciplinary perspective. Med. J. Aust. 216, 501–503 (2022). https://doi.org/10.5694/mja2.51543. Henningsen, P., Zipfel, S., Sattel, H., Creed, F.: Management of Functional Somatic Syndromes and Bodily Distress. Psychother. Psychosom. 87, 12–31 (2018). https://doi.org/10.1159/000484413. Mamo, N., Tak, L.M., Van De Klundert, M.A.W., Olde Hartman, T.C., Rosmalen, J.G.M., Hanssen, D.J.C.: Quality indicators for collaborative care networks in persistent somatic symptoms and functional disorders: a modified delphi study. BMC Health Serv. Res. 24, (2024). https://doi.org/10.1186/s12913-024-10589-w. Vance, R., Clarke, S., O’Keeffe, F., Galligan, T., Doherty, A., Flynn, C., Kelleher, E., Laffan, A., Doherty, C., Gillan, D.: Attitudes and perceptions of Irish health care professionals regarding functional neurological disorder: A national survey. Brain Behav. 14, (2024). https://doi.org/10.1002/brb3.3362. Cope, S.R., Smith, J.G., Edwards, M.J., Holt, K., Agrawal, N.: Enhancing the communication of functional neurological disorder diagnosis: a multidisciplinary education session. Eur. J. Neurol. 28, 40–47 (2021). https://doi.org/10.1111/ene.14525. Lehn, A., Navaratnam, D., Broughton, M., Cheah, V., Fenton, A., Harm, K., Owen, D., Pun, P.: Functional neurological disorders: effective teaching for health professionals. BMJ Neurol. Open. 2, e000065 (2020). https://doi.org/10.1136/bmjno-2020-000065. O’Keeffe, S., Chowdhury, I., Sinanaj, A., Ewang, I., Blain, C., Teodoro, T., Edwards, M., Yogarajah, M.: A Service Evaluation of the Experiences of Patients With Functional Neurological Disorders Within the NHS. Front. Neurol. 12, (2021). https://doi.org/10.3389/fneur.2021.656466. Mitchell, W.: Positive language leads to positive wellbeing. BMJ. i4426 (2016). https://doi.org/10.1136/bmj.i4426. Thorne, S.E., Harris, S.R., Mahoney, K., Con, A., McGuinness, L.: The context of health care communication in chronic illness. Patient Educ. Couns. 54, 299–306 (2004). https://doi.org/10.1016/j.pec.2003.11.009. van der Hulst: A Clinician’s Guide to Functional Neurological Disorder: A Practical Neuropsychological Approach. London: Routledge (2023). Bailey, C., Agrawal, N., Cope, S., Proctor, B., Mildon, B., Butler, M., Holt, K., Edwards, M., Poole, N., Nicholson, T.R.: Illness perceptions, experiences of stigma and engagement in functional neurological disorder (FND): exploring the role of multidisciplinary group education sessions. BMJ Neurol. Open. 6, e000633 (2024). https://doi.org/10.1136/bmjno-2024-000633. MacDuffie, K.E., Grubbs, L., Best, T., LaRoche, S., Mildon, B., Myers, L., Stafford, E., Rommelfanger, K.S.: Stigma and functional neurological disorder: a research agenda targeting the clinical encounter. CNS Spectr. 26, 587–592 (2021). https://doi.org/10.1017/S1092852920002084. Staton, A., Dawson, D., Merdian, H., Tickle, A., Walker, T.: Functional neurological disorder: A qualitative study exploring individuals’ experiences of psychological services. Psychol. Psychother. Theory Res. Pract. 97, 138–156 (2024). https://doi.org/10.1111/papt.12504. Haskard Zolnierek, K.B., Dimatteo, M.R.: Physician Communication and Patient Adherence to Treatment. Med. Care. 47, 826–834 (2009). https://doi.org/10.1097/mlr.0b013e31819a5acc. Jenstad, L.M., Howe, T., Breau, G., Abel, J., Colozzo, P., Halas, G., Mason, G., Rieger, C., Simon, L., Strachan, S.: Communication between healthcare providers and communicatively-vulnerable patients with associated health outcomes: A scoping review of knowledge syntheses. Patient Educ. Couns. 119, 108040 (2024). https://doi.org/10.1016/j.pec.2023.108040. Sharkiya, S.H.: Quality communication can improve patient-centred health outcomes among older patients: a rapid review. BMC Health Serv. Res. 23, 886 (2023). https://doi.org/10.1186/s12913-023-09869-8. Foley, C., Kirkby, A., Eccles, F.J.R.: A meta-ethnographic synthesis of the experiences of stigma amongst people with functional neurological disorder. Disabil. Rehabil. 46, 1–12 (2024). https://doi.org/10.1080/09638288.2022.2155714. Myers, L., Gray, C., Roberts, N., Levita, L., Reuber, M.: Shame in the treatment of patients with psychogenic nonepileptic seizures: The elephant in the room. Seizure. 94, 176–182 (2022). https://doi.org/10.1016/j.seizure.2021.10.018. Hamid, H., Fodeh, S.J., Lizama, A.G., Czlapinski, R., Pugh, M.J., LaFrance, W.C., Jr., Brandt, C.A.: Validating a natural language processing tool to exclude psychogenic nonepileptic seizures in electronic medical record-based epilepsy research. Epilepsy Behav. 29, 578–580 (2013). https://doi.org/10.1016/j.yebeh.2013.09.025. Pevy, N., Christensen, H., Walker, T., Reuber, M.: Feasibility of using an automated analysis of formulation effort in patients’ spoken seizure descriptions in the differential diagnosis of epileptic and nonepileptic seizures. Seizure. 91, 141–145 (2021). https://doi.org/10.1016/j.seizure.2021.06.009. Guetterman, T.C., Chang, T., Dejonckheere, M., Basu, T., Scruggs, E., Vydiswaran, V.V.: Augmenting Qualitative Text Analysis with Natural Language Processing: Methodological Study. J. Med. Internet Res. 20, e231 (2018). https://doi.org/10.2196/jmir.9702. Kassianos, A.P., Ignatowicz, A., Greenfield, G., Majeed, A., Car, J., Pappas, Y.: “Partners rather than just providers…”: A qualitative study on health care professionals’ views on implementation of multidisciplinary group meetings in the North West London Integrated Care Pilot. Int. J. Integr. Care. 15, (2015). https://doi.org/10.5334/ijic.2019. Lennox-Chhugani, N.: Inter-Disciplinary Work in the Context of Integrated Care – a Theoretical and Methodological Framework. Int. J. Integr. Care. 23, (2023). https://doi.org/10.5334/ijic.7544. Additional Declarations No competing interests reported. Supplementary Files SupplementarymaterialAppendices.docx Cite Share Download PDF Status: Published Journal Publication published 14 Jan, 2026 Read the published version in Frontiers in Digital Health → Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-6018381","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":415813106,"identity":"64d499e9-3a5a-4b8c-9ca6-675f3ff6336e","order_by":0,"name":"Md Shadab Mashuk","email":"","orcid":"","institution":"University of Salford","correspondingAuthor":false,"prefix":"","firstName":"Md","middleName":"Shadab","lastName":"Mashuk","suffix":""},{"id":415813107,"identity":"70445905-7ca4-496a-9767-38f3b8e2bcdf","order_by":1,"name":"Yang Lu","email":"","orcid":"","institution":"York St John University","correspondingAuthor":false,"prefix":"","firstName":"Yang","middleName":"","lastName":"Lu","suffix":""},{"id":415813108,"identity":"299134c0-c5d9-48d9-afa1-4f2cd540a200","order_by":2,"name":"Lana YH Lai","email":"","orcid":"","institution":"University of Manchester, Imaging \u0026 Data Sciences","correspondingAuthor":false,"prefix":"","firstName":"Lana","middleName":"YH","lastName":"Lai","suffix":""},{"id":415813109,"identity":"8b3be316-128e-48c6-bc82-f76b25f6d1d7","order_by":3,"name":"Matthew Shardlow","email":"","orcid":"","institution":"Manchester Metropolitan University","correspondingAuthor":false,"prefix":"","firstName":"Matthew","middleName":"","lastName":"Shardlow","suffix":""},{"id":415813110,"identity":"7946e6a1-f995-4d49-8b4e-a03c0a521f50","order_by":4,"name":"Shumit Saha","email":"","orcid":"","institution":"Meharry Medical College","correspondingAuthor":false,"prefix":"","firstName":"Shumit","middleName":"","lastName":"Saha","suffix":""},{"id":415813111,"identity":"c0546f15-f3bd-4e84-aa44-c32f0b0e04bc","order_by":5,"name":"Ashley Williams","email":"","orcid":"","institution":"Manchester Metropolitan University","correspondingAuthor":false,"prefix":"","firstName":"Ashley","middleName":"","lastName":"Williams","suffix":""},{"id":415813112,"identity":"4c8907f2-bccb-48fc-84d1-a02a0d9d9614","order_by":6,"name":"Anna Lee","email":"","orcid":"","institution":"Salford Royal NHS Foundation Trust, Northern Care Alliance","correspondingAuthor":false,"prefix":"","firstName":"Anna","middleName":"","lastName":"Lee","suffix":""},{"id":415813113,"identity":"f482596a-18e6-4843-989a-f492fa37fb7b","order_by":7,"name":"Sarah Lloyd","email":"","orcid":"","institution":"Salford Royal NHS Foundation Trust, Northern Care Alliance","correspondingAuthor":false,"prefix":"","firstName":"Sarah","middleName":"","lastName":"Lloyd","suffix":""},{"id":415813114,"identity":"8286d860-aaa9-491b-8e94-1427e336d9c9","order_by":8,"name":"Rajiv Mohanraj","email":"","orcid":"","institution":"Salford Royal NHS Foundation Trust, Northern Care Alliance","correspondingAuthor":false,"prefix":"","firstName":"Rajiv","middleName":"","lastName":"Mohanraj","suffix":""},{"id":415813116,"identity":"f95e36b4-1748-49d2-9d34-9d46a27312e5","order_by":9,"name":"Daniela Di Basilio","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABDUlEQVRIie2RMUvEMBTH3/EgXWq7piD2K6QIjvpVcgTq2rHgUQNCx3M9P8bhF0h50FuErhkcToSbT4QDl8NQBFHa80aH/JZAXn7k/+cBeDz/EQOC3BFGCJP1+ueMHVYYAgrZX+HfCn6NGT9KiQwuqZhVpyzAtpSz5zS+75rXEi5T4LkcUhLDClq05IKx3Mp2ky2swuwJVKZ5boYUYULh3hunhBdWMpJgkSUaUAK/1uPKvuqVQu5Jph0FHxpuDysnNfYKTGuSwig20eC+GwmWkOvyMO+7KD6dU7a06jzRYpXV4WawfrS6e3wvdtVVHFOz3e4oPeualzdd3qRxkIsh5XsJvwKPLtLj8Xg8R/AJgbtaBDwd7P4AAAAASUVORK5CYII=","orcid":"","institution":"Lancaster University","correspondingAuthor":true,"prefix":"","firstName":"Daniela","middleName":"Di","lastName":"Basilio","suffix":""}],"badges":[],"createdAt":"2025-02-12 23:53:12","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6018381/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6018381/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.3389/fdgth.2025.1691724","type":"published","date":"2026-01-15T00:00:00+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":76580910,"identity":"409ca0df-82f6-413a-91bc-e13f9553cf84","added_by":"auto","created_at":"2025-02-18 15:01:15","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":239713,"visible":true,"origin":"","legend":"\u003cp\u003eA process flow diagram showing the pipeline of the exploratory analysis of the medical records.\u003c/p\u003e","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-6018381/v1/71d45c532ad0583ee5ba4c3f.png"},{"id":76583201,"identity":"02353164-0475-4415-b1f3-7d252d870139","added_by":"auto","created_at":"2025-02-18 15:17:15","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":294964,"visible":true,"origin":"","legend":"\u003cp\u003eCoherence plot for different values of alpha for psychology and neurology data\u003c/p\u003e","description":"","filename":"2.png","url":"https://assets-eu.researchsquare.com/files/rs-6018381/v1/139c45ce5beb3a6538923938.png"},{"id":76580913,"identity":"2dbc6def-e382-41b1-8b01-8e3fa2610fcf","added_by":"auto","created_at":"2025-02-18 15:01:15","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":663428,"visible":true,"origin":"","legend":"\u003cp\u003eInter-topic distribution plot showing the uniqueness, spread and size of the topics\u003c/p\u003e","description":"","filename":"3.png","url":"https://assets-eu.researchsquare.com/files/rs-6018381/v1/b5f0812783d91dd68fbd1fa4.png"},{"id":76580915,"identity":"9c62c70f-7b15-450d-bb70-4458d11cef02","added_by":"auto","created_at":"2025-02-18 15:01:15","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":195583,"visible":true,"origin":"","legend":"\u003cp\u003eVADER-based compound sentiment scores between psychologists and neurologists across different letter type\u003c/p\u003e","description":"","filename":"floatimage12.png","url":"https://assets-eu.researchsquare.com/files/rs-6018381/v1/be5086a859b185f61994012c.png"},{"id":76580914,"identity":"b69ad6b7-1ea7-4397-87a5-337800eacef9","added_by":"auto","created_at":"2025-02-18 15:01:15","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":268894,"visible":true,"origin":"","legend":"\u003cp\u003eVADER-based Compound and non-compound sentiment score distribution across professional groups only\u003c/p\u003e","description":"","filename":"floatimage13.png","url":"https://assets-eu.researchsquare.com/files/rs-6018381/v1/63d715a5af00400f1b4d7aef.png"},{"id":76583206,"identity":"9196603a-9630-441e-96c2-4bca5eab2409","added_by":"auto","created_at":"2025-02-18 15:17:16","extension":"png","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":130821,"visible":true,"origin":"","legend":"\u003cp\u003eFlair-based sentiment scores across the two professional groups\u003c/p\u003e","description":"","filename":"floatimage14.png","url":"https://assets-eu.researchsquare.com/files/rs-6018381/v1/aeb0810325a9e590628b5b78.png"},{"id":76584090,"identity":"d27028ed-5661-4638-b80f-04c1b9cf7e53","added_by":"auto","created_at":"2025-02-18 15:25:16","extension":"png","order_by":7,"title":"Figure 7","display":"","copyAsset":false,"role":"figure","size":175988,"visible":true,"origin":"","legend":"\u003cp\u003eFlair-based sentiment scores across the two professional groups by letter types\u003c/p\u003e","description":"","filename":"floatimage15.png","url":"https://assets-eu.researchsquare.com/files/rs-6018381/v1/abbeb95c087eb19154b73240.png"},{"id":100448735,"identity":"7f51128d-9885-4ca1-a82f-3e871c461373","added_by":"auto","created_at":"2026-01-16 19:29:09","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3319516,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6018381/v1/123c1def-a578-49cd-9c74-753df10e342f.pdf"},{"id":76584397,"identity":"54df564e-9565-4a0d-bb26-d8fa74da7e17","added_by":"auto","created_at":"2025-02-18 15:33:16","extension":"docx","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":335994,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementarymaterialAppendices.docx","url":"https://assets-eu.researchsquare.com/files/rs-6018381/v1/77106f5c27da3ddb47138079.docx"}],"financialInterests":"No competing interests reported.","formattedTitle":"Using Natural Language Processing to Explore Differences in Healthcare Professionals’ Language On Functional Neurological Disorders: A Comparative Topic and Sentiment Analysis Study","fulltext":[{"header":"1. INTRODUCTION","content":"\u003cdiv id=\"Sec2\" class=\"Section2\"\u003e \u003ch2\u003e1.1 \u003cem\u003eFunctional Neurological Disorder (FND) and the importance of clinician-patient communication\u003c/em\u003e\u003c/h2\u003e \u003cp\u003eFunctional Neurological Disorder (FND) is a neurological condition caused by a functional rather than a structural disorder, i.e., by changes in the brain network, rather than in the brain structure [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e, \u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e]. Symptoms of FND, which include tremor, paralysis, dystonia, sensory disturbances, speech difficulties, and dissociative seizures, are genuine and often likely to interfere with how a person functions and copes with daily life [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e, \u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e]. The burden of this disease is remarkable as FND is associated with high rates of distress and disability [\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e, \u003cspan additionalcitationids=\"CR5\" citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e] and a substantial reduction in quality of life, as well as impairments across multiple life domains, such as employment, socialisation, ability to be independent and experience of social stigma [\u003cspan additionalcitationids=\"CR8\" citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eFurthermore, evidence indicates that FND is the second most common reason for neurological consultations after headaches [\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e, \u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e] and is linked to substantial healthcare costs for both individuals and services [\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e], with estimated costs exceeding US\u003cspan\u003e$\u003c/span\u003e1\u0026nbsp;billion/year in the United States [\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e] and \u0026pound;3\u0026nbsp;billion/year in England alone [\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e]. Healthcare costs may be further enhanced by the frequent misdiagnosis of this disorder [\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e] and an average diagnostic delay of 7.2 years [\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e], which contributed to FND being labelled as medicine\u0026rsquo;s \u0026ldquo;silent epidemic,\u0026rdquo; psychiatry\u0026rsquo;s \u0026ldquo;blind spot\u0026rdquo; and a \u0026ldquo;demonised diagnosis\u0026rdquo; [\u003cspan additionalcitationids=\"CR17 CR18\" citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eFundamental to an individual\u0026rsquo;s understanding and management of their FND diagnosis is the communication and therapeutic relationship with healthcare professionals [\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e, \u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e]. Literature on FND highlighted that relationships with clinical professionals can, at times, entail negative interactions with FND patients [\u003cspan additionalcitationids=\"CR23 CR24\" citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e]. More specifically, studies on this topic highlighted that healthcare professionals in different roles, e.g., neurologists, general practitioners (GPs) and nurses, often express stigmatising views of FND patients as feigning their symptoms and pretending not to have control over them [\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e, \u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e]. Additionally, they can perceive FND patients as \u0026lsquo;difficult\u0026rsquo; and frustrating, which in turn can lead patients to feel misunderstood, disbelieved, and rejected by their physicians [\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eProfessionals\u0026rsquo; negative attitudes are often conveyed via the language they use in routine interactions with FND patients, and some studies shed light on professionals\u0026rsquo; use of stigmatising language concerning FND, including terms such as \u0026ldquo;fake\u0026rdquo; or \u0026ldquo;hysterical seizure\u0026rdquo; [\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e] and disparaging phrases such as \u0026ldquo;it\u0026rsquo;s all in your head\u0026rdquo; [\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e]. A recent review [\u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e] reported how common ways used by healthcare professionals to describe individuals with FND included \u0026ldquo;attention-seeking\u0026rdquo;, \u0026ldquo;manipulative\u0026rdquo;, \u0026ldquo;annoying\u0026rdquo;, \u0026ldquo;impossible to help\u0026rdquo;, \u0026ldquo;troublesome\u0026rdquo;, \u0026ldquo;challenging\u0026rdquo;, and \u0026ldquo;frustrating\u0026rdquo; [\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e, \u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e, \u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e, \u003cspan additionalcitationids=\"CR30\" citationid=\"CR29\" class=\"CitationRef\"\u003e29\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e31\u003c/span\u003e]. In contrast, FND patients reported being made to feel as if they were feigning or exaggerating their symptoms [\u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e32\u003c/span\u003e, \u003cspan citationid=\"CR33\" class=\"CitationRef\"\u003e33\u003c/span\u003e]. This highlights the need to develop a shared consensus on FND terminologies through standardising vocabulary across clinical professionals, in order to improve patient-clinician communication and reduce patient stigmatisation [\u003cspan additionalcitationids=\"CR35\" citationid=\"CR34\" class=\"CitationRef\"\u003e34\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR36\" class=\"CitationRef\"\u003e36\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eThe necessity for shared vocabularies supporting multidisciplinary work in FND is also underscored by existing literature, which reveals both distinct and overlapping realms of expertise between the two types of professionals most frequently involved with the treatment of FND patients, i.e., neurologists and psychologists [\u003cspan citationid=\"CR37\" class=\"CitationRef\"\u003e37\u003c/span\u003e, \u003cspan citationid=\"CR38\" class=\"CitationRef\"\u003e38\u003c/span\u003e]. Neurologists\u0026rsquo; proficiency in diagnosing FND and identifying its symptoms through its distinguishing physiological features is well-documented [\u003cspan citationid=\"CR38\" class=\"CitationRef\"\u003e38\u003c/span\u003e, \u003cspan citationid=\"CR39\" class=\"CitationRef\"\u003e39\u003c/span\u003e]. Psychologists, conversely, are often described in FND literature as focusing on the more intrinsic \u0026lsquo;root factors\u0026rsquo;, behaviours, personality traits and psychosocial sequelae that are linked to FND [\u003cspan citationid=\"CR40\" class=\"CitationRef\"\u003e40\u003c/span\u003e]. The need for complex, multidisciplinary approaches to treating FND has often been outlined as necessary [\u003cspan citationid=\"CR41\" class=\"CitationRef\"\u003e41\u003c/span\u003e, \u003cspan citationid=\"CR42\" class=\"CitationRef\"\u003e42\u003c/span\u003e], although challenges persist in adopting clear, standardised guidelines to communicate with patients and in sharing information across services and healthcare professionals [\u003cspan citationid=\"CR43\" class=\"CitationRef\"\u003e43\u003c/span\u003e, \u003cspan citationid=\"CR44\" class=\"CitationRef\"\u003e44\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eOne key factor in building collaborative, multidisciplinary approaches lies in the need to analyse the language used by healthcare professionals who support people with FND, to understand their vocabulary and the \u0026lsquo;emotional tone\u0026rsquo; underpinning their communications. This would allow for a better understanding of their core beliefs and conceptualisation of FND, and how these might influence both their relationships with patients and the overall quality of the support offered.\u003c/p\u003e \u003cp\u003e \u003cb\u003e1.2\u003c/b\u003e \u003cb\u003eThe application of Artificial Intelligence (AI) and Natural Language Processing (NLP) to the analysis of clinician-patient interactions\u003c/b\u003e\u003c/p\u003e \u003cp\u003e Natural Language Processing (NLP) is a technique within the broader field of Artificial Intelligence (AI) that draws from linguistics and machine learning and aims at quantifying written language as vectors that can be statistically evaluated. It offers to broaden the reach of computational analysis to include human experience, emotion, and relationships [\u003cspan citationid=\"CR45\" class=\"CitationRef\"\u003e45\u003c/span\u003e, \u003cspan citationid=\"CR46\" class=\"CitationRef\"\u003e46\u003c/span\u003e], and its application in the mental health domain has broadened exponentially in the past two decades [\u003cspan additionalcitationids=\"CR48 CR49\" citationid=\"CR47\" class=\"CitationRef\"\u003e47\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR50\" class=\"CitationRef\"\u003e50\u003c/span\u003e]. NLP is commonly applied to electronic health records (EHRs) to process large quantities of unstructured (human-authored) text, in order to return information about different text aspects, such as syntactic processing, semantic analysis (e.g., capturing meanings from single words or groups of words), and detecting relationships among terms and concepts [\u003cspan additionalcitationids=\"CR52 CR53\" citationid=\"CR51\" class=\"CitationRef\"\u003e51\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR54\" class=\"CitationRef\"\u003e54\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eElectronic health records are a rich source of data in the analysis and treatment of patients [\u003cspan citationid=\"CR55\" class=\"CitationRef\"\u003e55\u003c/span\u003e, \u003cspan citationid=\"CR56\" class=\"CitationRef\"\u003e56\u003c/span\u003e], and NLP has proven to be effective in analysing and extracting information from clinical text data [\u003cspan additionalcitationids=\"CR58\" citationid=\"CR57\" class=\"CitationRef\"\u003e57\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR59\" class=\"CitationRef\"\u003e59\u003c/span\u003e]. NLP applied to EHRs might be particularly useful in exploring health professionals\u0026rsquo; vocabularies, as written text is likely to reflect the specific variations in their knowledge and expertise and their use of lay and professional vocabularies [\u003cspan citationid=\"CR58\" class=\"CitationRef\"\u003e58\u003c/span\u003e]. NLP analysis on healthcare professionals\u0026rsquo; vocabularies has been applied in a variety of settings, for example, to explore and bridge the gap in vocabularies between healthcare professionals and their patients as well as people looking for health information online [\u003cspan additionalcitationids=\"CR61 CR62\" citationid=\"CR60\" class=\"CitationRef\"\u003e60\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR63\" class=\"CitationRef\"\u003e63\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eA specific NLP-related technique, known as \u0026lsquo;topic modelling\u0026rsquo;, has been increasingly used over the past few years to analyse textual data in EHRs to identify recurrent keywords and discussion themes [\u003cspan citationid=\"CR64\" class=\"CitationRef\"\u003e64\u003c/span\u003e] and identify people\u0026rsquo;s perspectives on their mental health issues [\u003cspan citationid=\"CR65\" class=\"CitationRef\"\u003e65\u003c/span\u003e]. Increasing interest in the healthcare domain has also been given to another NLP-derived technique, sentiment analysis, which has also been utilised to understand the general tone and emotion of clinical narratives [\u003cspan citationid=\"CR66\" class=\"CitationRef\"\u003e66\u003c/span\u003e]. In other studies [\u003cspan citationid=\"CR67\" class=\"CitationRef\"\u003e67\u003c/span\u003e], EHRs such as hospital discharge notes were analysed to determine potential readmission and mortality risk from the \u0026lsquo;sentiment\u0026rsquo; of the notes, highlighting the multifaceted potential value of capturing \u0026lsquo;emotional tones\u0026rsquo; from EHRs to inform improvement in care pathways.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec3\" class=\"Section2\"\u003e \u003ch2\u003e1.3. \u003cem\u003eIdentifying gaps and opportunities\u003c/em\u003e\u003c/h2\u003e \u003cp\u003eWhile existing studies highlight the potential of NLP in healthcare research, its role in the FND domain has received little consideration. Moreover, the comparative analysis of professional discourse between neurologists and psychologists on FND through topic modelling and sentiment analysis remains unexplored. By applying these techniques on written documents produced by neurologists and psychologists supporting patients with FND, the present study sought to understand how different professionals communicate about and perceive FND. In turn, understanding clinical narratives, as well as their differences across care professionals, can inform training, clinical practice, and interdisciplinary collaboration, ultimately fostering a healthcare environment where the nuances of FND are more deeply understood and addressed with greater effectiveness. To the authors\u0026rsquo; knowledge, this is the first study employing well-known NLP techniques to comparatively analyse the narratives and underlying emotional tones of different healthcare professionals working in FND care.\u003c/p\u003e \u003c/div\u003e"},{"header":"2. METHODOLOGY","content":"\u003cp\u003eThe current study aimed to leverage the potential of NLP to conduct an in-depth analysis of the vocabularies used and emotional tones expressed by different groups of healthcare professionals supporting individuals with FND. Two NLP techniques, topic modelling and sentiment analysis, were used to extract and classify electronic clinical documents from the outpatient services of the Salford Royal Hospital (Northern Care Alliance NHS Group Trust), a large hospital located in the Northwest of the UK. Ethical approval to extract clinical documents from hospital records was obtained from the R\u0026amp;I department of the Northern Care Alliance NHS Group Trust (approval number 22HIP47).\u003c/p\u003e \u003cdiv id=\"Sec5\" class=\"Section2\"\u003e \u003ch2\u003e2.1. \u003cem\u003eData Source\u003c/em\u003e\u003c/h2\u003e \u003cp\u003eMore than a thousand clinical documents written by clinical professionals from 2011 to 2022 were extracted from EHRs. These documents were produced by healthcare professionals supporting people with FND in different roles, which, for analysis purposes, were divided into three categories: neurologists, psychologists and \u0026lsquo;others\u0026rsquo; (e.g., physiologists, GPs and pain experts). The retrieved documents were independently checked for quality and completeness by four research group members (two research assistants, a clinical psychologist and a neurologist). Incomplete documents or records that were deemed uninformative (e.g., documents only containing very short information) were excluded.\u003c/p\u003e \u003cp\u003eAll documents were manually anonymised by research assistants employed at the Salford Royal Hospital, by removing any identifiable information before study commencement. The date, type of document (i.e., letter type), professional group category (i.e., neurologists, psychologists or others) and raw unstructured text were preserved and provided as a Word file to researchers. A Python script was written to parse the document, retrieve, and store the relevant information of each letter into a csv file, and create a structured corpus containing the \u0026lsquo;document type\u0026rsquo;, \u0026lsquo;professional group\u0026rsquo;, \u0026lsquo;date\u0026rsquo; and \u0026lsquo;text\u0026rsquo;. The corpus was further cleaned for missing values, replacements, and misspelled medical terminologies, which were identified through manual observation.\u003c/p\u003e \u003cp\u003eOf the 978 documents identified for analysis, 550 were written by neurologists, 319 by psychologists, and 108 were unlabelled, hence they were categorised as \u0026ldquo;others\u0026rdquo;. The total word count per document ranged between 200 and 1200 words. Focus was given to the labelled professional groups (i.e. neurologists and psychologists), giving a total sample size of 869 documents. The documents were also categorised by types: i.e. referrals, clinic letters, GP letters, assessments and discharge letters. Details of the different letter types and contents are provided in Appendix 1.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec6\" class=\"Section2\"\u003e \u003ch2\u003e2.2. \u003cem\u003eFramework of Exploratory Analysis\u003c/em\u003e\u003c/h2\u003e \u003cp\u003eIn this section, the general framework of the exploratory analysis is presented in Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e. In addition to the steps discussed above, NLP preprocessing steps such as tokenization, bigrams, trigrams, lemmatization and removal of stop words were also applied. Then, the state-of-the-art topic modelling and sentiment analysis techniques were used to identify differences in the usage of words, topics of discussion, and tone/sentiment across healthcare professionals (i.e. psychologists and neurologists), as well as by document types.\u003c/p\u003e \u003cdiv id=\"Sec7\" class=\"Section3\"\u003e \u003ch2\u003e2.2.1. Preprocessing\u003c/h2\u003e \u003cp\u003eTo identify the topic of discussion, preprocessing of the data was carried out (Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e). The stages of data processing included the following:\u003c/p\u003e \u003cp\u003e \u003col\u003e \u003cspan\u003e \u003cli\u003e \u003cp\u003eTokenisation; Texts are lower cased and nltks\u0026rsquo; word tokenise library was used to tokenise sentences into tokens of words. Custom tags such as titles (ms, mrs, mr, miss), date and time, special characters and a minimum word length (4) were also applied to ensure that only the most relevant tokens were left. Parts of speech (POS) tags (NOUN) were also applied. Noun-only POS tags were used as we were only interested in identifying important keywords.\u003c/p\u003e \u003c/li\u003e \u003c/span\u003e \u003cspan\u003e \u003cli\u003e \u003cp\u003eNgrams; Bigram and Trigram models were also created and applied using Gensim\u0026rsquo;s Phrases library for any tokens that can be combined as bigram or trigram.\u003c/p\u003e \u003c/li\u003e \u003c/span\u003e \u003cspan\u003e \u003cli\u003e \u003cp\u003eLemmatisation; Lemmatisation was applied using nltks\u0026rsquo; wordnet/morphy library as appropriate.\u003c/p\u003e \u003c/li\u003e \u003c/span\u003e \u003cspan\u003e \u003cli\u003e \u003cp\u003eStop words; Stop words were removed using Gensim\u0026rsquo;s simple preprocess library. To optimise the quality of topic keywords, some common and high-frequency junk terms found across both psychologists\u0026rsquo; and neurologists\u0026rsquo; records were removed during tokenisation. This was done based on empirical observation by running the topic model several times and identifying keywords that commonly occurred within the topics. The clean data was then passed on to the topic modelling algorithm.\u003c/p\u003e \u003c/li\u003e \u003c/span\u003e \u003c/ol\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec8\" class=\"Section3\"\u003e \u003ch2\u003e2.2.2. Topic Modeling\u003c/h2\u003e \u003cp\u003eTo understand the differences in how psychologists and neurologists approach FND patients, it is important to identify common discussion topics and the words associated with each topic. To do so, topic modelling, a form of computational text mining based on word co-occurrence within a corpus, was used. Topic modelling algorithms take a collection of documents as input, discover recurring \u0026lsquo;themes\u0026rsquo; discussed within the collection (topics), and then determine the degree to which each document presents each of the topics identified [\u003cspan citationid=\"CR68\" class=\"CitationRef\"\u003e68\u003c/span\u003e]. One of the most widely used unsupervised document modelling techniques, Latent Dirichlet Allocation (LDA), was applied. LDA is a generative probabilistic Bayesian model providing a representation of a document in the form of topics and topic probabilities, and it is claimed to be the simplest and most widely used topic modeling technique in fields outside of computer science [\u003cspan citationid=\"CR68\" class=\"CitationRef\"\u003e68\u003c/span\u003e, \u003cspan citationid=\"CR69\" class=\"CitationRef\"\u003e69\u003c/span\u003e]. Further details related to the underlying mathematical principles can be found in the original paper [\u003cspan citationid=\"CR70\" class=\"CitationRef\"\u003e70\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eIn our study, Gensim\u0026rsquo;s LDA model for Python was used to generate the topics of discussion. Before generating the topics, the optimal topic number was estimated by tuning the hyperparameter α, which is the Dirichlet prior to the per-document topic distribution and determines theta (θ). θ is the distribution of words per topic that, in turn, determines the shape of the overall distribution of topics. The model rearranges the topic distribution within the documents and keyword distribution within the topics to achieve good probabilities of topic-keywords distribution. For different values of α, the corresponding coherence plots were generated and used to estimate the optimal topic number. The final LDA model was then configured accordingly and used to generate the topics for each set of documents.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eFigure 2 shows that the coherence metric started with a value closer to zero before falling sharply approximately between topics 6 and 4 and then flattening out for α\u0026thinsp;=\u0026thinsp;0.001 and 0.01 for psychology and neurology records, respectively. The higher coherence value signifies dominance and importance of topic within the analysed data set. When α\u0026thinsp;=\u0026thinsp;5, the coherence plot does not show a clear distinction between dominant topics and shows a gradual fall; similarly, when α\u0026thinsp;=\u0026thinsp;1000, it again shows a reasonably gradual fall from topic 8 onward. In addition, the coherence value is close to zero for the neurology and psychology data when α\u0026thinsp;=\u0026thinsp;1000 but they do not seem to be converging quickly enough as is the case with α\u0026thinsp;=\u0026thinsp;5 values. As such, there is the need to achieve a right balance between the topic distribution not being too widely spread across the document, and a topic number which has a coherence value reasonably closer to zero. Hence, it can be concluded that it is reasonable and safe to choose the optimal topic number as 5 as it is more dominant and coherent in both the neurology and psychology dataset and also choose the value α\u0026thinsp;=\u0026thinsp;0.01 as the optimal value for creating the final model.\u003c/p\u003e\u003cdiv class=\"gridtable\"\u003e\n \u003cdiv align=\"left\" class=\"colspec\"\u003eBased on the discussion above, the following hyperparameter configuration was used in the final model for both scenarios:\u003c/div\u003e\n\u003c/div\u003e\n\u003cp\u003e\u003cimg src=\"https://myfiles.space/user_files/122228_c8a1650c59388082/122228_custom_files/img1739774642.png\"\u003e\u003cbr\u003e\u003c/p\u003e\n\u003cdiv id=\"Sec9\" class=\"Section3\"\u003e\n \u003ch2\u003e2.2.3. Sentiment Analysis\u003c/h2\u003e\n \u003cp\u003eSentiment analysis is a computational method for determining the emotional tone behind words. It is essential for understanding the attitudes, opinions, and emotions expressed in textual data.\u003c/p\u003e\n \u003cp\u003eIn this study, sentiment analysis was conducted to explore the sentiment levels of neurologists and psychologists as reflected in various types of clinical documentation and also verify the topics and themes of discussion observed from the topic modelling analysis. Two pre-trained sentiment models, VADER and Flair, were implemented. VADER is a lexicon and rule-based sentiment analysis tool [\u003cspan class=\"CitationRef\"\u003e72\u003c/span\u003e] deployed to assess sentiment levels across different file types within the clinical documentation of each professional group. Its efficiency and sensitivity to subtle linguistic cues make it particularly suitable for analysing the structured format and concise language often found in such documents. However, it does not examine the context-dependent nuances of the sentences. Therefore, while VADER\u0026rsquo;s lexicon-based may be a fast and effective tool for processing large volumes of documents, it may not fully capture the context-dependent nuances of sentiment. Flair\u0026rsquo;s deep learning approach fills this gap by analysing sentences in their entirety, considering the context to provide a nuanced understanding of sentiment. This is crucial for understanding complex narratives found in referral letters or discharge summaries, where the sentiment may be influenced by medical conditions, treatment outcomes, or patient experiences. Also, clinical documents present a unique challenge due to their use of specialised medical terminology. Together, these models offer a comprehensive sentiment analysis that can be used to cross-validate each other\u0026apos;s output since the models are not specifically trained with medical terminologies. This tailored application can enhance the reliability of sentiment analysis and contribute valuable perspectives on the emotional and professional dynamics within clinical settings.\u003c/p\u003e\n\u003c/div\u003e"},{"header":"3. RESULTS","content":"\u003cdiv id=\"Sec11\" class=\"Section2\"\u003e \u003ch2\u003e3.1 \u003cb\u003eTopic modeling\u003c/b\u003e\u003c/h2\u003e \u003cp\u003eThe topic analysis was divided into two stages. In the first stage, words and themes of topic discussions between psychologists and neurologists were compared. In the second stage, a detailed analysis was conducted on psychology and neurology records according to letter types.\u003c/p\u003e \u003cdiv id=\"Sec12\" class=\"Section3\"\u003e \u003ch2\u003e3.1.1 Professional group comparison: identifying main differences in communication between neurologists and psychologists\u003c/h2\u003e \u003cp\u003eFirstly, the main differences between the two professional groups were considered across all documents (regardless of the document type \u0026ndash; e.g., discharge letter). Figures\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e3\u003c/span\u003ea and \u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e3\u003c/span\u003eb below show the most salient terms used by neurologists and psychology professionals in all clinical documents. Additionally, they also show inter-topic distribution plots, which demonstrate the \u0026lsquo;importance\u0026rsquo; of each topic (i.e., the frequency with which that topic was addressed in clinical documents). Both psychological and neurological medical records had evenly distributed and similar-sized topics of discussion, with some contributing less to the discussion. Most of the topics were distinct from one another, although there were some overlaps between topics 1 and 2 in the psychology records.\u003c/p\u003e \u003cp\u003eTo maintain the quality of topic distribution, some common terms widely used by both professional groups, such as \u0026ldquo;diagnosis\u0026rdquo;, \u0026ldquo;session\u0026rdquo;, \u0026ldquo;therapy\u0026rdquo;, \u0026ldquo;service\u0026rdquo;, \u0026ldquo;attack\u0026rdquo;, and \u0026ldquo;episode\u0026rdquo;, were removed before generating the topics.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eFigure \u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e3\u003c/span\u003e. Inter-topic distribution plot showing the uniqueness, spread and size of the topics\u003c/p\u003e \u003cp\u003eThe top thirty salient terms across all the psychology documents \u0026ndash; as seen in the inter-topic distribution plots (Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e3\u003c/span\u003ea above)- highlighted the frequent use of terms related to inner/subjective experiences of people with FND (e.g., \u0026lsquo;experience\u0026rsquo;, \u0026lsquo;stress\u0026rsquo; and \u0026lsquo;awareness\u0026rsquo;) and the emotional and psychological correlates of living with their symptoms (e.g., \u0026lsquo;feeling\u0026rsquo;, \u0026lsquo;impact\u0026rsquo;, \u0026lsquo;control\u0026rsquo; [or lack of thereof] and \u0026lsquo;pressure\u0026rsquo;). It is also worth noticing that the most commonly used terms include positive and proactive language, such as \u0026lsquo;action\u0026rsquo;, \u0026lsquo;progress\u0026rsquo; and \u0026lsquo;opportunity\u0026rsquo;.\u003c/p\u003e \u003cp\u003e Overall, in psychology professionals\u0026rsquo; language, there seems to be a well-balanced importance given to patients\u0026rsquo; treatment (including aspects such as medication, care approaches and intervention planning) as well as more personal dimensions, such as the psychological sequelae of living with FND.\u003c/p\u003e \u003cp\u003eTable\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e below shows the important keywords for psychology documents based on topics of discussion. Although the topic modelling algorithm produced five topics, as seen in Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e3\u003c/span\u003e, Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e only showed the four most relevant topics of discussion as these were deemed to be the most representative of relevant aspects in clinicians\u0026rsquo; communication with and about patients. For each topic, some of the most relevant keywords are reported, together with a topic name based on the semantic commonalities among topic keywords. Following the identification of topics through topic modelling, a human-led process of interpretation was applied to the topics retrieved. As several authors pointed out [\u003cspan citationid=\"CR55\" class=\"CitationRef\"\u003e55\u003c/span\u003e, \u003cspan additionalcitationids=\"CR74\" citationid=\"CR73\" class=\"CitationRef\"\u003e73\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR75\" class=\"CitationRef\"\u003e75\u003c/span\u003e], the topics retrieved by topic modelling techniques need to undergo a process of sense-making based on the researcher\u0026rsquo;s understanding of words reported as strongly associated with each topic. To do this, an interpretation process was performed independently by the study principal investigator (MSM) and a researcher team member with clinical expertise (DDB). Interpretations and themes were compared, and discrepancies were resolved by consensus.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eKeywords and topics: Psychology documents\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"3\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colspan=\"3\" nameend=\"c3\" namest=\"c1\"\u003e \u003cp\u003ePsychology Documents\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTopic No.\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eTopic Name\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eSelected keywords\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePsychoeducation about FND\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eapproach, information, change, exercise, compassion, respect, health, body, trauma\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eDiagnosis and prognosis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eassessment, disorder, symptom, progress, stress, year, appointment, history, treatment\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePragmatic support for symptom management\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eappointment, telephone, letter, strategy, treatment, support, health, medication, breathing\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eEmotional and social support for symptom management\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003efeeling, pressure, anxiety, management, family, emotion, sensation, awareness, communication\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003e \u003cul\u003e \u003cli\u003e \u003cp\u003eTopic 1 (Psychoeducation about FND): The dominant terms revolved around discussions of factors and experiences related to seizures, access to information, and approaches to managing FND (e.g., adopting self-compassion, and taking care of one\u0026rsquo;s mental and physical health).\u003c/p\u003e \u003c/li\u003e \u003cli\u003e \u003cp\u003eTopic 2 (Diagnosis and prognosis): This theme focused on the diagnostic process both from a medical perspective (with related keywords such as \u0026lsquo;assessment\u0026rsquo; and \u0026lsquo;disorder\u0026rsquo;) and from a more subjective one, with terms such as \u0026lsquo;stress\u0026rsquo; that suggest a consideration of how the diagnosis of FND can impact on people\u0026rsquo;s wellbeing and personal experiences in different areas of their lives.\u003c/p\u003e \u003c/li\u003e \u003cli\u003e \u003cp\u003eTopic 3 (Pragmatic support): The dominant terms referred to objective ways of obtaining support for FND symptoms, including appointments, receiving clinical letters, adopting different strategies for treatment and using medication.\u003c/p\u003e \u003c/li\u003e \u003cli\u003e \u003cp\u003eTopic 4 (Emotional/personal support): Although similar to the previous topic in its focus on long-term management strategies (e.g., \u0026lsquo;management and \u0026lsquo;review\u0026rsquo;), this topic also seemed to stress a social and emotional component that may play a key role in coping with FND in the long term. Indeed, there were terms such as \u0026lsquo;family\u0026rsquo;, \u0026lsquo;emotion\u0026rsquo;, \u0026lsquo;sensation\u0026rsquo; and \u0026lsquo;feeling\u0026rsquo; that seemed to refer to the importance of emphasising relational and emotional components of symptomatic management in FND.\u003c/p\u003e \u003c/li\u003e \u003c/ul\u003e \u003c/p\u003e \u003cp\u003eNeurologists\u0026rsquo; conversations, on the other hand, seemed to show different patterns in their communications with and about clients (Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e3\u003c/span\u003eb). More specifically, the 30 most salient terms across all neurology documents showed that their discussion mostly revolved around seizure attacks, admission and potential actions taken during those episodes. The focus was also on patients\u0026rsquo; health and their treatment, history and medication, as well as the duration of attacks, due to using terms such as \u0026lsquo;month\u0026rsquo;, \u0026lsquo;night\u0026rsquo;, \u0026lsquo;minute\u0026rsquo;, and \u0026lsquo;today\u0026rsquo;. A closer look at the topic distribution in Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e showed topic-wise discussion themes mentioned by neurologists.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eKeywords and topics - Neurology documents\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"3\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colspan=\"3\" nameend=\"c3\" namest=\"c1\"\u003e \u003cp\u003eNeurology Documents\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTopic No.\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eTopic Name\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eSelected keywords\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e1\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eAssessment of FND and contributing/maintaining factors\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003emedication, seizure, assessment, patient, admission, management, clinic, stress, sleep, neuropsychology\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eTreatment planning\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eseizure, telemetry, treatment, medication, admission, discharge\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eManagement of FND symptoms\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003emedication, today, year, appointment, week, attendance, management\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e4\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eRecommendations for support and long-term management\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003ecitalopram, behaviour, health, husband, disturbance, awareness, management\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003e \u003cul\u003e \u003cli\u003e \u003cp\u003eTopic 1 (Assessment of FND and contributing/maintaining factors): The dominant theme revolved around discussions about the assessment of FND symptoms (\u0026lsquo;seizure\u0026rsquo; and \u0026lsquo;assessment\u0026rsquo;), medication, and characteristics of service provision (\u0026lsquo;e.g., admission\u0026rsquo; and \u0026lsquo;neuropsychology\u0026rsquo;).\u003c/p\u003e \u003c/li\u003e \u003cli\u003e \u003cp\u003eTopic 2 (Treatment planning) \u0026ndash; The second theme placed an emphasis on strategies for ongoing monitoring aimed at establishing best treatment options (e.g., \u0026lsquo;telemetry\u0026rsquo;, \u0026lsquo;video\u0026rsquo;, \u0026lsquo;treatment\u0026rsquo; and \u0026lsquo;medication\u0026rsquo;) according to both patient symptoms (\u0026lsquo;seizure\u0026rsquo;) and other conditions (\u0026lsquo;pregnancy\u0026rsquo;). It also contained a reference to different stages of the patient journey, such as \u0026lsquo;admission\u0026rsquo; and \u0026lsquo;discharge\u0026rsquo;.\u003c/p\u003e \u003c/li\u003e \u003cli\u003e \u003cp\u003eTopic 3 (Management of FND symptoms) \u0026ndash; Quite similar to the previous theme, this third theme focused on different aspects of managing FND, including taking \u0026lsquo;medication\u0026rsquo;, attending \u0026lsquo;appointments\u0026rsquo; and adopting strategies for ongoing \u0026lsquo;management\u0026rsquo; of this condition.\u003c/p\u003e \u003c/li\u003e \u003cli\u003e \u003cp\u003eTopic 4 (Recommendations for support and long-term management) \u0026ndash; this theme included terms related to modifications in \u0026lsquo;behaviour\u0026rsquo; and \u0026lsquo;health\u0026rsquo; attitudes to manage FND symptoms in the long term. Interestingly, though, there were some terms related to key aspects that neurologists appear to consider as crucial in FND management: the involvement of patients\u0026rsquo; family and close network (\u0026lsquo;father\u0026rsquo;, \u0026lsquo;husband\u0026rsquo; and \u0026lsquo;friend\u0026rsquo;), attention to the person overall mental health (\u0026lsquo;citalopram\u0026rsquo;) and psychological wellbeing (\u0026lsquo;awareness\u0026rsquo; and \u0026lsquo;disturbance\u0026rsquo;).\u003c/p\u003e \u003c/li\u003e \u003c/ul\u003e \u003c/p\u003e \u003cp\u003eFollowing these analyses, a further set was performed to gain a more granular understanding of communication differences between the two professional groups (psychologists and neurologists) across different document types (referral letters, clinic letters, GP letters, assessment and discharge letters). The topics retrieved and the related most relevant keywords topic-wise are illustrated in Appendices 2\u0026ndash;6, and the main differences that emerged are presented descriptively below.\u003c/p\u003e \u003cp\u003e \u003cb\u003e3.1.2. Group comparisons across document \u0026lsquo;types\u0026rsquo;: exploring document types separately better to understand differences in communications between neurologists and psychologists\u003c/b\u003e \u003c/p\u003e \u003cp\u003eOnce the main language differences between psychologists and neurologists had been outlined, our analyses progressed toward further investigating the granularity of these differences by analysing their communication patterns and topics, focusing on each document type (referral letters, clinic letters, GP letters, assessment letters, and discharge letters) separately.\u003c/p\u003e \u003cdiv id=\"Sec13\" class=\"Section4\"\u003e \u003ch2\u003e3.1.2.1. Referral letters\u003c/h2\u003e \u003cp\u003eBoth referral letters written by neurologists and by psychologists showed some commonly recurring topics, such as the reference to FND symptoms (\u0026lsquo;seizure\u0026rsquo;, [alteration in] \u0026lsquo;consciousness\u0026rsquo;) and mention of assessment, intervention planning and management of FND (\u0026lsquo;assessment\u0026rsquo;, \u0026lsquo;intervention\u0026rsquo;, \u0026lsquo;hospital\u0026rsquo;, \u0026lsquo;outpatient\u0026rsquo; and \u0026lsquo;clinic\u0026rsquo;). Another important commonality between the two groups is the reference to aetiological and maintaining factors of FND, such as \u0026lsquo;trauma\u0026rsquo; and \u0026lsquo;stress\u0026rsquo;).\u003c/p\u003e \u003cp\u003eThe main differences between the two professional categories were reflected in the use of medical terminology (e.g., \u0026lsquo;disorder\u0026rsquo;), which was more frequent in neurologists\u0026rsquo; referral letters as compared to psychologists\u0026rsquo;. On this note, neurologists also seemed to refer more often to other medical conditions (e.g., \u0026lsquo;epilepsy\u0026rsquo; and \u0026lsquo;autism\u0026rsquo;, \u0026lsquo;drug\u0026rsquo; [abuse] comorbid to FND, that they may have considered and/or assessed for during patient visits. They also mentioned a broader list of FND-related medical terms, such as \u0026lsquo;convulsions\u0026rsquo;, [lack/loss of] \u0026lsquo;consciousness\u0026rsquo; and \u0026lsquo;myoclonus\u0026rsquo;.\u003c/p\u003e \u003cp\u003eInterestingly, psychologists, but not neurologists, mentioned that patients were usually women, therefore giving relevance to personal characteristics such as their gender. They also placed great importance on the overall quality of patients\u0026rsquo; lives by frequently paying attention to pain (\u0026lsquo;painkillers\u0026rsquo;, \u0026lsquo;headaches\u0026rsquo;) and quality of \u0026lsquo;sleep\u0026rsquo;. They also mentioned the term \u0026lsquo;goal\u0026rsquo;, which in their referral letters was often used to indicate the goals agreed upon with the patient and to achieve which a referral to another service might have been needed (e.g., psychological services offering trauma-focused therapy). Neurologists showed appreciation of the \u0026lsquo;burden\u0026rsquo; that FND can represent on patients\u0026rsquo; lives and mentioned this term in a few of their referral letters, mostly to indicate the need and/or urgency for a patient to receive support.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec14\" class=\"Section4\"\u003e \u003ch2\u003e\u003cb\u003e3.1.2.2 Clinic letters\u003c/b\u003e\u003c/h2\u003e \u003cp\u003eThe split between a \u0026lsquo;medical focus\u0026rsquo; versus a more comprehensive attention to a range of factors influencing FND in the two professional groups is perhaps even more evident in the topics retrieved in the clinic letters. Whilst neurologists\u0026rsquo; discussions revolved around the \u0026lsquo;brain\u0026rsquo; and physiological manifestations of FND such as \u0026lsquo;myokymia\u0026rsquo;, \u0026lsquo;seizure\u0026rsquo; and \u0026lsquo;memory\u0026rsquo;, psychologists\u0026rsquo; vocabulary encompassed a range of terms that showcased their appreciation for different FND-related and personal aspects of people's lives. Among these, there were \u0026lsquo;childhood\u0026rsquo; experiences, \u0026lsquo;feeling[s] and emotions[s]\u0026rsquo; reported in clinical appointments, and an appreciation for the subjective experience of FND-related \u0026lsquo;stress\u0026rsquo;, \u0026lsquo;overwhelm\u0026rsquo; and \u0026lsquo;pressure\u0026rsquo; experienced by patients. There was also a reference to psychological correlates of FND, such as \u0026lsquo;dissociation\u0026rsquo;, and a mention of cognitive, emotional and behavioural coping strategies (e.g., \u0026lsquo;belief\u0026rsquo;, \u0026lsquo;habit\u0026rsquo;, \u0026lsquo;commitment\u0026rsquo;), representing a unique feature in psychologists\u0026rsquo; communication. Although terms such as \u0026lsquo;partners\u0026rsquo; and \u0026lsquo;family\u0026rsquo; - referring to personal dimensions of people\u0026rsquo;s lives- were also present in neurologists\u0026rsquo; communication, these terms were used in a more factual/descriptive way, e.g., to describe the caregiver(s) accompanying patients to neurology appointments, rather than to convey an appreciation of patients\u0026rsquo; social/family network and the role they might play in FND management.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec15\" class=\"Section4\"\u003e \u003ch2\u003e\u003cb\u003e3.1.2.3 GP letters\u003c/b\u003e\u003c/h2\u003e \u003cp\u003eThe trend described above (using a medical vocabulary vs a more holistic one) was once again evident in the topics retrieved from letters sent to GPs. All the five topics that were more relevant in neurologists\u0026rsquo; communications with other medical professionals (GPs) contained a reference to symptoms, diagnostic and prognostic processes (\u0026lsquo;NEAD\u0026rsquo;, \u0026lsquo;recovery\u0026rsquo;) and types of support and services (e.g., \u0026lsquo;neurology\u0026rsquo; and \u0026lsquo;community\u0026rsquo; services, \u0026lsquo;letter\u0026rsquo; and \u0026lsquo;telephone\u0026rsquo;) that may be part of the patient journey. Words such as \u0026lsquo;friend\u0026rsquo; were present, but as above, they were mostly used to provide contextual information, as exemplified by the following excerpt from a neurologist\u0026rsquo;s letter to a GP: \u0026ldquo;\u003cem\u003eHer friend (\u0026hellip;) says that (\u0026hellip;) was at her home and was about to sleep on her couch when she started staring into space\u003c/em\u003e\u0026rdquo;.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec16\" class=\"Section4\"\u003e \u003ch2\u003e\u003cb\u003e3.1.2.4 Assessment letters\u003c/b\u003e\u003c/h2\u003e \u003cp\u003eThe topics retrieved in assessment letters showed the different conceptualisations of the assessment processes in the two professional groups considered, with once again a medical and a biopsychosocial model emerging from clinicians\u0026rsquo; written communications. The primary dimensions considered in neurologists\u0026rsquo; assessments are physiological \u0026lsquo;signs\u0026rsquo; such as \u0026lsquo;tremor\u0026rsquo;, service engagement (\u0026lsquo;treatment, \u0026lsquo;attendance\u0026rsquo;, \u0026lsquo;history, \u0026lsquo;month\u0026rsquo;), medication (\u0026lsquo;lamotrigine\u0026rsquo;, \u0026rsquo;risperidone\u0026rsquo;) and comorbidities that may be present or warrant further exploration (\u0026lsquo;anxiety\u0026rsquo; and \u0026lsquo;depression\u0026rsquo;). The term \u0026rsquo;childhood\u0026rsquo;, indicating a consideration for early traumatic experiences influencing FND, was present but was retrieved as part of topic five, meaning its use was not so frequent. Conversely, psychologists\u0026rsquo; assessment letters offered proof of the importance of many factors when considering the best care options for patients. More specifically, a set of medical/physiological aspects was considered (\u0026lsquo;stress\u0026rsquo;, \u0026lsquo;seizure\u0026rsquo;, \u0026lsquo;medication\u0026rsquo;), but this was in conjunction with psychosocial aspects (\u0026lsquo;exercise\u0026rsquo;, \u0026lsquo;emotion\u0026rsquo;, \u0026lsquo;relaxation\u0026rsquo;, \u0026lsquo;awareness\u0026rsquo;) that showed how psychologists think of FND patients from a perspective of complexity, encompassing disorder-related dimensions but also opportunities for symptomatic management through engagement in activities that can improve psychosomatic wellbeing. In this regard, it was worth noticing the presence of positive and encouraging terms in their vocabulary, such as \u0026lsquo;opportunity\u0026rsquo;, \u0026lsquo;strategy\u0026rsquo; and \u0026lsquo;development\u0026rsquo;.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec17\" class=\"Section4\"\u003e \u003ch2\u003e\u003cb\u003e3.1.2.5 Discharge letters\u003c/b\u003e\u003c/h2\u003e \u003cp\u003e In line with previous considerations, the analysis of discharge letters evidenced the presence of a communicative approach in neurologists\u0026rsquo; written text that favoured objective/factual information to motivate patient discharge, as evidenced, for example, by salient terms composing topic one (e.g., \u0026lsquo;discharge\u0026rsquo;, \u0026lsquo;admission\u0026rsquo;, \u0026lsquo;neurology\u0026rsquo;, \u0026lsquo;assessment\u0026rsquo;, \u0026lsquo;gynaecology\u0026rsquo;, \u0026lsquo;medication\u0026rsquo;, \u0026lsquo;history\u0026rsquo;, \u0026lsquo;telemetry\u0026rsquo;, \u0026lsquo;haemoglobin\u0026rsquo;, \u0026lsquo;pregnancy\u0026rsquo;). Psychologists, instead, tended to use terms referring to a more general appraisal of patients\u0026rsquo; conditions as characterised by \u0026lsquo;deterioration\u0026rsquo;, \u0026lsquo;alcohol consumption\u0026rsquo; leading to a feeling of \u0026lsquo;concern\u0026rsquo;, but also by the appreciation for \u0026lsquo;progress\u0026rsquo; and \u0026lsquo;goals\u0026rsquo; that patients were pursuing in their journey. Further to this point, psychologists\u0026rsquo; discharge letters tended to refer to \u0026lsquo;goals\u0026rsquo; and future directions when informing suggestions or more direct requests for patients to access additional support upon discharge.\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv id=\"Sec18\" class=\"Section2\"\u003e \u003ch2\u003e\u003cb\u003e3.2\u003c/b\u003e \u003cb\u003eSentiment Analysis\u003c/b\u003e\u003c/h2\u003e \u003cp\u003eBased on the results from topic modelling, the next step was to use sentiment analysis to investigate how the two health professional groups' different choices of words and approaches signaled the \u0026lsquo;emotional tone\u0026rsquo; underpinning their interactions. The section below presents the tone variation between professional groups (psychologists and neurologists) and among document types. The previously mentioned pre-trained sentiment analysis models (VADER and Flair) were used to cross-validate the sentiment scores. A subset of patient records was analysed by domain experts to validate the tone of the patient records, and the results across letter types were implemented to further verify the model\u0026rsquo;s sentiment output. It is important to note, in this regard, that the terms \u0026lsquo;positive\u0026rsquo;, \u0026lsquo;neutral\u0026rsquo; and \u0026lsquo;negative\u0026rsquo; emotional tone are used to refer to the overall emotional tone expressed within the text, essentially analysing whether the general sentiment conveyed by healthcare professionals in their letters is favourable, unfavourable, or neutral [\u003cspan citationid=\"CR76\" class=\"CitationRef\"\u003e76\u003c/span\u003e].\u003c/p\u003e \u003cdiv id=\"Sec19\" class=\"Section3\"\u003e \u003ch2\u003e\u003cb\u003e3.2.1 VADER sentiment analysis\u003c/b\u003e\u003c/h2\u003e \u003cp\u003eThe compound sentiment scores across the two professional groups according to letter types are presented in Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e4\u003c/span\u003e. Based on the plots, it can be inferred that neurologists\u0026rsquo; interactions with patients across all the stages of care tend to be quite cautious, which could explain the pronounced negative score. For psychologists, assessments and clinic letters tend to be more positive compared to GP letters and referral letters, with discharge letters showing a high level of positivity.\u003c/p\u003e \u003cp\u003eThis was reflected when looking at the compound sentiment score distribution of the professional groups through the violin plots in Fig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e5\u003c/span\u003e. Psychologists seemed to take a more positive, friendly, and informal approach than neurologists, with the bulk of their records leaning towards the positive side. Looking at the non-compound sentiment scores, it seemed that both psychologists and neurologists tended to use neutral sentiment keywords, with similar distributions of positive and negative sentiment keywords.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec20\" class=\"Section3\"\u003e \u003ch2\u003e\u003cb\u003e3.2.2 Flair sentiment analysis\u003c/b\u003e\u003c/h2\u003e \u003cp\u003eTo cross-validate our sentiment results from VADER, the Flair model was also used to generate sentiment scores, as seen in Figs.\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e6\u003c/span\u003e and \u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e7\u003c/span\u003e. The results showed similar outcomes to our findings derived from the VADER model. As seen in Fig.\u0026nbsp;\u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e7\u003c/span\u003e, neurologists\u0026rsquo; sentiment scores were clearly situated at the negative end across all the letter types except for referral letters. Psychologists, instead, seemed to show a more positive and friendly approach when dealing with patients. This is further reflected in Fig.\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e6\u003c/span\u003e, referring to the analyses of patient records across the two professional groups. Overall, neurologists tend to be more critical and reserved in their approach when dealing with FND patients.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv id=\"Sec21\" class=\"Section2\"\u003e \u003ch2\u003e\u003cb\u003e3.3 Expert Review\u003c/b\u003e\u003c/h2\u003e \u003cp\u003eTo evaluate the performance of the sentiment model for medical notes analysis, an expert review was conducted to compare the analysis results with the domain expert\u0026rsquo;s opinions. Approximately 100 medical records were first selected from the neutral, positive, and negative groups (34, 33, 33, respectively) as the ground truth. Then, a healthcare professional (expert clinical psychologist) who was \u0026lsquo;blind\u0026rsquo; to the results of the sentiment analysis was asked to rate the records selected, classifying them as positive, negative, and neutral. The results obtained were then compared with the sentiment classification results of VADER using the compound sentiment score and the non-compound percentage score of negative, positive, and neutral words in each record. The results are tabulated below (Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e). There was a 61% match using the compound sentiment score. For the remaining 39%, a high percentage of the records not matching was mostly one-degree differences, e.g., model rated negative, but expert rated neutral, or model rated positive, expert rated neutral, or vice versa. In total, 17 nonmatching records were falling into the \u0026lsquo;negative to neutral/neutral to negative\u0026rsquo; labels, with the majority being from neurology records (11/17). Looking at the \u0026lsquo;positive to neutral/neutral to positive\u0026rsquo; group, there were 13 nonmatching records, with the majority being from the neurology records (11/13).\u003c/p\u003e \u003cp\u003eThere were only nine records showing two-degree differences, i.e., model rated positive, expert rated negative (or vice versa), with eight of such cases showing the expert assigned negative sentiment labels, with most of them being neurology records (8/9). There are different possible explanations for the presence of these expert/model divergences. One lies in the VADER model not being trained with medical terminologies related to FND patients and not considering the context in which clinician-patient conversations take place. This might help to explain why the expert, and more widely, healthcare professionals, might tend to have more neutral or pessimistic views of the \u0026lsquo;sentiment\u0026rsquo; underlying a conversation. In other words, whilst the model might render a \u0026lsquo;positive\u0026rsquo; label based on the presence of positive terms in the document analysed, clinical professionals are likely to consider the content of that document in light of wider dimensions \u0026ndash; e.g., the severity of patient\u0026rsquo;s symptoms (despite possible positive events or improvements occurring) or whether a patient is experiencing pivotal life changes that might bear a negative influence on their overall mental health. Furthermore, it appears evident that most \u0026lsquo;mismatches\u0026rsquo; are present in documents produced by neurologists, which calls into question whether a more medicalised language could lead to greater difficulties for AI models to capture the underlying \u0026lsquo;sentiment\u0026rsquo; of the conversation.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab3\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 3\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eExpert review results\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"2\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMetric\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eObservation\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCompound sentiment score\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e61 matches\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eOne-degree difference\u003c/p\u003e \u003cp\u003e(neg to neutral or neutral to neg)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e17\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eOne-degree difference\u003c/p\u003e \u003cp\u003e(pos to neutral or neutral to pos)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e13\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTwo-degree difference\u003c/p\u003e \u003cp\u003e(pos to neg or neg to pos)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e9\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003c/div\u003e"},{"header":"4. DISCUSSION","content":"\u003cp\u003eThe results of this study provide significant insights into the linguistic and tonal differences between neurologists and psychologists when addressing FND patients in written clinical documents. By leveraging NLP techniques and sentiment analysis, the study highlighted how these professional groups differed in their clinical discourse, which may have direct implications for patient care, communication, and treatment approaches. This discussion will interpret these findings in light of their clinical relevance, theoretical implications, and potential for future research and practice.\u003c/p\u003e \u003cdiv id=\"Sec23\" class=\"Section2\"\u003e \u003ch2\u003e4.1. \u003cem\u003eTopic modeling: Thematic differences between psychologists and neurologists\u003c/em\u003e\u003c/h2\u003e \u003cp\u003eThe topic modeling analysis revealed clear distinctions in the focus of communication between psychologists and neurologists, which underscores the different professional orientations of these two groups. Psychologists predominantly focused on themes related to emotional and subjective experiences, personal care, and the long-term management of symptoms. This is evident in the frequent use of words like \u0026lsquo;stress\u0026rsquo;, \u0026lsquo;awareness\u0026rsquo;, \u0026lsquo;feeling\u0026rsquo; and \u0026lsquo;support\u0026rsquo;, which reflect a holistic and patient-centred approach. This finding aligns with the role of psychology in FND, which is not only to diagnose and treat this condition, but also to address how patients manage their symptoms in their everyday life, help them to improve their overall mental health and quality of life, and decrease medical service utilisation [\u003cspan additionalcitationids=\"CR78 CR79 CR80\" citationid=\"CR77\" class=\"CitationRef\"\u003e77\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR81\" class=\"CitationRef\"\u003e81\u003c/span\u003e]. On the other hand, neurologists used more medical and technical language, with their communication centring on clinical and diagnostic terms such as \u0026lsquo;seizure\u0026rsquo;, \u0026lsquo;medication\u0026rsquo;, \u0026lsquo;assessment\u0026rsquo; and \u0026lsquo;history\u0026rsquo;. This is reflective of the medical model that neurologists employ in their treatment of FND, where the emphasis is on identifying physiological abnormalities and managing symptoms through clinical interventions [\u003cspan citationid=\"CR82\" class=\"CitationRef\"\u003e82\u003c/span\u003e]. This also aligns with evidence on neurologists\u0026rsquo; pivotal role in diagnosing FND, explaining its mechanisms to patients and suggesting appropriate medical treatment to reduce the burden of FND symptoms [\u003cspan citationid=\"CR83\" class=\"CitationRef\"\u003e83\u003c/span\u003e, \u003cspan citationid=\"CR84\" class=\"CitationRef\"\u003e84\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eIn other words, the findings of the present study seem to suggest that neurologists\u0026rsquo; communications are more likely to emphasise the patient\u0026rsquo;s immediate clinical state and medical treatment, while psychologists take a broader view that encompasses emotional, psychological, and social factors. Importantly, this divergence in focus may reflect differences in training, professional responsibilities, and expectations placed upon these healthcare professionals. This finding has implications for interdisciplinary collaboration, as it suggests that optimal care for FND patients requires the integration of both perspectives: the neurological focus on symptom management and the psychological attention to emotional support and coping mechanisms.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec24\" class=\"Section2\"\u003e \u003ch2\u003e4.2. \u003cem\u003eDocument types and professional communication styles\u003c/em\u003e\u003c/h2\u003e \u003cp\u003eThe analysis of specific document types (referral letters, clinic letters, GP letters, assessment letters, and discharge letters) shed further light on the granularity of communication differences between the two groups. Across all document types, psychologists tended to focus on a broad array of factors influencing FND patients, including psychosocial aspects such as childhood trauma, quality of life, and emotional coping strategies. Neurologists focused more narrowly on clinical symptoms, diagnosis, and medical treatment plans. For example, in referral letters, neurologists' communications were more clinical and diagnostic, with references to seizure types, medical history, and medications. Psychologists, by contrast, incorporated a broader understanding of the patient\u0026rsquo;s life, discussing personal goals and emotional factors such as pain, stress, and sleep quality. This suggests that psychologists may be more likely to take a holistic view of the patient when communicating with other professionals, while neurologists may focus on ensuring that other clinicians are aware of the patient\u0026rsquo;s medical condition and treatment needs.\u003c/p\u003e \u003cp\u003eMore generally, the neurologists\u0026rsquo; tendency to use medical and diagnostic-centred communication and psychologists\u0026rsquo; proclivity to adopt a biopsychosocial perspective on assessment and care for FND was evident across all types of documents analysed. This calls for effective interdisciplinary collaboration to ensure that patients receive comprehensive care that addresses both their medical and psychological needs [\u003cspan citationid=\"CR85\" class=\"CitationRef\"\u003e85\u003c/span\u003e, \u003cspan citationid=\"CR86\" class=\"CitationRef\"\u003e86\u003c/span\u003e]. A failure to appreciate the complementary nature of these communication styles could lead to fragmented care, with one aspect of the patient\u0026rsquo;s experience being overlooked [\u003cspan citationid=\"CR87\" class=\"CitationRef\"\u003e87\u003c/span\u003e]. This integration in domain knowledge and communication styles appears to be even more relevant when considering that for the past half-century, the clinical management of FND has been subject to a great deal of fragmentation, with a paucity of care pathways mutually agreed upon between neurologists and psychiatrists [\u003cspan citationid=\"CR88\" class=\"CitationRef\"\u003e88\u003c/span\u003e]. Besides being potentially detrimental to FND patients, this fragmentation often leads to poor outcomes and frustrations for both patients and professionals [\u003cspan citationid=\"CR89\" class=\"CitationRef\"\u003e89\u003c/span\u003e]. In light of these considerations, studies such as the current one offer support for the need for a more substantial shift in these care models and the consequent recognition of the need for truly multidisciplinary and integrated care [\u003cspan citationid=\"CR90\" class=\"CitationRef\"\u003e90\u003c/span\u003e, \u003cspan citationid=\"CR91\" class=\"CitationRef\"\u003e91\u003c/span\u003e].\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec25\" class=\"Section2\"\u003e \u003ch2\u003e4.3. \u003cem\u003eSentiment analysis: Tone and emotional engagement\u003c/em\u003e\u003c/h2\u003e \u003cp\u003eThe sentiment analysis results provided another layer of insight into how psychologists and neurologists differ in their interactions with FND patients. Across all stages of care, neurologists tended to have a more cautious and often negative tone, while psychologists exhibited a more positive and emotionally supportive tone. This difference is particularly salient in the context of patient care, as the tone of communication can significantly impact a patient\u0026rsquo;s experience, trust, and engagement with their treatment plan [\u003cspan additionalcitationids=\"CR93\" citationid=\"CR92\" class=\"CitationRef\"\u003e92\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR94\" class=\"CitationRef\"\u003e94\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eThe positive language in psychological documents, such as \u0026lsquo;opportunity\u0026rsquo;, \u0026lsquo;progress\u0026rsquo; and \u0026lsquo;support\u0026rsquo;, may help to foster a more hopeful and proactive patient mindset, which evidence increasingly suggests can be particularly important in the management of chronic conditions like FND [\u003cspan citationid=\"CR95\" class=\"CitationRef\"\u003e95\u003c/span\u003e, \u003cspan citationid=\"CR96\" class=\"CitationRef\"\u003e96\u003c/span\u003e]. Conversely, the more negative tone found in neurologists\u0026rsquo; documents may reflect the cautious and often uncertain nature of medical diagnosis and treatment in FND, a condition that is still not fully understood and can be challenging to treat [\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e, \u003cspan citationid=\"CR97\" class=\"CitationRef\"\u003e97\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eNeurologists may also focus more on risk factors, complications, and the need for medical interventions, which could explain the prevalence of negative sentiment. While this cautious tone is likely a reflection of the complexities and challenges of managing FND, it may also have unintended consequences for patient engagement and satisfaction. For instance, patients may feel discouraged or less hopeful if their interactions with neurologists are perceived as overly negative or detached. This datum appears to be even more important when applied to FND, as there is abundant evidence regarding the role that problematic conversations and stigmatising attitudes from clinicians can have on FND patients\u0026rsquo; disease management, access and experiences of care[\u003cspan additionalcitationids=\"CR99\" citationid=\"CR98\" class=\"CitationRef\"\u003e98\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR100\" class=\"CitationRef\"\u003e100\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eThe differences in sentiment between the two professional groups also raise important questions about how tone influences patient outcomes. Research in healthcare communication has shown that positive, supportive language can improve patient satisfaction, adherence to treatment, and even health outcomes [\u003cspan additionalcitationids=\"CR102\" citationid=\"CR101\" class=\"CitationRef\"\u003e101\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR103\" class=\"CitationRef\"\u003e103\u003c/span\u003e]. In contrast, negative or overly cautious language may contribute to patient anxiety, dissatisfaction, and disengagement [\u003cspan citationid=\"CR100\" class=\"CitationRef\"\u003e100\u003c/span\u003e, \u003cspan citationid=\"CR104\" class=\"CitationRef\"\u003e104\u003c/span\u003e, \u003cspan citationid=\"CR105\" class=\"CitationRef\"\u003e105\u003c/span\u003e]. Therefore, these findings suggest that neurologists may benefit from incorporating more positive and empathetic language into their communications, particularly when discussing treatment options and prognosis with patients.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec26\" class=\"Section2\"\u003e \u003ch2\u003e4.4. \u003cem\u003eExpert review and model validation\u003c/em\u003e\u003c/h2\u003e \u003cp\u003eThe expert review of the sentiment analysis provides a critical reflection on the limitations of using NLP models like VADER and Flair in clinical contexts. The relatively low match (61%) between the model\u0026rsquo;s sentiment classification and the expert\u0026rsquo;s ratings highlights the challenges of applying general sentiment analysis tools to specialised medical documents. One key issue is that these models are not trained to understand medical terminology or the nuanced ways in which healthcare professionals discuss patients\u0026rsquo; conditions. For example, terms that the model may interpret as negative, such as \u0026lsquo;seizure\u0026rsquo; or \u0026lsquo;disorder\u0026rsquo; may not necessarily carry a negative connotation in the context of a clinical document, where they are part of the routine language used to describe medical conditions. Likewise, positive terms like \u0026lsquo;progress\u0026rsquo; might not fully capture the severity or complexity of a patient\u0026rsquo;s condition, leading to potential discrepancies between the model\u0026rsquo;s output and the expert\u0026rsquo;s interpretation.\u003c/p\u003e \u003cp\u003eThere is increasing interest in using NLP to analyse textual information from clinical records. NLP has been successfully implemented in the FND domain, for example, to aid in accurately differentiating epileptic seizures from psychogenic seizures [\u003cspan citationid=\"CR106\" class=\"CitationRef\"\u003e106\u003c/span\u003e, \u003cspan citationid=\"CR107\" class=\"CitationRef\"\u003e107\u003c/span\u003e]. Nonetheless, subsequent manual analyses are often required to supplement the NLP-generated outcomes with essential details and context, as NLP can fail to detect all nuances in text [\u003cspan citationid=\"CR108\" class=\"CitationRef\"\u003e108\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eThis suggests the need to develop specialised NLP models specifically trained on medical documents and to account for the need for expert input to provide details and interpretations that NLP analyses alone may not be able to capture, thus improving the accuracy of NLP output and its effectiveness to aid clinical practice and clinical decision-making processes. Lastly, future NLP applications in clinical practice (including, but not limited to, FND) would need to account for the specific context in which clinical language is used and understand the implicit meanings that healthcare professionals attribute to certain terms and phrases. Additionally, further research could explore how integrating domain-specific knowledge into NLP models might enhance their ability to capture not just sentiment, but also the intent and nuance of clinical communications.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec27\" class=\"Section2\"\u003e \u003ch2\u003e4.5. \u003cem\u003eImplications for practice and future research\u003c/em\u003e\u003c/h2\u003e \u003cp\u003eThe findings of this study have several important implications for clinical practice and future research. First, the clear differences in communication styles between psychologists and neurologists suggest that interdisciplinary teams must be mindful of these differences when coordinating patient care. Neurologists and psychologists should aim to communicate more effectively, ensuring that both the medical and psychosocial aspects of a patient\u0026rsquo;s care are given equal attention. Regular interdisciplinary meetings and joint case discussions could help bridge this gap and ensure that patients receive holistic, integrated care [\u003cspan citationid=\"CR41\" class=\"CitationRef\"\u003e41\u003c/span\u003e, \u003cspan citationid=\"CR109\" class=\"CitationRef\"\u003e109\u003c/span\u003e, \u003cspan citationid=\"CR110\" class=\"CitationRef\"\u003e110\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eSecond, the sentiment analysis results suggest that neurologists could benefit from adopting more positive and supportive language when interacting with patients. This could be particularly important in cases where patients are struggling with the emotional and psychological burden of FND, and where a more empathetic and hopeful approach may improve patient engagement and outcomes.\u003c/p\u003e \u003cp\u003eFuture research should explore how these communication differences and sentiment patterns may influence patient outcomes. For example, it would be useful to determine whether patients who receive more positive and supportive communications from their healthcare providers report higher levels of satisfaction or adherence to treatment or if different communication styles may lead to differences in clinical outcomes. More generally, understanding the impact of communication on patient care in more detail could provide valuable insights for improving interdisciplinary collaboration and enhancing patient outcomes in FND management.\u003c/p\u003e \u003c/div\u003e"},{"header":"5. Conclusion","content":"\u003cp\u003eIn conclusion, this study demonstrates that neurologists and psychologists use distinct communication styles when interacting with FND patients, with neurologists adopting a more clinical and cautious approach. In contrast, psychologists focus on emotional support and holistic care. These differences are also reflected in the sentiment analysis, with neurologists exhibiting a more negative tone and psychologists taking a more positive and supportive approach. These findings have important implications for interdisciplinary collaboration and patient care, highlighting the need for integrated approaches that address both the medical and psychosocial dimensions of FND. Further research is needed to explore how these communication differences affect patient outcomes and to develop more specialised NLP models that can accurately capture the nuances of medical discourse.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eCONFLICT OF INTEREST STATEMENT\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe authors declare that the research was conducted in the absence of any commercial or financial\u003c/p\u003e\n\u003cp\u003erelationships that could be construed as a potential conflict of interest.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAUTHOR\u003c/strong\u003e\u003cstrong\u003eCONTRIBUTIONS\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eAll authors have contributed to the study conceptualisation and the write-up of the current manuscript. The first and second authors (MSM and YL) processed, analysed and interpreted the findings. LHYL and DDB had a steering role in study management and extraction of clinical documents from clinical records, helped by research assistants (AL and SL). DDB also provided clinical insights informing the interpretations of the clinical significance of the findings and the recommendations deriving from the study. MS, SS and AW assisted in writing and reviewing the manuscript and RJ, as a clinical expert in the field of neurology and FND, provided feedback on the relevance and informativeness of the findings obtained.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eFUNDING\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis work was supported by the Alan Turing Institute - Manchester Sandpit Project Grant, 2022.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eETHICS STATEMENT\u003c/strong\u003e\u003c/p\u003e\n\u003col\u003e\n \u003cli\u003eThis study was approved by the Northern Care Alliance NHS Group Trust.\u003c/li\u003e\n \u003cli\u003eThis study was performed with Ethical approval to extract clinical documents from hospital records, which was obtained with relevant guidelines from the R\u0026amp;I department of the Northern Care Alliance NHS Group Trust (approval number 22HIP47).\u003c/li\u003e\n\u003c/ol\u003e\n\u003cp\u003e\u003cstrong\u003eCONSENT STATEMENT (PERMISSION TO ACCESS CLINICAL RECORDS)\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003ePermission to access and analyse these records was granted by the Trust following Research and Development (R\u0026amp;D) approval. The study was conducted in compliance with applicable legal and ethical frameworks governing the use of patient data for research, including the principles of lawful access to healthcare data for research purposes. All data processing adhered to institutional and national guidelines for data protection and confidentiality, ensuring that patient anonymity and privacy were maintained throughout the study.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eDATA AVAILABILITY\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe data that support the findings of this study are available from Northern Care Alliance NHS Group Trust (approval number 22HIP47) but restrictions apply to the availability of these data due to the nature and sensitivity related to patient records, which were obtained and used with relevant guidelines from the R\u0026amp;I department of the Northern Care Alliance NHS Group Trust for the current study, and so are not publicly available.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eCLINICAL TRIAL NUMBER\u003c/strong\u003e: not applicable.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\n\u003cli\u003eBennett, K., Diamond, C., Hoeritzauer, I., Gardiner, P., McWhirter, L., Carson, A., Stone, J.: A practical review of functional neurological disorder (FND) for the general physician. Clin. Med. 21, 28 (2021). https://doi.org/10.7861/clinmed.2020-0987.\u003c/li\u003e\n\u003cli\u003eOriuwa, C., Mollica, A., Feinstein, A., Giacobbe, P., Lipsman, N., Perez, D.L., Burke, M.J.: Neuromodulation for the treatment of functional neurological disorder and somatic symptom disorder: a systematic review. J. Neurol. Neurosurg. Amp Psychiatry. 93, 280 (2022). https://doi.org/10.1136/jnnp-2021-327025.\u003c/li\u003e\n\u003cli\u003eStone, J., Campbell, K., Sharma, N., Carson, A., Warlow, C.P., Sharpe, M.: What should we call pseudoseizures? Seizure. 12, 568\u0026ndash;572 (2003). https://doi.org/10.1016/s1059-1311(03)00055-4.\u003c/li\u003e\n\u003cli\u003eCarson, A., Stone, J., Hibberd, C., Murray, G., Duncan, R., R Coleman, C Warlow, R Roberts, A Pelosi, J Cavanagh, K Matthews, R Goldbeck, C Hansen, M Sharpe: Disability, distress and unemployment in neurology outpatients with symptoms \u0026lsquo;unexplained by organic disease.\u0026rsquo; J. Neurol. Neurosurg. Amp Psychiatry. 82, 810 (2011). https://doi.org/10.1136/jnnp.2010.220640.\u003c/li\u003e\n\u003cli\u003eGelauff, J., Stone, J., Edwards, M., Carson, A.: The prognosis of functional (psychogenic) motor symptoms: a systematic review. J. Neurol. Neurosurg. Amp Psychiatry. 85, 220 (2014). https://doi.org/10.1136/jnnp-2013-305321.\u003c/li\u003e\n\u003cli\u003eStone, J., Burton, C., Carson, A.: Recognising and explaining functional neurological disorder. BMJ. 371, m3745 (2020). https://doi.org/10.1136/bmj.m3745.\u003c/li\u003e\n\u003cli\u003eAsadi-Pooya, A.A.: Psychogenic nonepileptic seizures: a concise review. Neurol. Sci. 38, 935\u0026ndash;940 (2017). https://doi.org/10.1007/s10072-017-2887-8.\u003c/li\u003e\n\u003cli\u003eJones, B., Reuber, M., Norman, P.: Correlates of health‐related quality of life in adults with psychogenic nonepileptic seizures: a systematic review. Epilepsia. 57, 171\u0026ndash;181 (2016).\u003c/li\u003e\n\u003cli\u003eRawlings, G.H., Brown, I., Reuber, M.: Predictors of health-related quality of life in patients with epilepsy and psychogenic nonepileptic seizures. Epilepsy Behav. 68, 153\u0026ndash;158 (2017).\u003c/li\u003e\n\u003cli\u003eCarson, A., Lehn, A.: Chapter 5 - Epidemiology. In: Hallett, M., Stone, J., and Carson, A. (eds.) Handbook of Clinical Neurology. pp. 47\u0026ndash;60. Elsevier (2016). https://doi.org/10.1016/B978-0-12-801772-2.00005-9.\u003c/li\u003e\n\u003cli\u003eWatson, M., Woodward, J., Strom, L.A.: The Financial Burden of Functional Neurological Disorders. Curr. Neurol. Neurosci. Rep. 23, 637\u0026ndash;643 (2023). https://doi.org/10.1007/s11910-023-01298-8.\u003c/li\u003e\n\u003cli\u003eStephen, C.D., Fung, V., Lungu, C.I., Espay, A.J.: Assessment of Emergency Department and Inpatient Use and Costs in Adult and Pediatric Functional Neurological Disorders. JAMA Neurol. 78, 88\u0026ndash;101 (2021). https://doi.org/10.1001/jamaneurol.2020.3753.\u003c/li\u003e\n\u003cli\u003eFND Hope: FND 2021 impact report. (2022).\u003c/li\u003e\n\u003cli\u003eCuoco, S., Scannapieco, S., Carotenuto, I., Picillo, M., Pellecchia, M.T., Barone, P., Erro, R.: Higher Health Service Costs Associated With Delayed Diagnosis of Functional Neurological Disorder. J. Neuropsychiatry Clin. Neurosci. 35, 86\u0026ndash;91 (2023). https://doi.org/10.1176/appi.neuropsych.21110288.\u003c/li\u003e\n\u003cli\u003eEl-Naggar, H., Moloney, P., Widdess-Walsh, P., Kilbride, R., Delanty, N., Mullins, G.: Simultaneous occurrence of nonepileptic and epileptic seizures during a single period of in-patient video-electroencephalographic monitoring. Epilepsia Open. 2, 467\u0026ndash;471 (2017). https://doi.org/10.1002/epi4.12071.\u003c/li\u003e\n\u003cli\u003eBurke, M.J.: \u0026ldquo;It\u0026rsquo;s All in Your Head\u0026rdquo;\u0026mdash;Medicine\u0026rsquo;s Silent Epidemic. JAMA Neurol. 76, 1417\u0026ndash;1418 (2019). https://doi.org/10.1001/jamaneurol.2019.3043.\u003c/li\u003e\n\u003cli\u003eDickson, B.E., Hay-Smith, E.J.C., Dean, S.G.: Demonised diagnosis: the influence of stigma on interdisciplinary rehabilitation of somatoform disorder. N. Z. J. Physiother. 37, (2009).\u003c/li\u003e\n\u003cli\u003eKeynejad, R.C., Carson, A.J., David, A.S., Nicholson, T.R.: Functional neurological disorder: psychiatry\u0026rsquo;s blind spot. Lancet Psychiatry. 4, e2\u0026ndash;e3 (2017). https://doi.org/10.1016/S2215-0366(17)30036-6.\u003c/li\u003e\n\u003cli\u003eOnofrj, M., Ajdinaj, P., Digiovanni, A., Malek, N., Martinotti, G., Ferro, F.M., Russo, M., Thomas, A., Sensi, S.L.: Functional Neurologic Disorders, disorders to be managed by neurologists, or are neurologists wandering in a dangerous field with inadequate resources? Front. Psychiatry. 14, (2023).\u003c/li\u003e\n\u003cli\u003ePretorius, C.: Barriers and facilitators to reaching a diagnosis of PNES from the patients\u0026rsquo; perspective: Preliminary findings. Seizure. 38, 1\u0026ndash;6 (2016). https://doi.org/10.1016/j.seizure.2016.03.007.\u003c/li\u003e\n\u003cli\u003eVarley, D., Sweetman, J., Brabyn, S., Lagos, D., van der Feltz-Cornelis, C.: The clinical management of functional neurological disorder: A scoping review of the literature. J. Psychosom. Res. 165, 111121 (2023). https://doi.org/10.1016/j.jpsychores.2022.111121.\u003c/li\u003e\n\u003cli\u003eBrownell, A.K.W., Atkins, C., Whiteley, A., Woollard, R.F., Kornelsen, J.: Clinical practitioners\u0026rsquo; views on the management of patients with medically unexplained physical symptoms (MUPS): a qualitative study. BMJ Open. 6, e012379 (2016). https://doi.org/10.1136/bmjopen-2016-012379.\u003c/li\u003e\n\u003cli\u003eDickson, J.M., Peacock, M., Gr\u0026uuml;newald, R.A., Howlett, S., Bissell, P., Reuber, M.: Non-epileptic attack disorder: the importance of diagnosis and treatment. BMJ Case Rep. bcr2016218278 (2017). https://doi.org/10.1136/bcr-2016-218278.\u003c/li\u003e\n\u003cli\u003eMcNicholas, O., Pryce, H.: Clinical physiologists\u0026rsquo; experiences of working with people with nonepileptic attack disorder: A qualitative study. Epilepsy Behav. 127, 108501 (2022). https://doi.org/10.1016/j.yebeh.2021.108501.\u003c/li\u003e\n\u003cli\u003eYon, K., Nettleton, S., Walters, K., Lamahewa, K., Buszewicz, M.: Junior doctors\u0026rsquo; experiences of managing patients with medically unexplained symptoms: a qualitative study. BMJ Open. 5, e009593 (2015). https://doi.org/10.1136/bmjopen-2015-009593.\u003c/li\u003e\n\u003cli\u003eKanaan, R.A., Armstrong, D., Wessely, S.C.: Neurologists\u0026rsquo; understanding and management of conversion disorder. J. Neurol. Neurosurg. Amp Psychiatry. 82, 961 (2011). https://doi.org/10.1136/jnnp.2010.233114.\u003c/li\u003e\n\u003cli\u003eSahaya, K., Dholakia, S.A., Lardizabal, D., Sahota, P.K.: Opinion survey of health care providers towards psychogenic non epileptic seizures. Clin. Neurol. Neurosurg. 114, 1304\u0026ndash;1307 (2012). https://doi.org/10.1016/j.clineuro.2012.03.047.\u003c/li\u003e\n\u003cli\u003eBarnett, C., Davis, R., Mitchell, C., Tyson, S.: The vicious cycle of functional neurological disorders: a synthesis of healthcare professionals\u0026rsquo; views on working with patients with functional neurological disorder. Disabil. Rehabil. 44, 1802\u0026ndash;1811 (2022). https://doi.org/10.1080/09638288.2020.1822935.\u003c/li\u003e\n\u003cli\u003eAhern, L., Stone, J., Sharpe, M.C.: Attitudes of Neuroscience Nurses Toward Patients With Conversion Symptoms. Psychosomatics. 50, 336\u0026ndash;339 (2009). https://doi.org/10.1176/appi.psy.50.4.336.\u003c/li\u003e\n\u003cli\u003eMcMillan, K.K., Pugh, M.J., Hamid, H., Salinsky, M., Pugh, J., No\u0026euml;l, P.H., Finley, E.P., Leykum, L.K., Lanham, H.J., LaFrance, W.C., Jr.: Providers\u0026rsquo; perspectives on treating psychogenic nonepileptic seizures: Frustration and hope. Epilepsy Behav. 37, 276\u0026ndash;281 (2014). https://doi.org/10.1016/j.yebeh.2014.07.001.\u003c/li\u003e\n\u003cli\u003eRobson, C., Lian, O.S.: \u0026ldquo;Blaming, shaming, humiliation\u0026rdquo;: Stigmatising medical interactions among people with non-epileptic seizures. Wellcome Open Res. 2, 55 (2017). https://doi.org/10.12688/wellcomeopenres.12133.2.\u003c/li\u003e\n\u003cli\u003eEdwards, M.J., Yogarajah, M., Stone, J.: Why functional neurological disorder is not feigning or malingering. Nat. Rev. Neurol. 19, 246\u0026ndash;256 (2023). https://doi.org/10.1038/s41582-022-00765-z.\u003c/li\u003e\n\u003cli\u003eMcLoughlin, C., McGhie-Fraser, B., Carson, A., Olde Hartman, T., Stone, J.: How stigma unfolds for patients with Functional Neurological Disorder. J. Psychosom. Res. 181, 111667 (2024). https://doi.org/10.1016/j.jpsychores.2024.111667.\u003c/li\u003e\n\u003cli\u003eAsadi-Pooya, A.A., Brigo, F., Mildon, B., Nicholson, T.R.: Terminology for psychogenic nonepileptic seizures: Making the case for \u0026ldquo;functional seizures.\u0026rdquo; Epilepsy Behav. 104, 106895 (2020). https://doi.org/10.1016/j.yebeh.2019.106895.\u003c/li\u003e\n\u003cli\u003eBrigo, F., Igwe, S.C., Ausserer, H., Nardone, R., Tezzon, F., Bongiovanni, L.G., Tinazzi, M., Trinka, E.: Terminology of psychogenic nonepileptic seizures. Epilepsia. 56, e21\u0026ndash;e25 (2015). https://doi.org/10.1111/epi.12911.\u003c/li\u003e\n\u003cli\u003eBrigo, F., Tinazzi, M., Trinka, E.: In Response: Terminology of psychogenic nonepileptic seizures\u0026mdash;a Babel of different names? Epilepsia. 56, 1179\u0026ndash;1180 (2015). https://doi.org/10.1111/epi.13028.\u003c/li\u003e\n\u003cli\u003eCarson, A., Lehn, A., Ludwig, L., Stone, J.: Explaining functional disorders in the neurology clinic: a photo story. Pract. Neurol. 16, 56 (2016). https://doi.org/10.1136/practneurol-2015-001242.\u003c/li\u003e\n\u003cli\u003eMarotta, A., Lasalvia, A., Fiorio, M., Zanalda, E., Di Sciascio, G., Palumbo, C., Papola, D., Barbui, C., Tinazzi, M.: Psychiatrists\u0026rsquo; attitudes towards functional neurological disorders: results from a national survey. Front. Psychiatry. 14, (2023). https://doi.org/10.3389/fpsyt.2023.1216756.\u003c/li\u003e\n\u003cli\u003eStone, J.: Functional neurological disorders: the neurological assessment as treatment. Pract. Neurol. 16, 7\u0026ndash;17 (2016). https://doi.org/10.1136/practneurol-2015-001241.\u003c/li\u003e\n\u003cli\u003eKeatley, E., Molton, I.: A shift in approach: assessment and treatment of adults with functional neurological disorder. J. Health Serv. Psychol. 48, 79\u0026ndash;87 (2022).\u003c/li\u003e\n\u003cli\u003ePalmer, D.D.G., Gamble, M., Higgins, M., Maley, J., Watson, E.: Outcomes of an Integrated Multidisciplinary Clinic for People with Functional Neurological Disorder. Mov. Disord. Clin. Pract. 10, 967\u0026ndash;973 (2023). https://doi.org/10.1002/mdc3.13757.\u003c/li\u003e\n\u003cli\u003eJimenez, X.F., Aboussouan, A., Johnson, J.: Functional neurological disorder responds favorably to interdisciplinary rehabilitation models. Psychosomatics. 60, 556\u0026ndash;562 (2019).\u003c/li\u003e\n\u003cli\u003eLaFaver, K., LaFrance, W.C., Price, M.E., Rosen, P.B., Rapaport, M.: Treatment of functional neurological disorder: current state, future directions, and a research agenda. CNS Spectr. 26, 607\u0026ndash;613 (2021). https://doi.org/10.1017/S1092852920002138.\u003c/li\u003e\n\u003cli\u003eVelazquez-Rodriquez, Y., Fehily, B.: Functional Neurological Disorder: Historical Trends and Urgent Directions. J. Neurol. Res. 13, 12\u0026ndash;32 (2023). https://doi.org/10.14740/jnr754.\u003c/li\u003e\n\u003cli\u003eLevis, M., Leonard Westgate, C., Gui, J., Watts, B.V., Shiner, B.: Natural language processing of clinical mental health notes may add predictive value to existing suicide risk models. Psychol. Med. 51, 1382\u0026ndash;1391 (2021). https://doi.org/10.1017/S0033291720000173.\u003c/li\u003e\n\u003cli\u003eLocke, S., Bashall, A., Al-Adely, S., Moore, J., Wilson, A., Kitchen, G.B.: Natural language processing in medicine: A review. Trends Anaesth. Crit. Care. 38, 4\u0026ndash;9 (2021). https://doi.org/10.1016/j.tacc.2021.02.007.\u003c/li\u003e\n\u003cli\u003eLe Glaz, A., Haralambous, Y., Kim-Dufor, D.-H., Lenca, P., Billot, R., Ryan, T.C., Marsh, J., DeVylder, J., Walter, M., Berrouiguet, S., Lemey, C.: Machine Learning and Natural Language Processing in Mental Health: Systematic Review. J Med Internet Res. 23, e15708 (2021). https://doi.org/10.2196/15708.\u003c/li\u003e\n\u003cli\u003eMalgaroli, M., Hull, T.D., Zech, J.M., Althoff, T.: Natural language processing for mental health interventions: a systematic review and research framework. Transl. Psychiatry. 13, 309 (2023).\u003c/li\u003e\n\u003cli\u003eMukherjee, S.S., Yu, J., Won, Y., McClay, M.J., Wang, L., Rush, A.J., Sarkar, J.: Natural language processing-based quantification of the mental state of psychiatric patients. Comput. Psychiatry. 4, (2020).\u003c/li\u003e\n\u003cli\u003eZhang, T., Schoene, A.M., Ji, S., Ananiadou, S.: Natural language processing applied to mental illness detection: a narrative review. Npj Digit. Med. 5, 46 (2022). https://doi.org/10.1038/s41746-022-00589-7.\u003c/li\u003e\n\u003cli\u003eFleuren, W.W.M., Alkema, W.: Application of text mining in the biomedical domain. Text Min. Biomed. Lit. 74, 97\u0026ndash;106 (2015). https://doi.org/10.1016/j.ymeth.2015.01.015.\u003c/li\u003e\n\u003cli\u003eJackson, R.G., Patel, R., Jayatilleke, N., Kolliakou, A., Ball, M., Genevieve Gorrell, Angus Roberts, Richard J Dobson, Robert Stewart: Natural language processing to extract symptoms of severe mental illness from clinical text: the Clinical Record Interactive Search Comprehensive Data Extraction (CRIS-CODE) project. BMJ Open. 7, e012012 (2017). https://doi.org/10.1136/bmjopen-2016-012012.\u003c/li\u003e\n\u003cli\u003eKoleck, T.A., Dreisbach, C., Bourne, P.E., Bakken, S.: Natural language processing of symptoms documented in free-text narratives of electronic health records: a systematic review. J. Am. Med. Inform. Assoc. 26, 364\u0026ndash;379 (2019). https://doi.org/10.1093/jamia/ocy173.\u003c/li\u003e\n\u003cli\u003eWang, Y., Wang, L., Rastegar-Mojarad, M., Moon, S., Shen, F., Afzal, N., Liu, S., Zeng, Y., Mehrabi, S., Sohn, S.: Clinical information extraction applications: a literature review. J. Biomed. Inform. 77, 34\u0026ndash;49 (2018).\u003c/li\u003e\n\u003cli\u003eRoberts, A.: Language, structure, and reuse in the electronic health record. AMA J. Ethics. 19, 281\u0026ndash;288 (2017).\u003c/li\u003e\n\u003cli\u003eVelupillai, S., Suominen, H., Liakata, M., Roberts, A., Shah, A.D., Morley, K., Osborn, D., Hayes, J., Stewart, R., Downs, J., Chapman, W., Dutta, R.: Using clinical Natural Language Processing for health outcomes research: Overview and actionable suggestions for future advances. J. Biomed. Inform. 88, 11\u0026ndash;19 (2018). https://doi.org/10.1016/j.jbi.2018.10.005.\u003c/li\u003e\n\u003cli\u003eFord, E., Carroll, J.A., Smith, H.E., Scott, D., Cassell, J.A.: Extracting information from the text of electronic medical records to improve case detection: a systematic review. J. Am. Med. Inform. Assoc. 23, 1007\u0026ndash;1015 (2016). https://doi.org/10.1093/jamia/ocv180.\u003c/li\u003e\n\u003cli\u003eLe, D.V., Montgomery, J., Kirkby, K.C., Scanlan, J.: Risk prediction using natural language processing of electronic mental health records in an inpatient forensic psychiatry setting. J. Biomed. Inform. 86, 49\u0026ndash;58 (2018). https://doi.org/10.1016/j.jbi.2018.08.007.\u003c/li\u003e\n\u003cli\u003eSohn, S., Kocher, J.-P.A., Chute, C.G., Savova, G.K.: Drug side effect extraction from clinical narratives of psychiatry and psychology patients. J. Am. Med. Inform. Assoc. 18, i144\u0026ndash;i149 (2011). https://doi.org/10.1136/amiajnl-2011-000351.\u003c/li\u003e\n\u003cli\u003eBoden, C.: Overcoming the linguistic divide: a barrier to consumer health information. J. Can. Health Libr. Assoc. Assoc. Bibl. Sant\u0026eacute; Can. 30, 75\u0026ndash;80 (2009).\u003c/li\u003e\n\u003cli\u003eHe, Z.: Understanding and Bridging the Language and Terminology Gap Between Health Professionals and Consumers Using Social Media. In: Bian, J., Guo, Y., He, Z., and Hu, X. (eds.) Social Web and Health Research: Benefits, Limitations, and Best Practices. pp. 103\u0026ndash;121. Springer International Publishing, Cham (2019). https://doi.org/10.1007/978-3-030-14714-3_6.\u003c/li\u003e\n\u003cli\u003eNie, L., Zhao, Y.-L., Akbari, M., Shen, J., Chua, T.-S.: Bridging the vocabulary gap between health seekers and healthcare knowledge. IEEE Trans. Knowl. Data Eng. 27, 396\u0026ndash;409 (2014).\u003c/li\u003e\n\u003cli\u003eVarma, J.B., Deeba, K.: Mapping of terms between healthcare providers and patients. In: 2017 International Conference on Trends in Electronics and Informatics (ICEI). pp. 773\u0026ndash;776 (2017). https://doi.org/10.1109/ICOEI.2017.8300808.\u003c/li\u003e\n\u003cli\u003ePuerari, I., Duarte, D., Dal Bianco, G., Felipette Lima, J.: Exploratory Analysis of Electronic Health Records using Topic Modeling. J. Inf. Data Manag. 11, (2021). https://doi.org/10.5753/jidm.2020.2024.\u003c/li\u003e\n\u003cli\u003eCarron-Arthur, B., Reynolds, J., Bennett, K., Bennett, A., Griffiths, K.M.: What\u0026rsquo;s all the talk about? Topic modelling in a mental health Internet support group. BMC Psychiatry. 16, (2016). https://doi.org/10.1186/s12888-016-1073-5.\u003c/li\u003e\n\u003cli\u003eDenecke, K., Reichenpfader, D.: Sentiment analysis of clinical narratives: A scoping review. J. Biomed. Inform. 140, 104336 (2023). https://doi.org/10.1016/j.jbi.2023.104336.\u003c/li\u003e\n\u003cli\u003eMccoy, T.H., Castro, V.M., Cagan, A., Roberson, A.M., Kohane, I.S., Perlis, R.H.: Sentiment Measured in Hospital Discharge Notes Is Associated with Readmission and Mortality Risk: An Electronic Health Record Study. PLOS ONE. 10, e0136341 (2015). https://doi.org/10.1371/journal.pone.0136341.\u003c/li\u003e\n\u003cli\u003eBlei, D.M.: Probabilistic topic models. Commun. ACM. 55, 77\u0026ndash;84 (2012). https://doi.org/10.1145/2133806.2133826.\u003c/li\u003e\n\u003cli\u003eGillings, M., Hardie, A.: The interpretation of topic models for scholarly analysis: An evaluation and critique of current practice. Digit. Scholarsh. Humanit. 38, 530\u0026ndash;543 (2023). https://doi.org/10.1093/llc/fqac075.\u003c/li\u003e\n\u003cli\u003eBlei, D., Ng, A., Jordan, M.: Latent Dirichlet Allocation. J. Mach. Learn. Res. 3, 993\u0026ndash;1022 (2003).\u003c/li\u003e\n\u003cli\u003eSyed, S., Spruit, M.: Full-Text or Abstract? Examining Topic Coherence Scores Using Latent Dirichlet Allocation. (2017). https://doi.org/10.1109/DSAA.2017.61.\u003c/li\u003e\n\u003cli\u003eHutto, C., Gilbert, E.: VADER: A Parsimonious Rule-Based Model for Sentiment Analysis of Social Media Text. Proc. Int. AAAI Conf. Web Soc. Media. 8, 216\u0026ndash;225 (2014). https://doi.org/10.1609/icwsm.v8i1.14550.\u003c/li\u003e\n\u003cli\u003eRhody, L.M.: Topic modeling and figurative language. (2012).\u003c/li\u003e\n\u003cli\u003eGiannoulakis, S., Tsapatsoulis, N.: Topic Identification via Human Interpretation of Word Clouds: The Case of Instagram Hashtags. In: Maglogiannis, I., Macintyre, J., and Iliadis, L. (eds.) Artificial Intelligence Applications and Innovations. pp. 283\u0026ndash;294. Springer International Publishing, Cham (2021).\u003c/li\u003e\n\u003cli\u003eArnold, C.W., Oh, A., Chen, S., Speier, W.: Evaluating topic model interpretability from a primary care physician perspective. Comput. Methods Programs Biomed. 124, 67\u0026ndash;75 (2016).\u003c/li\u003e\n\u003cli\u003eCambria, E., Das, D., Bandyopadhyay, S., Feraco, A.: A practical guide to sentiment analysis. Springer (2017).\u003c/li\u003e\n\u003cli\u003eEspay, A.J., Aybek, S., Carson, A., Edwards, M.J., Goldstein, L.H., Hallett, M., Lafaver, K., Lafrance, W.C., Lang, A.E., Nicholson, T., Nielsen, G., Reuber, M., Voon, V., Stone, J., Morgante, F.: Current Concepts in Diagnosis and Treatment of Functional Neurological Disorders. JAMA Neurol. 75, 1132 (2018). https://doi.org/10.1001/jamaneurol.2018.1264.\u003c/li\u003e\n\u003cli\u003eGoldstein, L.H., Mellers, J.D.C.: Chapter 46 - Psychologic treatment of functional neurologic disorders. In: Hallett, M., Stone, J., and Carson, A. (eds.) Handbook of Clinical Neurology. pp. 571\u0026ndash;583. Elsevier (2016). https://doi.org/10.1016/B978-0-12-801772-2.00046-1.\u003c/li\u003e\n\u003cli\u003eLaFrance Jr., W.C., Miller, I.W., Ryan, C.E., Blum, A.S., Solomon, D.A., Kelley, J.E., Keitner, G.I.: Cognitive behavioral therapy for psychogenic nonepileptic seizures. Epilepsy Behav. 14, 591\u0026ndash;596 (2009). https://doi.org/10.1016/j.yebeh.2009.02.016.\u003c/li\u003e\n\u003cli\u003eMyers, L., Sarudiansky, M., Korman, G., Baslet, G.: Using evidence-based psychotherapy to tailor treatment for patients with functional neurological disorders. Epilepsy Behav. Rep. 16, 100478 (2021). https://doi.org/10.1016/j.ebr.2021.100478.\u003c/li\u003e\n\u003cli\u003eGoldstein, L.H., Chalder, T., Chigwedere, C., Khondoker, M.R., Moriarty, J., Toone, B.K., Mellers, J.D.C.: Cognitive-behavioral therapy for psychogenic nonepileptic seizures: A pilot RCT. Neurology. 74, 1986\u0026ndash;1994 (2010). https://doi.org/10.1212/wnl.0b013e3181e39658.\u003c/li\u003e\n\u003cli\u003ePerez, D.L., Haller, A.L., Espay, A.J.: Should neurologists diagnose and manage functional neurologic disorders? It is complicated. Neurol. Clin. Pract. 9, 165\u0026ndash;167 (2019). https://doi.org/10.1212/cpj.0000000000000573.\u003c/li\u003e\n\u003cli\u003eGilmour, G.S., Nielsen, G., Teodoro, T., Yogarajah, M., Coebergh, J.A., Dilley, M.D., Martino, D., Edwards, M.J.: Management of functional neurological disorder. J. Neurol. 267, 2164\u0026ndash;2172 (2020). https://doi.org/10.1007/s00415-020-09772-w.\u003c/li\u003e\n\u003cli\u003eTinazzi, M., Fiorio, M., Berardelli, A., Bonetti, B., Bonifati, D.M., Burlina, A., Cagnin, A., Calabria, F., Corbetta, M., Cortelli, P., Giometto, B., Guidoni, S.V., Lopiano, L., Mancardi, G., Marchioretto, F., Pellegrini, M., Teatini, F., Tedeschi, G., Tesolin, L., Turinese, E., Zappia, M., Marotta, A.: Opinion, knowledge, and clinical experience with functional neurological disorders among Italian neurologists: results from an online survey. J Neurol. 269, 2549\u0026ndash;2559 (2022). https://doi.org/10.1007/s00415-021-10840-y.\u003c/li\u003e\n\u003cli\u003eMcKee, K., Glass, S., Adams, C., Stephen, C.D., King, F., Parlman, K., Perez, D.L., Kontos, N.: The Inpatient Assessment and Management of Motor Functional Neurological Disorders: An Interdisciplinary Perspective. Psychosomatics. 59, 358\u0026ndash;368 (2018). https://doi.org/10.1016/j.psym.2017.12.006.\u003c/li\u003e\n\u003cli\u003eSireci, F., Moretti, V., Cavallieri, F., Ferrari, S., Minardi, V., Ferrari, F., Balestra, G.L., Ghirotto, L., Valzania, F.: \u0026ldquo;Somewhere Between an Actual Disease and a Disease\u0026rdquo;: A Grounded Theory Study on Diagnosing Functional Neurological Disorders From a Multi-Informant Perspective. Qual. Health Res. 10497323231216346 (2023). https://doi.org/10.1177/10497323231216346.\u003c/li\u003e\n\u003cli\u003eWinton-Brown, T., Wilson, S.J., Felmingham, K., Rayner, G., O\u0026rsquo;Brien, T.J., O\u0026rsquo;Brien, P., Mohan, A., Velakoulis, D., Kanaan, R.: Principles for delivering improved care of people with functional seizures: Closing the treatment gap. Aust. N. Z. J. Psychiatry. 57, 1511\u0026ndash;1517 (2023). https://doi.org/10.1177/00048674231180509.\u003c/li\u003e\n\u003cli\u003ePepper, E., Mohan, A., Butcher, K., Parsons, M., Curtis, J.: Functional neurological disorders: an Australian interdisciplinary perspective. Med. J. Aust. 216, 501\u0026ndash;503 (2022). https://doi.org/10.5694/mja2.51543.\u003c/li\u003e\n\u003cli\u003eHenningsen, P., Zipfel, S., Sattel, H., Creed, F.: Management of Functional Somatic Syndromes and Bodily Distress. Psychother. Psychosom. 87, 12\u0026ndash;31 (2018). https://doi.org/10.1159/000484413.\u003c/li\u003e\n\u003cli\u003eMamo, N., Tak, L.M., Van De Klundert, M.A.W., Olde Hartman, T.C., Rosmalen, J.G.M., Hanssen, D.J.C.: Quality indicators for collaborative care networks in persistent somatic symptoms and functional disorders: a modified delphi study. BMC Health Serv. Res. 24, (2024). https://doi.org/10.1186/s12913-024-10589-w.\u003c/li\u003e\n\u003cli\u003eVance, R., Clarke, S., O\u0026rsquo;Keeffe, F., Galligan, T., Doherty, A., Flynn, C., Kelleher, E., Laffan, A., Doherty, C., Gillan, D.: Attitudes and perceptions of Irish health care professionals regarding functional neurological disorder: A national survey. Brain Behav. 14, (2024). https://doi.org/10.1002/brb3.3362.\u003c/li\u003e\n\u003cli\u003eCope, S.R., Smith, J.G., Edwards, M.J., Holt, K., Agrawal, N.: Enhancing the communication of functional neurological disorder diagnosis: a multidisciplinary education session. Eur. J. Neurol. 28, 40\u0026ndash;47 (2021). https://doi.org/10.1111/ene.14525.\u003c/li\u003e\n\u003cli\u003eLehn, A., Navaratnam, D., Broughton, M., Cheah, V., Fenton, A., Harm, K., Owen, D., Pun, P.: Functional neurological disorders: effective teaching for health professionals. BMJ Neurol. Open. 2, e000065 (2020). https://doi.org/10.1136/bmjno-2020-000065.\u003c/li\u003e\n\u003cli\u003eO\u0026rsquo;Keeffe, S., Chowdhury, I., Sinanaj, A., Ewang, I., Blain, C., Teodoro, T., Edwards, M., Yogarajah, M.: A Service Evaluation of the Experiences of Patients With Functional Neurological Disorders Within the NHS. Front. Neurol. 12, (2021). https://doi.org/10.3389/fneur.2021.656466.\u003c/li\u003e\n\u003cli\u003eMitchell, W.: Positive language leads to positive wellbeing. BMJ. i4426 (2016). https://doi.org/10.1136/bmj.i4426.\u003c/li\u003e\n\u003cli\u003eThorne, S.E., Harris, S.R., Mahoney, K., Con, A., McGuinness, L.: The context of health care communication in chronic illness. Patient Educ. Couns. 54, 299\u0026ndash;306 (2004). https://doi.org/10.1016/j.pec.2003.11.009.\u003c/li\u003e\n\u003cli\u003evan der Hulst: A Clinician\u0026rsquo;s Guide to Functional Neurological Disorder: A Practical Neuropsychological Approach. London: Routledge (2023).\u003c/li\u003e\n\u003cli\u003eBailey, C., Agrawal, N., Cope, S., Proctor, B., Mildon, B., Butler, M., Holt, K., Edwards, M., Poole, N., Nicholson, T.R.: Illness perceptions, experiences of stigma and engagement in functional neurological disorder (FND): exploring the role of multidisciplinary group education sessions. BMJ Neurol. Open. 6, e000633 (2024). https://doi.org/10.1136/bmjno-2024-000633.\u003c/li\u003e\n\u003cli\u003eMacDuffie, K.E., Grubbs, L., Best, T., LaRoche, S., Mildon, B., Myers, L., Stafford, E., Rommelfanger, K.S.: Stigma and functional neurological disorder: a research agenda targeting the clinical encounter. CNS Spectr. 26, 587\u0026ndash;592 (2021). https://doi.org/10.1017/S1092852920002084.\u003c/li\u003e\n\u003cli\u003eStaton, A., Dawson, D., Merdian, H., Tickle, A., Walker, T.: Functional neurological disorder: A qualitative study exploring individuals\u0026rsquo; experiences of psychological services. Psychol. Psychother. Theory Res. Pract. 97, 138\u0026ndash;156 (2024). https://doi.org/10.1111/papt.12504.\u003c/li\u003e\n\u003cli\u003eHaskard Zolnierek, K.B., Dimatteo, M.R.: Physician Communication and Patient Adherence to Treatment. Med. Care. 47, 826\u0026ndash;834 (2009). https://doi.org/10.1097/mlr.0b013e31819a5acc.\u003c/li\u003e\n\u003cli\u003eJenstad, L.M., Howe, T., Breau, G., Abel, J., Colozzo, P., Halas, G., Mason, G., Rieger, C., Simon, L., Strachan, S.: Communication between healthcare providers and communicatively-vulnerable patients with associated health outcomes: A scoping review of knowledge syntheses. Patient Educ. Couns. 119, 108040 (2024). https://doi.org/10.1016/j.pec.2023.108040.\u003c/li\u003e\n\u003cli\u003eSharkiya, S.H.: Quality communication can improve patient-centred health outcomes among older patients: a rapid review. BMC Health Serv. Res. 23, 886 (2023). https://doi.org/10.1186/s12913-023-09869-8.\u003c/li\u003e\n\u003cli\u003eFoley, C., Kirkby, A., Eccles, F.J.R.: A meta-ethnographic synthesis of the experiences of stigma amongst people with functional neurological disorder. Disabil. Rehabil. 46, 1\u0026ndash;12 (2024). https://doi.org/10.1080/09638288.2022.2155714.\u003c/li\u003e\n\u003cli\u003eMyers, L., Gray, C., Roberts, N., Levita, L., Reuber, M.: Shame in the treatment of patients with psychogenic nonepileptic seizures: The elephant in the room. Seizure. 94, 176\u0026ndash;182 (2022). https://doi.org/10.1016/j.seizure.2021.10.018.\u003c/li\u003e\n\u003cli\u003eHamid, H., Fodeh, S.J., Lizama, A.G., Czlapinski, R., Pugh, M.J., LaFrance, W.C., Jr., Brandt, C.A.: Validating a natural language processing tool to exclude psychogenic nonepileptic seizures in electronic medical record-based epilepsy research. Epilepsy Behav. 29, 578\u0026ndash;580 (2013). https://doi.org/10.1016/j.yebeh.2013.09.025.\u003c/li\u003e\n\u003cli\u003ePevy, N., Christensen, H., Walker, T., Reuber, M.: Feasibility of using an automated analysis of formulation effort in patients\u0026rsquo; spoken seizure descriptions in the differential diagnosis of epileptic and nonepileptic seizures. Seizure. 91, 141\u0026ndash;145 (2021). https://doi.org/10.1016/j.seizure.2021.06.009.\u003c/li\u003e\n\u003cli\u003eGuetterman, T.C., Chang, T., Dejonckheere, M., Basu, T., Scruggs, E., Vydiswaran, V.V.: Augmenting Qualitative Text Analysis with Natural Language Processing: Methodological Study. J. Med. Internet Res. 20, e231 (2018). https://doi.org/10.2196/jmir.9702.\u003c/li\u003e\n\u003cli\u003eKassianos, A.P., Ignatowicz, A., Greenfield, G., Majeed, A., Car, J., Pappas, Y.: \u0026ldquo;Partners rather than just providers\u0026hellip;\u0026rdquo;: A qualitative study on health care professionals\u0026rsquo; views on implementation of multidisciplinary group meetings in the North West London Integrated Care Pilot. Int. J. Integr. Care. 15, (2015). https://doi.org/10.5334/ijic.2019.\u003c/li\u003e\n\u003cli\u003eLennox-Chhugani, N.: Inter-Disciplinary Work in the Context of Integrated Care \u0026ndash; a Theoretical and Methodological Framework. Int. J. Integr. Care. 23, (2023). https://doi.org/10.5334/ijic.7544.\u003c/li\u003e\n\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Functional Neurological Disorders (FND), Natural Language Processing (NLP), Topic modelling, Sentiment analysis, Healthcare Professionals, Electronic Medical Records","lastPublishedDoi":"10.21203/rs.3.rs-6018381/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6018381/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eBackground\u003c/h2\u003e \u003cp\u003eEffective communication is essential for delivering quality healthcare, particularly for individuals with Functional Neurological Disorders (FND), who are often subject to misdiagnosis and stigmatising language that implies symptom fabrication. Variability in communication styles among healthcare professionals may contribute to these challenges, affecting patient understanding and care outcomes.\u003c/p\u003e\u003ch2\u003eMethods\u003c/h2\u003e \u003cp\u003eThis study employed natural language processing (NLP) to analyse clinician-to-clinician and clinician-to-patient communication regarding FND. A total of 869 electronic health records (EHRs) were examined to assess differences in language use and emotional tone across various professionals\u0026mdash;specifically, neurologists and psychologists\u0026mdash;and different document types, such as discharge summaries and letters to general practitioners (GPs). Sentiment analysis was also applied to evaluate the emotional tone of communications.\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e \u003cp\u003eFindings revealed distinct communication patterns between neurologists and psychologists. Psychologists frequently used terms related to subjective experiences, such as \u0026lsquo;trauma\u0026rsquo; and \u0026lsquo;awareness,\u0026rsquo; aiming to help patients understand their diagnosis. In contrast, neurologists focused on medicalised narratives, emphasising symptoms like \u0026lsquo;seizures\u0026rsquo; and clinical interventions, including assessment (\u0026lsquo;telemetry\u0026rsquo;) and treatment (\u0026lsquo;medication\u0026rsquo;). Sentiment analysis indicated that psychologists tended to use more positive and proactive language, whereas neurologists generally adopted a neutral or cautious tone.\u003c/p\u003e\u003ch2\u003eConclusions\u003c/h2\u003e \u003cp\u003e These findings highlight significant differences in communication styles and emotional tones among professionals involved in FND care. The study underscores the importance of fostering integrated, multidisciplinary care pathways and developing standardised guidelines for clinical terminology in FND to improve communication and patient outcomes. Future research should explore how these communication patterns influence patient experiences and treatment adherence.\u003c/p\u003e","manuscriptTitle":"Using Natural Language Processing to Explore Differences in Healthcare Professionals’ Language On Functional Neurological Disorders: A Comparative Topic and Sentiment Analysis Study","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-02-18 15:01:11","doi":"10.21203/rs.3.rs-6018381/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"0f621600-fb02-4508-824c-cdae9f0ef7d7","owner":[],"postedDate":"February 18th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2026-01-16T19:29:03+00:00","versionOfRecord":{"articleIdentity":"rs-6018381","link":"https://doi.org/10.3389/fdgth.2025.1691724","journal":{"identity":"frontiers-in-digital-health","isVorOnly":true,"title":"Frontiers in Digital Health"},"publishedOn":"2026-01-15 00:00:00","publishedOnDateReadable":"January 15th, 2026"},"versionCreatedAt":"2025-02-18 15:01:11","video":"","vorDoi":"10.3389/fdgth.2025.1691724","vorDoiUrl":"https://doi.org/10.3389/fdgth.2025.1691724","workflowStages":[]},"version":"v1","identity":"rs-6018381","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6018381","identity":"rs-6018381","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}