The nursing process and total health cost variability: an analysis using machine learning

The nursing process and total health cost variability: an analysis using machine learning | 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 The nursing process and total health cost variability: an analysis using machine learning MARIA CONSUELO COMPANY-SANCHO, VICTOR M. GONZÁLEZ-CHORDÁ, MARIA ISABEL ORTS-CORTÉS This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5700089/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 01 Jul, 2025 Read the published version in BMC Nursing → Version 1 posted 8 You are reading this latest preprint version Abstract Aims: To find out whether the information that the nursing process provides (functional patterns and the NANDA-NIC-NOC taxonomy), presented through clinical histories, influences predictions of total healthcare costs. Background: The nursing process, is not included in the systems that calculate expenditure in the Spanish healthcare system. Such an omission can result in suboptimal resource allocation. Methods: Analytical and retrospective observational study of a population of 1,691,075 people over the age of 15. The explanatory variables were age, sex and nursing process data, with total healthcare cost as the outcome variable. A bivariate analysis and a multiple regression were performed for the multivariate analysis. To improve prediction accuracy and account for non-linear relationships, the analysis was completed using two machine learning models. Results: 58% (n = 980,437) of the population presented some data from the nursing process, for individuals with an assessed pattern, the average cost was €2304.17 compared with €950.93 for those who had none; with a nursing diagnosis, the average cost was €1,666 versus €840 without it. Having created the best model for the analysis using neural networks and XGBOOST, an average coefficient of determination of R 2 = 21.45% was obtained. Conclusions: The variability in total healthcare costs can be explained in more than 21% of cases by the model created, including sex, age, and the information related to the nursing process. Implications for health policy: Demonstrating the influence of nursing care on total patient costs will facilitate its inclusion in management programs, promoting the use of nursing data in risk adjustment models and healthcare planning. North American Nursing Diagnosis Association Nursing Interventions Classification Nursing Outcomes Classification standardized nursing terminology Nursing Process Nursing Diagnosis total costs Figures Figure 1 Figure 2 Introduction Determining the total costs of healthcare services is critical to ensuring the sustainability of healthcare systems ( 1 ). Inefficient management has significant policy relevance ( 2 ). However, it is a complex process and the inclusion of resources in the equation to estimate costs will depend on the importance placed on a given resource, impacting the accuracy of this estimate ( 3 ). In Spain, health policies do not include the calculation of the cost of nursing care, and international experiences in systematically incorporating the calculation of the cost of nursing care into their health policies are limited, especially in primary care ( 4 ). Traditionally, costing systems have been developed as tools for hospital management. Specifically, the Diagnosis Related Groups (DRGs) are the classification system used in the US and Europe, including Spain. However, this task is much more complex in primary care due to its idiosyncrasies. Specifically, the Adjusted Morbidity Groups (AMG) system is a stratification tool tailored to the Spanish healthcare, the population is thus grouped into 31 mutually exclusive categories ( 5 ). Both systems, DRG and AMG, can be used in clinical care management, epidemiology, or healthcare administration, although several studies conclude that there is unexplained intra-group variability in the consumption of resources and costs ( 6 , 7 ). A possible cause of this variability is that nursing care is considered an indirect and fixed cost, causing a significant loss of information as it does not factor in variations related to care needs. Both systems in Spain are based on medical classification codes such as the International Classification of Primary Care (ICAP2) and the International Classification of Diseases (ICD-9 or ICD-10), but neither includes information related to the nursing process, such as assessment results, standardized languages, or nursing taxonomies. The lack of visibility of the nurse's work in these classification models may influence human resource policies, patient trust, patient safety and result in inefficient resource allocation. Underestimation of the costs associated with nursing staff may negatively affect health system financing and planning ( 8 ) Some studies conclude that classification in the DRG system is an improvement as it factors the weight of care into the Eq. (9) or measures the direct costs of care ( 10 ). Moreover, a previous study concluded that nursing diagnoses (NDs) enhance the explanatory capacity of the use of healthcare resources ( 11 ), but the nursing process (NP) also provides, as well as diagnoses, information about the assessment, outcomes and care interventions, and this has not been studied in relation to the total healthcare cost. This nursing process is a systematic, sequential and dynamic method, designed to address the evolving needs of patients ( 12 ) and comprises five interconnected stages: assessment, diagnosis, planning, implementation, and evaluation. Assessment systems where used, such as the Functional Health Patterns (FHPs) from Marjory Gordon and taxonomies such as the North American Nursing Diagnosis Association (NANDA), the Nursing Interventions Classification (NIC), and the Nursing Outcomes Classification (NOC). These classifications make it possible to quantify, establish and ascertain nursing care interventions ( 13 ), thus improving the quality of care, saving time, and reducing healthcare costs ( 14 ). Their inclusion in medical histories is a way of determining the cost effectiveness of nursing care, nurse allocation, and job satisfaction, as well as patient outcomes and satisfaction ( 14 ) directly. Furthermore, their use reduces variability in clinical practice and makes it easier to measure the effectiveness of work ( 15 , 16 ). The use of classifications significantly improves predictions of patient outcomes and the organization’s results ( 17 ). It is approved in many countries around the world, showing clinical impact wherever it is used ( 18 ) which enables its transfer and replication. In Spain, nurses are university graduates, with the option to pursue different specialties. Their work encompasses various levels, such as community or hospital settings, primarily within the public healthcare system. Royal Decree 1093/2010 ( 19 ), recommends the use of NANDA-NIC-NOC (NNN) in medical histories of public institutions filled out by nurses. All the autonomous communities have health records with a variable development of NNN, with economic incentives for their use in some communities. This makes it possible to avail of a large amount of data for study, contributing to analysis with data mining techniques and artificial intelligence. The priority nursing topics studied with machine learning are patient supervision, monitoring, and classification, prediction of falls, and support for clinical decisions ( 20 ), but not costs. In the literature, we can identify analyses of the costs of nursing products, whether these are partial costs of techniques, procedures, or services or the study of cost-effectiveness ( 21 , 22 ), cost-benefit analysis( 23 ) or cost-utility ( 24 ), and related to the variability of costs in the DRG. However, there are still very few studies that conduct economic assessments (a broad concept encompassing methods to compare costs and outcomes)( 25 ) and studies are very seldom performed in terms of total costs. For the above reasons, the main aim of this study was to confirm whether the information provided by the nursing process influences the prediction of the total healthcare cost. Methodology Observational, analytical, retrospective study based on data from healthcare records. The study was conducted in the Autonomous Community of the Canary Islands (Spain) with data from 2017 and 2018. The predictor variables were considered until 2017 and the total cost was calculated in 2018 (Outcome variables used in the machine learning analysis.). Each patient has a unique primary care history and an individual health card with entitlement to public health care. The study population consisted of people over 15 years of age enrolled in the Health Card database of the Canary Islands Health Service (N = 1,691,075). Mutual society members defined as patients cared for by national mutual societies that provide social benefits and health care only to national civil servants were excluded. Data were requested via protocol from the Information Security Office of the Health Service, and the data were encrypted and dissociated. The explanatory variables were sociodemographic (age and sex) and nursing process data (assessment, diagnosis, objectives and interventions) extracted from primary care medical histories. The assessment was carried out on the basis of the Functional Patterns with 44 variables, four per pattern, specifying the last result of that functional pattern in each person (Normal, Risk of alteration, Altered, Not assessable). In addition, 211 NANDA nursing diagnoses (NANDA-I 2009–2011), 388 NOCs (fourth version), and 558 different NICs (fifth version) used in the electronic medical record were considered as variables, the NNNs from previous versions were not removed from the medical record. Those that appeared in fewer than 1/10,000 patients were filtered to make the analysis more complex. The outcome variable was the total cost per patient, adding consultations and emergency visits to public and state-funded centres, hospitalizations, major outpatient surgery, and dispensing in pharmacies during 2018, [information available in Appendix A]. The variables of the different health information systems were integrated with the patient's file number, which was encrypted and transformed into a single unique key per individual. The statistical analysis was carried out using the statistics program R Commander 2.6-2, the graphical interface of the statistics package R 4.0.0. For machine learning, the Python programming environment (version 3.10.8) was used with the pandas, Numpy, Scikit-learn, Tensorflow, and XGBOOST libraries. As the study was based on the complete population of users in the healthcare system, inferential statistical methods were not applied. First, the nursing process variables and costs were described. Second, the distribution of total costs was examined in relation to each independent variable using descriptive statistics. Thirdly, total costs were normalized with a logarithm and the influence of age, sex, and FHP was analysed with a multiple linear regression model built using a forward selection approach. Subsequently, two machine learning models were used including the set of variables: a pre-fed neural network ( 26 ) and a tree-based regression algorithm called XGBoost ( 27 ). Both models are capable of capturing non-linear and complex relationships among variables and are therefore not affected by multicollinearity, unlike simpler models such as logistic regression. Consequently, it was not necessary to eliminate correlated predictors. Furthermore, they are well-suited to handling large volumes of data and demonstrate high predictive performance. Finally, a mean of the prediction of these two algorithms was performed in an ensemble ( 28 ). To this end, the cases were segmented into three groups: training (80%), validation (10%) and test (10%). The RMSE (Root Mean Square Error) was used as the training metric (prediction error) of the learning algorithms, and R-squared (R 2 ) was used for validation of the models. Several deep neural network architectures were evaluated, starting with a single hidden layer of 32 nodes and progressively increasing complexity. Performance improved with 64 and 128 nodes, prompting the addition of a second, third, and fourth hidden layer. Various node combinations were tested at each level. The optimal configuration was achieved with four hidden layers containing 128, 64, 32, and 16 nodes, respectively, as the inclusion of a fifth layer did not further enhance model performance. For XGBoost, hyperparameters were optimized using Bayesian optimization with the skopt library, automatically exploring the most effective combinations within a predefined range of values. Once the best configuration of each algorithm was chosen, the final result published was that which this configuration achieved when applied to the test dataset, which was only used once by each algorithm. The study was conducted in compliance with Organic Law 3/2018 on Personal Data Protection and Digital Rights Guarantee and the provisions of the General Data Protection Regulation (EU) 2016/679 (GDPR). Specifically, it adheres to the second point of the Seventeenth Additional Provision (subsection d), which deems the use of pseudonymized personal data for health research, particularly biomedical research, as lawful and allows for the exemption of informed consent for such purposes. The variables extracted from health information systems were linked using an encrypted record number, which was transformed into a unique identifier to ensure data anonymization. The database is exclusively held by the principal investigator, who ensures its security through password protection and commits to neither performing any re-identification of participants nor sharing the data via cloud-based services. The study also complies with the provisions of the Regulation (EU) 2016/679 of the European Parliament and of the Council of April 27, 2016, on Data Protection. Results Descriptive statistics The study population consisted of 1,691,075 people over 15 years of age who had a health card. A total of 51.04% were female and the mean age was 46.6 years (SD 17.9). Some 17.39% (n = 294,077) of the population were over 65. The mean cost per patient was €1,283.08 (SD 3007; €1,377.04 female vs €1,185.14 male). A total of 58% (n = 980,437) of the population had some nursing methodology data (FHP, ND, NIC, NOC). The complete NP (with all 11 FHPs assessed, one ND, one NOC and one NIC code) was performed in 2.74% (n = 46,380; 63.4% female) of the subjects. There were 1,591,840 different FHP assessments in the patient cohort that had at least one FHP recorded and 24.5% (n = 415,068; 59.5% female) of the population had at least one assessed pattern. The mean number of assessed FHPs with a recorded result per person was 3.84 (SD 3.58), with a mean age of 56.9 (SD 18.2) years (57.0 male, 56.9 female) and the most frequently assessed FHP was Health Perception. A total of 3.32% (n = 46,380) had the 11 patterns assessed at some point, with a mean age of 69.7 (SD 15.6) years and 60.7% (n = 595,125) of the individuals with an altered pattern were female. The main FHP assessment response was Normal, with Sexuality– Reproductive being the FHP with the highest value in the total (83%), although for males it was Value–Belief. Cognitive-Perceptual was the lowest value (44%). In the Risk of Alteration response, the Health Perception– Management pattern was the most assessed (17%), and Sexuality– Reproductive plus Value–Belief were the least assessed (3%). In the Altered response, the Cognitive-Perceptual FHP was the most assessed (45%), and Value–Belief the least (3%). In Not Assessable, the most assessed was Value–Belief (15%), with several below 1%. The mean age of the sample with altered FHP was 60.3 (SD 18.3) years (58.9 males, 61.2 females). Table 1 . Table 1 Functional health patterns in the total population Pattern Altered [% (n)] Risk [% (n)] Nornal [% (n)] Not Assessable [% (n)] Total (n) Health Perception–Health Management 24 (59.688) 17 (42.555) 58 (146.899) 1 (2.253) 251.395 Nutritional–Metabolic 39 (94.084) 15 (35.530) 46 (112.229) < 1 (1.054) 242.897 Elimination 26 (41.837) 8 (12.477) 66 (106.184) < 1 (787) 161.285 Activity–Exercise 26 (51.113) 12 (23.569) 61 (118.681) < 1 (712) 194.075 Sleep–Rest 23 (34.415) 11 (15.667) 66 (97.378) < 1 (688) 148.148 Cognitive–Perceptual 45 (63.104) 10 (13.733) 44 (61.816) 1 (1.331) 139.984 Self-perception- self-concept 28 (26.046) 13 (11.599) 54 (49.602) 5 (4.213) 91.460 Role–Relationship 18 (17.362) 13 (12.899) 67 (64.168) 1 (1.161) 95.590 Sexuality–Reproductive 4 (4.569) 3 (3.334) 83 (95.226) 10 (11.734) 114.863 Coping–Stress Tolerance 13 (10.458) 13 (10.302) 70 (55.830) 5 (3.714) 80.304 Value–Belief 3 (1.917) 3 (2.324) 79 (56.729) 15 (10.869) 71.839 A total of 2,816,295 active NDs (still ongoing) were identified in the population. A total of 54.1% (n = 916,024; 53.5% female) had at least one active ND, and the mean ND per person was 3.07 (SD 2.90). The mean age of people with an ND was 48.9 (SD 20.7) years (53.41% male, 56.84% female). Of all the people with an ND, 39.2% (n = 359,605) had a recorded pattern. The 10 most frequent NDs can be found in Table 2 . In males, the first 8 diagnoses coincided with the most frequent except for the last two. A total of 14% of the diagnostic codes encompasses 80% of the diagnoses made. Table 2 Most frequently used terms. Frequency (%) Age (Mean,SD) Cost in euros (Mean,SD) NANDA Readiness for enhanced health management (00162) 40.37% 57.8 (18.5) 1.956 (3.677) Acute pain (00132) 35.16% 46 ( 17 ) 1.498 (3.133) Impaired skin integrity (00046) 29.17% 48.7 (18.7) 4.064 (3.939) Readiness for enhanced immunization status (00186) 24.14% 50.5 (22.2) 2.027 (3.734) Imbalanced nutrition: more than body requirements (00001) 10.78% 57.2 (18.5) 2.591 (4.213) Risk for infection (00004) 9.55% 50.8 (20.2) 2.101 (4.096) Health seeking behavior (specify) (00084) 9.55% 52.1 ( 20 ) 1.819 (3.455) Ineffective breathing pattern (00032) 6.49% 51.7 ( 20 ) 2.484 (4.304) Impaired urinary elimination (00016) 6.34% 52.9 (21.2) 2.471 (4.222) Anxiety (00146) 6.0% 53.5 (18.1) 2.500 (4.125) NOC Immunization behavior (1900) 22.48% 51.7 (22.2) 2.078 (3.801) Compliance behavior (1601) 18.09% 55.8 (18.4) 2.309 (4.098) Pain level (2102) 15.96% 48.6 (17.3) 1.733 (3.429) Risk control (1902) 13.49% 55.5 (18.4) 2.209 (3.919) Wound healing: primary intention (1102) 13.10% 48.9 ( 18 ) 1.826 (3.865) Wound healing: second intention (1103) 12.59% 51 (19.4) 2.253 (4.456) Pain control (1605) 10.89% 55.4 (19.5) 2.310 (4.105) Adherence behavior (1600) 10.23% 53 (18.05) 2.006 (3.763) Immune status (0702) 6.62% 54.3 (22.3) 2.360 (4.212) Personal well-being (2002) 5.51% 58.2 (20.1) 2.504 (4.178) NIC Medication administration: intramuscular (IM) (2313) 28.90% 48.5 (17.2) 1.751 (3.427) Immunization/vaccination management (6530) 23.94% 52.4 (22.3) 2.137 (3.869) Health education (5510) 22.63% 54.7 (19.6) 2.182 (3.937) Vital signs monitoring (6680) 15.99% 55 (18.8) 2.176 (3.832) Wound care (3660) 14.79% 50.4 (18.9) 2.108 (4.259) Phlebotomy: venous blood sample (4238) 11.18% 48.4 ( 18 ) 1.752 (3.672) Patient contracting (4420) 10.66% 57.9 (18.5) 2.593 (4.346) Nutritional counseling (5246) 9.56% 57.6 (18.8) 2.543 (4.098) Exercise promotion (200) 9.49% 60.7 (18.4) 2.799 (4.375) Risk identification (6610) 9.07% 58.4 (18.6) 2.457 (4.173) There were 2,140,298 NOCs. Some 45.7% (n = 772,730; 54.3% female) of the population had at least one active NOC, with an average of 2.77 (SD 2.96) per person. The average age with at least one NOC was 49.5 (SD 19.22) years. The 10 most frequent NOCs are listed in Table 2 . The first nine coincide in male and female patients, albeit with different frequencies. With 13 codes of the 388 NOCs used, 50% of the sample was reached, and with 115 codes 95% was achieved. Regarding NIC codes, there were 3,241,607 active interventions. A total of 46.5% (n = 787,510; 54.27% female) had at least one active NIC. The average number of NICs per person was 4.12 (SD 7.04). The average age of individuals with at least one NIC was 49.85 (SD 19.18) years. The 10 most frequent NICs are shown in Table 2 . The NICs coincided in males and females, except for Exercise promotion (0200) and Risk identification (6610), which were replaced by Monitoring infections (6540) and Administering topical medication in females (2316). There were 558 different NICs, and with 18 codes they reached 50% of la sample, with 53 reaching 75% and 262 NICs reaching 99%. Bivariate analysis The average cost of individuals with at least one assessed FHP was €2312.39 vs €954.01 with no assessment. In general, higher costs were observed in association with increased severity in the pattern classification, so an assessment as Normal had a lower cost than an assessment of Risk of Alteration and Altered. However, in the Cognitive-Perceptual and Role-Relationship, the average cost was higher with Risk of Alteration assessments than with Altered (Table 3 ). Table 3 Costs of the Function Pattern expressed in Euros (€) Pattern Altered Not Risk Normal Not Assessable Not assessed Health Perception–Health Management 3533,754 2958,436 2041,983 3443,164 1059,433 Nutritional–Metabolic 3056,578 3013,422 2298,93 2474,588 1045,817 Elimination 3988,626 3439,151 2515,886 2358,04 1105,381 Activity–Exercise 4186,485 3298,693 2217,979 3036,251 1077,262 Sleep–Rest 3594,369 3279,023 2707,341 2980,671 1120,615 Cognitive–Perceptual 3379,357 3482,454 2633,384 3388,975 1122,703 Self-perception- self-concept 3751,797 3575,209 2957,991 4705,034 1165,313 Role–Relationship 3684,936 3746,596 3148,426 3445,735 1160,432 Sexuality–Reproductive 3077,994 2526,025 2493,639 4352,435 1179,264 Coping–Stress Tolerance 4062,511 3850,92 3114,743 4398,015 1177,944 Value–Belief 4816,553 4546,019 3183,46 4203,634 1188,032 The average cost for patients with at least one ND was €1666 vs €840 without an ND. The risk of falls (€4,663), risk of unstable glycemia levels (€4,145), and chronic pain (€4,064) were the most frequent and expensive NDs. The average cost of people with at least one NOC was €2,711 vs €869 with no NOC. Of the most prevalent and costly NOCs the most prominent were Fall prevention behaviour (€4888) and Impaired urinary elimination (€2945). The average cost of people with at least one NIC was €2,717.25 vs €863.77 with no NIC. The highest NIC was Fall prevention (€4521). Costs increased as the number of NANDAs, NOCs and NICs increased, although a larger number of NICs was needed to reach similar costs to those with NANDA and NOC (Fig. 1 ). Multivariate analysis The predictive power on total costs increased as age and sex (R 2 = 11.47) and FHP (R 2 = 14.75) were included. Subsequently, the NANDA, NIC and NOC (791 input variables) variables were included by testing different neural network structures. The best results on the validation data were obtained with a structure of four hidden layers with 128, 64, 32 and 16 nodes, and a single variable in the output layer (the logarithm of cost), resulting in R 2 = 21.10 (RMSE: 6.058). (Fig. 2 ). In the XGBoost algorithm, Bayesian inference techniques were used to select the hyperparameters that optimized the results in the validation dataset. The R 2 obtained was 21.21% (RMSE: 6.014). The arithmetic mean of the predictions of both models (ensemble) returned an R 2 of 21.31%. When this prediction was compared with the actual values (test sample), the R 2 obtained was 21.45% (RMSE: 6.016), which was the best result (Fig. 2 ). Discussion Reducing unjustified cost variability and ensuring better suitability of resources are objectives of health management. However, healthcare systems are deficient when estimating costs, and insurer payout is based on inaccurate assumptions about the intensity of care ( 29 ). The results of this study show that the nursing process, together with age and sex, contributes to predicting total healthcare cost, explaining more than 21% of the variability. While no previous studies were found to be able to compare these results, it seems clear that complementing risk adjustment systems, such as DRGs or GMAs, with nursing process information will improve cost estimation. What is not measured cannot be managed or improved. Nursing care continues to be measured poorly and unevenly. Ignoring the consumption and production of goods and services that result from nursing decisions can distort health as a final product ( 30 ). Besides, the system could become perverse without this information. Establishing empirical links between nursing care, health outcomes, and the cost of care must be a priority both for the community and for health systems, which would enable more precise budgetary planning and personnel allocation, based on the specific care needs of patients. Although 21.45% may seem modest, in the context of cost prediction models using routinely collected health data, this is a substantial contribution, especially when relying solely on nursing and demographic variables. The bivariate analysis showed that the increase in costs correlated with a higher number of altered functional patterns and diagnoses, interventions, and outcomes recorded. Furthermore, costs increased with age, consistent with the profile of chronic and fragile patients with greater care needs. However, no other studies with a similar analysis were identified, as previous studies based on the secondary analysis of nursing classifications focus on specific pathologies, pain and end-of-life care, ulcers, bereavement, falls or suicide, among others, but not costs ( 31 ). Care intensity increases as patient complexity rises, suggesting that nurses may focus more on patients with higher comorbidity and complexity. However, further research is needed to confirm this hypothesis. One aspect worth highlighting is that the most frequently recorded action by nurses was diagnosis, followed by interventions, outcomes and, finally, assessments. In fact, fewer than 4% of patients had a complete assessment of the 11 FHPs. The lack of FHP use may be due to the use of tools such as programs and protocols established in centres, whose completion is prioritized in the medical record, and is no longer filled out in nursing records due to overlap. This lack of recording or indiscriminate recording by nurses, who fill out the data in free text not exploitable by the system, is another possible cause. In fact, another study on hospital population found that 52.1% of NDs were not supported by assessments ( 32 ). We recommend that future studies analyse the coherence of care plans. In the same vein, the most commonly made diagnosis is found in terms of health promotion, in line with the area analysed and, probably, because it is the first in the assessment. However, the most common diagnoses were related to biological aspects, which is consistent with other studies ( 33 , 34 ). Few studies were found that examine electronic health record (EHR) diagnostic labels. Some focus on reviewing the most frequent diagnoses, but in both settings (hospital and primary care), or in specific aspects of them. One study examined NDs over 9 years in adult and child populations, in a health area in Spain, finding that 15 NDs accounted for more than 80% of the NDs used( 34 ). In our study, with 23 NDs we reached 75%, and with 14% of the diagnostic codes we accounted for 80% of the diagnoses. Another study conducted in Italy ( 33 ) at the community level, the most similar to our sample, found that Class 4 diagnoses from domains 4 are the most frequent (22.4%), followed by the risk of unstable blood glucose levels-00179 (16.4%) and the risk for overweight-00234 (13%), these diagnoses overlap with the top 45 most frequent diagnoses identified in our study, indicating consistency in diagnostic patterns between both populations. The most commonly used results (NOCs) were vital signs-0802 (22.5%), blood glucose level-2,300 (16%), and weight loss behavior 1,627 (11%). These outcomes overlap with the top 65 most frequent outcomes identified in our study. The most frequent interventions (NICs) were wound care-3660 (27%), intramuscular medication administration-2313 (19%), and health education-5510 (14%), coinciding with the first 10 of our study. The lack of concordance between the two NNN studies could be due to different settings and cultures, to the updating of the taxonomies in successive editions to remove and add diagnoses, adjusting them to changing needs, lack of updating in the medical records, or how long it has been in use in the medical record. In addition, the Italian study only compares one year ( 33 ) while our study analyses data from a 15-year period. This makes it difficult to compare results in terms of independent variables. The NP set out in the EHR is a rich source of information for health systems. Standardized languages should not only be considered for patient care but can provide essential data to inform on the complexity of care and guide payment criteria ( 17 ). It is not enough to measure only the cost of an intervention, which would be a purely accounting exercise. To carry out a formal economic analysis, designed to make decisions based on both efficiency and cost, standardised terminologies need to be included ( 35 ). Our study disaggregates the data by sex. The study population is large, an uncommon feature in the referenced studies. Females received more treatment actions from nursing staff, although according to the 2020 Annual Report of the National Health System, it is predominantly males who come to nursing consultations from the age of 59. This may indicate a worse average health status of the women who present. Although there are not many studies specifically addressing nursing diagnoses, medical and public health literature supports that women have higher healthcare utilization and are therefore more likely to receive more diagnoses ( 36 ). There are few differences in the care problems attended to by nurses among males and females. Perhaps human responses to health problems or life processes and their intervention do not make as much difference between the sexes as pathologies. This would be a topic worth studying in future research. One of the study limitations is that we used registry data from medical records, and the quality of nursing records is a known problem ( 13 ). In fact, the nursing process was completed in only 2.74% of the sample. Moreover, poor data quality can affect the model's predictions. Analysis was restricted to primary care records, which may have limited the model accuracy. The inclusion of additional variables, such as comorbidities and health determinants, would allow for a more comprehensive understanding. Due to the retrospective observational design, it is not possible to establish causal relationships between costs and the nursing process. However, 791 variables were analysed in 1,691,075 participants, resulting in a total of over 1.3 billion parameters. The large volume of data ensured that cases with incomplete information did not compromise the statistical power of the study. The RMSE values obtained highlight the added value of nursing data in explaining resource utilization; however, they should complement rather than replace existing models. Data were normalized to eliminate outliers and improve quality using the entire baseline population. Nevertheless, it is very likely that the predictive capacity of total healthcare cost models will increase with better records. Future studies should take this limitation into account and develop strategies to improve the quality and quantity of nursing records. Conclusions The information provided by the nursing process (functional patterns and NANDA-NIC-NOC taxonomy), based on medical records, influences the prediction of total health expenditure. Nursing records are not only useful for improving nursing work and patient safety, but also improve total healthcare cost information. These findings underscore the importance of healthcare policy makers considering nursing care documented in clinical records. This entails promoting the use and training of standardized terminologies, which must be integrated into information systems to support clinical and management decisions The inclusion of nursing process data within national health information systems will enable improved resource planning, more efficient cost allocation, and enhanced visibility of the impact of nursing care on health outcomes. It is recommended that health administrations integrate structured nursing process data into electronic health records, develop protocols to ensure data quality, and consider this information in risk adjustment models for budgeting and planning. Declarations Ethics approval In accordance with the Declaration of Helsinki and Spanish legislation, this study was approved by the clinical research ethics committee of the Dr. Negrín University Hospital of Gran Canaria (Date: January 29, 2021; Code: 2021-037-1). Consent to participate Not Applicable. Consent for publication Not applicable Availability of data and materials: The datasets generated and/or analysed during the current study are not publicly available due to the inclusion of sensitive and confidential data, but are available from the corresponding author on reasonable request. Competing interests: The authors declare no competing interests. Funding: No funding has been received Authors' contributions: Study design: MC, MI, VM Data collection: MC, MI Data analysis: MC, VM Study supervision: MC, MI, VM Drafted the primary manuscript: MC, MI, VM Revised and approved the final manuscript.: MC,VM, MI References Lauzán O. Costos en salud: un asunto polémico. Rev Cub Salud Publica. 2020;46(2). https://scielosp.org/article/rcsp/2020.v46n2/e2054/es/ Walker RM, Boyne GA, Brewer GA. Public management and performance : research directions. Cambridge University Press; 2010. Cabo J. Gestión Sanitaria Integral: Pública y Privada. Madrid. CEF, editor;; 2014. Laport N, Sermeus W, Vanden Boer G, Van Herck P. Adjusting for Nursing Care Case Mix in Hospital Reimbursement. Policy Polit Nurs Pract 2008 6;9(2):94–102. https://doi.org/10.1177/1527154408319696 Monterde D, Vela E, Clèries M. Los grupos de morbilidad ajustados: nuevo agrupador de morbilidad poblacional de utilidad en el ámbito de la atención primaria. Aten Primaria. 2016;48(10):674–82. https://doi.org/10.1016/j.aprim.2016.06.003 . Cots F, Castells X, Mercadé L, Torre P, Riu M. Risk adjustment: beyond patient classification systems. Gac Sanit. 2001;15(5):423–31. https://doi.org/10.1016/S0213-9111(01)71596-8 . Company-Sancho MC, González-Chordá VM, Orts-Cortés MI. Variability in Healthcare Expenditure According to the Stratification of Adjusted Morbidity Groups in the Canary Islands (Spain). Int J Environ Res Public Health. 2022;19(7):4219. https://doi.org/10.3390/ijerph19074219 . Ball JE, Bruyneel L, Aiken LH, Sermeus W, Sloane DM, Rafferty AM, et al. Post-operative mortality, missed care and nurse staffing in nine countries: A cross-sectional study. Int J Nurs Stud. 2018;78:10–5. https://doi.org/10.1016/j.ijnurstu.2017.08.004 . Rich M, Cubillo B, Barberá M, Bravo M. Estimación de los costes de enfermería en el proceso de la enfermedad pulmonar obstrucctiva crónica (EPOC). Enfermería Global. 2003;2(1). https://revistas.um.es/eglobal/article/view/657 Costa A, Castilho V, Togeiro F, Silva B, Siqueira N, De Oliveira T. Costos de las actividades de enfermería realizadas con mayor frecuencia a los pacientes de alta dependencia hospitalizados. Rev Latino-Am Enfermagem. 2012;20(5). https://doi.org/10.1016/S0213-9111(01)71596-8 . Company-Sancho MC, Estupiñán-Ramírez M, Sánchez-Janáriz H, Tristancho-Ajamil R. Relación entre diagnósticos de enfermería y uso de recursos sanitarios. Enferm Clin. 2017;27(4):214–21. https://doi.org/10.1016/j.enfcli.2017.04.002 . Reina G. El proceso de enfermería: instrumento para el cuidado. Vol. (17), Umbral Científico. (17):18–23. https://www.redalyc.org/articulo.oa?id=30421294003 Törnvall E, Jansson I. Preliminary Evidence for the Usefulness of Standardized Nursing Terminologies in Different Fields of Application: A Literature Review. Int J Nurs Knowl. 2017;28(2):109–19. https://doi.org/10.1111/2047-3095.12123 . Chae S, Oh H, Moorhead S. Effectiveness of Nursing Interventions using Standardized Nursing Terminologies: An Integrative Review. West J Nurs Res. 2020;42(11):963–73. https://doi.org/10.1177/0193945919900488 . Pérez Rivas FJ, Martín-Iglesias S, Pacheco del Cerro JL, Minguet Arenas C, García López M, Beamud Lagos M. Effectiveness of Nursing Process Use in Primary Care. Int J Nurs Knowl. 2016;27(1):43–8. https://doi.org/10.1111/2047-3095.12073 . Cárdenas-Valladolid J, Salinero-Fort MA, Gómez-Campelo P, de Burgos-Lunar C, Abánades-Herranz JC, Arnal-Selfa R et al. Effectiveness of Standardized Nursing Care Plans in Health Outcomes in Patients with Type 2 Diabetes Mellitus: A Two-Year Prospective Follow-Up Study. Dasgupta K, editor. PLoS One. 2012;7(8):e43870. https://doi.org/10.1371/journal.pone.0043870 Bertocchi L, Dante A, La Cerra C, Masotta V, Marcotullio A, Jones D, et al. Impact of standardized nursing terminologies on patient and organizational outcomes: A systematic review and meta-analysis. J Nurs Scholarsh. 2023;55(6):1126–53. https://doi.org/10.1111/JNU.12894 . Rodríguez-Suárez CA, González-de la Torre H, Hernández-De Luis MN, Fernández-Gutiérrez DÁ, Martínez-Alberto CE, Brito-Brito PR. Effectiveness of a Standardized Nursing Process Using NANDA International, Nursing Interventions Classification and Nursing Outcome Classification Terminologies: A Systematic Review. Healthcare. 2023;11(17):2449. https://doi.org/10.3390/healthcare11172449 . Boe R. Decree 1093/2010, of 3 September, approving the mínimum data set of clinicial reports in the National Health System. Bol Oficial del Estado [Spanish Official State Gazette], 78742–67. 2010 https://www.google.com/search?q=Real+Decreto+1093%2F2010%2C+de+3+de+septiembre%2C+por+el+que+se+aprueba+el+conjunto +mínimo+de+datos+de+los+informes+clínicos+en+el+Sistema+Nacional+de+Salud.& rlz=1C1CHBF_esES843ES843 &oq=Real+Decreto+1093%2F2010%2C+de+3+de+s Seibert K, Domhoff D, Bruch D, Schulte-Althoff M, Fürstenau D, Biessmann F, et al. Application Scenarios for Artificial Intelligence in Nursing Care: Rapid Review. J Med Internet Res. 2021;23(11):e26522. https://doi.org/10.2196/26522 . Martin-Misener R, Harbman P, Donald F, Reid K, Kilpatrick K, Carter N, et al. Cost-effectiveness of nurse practitioners in primary and specialised ambulatory care: systematic review. BMJ Open. 2015;5(6):e007167–007167. https://doi.org/10.1136/bmjopen-2014-007167 . Vásquez-Hernández SM, Rico-Ardila DL, Gómez-Camargo LN, Álvarez-Quintero LM. Costo-efectividad de las intervenciones de enfermería para el manejo de úlceras por pie diabético: revisión sistemática. MedUNAB. 2021;24(1):13–40. https://doi.org/10.29375/01237047.3832 . Moran D, Wu AW, Connors C, Chappidi MR, Sreedhara SK, Selter JH, et al. Cost-Benefit Analysis of a Support Program for Nursing Staff. J Patient Saf. 2020;16(4):e250–4. https://doi.org/10.1097/PTS.0000000000000376 . Grochtdreis T, Zimmermann T, Puschmann E, Porzelt S, Dams J, Scherer M, et al. Cost-utility of collaborative nurse-led self-management support for primary care patients with anxiety, depressive or somatic symptoms: A cluster-randomized controlled trial (the SMADS trial). Int J Nurs Stud. 2018;80:67–75. https://doi.org/10.1016/j.ijnurstu.2017.12.010 . Mata VE, Schutz V, de Peregrino AA. Dificultades y oportunidades para la enfermería: Una revisión narrativa sobre evaluación económica en salud. Enfermeria Global. 2013;12(1):392–403. https://scielo.isciii.es/scielo.php?script=sci_abstract . &pid=S1695-61412013000100021&lng=es&nrm=iso. Goodfellow I, Bengio Y, Courville A. Deep Learning (Adaptive Computation and Machine Learning series). 1st ed. The MIT Press, editor.; 2016. Chen T, Guestrin C. XGBoost. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2016. pp. 785–94. https://doi.org/10.1145/2939672.2939785 Mahajan P, Uddin S, Hajati F, Moni MA. Ensemble Learning for Disease Prediction. Rev Healthc. 2023;11(12):1808. https://doi.org/10.3390/healthcare11121808 . Kaplan R, Porter M. How to Solve the Cost Crisis in Health Care. Harvard business review. 2011. https://hbr.org/2011/09/how-to-solve-the-cost-crisis-in-health-care González-Chordá VM, Maciá Soler L, Mena Tudela D, Cervera Gasch Á, Salas-Medina P, Román P. Gestión de cuidados en el ámbito sociosanitario. Gestión de cuidados en el ámbito sociosanitario. Universitat Jaume I. 2017. https://doi.org/10.6035/Sapientia122 . Macieira GR, Chianca CM, Smith B, Yao Y, Bian J, Wilkie J, et al. Secondary use of standardized nursing care data for advancing nursing science and practice: a systematic review. J Am Med Inform Assoc. 2019;26(11):1401–11. https://doi.org/10.1093/jamia/ocz086 . Mateos M. Metodología enfermera y sistemas estandarizados de lenguaje enfermero en la historia clínica digital. [Tesis doctoral]. Sevilla: Facultad de Enfermería, Fisioterapia y Podología; 2017 https://idus.us.es/handle/11441/69103 Aleandri M, Scalorbi S, Pirazzini MC. Electronic nursing care plans through the use of NANDA, NOC, and NIC taxonomies in community setting: A descriptive study in northern Italy. Int J Nurs Knowl. 2022;33(1):72–80. https://doi.org/10.1111/2047-3095.12326 . Pérez FJ, Santamaría JM, Minguet C, Beamud M, García M. Implementation and Evaluation of the Nursing Process in Primary Health Care. Int J Nurs Knowl. 2012;23(1):18–28. https://doi.org/10.1111/j.2047-3095.2011.01199.x . Stone P. Economic Evaluations and Usefulness of Standardized Nursing Terminologies. Int J Nurs terminologies classifications. 2004;15(4):101–13. https://doi.org/10.1111/j.1744-618x.2004.tb00007.x . Bertakis KD, Azari R, Helms LJ, Callahan EJ, Robbins JA. Gender differences in the utilization of health care services. J Fam Pract. 2000;49(2):147–52. PMID: 10718692. Additional Declarations No competing interests reported. Supplementary Files AppendixA.docx Cite Share Download PDF Status: Published Journal Publication published 01 Jul, 2025 Read the published version in BMC Nursing → Version 1 posted Editorial decision: Revision requested 14 May, 2025 Reviews received at journal 12 May, 2025 Reviews received at journal 12 May, 2025 Reviewers agreed at journal 06 May, 2025 Reviewers agreed at journal 05 May, 2025 Reviewers invited by journal 29 Apr, 2025 Submission checks completed at journal 29 Apr, 2025 First submitted to journal 07 Apr, 2025 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-5700089","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":449541430,"identity":"44126707-8d1c-4c10-86a7-4e85016726a4","order_by":0,"name":"MARIA CONSUELO COMPANY-SANCHO","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAzklEQVRIiWNgGAWjYDACCQbGA2AGewOQMLAgSgsDRAsPiDKQIEWLRAKUSwjwz24+cOBDjU20ueTzqxt+FEgw8Ld3J+C35M6xhIMzjqXl7pydU3azB+gwiTNnN+DVYiCRY3CYt+Fw7obbOWk3eIBaDCRyCWnJ/wDRcvNM2s0/xGnJYYBoucF+7DZRtkjcSDOA+KUnh+22jIEED0G/8M9IfvgAGGK529mPP7v55o+NHH97L34tCBcy8BiAaB7ilEO0sD8gXvUoGAWjYBSMKAAANThNUCIwbT0AAAAASUVORK5CYII=","orcid":"","institution":"Health Promotion Service, Directorate General for Public Health","correspondingAuthor":true,"prefix":"","firstName":"MARIA","middleName":"CONSUELO","lastName":"COMPANY-SANCHO","suffix":""},{"id":449541431,"identity":"64998ec6-5216-4318-ad25-c001fe6512bf","order_by":1,"name":"VICTOR M. GONZÁLEZ-CHORDÁ","email":"","orcid":"","institution":"Universitat Jaume I (Nursing Department)","correspondingAuthor":false,"prefix":"","firstName":"VICTOR","middleName":"M.","lastName":"GONZÁLEZ-CHORDÁ","suffix":""},{"id":449541432,"identity":"df536e3c-20f3-491a-8540-2259b2790c6a","order_by":2,"name":"MARIA ISABEL ORTS-CORTÉS","email":"","orcid":"","institution":"University of Alicante (Department of Nursing)","correspondingAuthor":false,"prefix":"","firstName":"MARIA","middleName":"ISABEL","lastName":"ORTS-CORTÉS","suffix":""}],"badges":[],"createdAt":"2024-12-23 13:38:17","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5700089/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5700089/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1186/s12912-025-03304-5","type":"published","date":"2025-07-01T15:58:01+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":82044259,"identity":"8b522e06-912a-4001-a023-e9ef8faf1dc4","added_by":"auto","created_at":"2025-05-06 09:29:35","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":6021,"visible":true,"origin":"","legend":"\u003cp\u003eAverage cost of NANDA, NOC, NIC by numbers\u003c/p\u003e","description":"","filename":"Onlinedrawingimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-5700089/v1/a016070f1ca03e803aafa7a4.png"},{"id":82044268,"identity":"2bc4e16c-2cea-41ec-8b68-ae66554d8906","added_by":"auto","created_at":"2025-05-06 09:29:35","extension":"jpeg","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":424689,"visible":true,"origin":"","legend":"\u003cp\u003eSequence diagram of the machine learning analysis\u003c/p\u003e","description":"","filename":"floatimage1.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-5700089/v1/fa06bc2620c770f0e88fa13a.jpeg"},{"id":86179136,"identity":"1190b84c-e6d7-420c-90f7-ad28971ced71","added_by":"auto","created_at":"2025-07-07 16:16:13","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1094996,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5700089/v1/750559c1-36df-4879-a0e9-1a78543efe7a.pdf"},{"id":82044261,"identity":"819d479f-e369-4d44-bd36-2a66485a9eb5","added_by":"auto","created_at":"2025-05-06 09:29:35","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":13750,"visible":true,"origin":"","legend":"","description":"","filename":"AppendixA.docx","url":"https://assets-eu.researchsquare.com/files/rs-5700089/v1/dcf94e6bc546867f0b1291d7.docx"}],"financialInterests":"No competing interests reported.","formattedTitle":"The nursing process and total health cost variability: an analysis using machine learning","fulltext":[{"header":"Introduction","content":"\u003cp\u003eDetermining the total costs of healthcare services is critical to ensuring the sustainability of healthcare systems (\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e). Inefficient management has significant policy relevance (\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e). However, it is a complex process and the inclusion of resources in the equation to estimate costs will depend on the importance placed on a given resource, impacting the accuracy of this estimate (\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e). In Spain, health policies do not include the calculation of the cost of nursing care, and international experiences in systematically incorporating the calculation of the cost of nursing care into their health policies are limited, especially in primary care (\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e).\u003c/p\u003e \u003cp\u003eTraditionally, costing systems have been developed as tools for hospital management. Specifically, the Diagnosis Related Groups (DRGs) are the classification system used in the US and Europe, including Spain.\u003c/p\u003e \u003cp\u003eHowever, this task is much more complex in primary care due to its idiosyncrasies. Specifically, the Adjusted Morbidity Groups (AMG) system is a stratification tool tailored to the Spanish healthcare, the population is thus grouped into 31 mutually exclusive categories (\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e).\u003c/p\u003e \u003cp\u003eBoth systems, DRG and AMG, can be used in clinical care management, epidemiology, or healthcare administration, although several studies conclude that there is unexplained intra-group variability in the consumption of resources and costs (\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e, \u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e). A possible cause of this variability is that nursing care is considered an indirect and fixed cost, causing a significant loss of information as it does not factor in variations related to care needs. Both systems in Spain are based on medical classification codes such as the International Classification of Primary Care (ICAP2) and the International Classification of Diseases (ICD-9 or ICD-10), but neither includes information related to the nursing process, such as assessment results, standardized languages, or nursing taxonomies. The lack of visibility of the nurse's work in these classification models may influence human resource policies, patient trust, patient safety and result in inefficient resource allocation. Underestimation of the costs associated with nursing staff may negatively affect health system financing and planning (\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e)\u003c/p\u003e \u003cp\u003eSome studies conclude that classification in the DRG system is an improvement as it factors the weight of care into the Eq.\u0026nbsp;(9) or measures the direct costs of care (\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e). Moreover, a previous study concluded that nursing diagnoses (NDs) enhance the explanatory capacity of the use of healthcare resources (\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e), but the nursing process (NP) also provides, as well as diagnoses, information about the assessment, outcomes and care interventions, and this has not been studied in relation to the total healthcare cost. This nursing process is a systematic, sequential and dynamic method, designed to address the evolving needs of patients (\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e) and comprises five interconnected stages: assessment, diagnosis, planning, implementation, and evaluation. Assessment systems where used, such as the Functional Health Patterns (FHPs) from Marjory Gordon and taxonomies such as the North American Nursing Diagnosis Association (NANDA), the Nursing Interventions Classification (NIC), and the Nursing Outcomes Classification (NOC). These classifications make it possible to quantify, establish and ascertain nursing care interventions (\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e), thus improving the quality of care, saving time, and reducing healthcare costs (\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e). Their inclusion in medical histories is a way of determining the cost effectiveness of nursing care, nurse allocation, and job satisfaction, as well as patient outcomes and satisfaction (\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e) directly. Furthermore, their use reduces variability in clinical practice and makes it easier to measure the effectiveness of work (\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e, \u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e). The use of classifications significantly improves predictions of patient outcomes and the organization\u0026rsquo;s results (\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e). It is approved in many countries around the world, showing clinical impact wherever it is used (\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e) which enables its transfer and replication.\u003c/p\u003e \u003cp\u003eIn Spain, nurses are university graduates, with the option to pursue different specialties. Their work encompasses various levels, such as community or hospital settings, primarily within the public healthcare system. Royal Decree 1093/2010 (\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e), recommends the use of NANDA-NIC-NOC (NNN) in medical histories of public institutions filled out by nurses. All the autonomous communities have health records with a variable development of NNN, with economic incentives for their use in some communities. This makes it possible to avail of a large amount of data for study, contributing to analysis with data mining techniques and artificial intelligence. The priority nursing topics studied with machine learning are patient supervision, monitoring, and classification, prediction of falls, and support for clinical decisions (\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e), but not costs. In the literature, we can identify analyses of the costs of nursing products, whether these are partial costs of techniques, procedures, or services or the study of cost-effectiveness (\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e, \u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e), cost-benefit analysis(\u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e) or cost-utility (\u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e), and related to the variability of costs in the DRG. However, there are still very few studies that conduct economic assessments (a broad concept encompassing methods to compare costs and outcomes)(\u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e) and studies are very seldom performed in terms of total costs. For the above reasons, the main aim of this study was to confirm whether the information provided by the nursing process influences the prediction of the total healthcare cost.\u003c/p\u003e"},{"header":"Methodology","content":" \u003cp\u003eObservational, analytical, retrospective study based on data from healthcare records. The study was conducted in the Autonomous Community of the Canary Islands (Spain) with data from 2017 and 2018. The predictor variables were considered until 2017 and the total cost was calculated in 2018 (Outcome variables used in the machine learning analysis.). Each patient has a unique primary care history and an individual health card with entitlement to public health care.\u003c/p\u003e \u003cp\u003eThe study population consisted of people over 15 years of age enrolled in the Health Card database of the Canary Islands Health Service (N\u0026thinsp;=\u0026thinsp;1,691,075). Mutual society members defined as patients cared for by national mutual societies that provide social benefits and health care only to national civil servants were excluded. Data were requested via protocol from the Information Security Office of the Health Service, and the data were encrypted and dissociated.\u003c/p\u003e \u003cp\u003eThe explanatory variables were sociodemographic (age and sex) and nursing process data (assessment, diagnosis, objectives and interventions) extracted from primary care medical histories. The assessment was carried out on the basis of the Functional Patterns with 44 variables, four per pattern, specifying the last result of that functional pattern in each person (Normal, Risk of alteration, Altered, Not assessable). In addition, 211 NANDA nursing diagnoses (NANDA-I 2009\u0026ndash;2011), 388 NOCs (fourth version), and 558 different NICs (fifth version) used in the electronic medical record were considered as variables, the NNNs from previous versions were not removed from the medical record. Those that appeared in fewer than 1/10,000 patients were filtered to make the analysis more complex.\u003c/p\u003e \u003cp\u003eThe outcome variable was the total cost per patient, adding consultations and emergency visits to public and state-funded centres, hospitalizations, major outpatient surgery, and dispensing in pharmacies during 2018, [information available in Appendix A]. The variables of the different health information systems were integrated with the patient's file number, which was encrypted and transformed into a single unique key per individual.\u003c/p\u003e \u003cp\u003eThe statistical analysis was carried out using the statistics program R Commander 2.6-2, the graphical interface of the statistics package R 4.0.0. For machine learning, the Python programming environment (version 3.10.8) was used with the pandas, Numpy, Scikit-learn, Tensorflow, and XGBOOST libraries. As the study was based on the complete population of users in the healthcare system, inferential statistical methods were not applied.\u003c/p\u003e \u003cp\u003eFirst, the nursing process variables and costs were described. Second, the distribution of total costs was examined in relation to each independent variable using descriptive statistics.\u003c/p\u003e \u003cp\u003eThirdly, total costs were normalized with a logarithm and the influence of age, sex, and FHP was analysed with a multiple linear regression model built using a forward selection approach. Subsequently, two machine learning models were used including the set of variables: a pre-fed neural network (\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e) and a tree-based regression algorithm called XGBoost (\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e). Both models are capable of capturing non-linear and complex relationships among variables and are therefore not affected by multicollinearity, unlike simpler models such as logistic regression. Consequently, it was not necessary to eliminate correlated predictors. Furthermore, they are well-suited to handling large volumes of data and demonstrate high predictive performance. Finally, a mean of the prediction of these two algorithms was performed in an ensemble (\u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e).\u003c/p\u003e \u003cp\u003eTo this end, the cases were segmented into three groups: training (80%), validation (10%) and test (10%). The RMSE (Root Mean Square Error) was used as the training metric (prediction error) of the learning algorithms, and R-squared (R\u003csup\u003e2\u003c/sup\u003e) was used for validation of the models. Several deep neural network architectures were evaluated, starting with a single hidden layer of 32 nodes and progressively increasing complexity. Performance improved with 64 and 128 nodes, prompting the addition of a second, third, and fourth hidden layer. Various node combinations were tested at each level. The optimal configuration was achieved with four hidden layers containing 128, 64, 32, and 16 nodes, respectively, as the inclusion of a fifth layer did not further enhance model performance. For XGBoost, hyperparameters were optimized using Bayesian optimization with the skopt library, automatically exploring the most effective combinations within a predefined range of values. Once the best configuration of each algorithm was chosen, the final result published was that which this configuration achieved when applied to the test dataset, which was only used once by each algorithm.\u003c/p\u003e \u003cp\u003eThe study was conducted in compliance with Organic Law 3/2018 on Personal Data Protection and Digital Rights Guarantee and the provisions of the General Data Protection Regulation (EU) 2016/679 (GDPR). Specifically, it adheres to the second point of the Seventeenth Additional Provision (subsection d), which deems the use of pseudonymized personal data for health research, particularly biomedical research, as lawful and allows for the exemption of informed consent for such purposes.\u003c/p\u003e \u003cp\u003eThe variables extracted from health information systems were linked using an encrypted record number, which was transformed into a unique identifier to ensure data anonymization. The database is exclusively held by the principal investigator, who ensures its security through password protection and commits to neither performing any re-identification of participants nor sharing the data via cloud-based services. The study also complies with the provisions of the Regulation (EU) 2016/679 of the European Parliament and of the Council of April 27, 2016, on Data Protection.\u003c/p\u003e"},{"header":"Results","content":"\u003cdiv id=\"Sec4\" class=\"Section2\"\u003e \u003ch2\u003eDescriptive statistics\u003c/h2\u003e \u003cp\u003eThe study population consisted of 1,691,075 people over 15 years of age who had a health card. A total of 51.04% were female and the mean age was 46.6 years (SD 17.9). Some 17.39% (n\u0026thinsp;=\u0026thinsp;294,077) of the population were over 65. The mean cost per patient was \u0026euro;1,283.08 (SD 3007; \u0026euro;1,377.04 female vs \u0026euro;1,185.14 male). A total of 58% (n\u0026thinsp;=\u0026thinsp;980,437) of the population had some nursing methodology data (FHP, ND, NIC, NOC). The complete NP (with all 11 FHPs assessed, one ND, one NOC and one NIC code) was performed in 2.74% (n\u0026thinsp;=\u0026thinsp;46,380; 63.4% female) of the subjects.\u003c/p\u003e \u003cp\u003eThere were 1,591,840 different FHP assessments in the patient cohort that had at least one FHP recorded and 24.5% (n\u0026thinsp;=\u0026thinsp;415,068; 59.5% female) of the population had at least one assessed pattern. The mean number of assessed FHPs with a recorded result per person was 3.84 (SD 3.58), with a mean age of 56.9 (SD 18.2) years (57.0 male, 56.9 female) and the most frequently assessed FHP was Health Perception. A total of 3.32% (n\u0026thinsp;=\u0026thinsp;46,380) had the 11 patterns assessed at some point, with a mean age of 69.7 (SD 15.6) years and 60.7% (n\u0026thinsp;=\u0026thinsp;595,125) of the individuals with an altered pattern were female.\u003c/p\u003e \u003cp\u003eThe main FHP assessment response was Normal, with Sexuality\u0026ndash; Reproductive being the FHP with the highest value in the total (83%), although for males it was Value\u0026ndash;Belief. Cognitive-Perceptual was the lowest value (44%). In the Risk of Alteration response, the Health Perception\u0026ndash; Management pattern was the most assessed (17%), and Sexuality\u0026ndash; Reproductive plus Value\u0026ndash;Belief were the least assessed (3%). In the Altered response, the Cognitive-Perceptual FHP was the most assessed (45%), and Value\u0026ndash;Belief the least (3%). In Not Assessable, the most assessed was Value\u0026ndash;Belief (15%), with several below 1%. The mean age of the sample with altered FHP was 60.3 (SD 18.3) years (58.9 males, 61.2 females). Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e.\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\u003eFunctional health patterns in the total population\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"6\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePattern\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eAltered\u003c/p\u003e \u003cp\u003e[% (n)]\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eRisk\u003c/p\u003e \u003cp\u003e[% (n)]\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eNornal\u003c/p\u003e \u003cp\u003e[% (n)]\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eNot Assessable\u003c/p\u003e \u003cp\u003e[% (n)]\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c6\"\u003e \u003cp\u003eTotal (n)\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHealth Perception\u0026ndash;Health Management\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e24 (59.688)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e17 (42.555)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e58 (146.899)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e1 (2.253)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e251.395\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNutritional\u0026ndash;Metabolic\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e39 (94.084)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e15 (35.530)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e46 (112.229)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;1 (1.054)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e242.897\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eElimination\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e26 (41.837)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e8 (12.477)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e66 (106.184)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;1 (787)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e161.285\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eActivity\u0026ndash;Exercise\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e26 (51.113)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e12 (23.569)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e61 (118.681)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;1 (712)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e194.075\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSleep\u0026ndash;Rest\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e23 (34.415)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e11 (15.667)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e66 (97.378)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e\u0026lt;\u0026thinsp;1 (688)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e148.148\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCognitive\u0026ndash;Perceptual\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e45 (63.104)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e10 (13.733)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e44 (61.816)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e1 (1.331)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e139.984\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSelf-perception- self-concept\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e28 (26.046)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e13 (11.599)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e54 (49.602)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e5 (4.213)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e91.460\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRole\u0026ndash;Relationship\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e18 (17.362)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e13 (12.899)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e67 (64.168)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e1 (1.161)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e95.590\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSexuality\u0026ndash;Reproductive\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e4 (4.569)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e3 (3.334)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e83 (95.226)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e10 (11.734)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e114.863\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCoping\u0026ndash;Stress Tolerance\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e13 (10.458)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e13 (10.302)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e70 (55.830)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e5 (3.714)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e80.304\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eValue\u0026ndash;Belief\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e3 (1.917)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e3 (2.324)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e79 (56.729)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e15 (10.869)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e71.839\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\u003eA total of 2,816,295 active NDs (still ongoing) were identified in the population. A total of 54.1% (n\u0026thinsp;=\u0026thinsp;916,024; 53.5% female) had at least one active ND, and the mean ND per person was 3.07 (SD 2.90). The mean age of people with an ND was 48.9 (SD 20.7) years (53.41% male, 56.84% female). Of all the people with an ND, 39.2% (n\u0026thinsp;=\u0026thinsp;359,605) had a recorded pattern. The 10 most frequent NDs can be found in Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e. In males, the first 8 diagnoses coincided with the most frequent except for the last two. A total of 14% of the diagnostic codes encompasses 80% of the diagnoses made.\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\u003eMost frequently used terms.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"4\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e\u0026nbsp;\u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eFrequency (%)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eAge\u003c/p\u003e \u003cp\u003e(Mean,SD)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eCost in euros (Mean,SD)\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNANDA\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eReadiness for enhanced health management (00162)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e40.37%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e57.8 (18.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e1.956 (3.677)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAcute pain (00132)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e35.16%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e46 (\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e1.498 (3.133)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eImpaired skin integrity (00046)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e29.17%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e48.7 (18.7)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e4.064 (3.939)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eReadiness for enhanced immunization status (00186)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e24.14%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e50.5 (22.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e2.027 (3.734)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eImbalanced nutrition: more than body requirements (00001)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e10.78%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e57.2 (18.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e2.591 (4.213)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRisk for infection (00004)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e9.55%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e50.8 (20.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e2.101 (4.096)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHealth seeking behavior (specify) (00084)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e9.55%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e52.1 (\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e1.819 (3.455)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eIneffective breathing pattern (00032)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e6.49%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e51.7 (\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e2.484 (4.304)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eImpaired urinary elimination (00016)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e6.34%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e52.9 (21.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e2.471 (4.222)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAnxiety (00146)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e6.0%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e53.5 (18.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e2.500 (4.125)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eNOC\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eImmunization behavior (1900)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e22.48%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e51.7 (22.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e2.078 (3.801)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCompliance behavior (1601)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e18.09%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e55.8 (18.4)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e2.309 (4.098)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePain level (2102)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e15.96%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e48.6 (17.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e1.733 (3.429)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRisk control (1902)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e13.49%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e55.5 (18.4)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e2.209 (3.919)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eWound healing: primary intention (1102)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e13.10%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e48.9 (\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e1.826 (3.865)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eWound healing: second intention (1103)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e12.59%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e51 (19.4)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e2.253 (4.456)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePain control (1605)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e10.89%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e55.4 (19.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e2.310 (4.105)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAdherence behavior (1600)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e10.23%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e53 (18.05)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e2.006 (3.763)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eImmune status (0702)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e6.62%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e54.3 (22.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e2.360 (4.212)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePersonal well-being (2002)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e5.51%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e58.2 (20.1)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e2.504 (4.178)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eNIC\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e\u0026nbsp;\u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e\u0026nbsp;\u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMedication administration: intramuscular (IM) (2313)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e28.90%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e48.5 (17.2)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e1.751 (3.427)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eImmunization/vaccination management (6530)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e23.94%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e52.4 (22.3)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e2.137 (3.869)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHealth education (5510)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e22.63%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e54.7 (19.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e2.182 (3.937)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eVital signs monitoring (6680)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e15.99%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e55 (18.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e2.176 (3.832)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eWound care (3660)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e14.79%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e50.4 (18.9)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e2.108 (4.259)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePhlebotomy: venous blood sample (4238)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e11.18%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e48.4 (\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e1.752 (3.672)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePatient contracting (4420)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e10.66%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e57.9 (18.5)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e2.593 (4.346)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNutritional counseling (5246)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e9.56%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e57.6 (18.8)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e2.543 (4.098)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eExercise promotion (200)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e9.49%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e60.7 (18.4)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e2.799 (4.375)\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRisk identification (6610)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e9.07%\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e58.4 (18.6)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e2.457 (4.173)\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\u003eThere were 2,140,298 NOCs. Some 45.7% (n\u0026thinsp;=\u0026thinsp;772,730; 54.3% female) of the population had at least one active NOC, with an average of 2.77 (SD 2.96) per person. The average age with at least one NOC was 49.5 (SD 19.22) years. The 10 most frequent NOCs are listed in Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e. The first nine coincide in male and female patients, albeit with different frequencies. With 13 codes of the 388 NOCs used, 50% of the sample was reached, and with 115 codes 95% was achieved.\u003c/p\u003e \u003cp\u003eRegarding NIC codes, there were 3,241,607 active interventions. A total of 46.5% (n\u0026thinsp;=\u0026thinsp;787,510; 54.27% female) had at least one active NIC. The average number of NICs per person was 4.12 (SD 7.04). The average age of individuals with at least one NIC was 49.85 (SD 19.18) years. The 10 most frequent NICs are shown in Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e. The NICs coincided in males and females, except for Exercise promotion (0200) and Risk identification (6610), which were replaced by Monitoring infections (6540) and Administering topical medication in females (2316). There were 558 different NICs, and with 18 codes they reached 50% of la sample, with 53 reaching 75% and 262 NICs reaching 99%.\u003c/p\u003e \u003c/div\u003e\n\u003ch3\u003eBivariate analysis\u003c/h3\u003e\n\u003cp\u003eThe average cost of individuals with at least one assessed FHP was \u0026euro;2312.39 vs \u0026euro;954.01 with no assessment. In general, higher costs were observed in association with increased severity in the pattern classification, so an assessment as Normal had a lower cost than an assessment of Risk of Alteration and Altered. However, in the Cognitive-Perceptual and Role-Relationship, the average cost was higher with Risk of Alteration assessments than with Altered (Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e).\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\u003eCosts of the Function Pattern expressed in Euros (\u0026euro;)\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"6\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePattern\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eAltered\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eNot Risk\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eNormal\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eNot Assessable\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c6\"\u003e \u003cp\u003eNot assessed\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHealth Perception\u0026ndash;Health Management\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e3533,754\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e2958,436\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e2041,983\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e3443,164\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e1059,433\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNutritional\u0026ndash;Metabolic\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e3056,578\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e3013,422\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e2298,93\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e2474,588\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e1045,817\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eElimination\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e3988,626\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e3439,151\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e2515,886\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e2358,04\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e1105,381\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eActivity\u0026ndash;Exercise\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e4186,485\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e3298,693\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e2217,979\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e3036,251\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e1077,262\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSleep\u0026ndash;Rest\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e3594,369\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e3279,023\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e2707,341\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e2980,671\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e1120,615\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCognitive\u0026ndash;Perceptual\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e3379,357\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e3482,454\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e2633,384\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e3388,975\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e1122,703\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSelf-perception- self-concept\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e3751,797\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e3575,209\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e2957,991\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e4705,034\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e1165,313\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRole\u0026ndash;Relationship\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e3684,936\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e3746,596\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e3148,426\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e3445,735\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e1160,432\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSexuality\u0026ndash;Reproductive\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e3077,994\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e2526,025\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e2493,639\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e4352,435\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e1179,264\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCoping\u0026ndash;Stress Tolerance\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e4062,511\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e3850,92\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e3114,743\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e4398,015\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e1177,944\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eValue\u0026ndash;Belief\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e4816,553\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e4546,019\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e3183,46\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e4203,634\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e \u003cp\u003e1188,032\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\u003eThe average cost for patients with at least one ND was \u0026euro;1666 vs \u0026euro;840 without an ND. The risk of falls (\u0026euro;4,663), risk of unstable glycemia levels (\u0026euro;4,145), and chronic pain (\u0026euro;4,064) were the most frequent and expensive NDs. The average cost of people with at least one NOC was \u0026euro;2,711 vs \u0026euro;869 with no NOC. Of the most prevalent and costly NOCs the most prominent were Fall prevention behaviour (\u0026euro;4888) and Impaired urinary elimination (\u0026euro;2945). The average cost of people with at least one NIC was \u0026euro;2,717.25 vs \u0026euro;863.77 with no NIC. The highest NIC was Fall prevention (\u0026euro;4521). Costs increased as the number of NANDAs, NOCs and NICs increased, although a larger number of NICs was needed to reach similar costs to those with NANDA and NOC (Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e).\u003c/p\u003e \u003cp\u003e \u003c/p\u003e\n\u003ch3\u003eMultivariate analysis\u003c/h3\u003e\n\u003cp\u003eThe predictive power on total costs increased as age and sex (R\u003csup\u003e2\u003c/sup\u003e\u0026thinsp;=\u0026thinsp;11.47) and FHP (R\u003csup\u003e2\u003c/sup\u003e\u0026thinsp;=\u0026thinsp;14.75) were included. Subsequently, the NANDA, NIC and NOC (791 input variables) variables were included by testing different neural network structures. The best results on the validation data were obtained with a structure of four hidden layers with 128, 64, 32 and 16 nodes, and a single variable in the output layer (the logarithm of cost), resulting in R\u003csup\u003e2\u003c/sup\u003e\u0026thinsp;=\u0026thinsp;21.10 (RMSE: 6.058). (Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e). In the XGBoost algorithm, Bayesian inference techniques were used to select the hyperparameters that optimized the results in the validation dataset. The R\u003csup\u003e2\u003c/sup\u003e obtained was 21.21% (RMSE: 6.014). The arithmetic mean of the predictions of both models (ensemble) returned an R\u003csup\u003e2\u003c/sup\u003e of 21.31%. When this prediction was compared with the actual values (test sample), the R\u003csup\u003e2\u003c/sup\u003e obtained was 21.45% (RMSE: 6.016), which was the best result (Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e).\u003c/p\u003e \u003cp\u003e \u003c/p\u003e"},{"header":"Discussion","content":"\u003cp\u003eReducing unjustified cost variability and ensuring better suitability of resources are objectives of health management. However, healthcare systems are deficient when estimating costs, and insurer payout is based on inaccurate assumptions about the intensity of care (\u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e29\u003c/span\u003e). The results of this study show that the nursing process, together with age and sex, contributes to predicting total healthcare cost, explaining more than 21% of the variability. While no previous studies were found to be able to compare these results, it seems clear that complementing risk adjustment systems, such as DRGs or GMAs, with nursing process information will improve cost estimation.\u003c/p\u003e \u003cp\u003eWhat is not measured cannot be managed or improved. Nursing care continues to be measured poorly and unevenly. Ignoring the consumption and production of goods and services that result from nursing decisions can distort health as a final product (\u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e30\u003c/span\u003e). Besides, the system could become perverse without this information. Establishing empirical links between nursing care, health outcomes, and the cost of care must be a priority both for the community and for health systems, which would enable more precise budgetary planning and personnel allocation, based on the specific care needs of patients. Although 21.45% may seem modest, in the context of cost prediction models using routinely collected health data, this is a substantial contribution, especially when relying solely on nursing and demographic variables.\u003c/p\u003e \u003cp\u003eThe bivariate analysis showed that the increase in costs correlated with a higher number of altered functional patterns and diagnoses, interventions, and outcomes recorded. Furthermore, costs increased with age, consistent with the profile of chronic and fragile patients with greater care needs. However, no other studies with a similar analysis were identified, as previous studies based on the secondary analysis of nursing classifications focus on specific pathologies, pain and end-of-life care, ulcers, bereavement, falls or suicide, among others, but not costs (\u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e31\u003c/span\u003e). Care intensity increases as patient complexity rises, suggesting that nurses may focus more on patients with higher comorbidity and complexity. However, further research is needed to confirm this hypothesis.\u003c/p\u003e \u003cp\u003eOne aspect worth highlighting is that the most frequently recorded action by nurses was diagnosis, followed by interventions, outcomes and, finally, assessments. In fact, fewer than 4% of patients had a complete assessment of the 11 FHPs. The lack of FHP use may be due to the use of tools such as programs and protocols established in centres, whose completion is prioritized in the medical record, and is no longer filled out in nursing records due to overlap. This lack of recording or indiscriminate recording by nurses, who fill out the data in free text not exploitable by the system, is another possible cause. In fact, another study on hospital population found that 52.1% of NDs were not supported by assessments (\u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e32\u003c/span\u003e). We recommend that future studies analyse the coherence of care plans.\u003c/p\u003e \u003cp\u003eIn the same vein, the most commonly made diagnosis is found in terms of health promotion, in line with the area analysed and, probably, because it is the first in the assessment. However, the most common diagnoses were related to biological aspects, which is consistent with other studies (\u003cspan citationid=\"CR33\" class=\"CitationRef\"\u003e33\u003c/span\u003e, \u003cspan citationid=\"CR34\" class=\"CitationRef\"\u003e34\u003c/span\u003e).\u003c/p\u003e \u003cp\u003eFew studies were found that examine electronic health record (EHR) diagnostic labels. Some focus on reviewing the most frequent diagnoses, but in both settings (hospital and primary care), or in specific aspects of them. One study examined NDs over 9 years in adult and child populations, in a health area in Spain, finding that 15 NDs accounted for more than 80% of the NDs used(\u003cspan citationid=\"CR34\" class=\"CitationRef\"\u003e34\u003c/span\u003e). In our study, with 23 NDs we reached 75%, and with 14% of the diagnostic codes we accounted for 80% of the diagnoses. Another study conducted in Italy (\u003cspan citationid=\"CR33\" class=\"CitationRef\"\u003e33\u003c/span\u003e) at the community level, the most similar to our sample, found that Class 4 diagnoses from domains 4 are the most frequent (22.4%), followed by the risk of unstable blood glucose levels-00179 (16.4%) and the risk for overweight-00234 (13%), these diagnoses overlap with the top 45 most frequent diagnoses identified in our study, indicating consistency in diagnostic patterns between both populations. The most commonly used results (NOCs) were vital signs-0802 (22.5%), blood glucose level-2,300 (16%), and weight loss behavior 1,627 (11%). These outcomes overlap with the top 65 most frequent outcomes identified in our study. The most frequent interventions (NICs) were wound care-3660 (27%), intramuscular medication administration-2313 (19%), and health education-5510 (14%), coinciding with the first 10 of our study. The lack of concordance between the two NNN studies could be due to different settings and cultures, to the updating of the taxonomies in successive editions to remove and add diagnoses, adjusting them to changing needs, lack of updating in the medical records, or how long it has been in use in the medical record. In addition, the Italian study only compares one year (\u003cspan citationid=\"CR33\" class=\"CitationRef\"\u003e33\u003c/span\u003e) while our study analyses data from a 15-year period. This makes it difficult to compare results in terms of independent variables.\u003c/p\u003e \u003cp\u003eThe NP set out in the EHR is a rich source of information for health systems. Standardized languages should not only be considered for patient care but can provide essential data to inform on the complexity of care and guide payment criteria (\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e). It is not enough to measure only the cost of an intervention, which would be a purely accounting exercise. To carry out a formal economic analysis, designed to make decisions based on both efficiency and cost, standardised terminologies need to be included (\u003cspan citationid=\"CR35\" class=\"CitationRef\"\u003e35\u003c/span\u003e).\u003c/p\u003e \u003cp\u003eOur study disaggregates the data by sex. The study population is large, an uncommon feature in the referenced studies. Females received more treatment actions from nursing staff, although according to the 2020 Annual Report of the National Health System, it is predominantly males who come to nursing consultations from the age of 59. This may indicate a worse average health status of the women who present. Although there are not many studies specifically addressing nursing diagnoses, medical and public health literature supports that women have higher healthcare utilization and are therefore more likely to receive more diagnoses (\u003cspan citationid=\"CR36\" class=\"CitationRef\"\u003e36\u003c/span\u003e). There are few differences in the care problems attended to by nurses among males and females. Perhaps human responses to health problems or life processes and their intervention do not make as much difference between the sexes as pathologies. This would be a topic worth studying in future research.\u003c/p\u003e \u003cp\u003eOne of the study limitations is that we used registry data from medical records, and the quality of nursing records is a known problem (\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e). In fact, the nursing process was completed in only 2.74% of the sample. Moreover, poor data quality can affect the model's predictions. Analysis was restricted to primary care records, which may have limited the model accuracy. The inclusion of additional variables, such as comorbidities and health determinants, would allow for a more comprehensive understanding. Due to the retrospective observational design, it is not possible to establish causal relationships between costs and the nursing process. However, 791 variables were analysed in 1,691,075 participants, resulting in a total of over 1.3\u0026nbsp;billion parameters. The large volume of data ensured that cases with incomplete information did not compromise the statistical power of the study. The RMSE values obtained highlight the added value of nursing data in explaining resource utilization; however, they should complement rather than replace existing models. Data were normalized to eliminate outliers and improve quality using the entire baseline population. Nevertheless, it is very likely that the predictive capacity of total healthcare cost models will increase with better records. Future studies should take this limitation into account and develop strategies to improve the quality and quantity of nursing records.\u003c/p\u003e"},{"header":"Conclusions","content":"\u003cp\u003eThe information provided by the nursing process (functional patterns and NANDA-NIC-NOC taxonomy), based on medical records, influences the prediction of total health expenditure. Nursing records are not only useful for improving nursing work and patient safety, but also improve total healthcare cost information. These findings underscore the importance of healthcare policy makers considering nursing care documented in clinical records. This entails promoting the use and training of standardized terminologies, which must be integrated into information systems to support clinical and management decisions\u003c/p\u003e \u003cp\u003eThe inclusion of nursing process data within national health information systems will enable improved resource planning, more efficient cost allocation, and enhanced visibility of the impact of nursing care on health outcomes. It is recommended that health administrations integrate structured nursing process data into electronic health records, develop protocols to ensure data quality, and consider this information in risk adjustment models for budgeting and planning.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003eEthics approval\u003c/p\u003e\n\u003cp\u003eIn accordance with the Declaration of Helsinki and Spanish legislation, this study was approved by the clinical research ethics committee of the Dr. Negrín University Hospital of Gran Canaria (Date: January 29, 2021; Code: 2021-037-1).\u003c/p\u003e\n\u003cp\u003eConsent to participate\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eNot Applicable.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eConsent for publication\u003c/p\u003e\n\u003cp\u003eNot applicable\u003c/p\u003e\n\u003cp\u003eAvailability of data and materials:\u003c/p\u003e\n\u003cp\u003eThe datasets generated and/or analysed during the current study are not publicly available due to the inclusion of sensitive and confidential data, but are available from the corresponding author on reasonable request.\u003c/p\u003e\n\u003cp\u003eCompeting interests:\u003c/p\u003e\n\u003cp\u003eThe authors declare no competing interests.\u003c/p\u003e\n\u003cp\u003eFunding:\u003c/p\u003e\n\u003cp\u003eNo funding has been received\u003c/p\u003e\n\u003cp\u003eAuthors' contributions:\u003c/p\u003e\n\u003cp\u003eStudy design: MC, MI, VM\u003c/p\u003e\n\u003cp\u003eData collection: MC, MI\u003c/p\u003e\n\u003cp\u003eData analysis: MC, VM\u003c/p\u003e\n\u003cp\u003eStudy supervision: MC, MI, VM\u003c/p\u003e\n\u003cp\u003eDrafted the primary manuscript: MC, MI, VM\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eRevised and approved the final manuscript.: MC,VM, MI\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eLauz\u0026aacute;n O. Costos en salud: un asunto pol\u0026eacute;mico. Rev Cub Salud Publica. 2020;46(2). \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://scielosp.org/article/rcsp/2020.v46n2/e2054/es/\u003c/span\u003e\u003cspan address=\"https://scielosp.org/article/rcsp/2020.v46n2/e2054/es/\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWalker RM, Boyne GA, Brewer GA. Public management and performance : research directions. Cambridge University Press; 2010.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCabo J. Gesti\u0026oacute;n Sanitaria Integral: P\u0026uacute;blica y Privada. Madrid. CEF, editor;; 2014.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLaport N, Sermeus W, Vanden Boer G, Van Herck P. Adjusting for Nursing Care Case Mix in Hospital Reimbursement. Policy Polit Nurs Pract 2008 6;9(2):94\u0026ndash;102. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1177/1527154408319696\u003c/span\u003e\u003cspan address=\"10.1177/1527154408319696\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMonterde D, Vela E, Cl\u0026egrave;ries M. Los grupos de morbilidad ajustados: nuevo agrupador de morbilidad poblacional de utilidad en el \u0026aacute;mbito de la atenci\u0026oacute;n primaria. Aten Primaria. 2016;48(10):674\u0026ndash;82. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.aprim.2016.06.003\u003c/span\u003e\u003cspan address=\"10.1016/j.aprim.2016.06.003\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCots F, Castells X, Mercad\u0026eacute; L, Torre P, Riu M. Risk adjustment: beyond patient classification systems. Gac Sanit. 2001;15(5):423\u0026ndash;31. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/S0213-9111(01)71596-8\u003c/span\u003e\u003cspan address=\"10.1016/S0213-9111(01)71596-8\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCompany-Sancho MC, Gonz\u0026aacute;lez-Chord\u0026aacute; VM, Orts-Cort\u0026eacute;s MI. Variability in Healthcare Expenditure According to the Stratification of Adjusted Morbidity Groups in the Canary Islands (Spain). Int J Environ Res Public Health. 2022;19(7):4219. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.3390/ijerph19074219\u003c/span\u003e\u003cspan address=\"10.3390/ijerph19074219\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBall JE, Bruyneel L, Aiken LH, Sermeus W, Sloane DM, Rafferty AM, et al. Post-operative mortality, missed care and nurse staffing in nine countries: A cross-sectional study. Int J Nurs Stud. 2018;78:10\u0026ndash;5. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.ijnurstu.2017.08.004\u003c/span\u003e\u003cspan address=\"10.1016/j.ijnurstu.2017.08.004\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRich M, Cubillo B, Barber\u0026aacute; M, Bravo M. Estimaci\u0026oacute;n de los costes de enfermer\u0026iacute;a en el proceso de la enfermedad pulmonar obstrucctiva cr\u0026oacute;nica (EPOC). Enfermer\u0026iacute;a Global. 2003;2(1). \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://revistas.um.es/eglobal/article/view/657\u003c/span\u003e\u003cspan address=\"https://revistas.um.es/eglobal/article/view/657\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCosta A, Castilho V, Togeiro F, Silva B, Siqueira N, De Oliveira T. Costos de las actividades de enfermer\u0026iacute;a realizadas con mayor frecuencia a los pacientes de alta dependencia hospitalizados. Rev Latino-Am Enfermagem. 2012;20(5). \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/S0213-9111(01)71596-8\u003c/span\u003e\u003cspan address=\"10.1016/S0213-9111(01)71596-8\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCompany-Sancho MC, Estupi\u0026ntilde;\u0026aacute;n-Ram\u0026iacute;rez M, S\u0026aacute;nchez-Jan\u0026aacute;riz H, Tristancho-Ajamil R. Relaci\u0026oacute;n entre diagn\u0026oacute;sticos de enfermer\u0026iacute;a y uso de recursos sanitarios. Enferm Clin. 2017;27(4):214\u0026ndash;21. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.enfcli.2017.04.002\u003c/span\u003e\u003cspan address=\"10.1016/j.enfcli.2017.04.002\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eReina G. El proceso de enfermer\u0026iacute;a: instrumento para el cuidado. Vol. (17), Umbral Cient\u0026iacute;fico. (17):18\u0026ndash;23. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://www.redalyc.org/articulo.oa?id=30421294003\u003c/span\u003e\u003cspan address=\"https://www.redalyc.org/articulo.oa?id=30421294003\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eT\u0026ouml;rnvall E, Jansson I. Preliminary Evidence for the Usefulness of Standardized Nursing Terminologies in Different Fields of Application: A Literature Review. Int J Nurs Knowl. 2017;28(2):109\u0026ndash;19. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1111/2047-3095.12123\u003c/span\u003e\u003cspan address=\"10.1111/2047-3095.12123\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChae S, Oh H, Moorhead S. Effectiveness of Nursing Interventions using Standardized Nursing Terminologies: An Integrative Review. West J Nurs Res. 2020;42(11):963\u0026ndash;73. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1177/0193945919900488\u003c/span\u003e\u003cspan address=\"10.1177/0193945919900488\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eP\u0026eacute;rez Rivas FJ, Mart\u0026iacute;n-Iglesias S, Pacheco del Cerro JL, Minguet Arenas C, Garc\u0026iacute;a L\u0026oacute;pez M, Beamud Lagos M. Effectiveness of Nursing Process Use in Primary Care. Int J Nurs Knowl. 2016;27(1):43\u0026ndash;8. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1111/2047-3095.12073\u003c/span\u003e\u003cspan address=\"10.1111/2047-3095.12073\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eC\u0026aacute;rdenas-Valladolid J, Salinero-Fort MA, G\u0026oacute;mez-Campelo P, de Burgos-Lunar C, Ab\u0026aacute;nades-Herranz JC, Arnal-Selfa R et al. Effectiveness of Standardized Nursing Care Plans in Health Outcomes in Patients with Type 2 Diabetes Mellitus: A Two-Year Prospective Follow-Up Study. Dasgupta K, editor. PLoS One. 2012;7(8):e43870. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1371/journal.pone.0043870\u003c/span\u003e\u003cspan address=\"10.1371/journal.pone.0043870\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBertocchi L, Dante A, La Cerra C, Masotta V, Marcotullio A, Jones D, et al. Impact of standardized nursing terminologies on patient and organizational outcomes: A systematic review and meta-analysis. J Nurs Scholarsh. 2023;55(6):1126\u0026ndash;53. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1111/JNU.12894\u003c/span\u003e\u003cspan address=\"10.1111/JNU.12894\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRodr\u0026iacute;guez-Su\u0026aacute;rez CA, Gonz\u0026aacute;lez-de la Torre H, Hern\u0026aacute;ndez-De Luis MN, Fern\u0026aacute;ndez-Guti\u0026eacute;rrez D\u0026Aacute;, Mart\u0026iacute;nez-Alberto CE, Brito-Brito PR. Effectiveness of a Standardized Nursing Process Using NANDA International, Nursing Interventions Classification and Nursing Outcome Classification Terminologies: A Systematic Review. Healthcare. 2023;11(17):2449. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.3390/healthcare11172449\u003c/span\u003e\u003cspan address=\"10.3390/healthcare11172449\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBoe R. Decree 1093/2010, of 3 September, approving the m\u0026iacute;nimum data set of clinicial reports in the National Health System. Bol Oficial del Estado [Spanish Official State Gazette], 78742\u0026ndash;67. 2010 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://www.google.com/search?q=Real+Decreto+1093%2F2010%2C+de+3+de+septiembre%2C+por+el+que+se+aprueba+el+conjunto +m\u0026iacute;nimo+de+datos+de+los+informes+cl\u0026iacute;nicos+en+el+Sistema+Nacional+de+Salud.\u0026amp;\u003c/span\u003e\u003cspan address=\"https://www.google.com/search?q=Real+Decreto+1093%2F2010%2C+de+3+de+septiembre%2C+por+el+que+se+aprueba+el+conjunto +m\u0026iacute;nimo+de+datos+de+los+informes+cl\u0026iacute;nicos+en+el+Sistema+Nacional+de+Salud.\u0026amp;\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003erlz=1C1CHBF_esES843ES843 \u0026amp;oq=Real+Decreto+1093%2F2010%2C+de+3+de+s\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSeibert K, Domhoff D, Bruch D, Schulte-Althoff M, F\u0026uuml;rstenau D, Biessmann F, et al. Application Scenarios for Artificial Intelligence in Nursing Care: Rapid Review. J Med Internet Res. 2021;23(11):e26522. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.2196/26522\u003c/span\u003e\u003cspan address=\"10.2196/26522\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMartin-Misener R, Harbman P, Donald F, Reid K, Kilpatrick K, Carter N, et al. Cost-effectiveness of nurse practitioners in primary and specialised ambulatory care: systematic review. BMJ Open. 2015;5(6):e007167\u0026ndash;007167. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1136/bmjopen-2014-007167\u003c/span\u003e\u003cspan address=\"10.1136/bmjopen-2014-007167\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eV\u0026aacute;squez-Hern\u0026aacute;ndez SM, Rico-Ardila DL, G\u0026oacute;mez-Camargo LN, \u0026Aacute;lvarez-Quintero LM. Costo-efectividad de las intervenciones de enfermer\u0026iacute;a para el manejo de \u0026uacute;lceras por pie diab\u0026eacute;tico: revisi\u0026oacute;n sistem\u0026aacute;tica. MedUNAB. 2021;24(1):13\u0026ndash;40. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.29375/01237047.3832\u003c/span\u003e\u003cspan address=\"10.29375/01237047.3832\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMoran D, Wu AW, Connors C, Chappidi MR, Sreedhara SK, Selter JH, et al. Cost-Benefit Analysis of a Support Program for Nursing Staff. J Patient Saf. 2020;16(4):e250\u0026ndash;4. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1097/PTS.0000000000000376\u003c/span\u003e\u003cspan address=\"10.1097/PTS.0000000000000376\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGrochtdreis T, Zimmermann T, Puschmann E, Porzelt S, Dams J, Scherer M, et al. Cost-utility of collaborative nurse-led self-management support for primary care patients with anxiety, depressive or somatic symptoms: A cluster-randomized controlled trial (the SMADS trial). Int J Nurs Stud. 2018;80:67\u0026ndash;75. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1016/j.ijnurstu.2017.12.010\u003c/span\u003e\u003cspan address=\"10.1016/j.ijnurstu.2017.12.010\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMata VE, Schutz V, de Peregrino AA. Dificultades y oportunidades para la enfermer\u0026iacute;a: Una revisi\u0026oacute;n narrativa sobre evaluaci\u0026oacute;n econ\u0026oacute;mica en salud. Enfermeria Global. 2013;12(1):392\u0026ndash;403. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://scielo.isciii.es/scielo.php?script=sci_abstract\u003c/span\u003e\u003cspan address=\"https://scielo.isciii.es/scielo.php?script=sci_abstract\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e. \u0026amp;pid=S1695-61412013000100021\u0026amp;lng=es\u0026amp;nrm=iso.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGoodfellow I, Bengio Y, Courville A. Deep Learning (Adaptive Computation and Machine Learning series). 1st ed. The MIT Press, editor.; 2016.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChen T, Guestrin C. XGBoost. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2016. pp. 785\u0026ndash;94. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1145/2939672.2939785\u003c/span\u003e\u003cspan address=\"10.1145/2939672.2939785\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMahajan P, Uddin S, Hajati F, Moni MA. Ensemble Learning for Disease Prediction. Rev Healthc. 2023;11(12):1808. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.3390/healthcare11121808\u003c/span\u003e\u003cspan address=\"10.3390/healthcare11121808\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKaplan R, Porter M. How to Solve the Cost Crisis in Health Care. Harvard business review. 2011. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://hbr.org/2011/09/how-to-solve-the-cost-crisis-in-health-care\u003c/span\u003e\u003cspan address=\"https://hbr.org/2011/09/how-to-solve-the-cost-crisis-in-health-care\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGonz\u0026aacute;lez-Chord\u0026aacute; VM, Maci\u0026aacute; Soler L, Mena Tudela D, Cervera Gasch \u0026Aacute;, Salas-Medina P, Rom\u0026aacute;n P. Gesti\u0026oacute;n de cuidados en el \u0026aacute;mbito sociosanitario. Gesti\u0026oacute;n de cuidados en el \u0026aacute;mbito sociosanitario. Universitat Jaume I. 2017. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.6035/Sapientia122\u003c/span\u003e\u003cspan address=\"10.6035/Sapientia122\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMacieira GR, Chianca CM, Smith B, Yao Y, Bian J, Wilkie J, et al. Secondary use of standardized nursing care data for advancing nursing science and practice: a systematic review. J Am Med Inform Assoc. 2019;26(11):1401\u0026ndash;11. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1093/jamia/ocz086\u003c/span\u003e\u003cspan address=\"10.1093/jamia/ocz086\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMateos M. Metodolog\u0026iacute;a enfermera y sistemas estandarizados de lenguaje enfermero en la historia cl\u0026iacute;nica digital. [Tesis doctoral]. Sevilla: Facultad de Enfermer\u0026iacute;a, Fisioterapia y Podolog\u0026iacute;a; 2017 \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://idus.us.es/handle/11441/69103\u003c/span\u003e\u003cspan address=\"https://idus.us.es/handle/11441/69103\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAleandri M, Scalorbi S, Pirazzini MC. Electronic nursing care plans through the use of NANDA, NOC, and NIC taxonomies in community setting: A descriptive study in northern Italy. Int J Nurs Knowl. 2022;33(1):72\u0026ndash;80. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1111/2047-3095.12326\u003c/span\u003e\u003cspan address=\"10.1111/2047-3095.12326\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eP\u0026eacute;rez FJ, Santamar\u0026iacute;a JM, Minguet C, Beamud M, Garc\u0026iacute;a M. Implementation and Evaluation of the Nursing Process in Primary Health Care. Int J Nurs Knowl. 2012;23(1):18\u0026ndash;28. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1111/j.2047-3095.2011.01199.x\u003c/span\u003e\u003cspan address=\"10.1111/j.2047-3095.2011.01199.x\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eStone P. Economic Evaluations and Usefulness of Standardized Nursing Terminologies. Int J Nurs terminologies classifications. 2004;15(4):101\u0026ndash;13. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://doi.org/10.1111/j.1744-618x.2004.tb00007.x\u003c/span\u003e\u003cspan address=\"10.1111/j.1744-618x.2004.tb00007.x\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBertakis KD, Azari R, Helms LJ, Callahan EJ, Robbins JA. Gender differences in the utilization of health care services. J Fam Pract. 2000;49(2):147\u0026ndash;52. PMID: 10718692.\u003c/span\u003e\u003c/li\u003e\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":"bmc-nursing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"nurs","sideBox":"Learn more about [BMC Nursing](http://bmcnurs.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/nurs/default.aspx","title":"BMC Nursing","twitterHandle":"@BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"North American Nursing Diagnosis Association, Nursing Interventions Classification, Nursing Outcomes Classification, standardized nursing terminology, Nursing Process, Nursing Diagnosis, total costs","lastPublishedDoi":"10.21203/rs.3.rs-5700089/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5700089/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAims: To find out whether the information that the nursing process provides (functional patterns and the NANDA-NIC-NOC taxonomy), presented through clinical histories, influences predictions of total healthcare costs.\u003c/p\u003e \u003cp\u003eBackground: The nursing process, is not included in the systems that calculate expenditure in the Spanish healthcare system. Such an omission can result in suboptimal resource allocation.\u003c/p\u003e \u003cp\u003eMethods: Analytical and retrospective observational study of a population of 1,691,075 people over the age of 15. The explanatory variables were age, sex and nursing process data, with total healthcare cost as the outcome variable. A bivariate analysis and a multiple regression were performed for the multivariate analysis. To improve prediction accuracy and account for non-linear relationships, the analysis was completed using two machine learning models.\u003c/p\u003e \u003cp\u003eResults: 58% (n\u0026thinsp;=\u0026thinsp;980,437) of the population presented some data from the nursing process, for individuals with an assessed pattern, the average cost was \u0026euro;2304.17 compared with \u0026euro;950.93 for those who had none; with a nursing diagnosis, the average cost was \u0026euro;1,666 versus \u0026euro;840 without it. Having created the best model for the analysis using neural networks and XGBOOST, an average coefficient of determination of R\u003csup\u003e2\u003c/sup\u003e\u0026thinsp;=\u0026thinsp;21.45% was obtained.\u003c/p\u003e \u003cp\u003eConclusions: The variability in total healthcare costs can be explained in more than 21% of cases by the model created, including sex, age, and the information related to the nursing process.\u003c/p\u003e \u003cp\u003eImplications for health policy: Demonstrating the influence of nursing care on total patient costs will facilitate its inclusion in management programs, promoting the use of nursing data in risk adjustment models and healthcare planning.\u003c/p\u003e","manuscriptTitle":"The nursing process and total health cost variability: an analysis using machine learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-05-06 09:29:31","doi":"10.21203/rs.3.rs-5700089/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-05-14T05:22:10+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-05-12T16:07:08+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-05-12T06:14:18+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"53769916568610757495005832913494544811","date":"2025-05-06T09:08:02+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"123338788630959411783209473392614688548","date":"2025-05-05T10:08:59+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-04-29T07:52:47+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-04-29T05:52:12+00:00","index":"","fulltext":""},{"type":"submitted","content":"BMC Nursing","date":"2025-04-07T18:55:41+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"bmc-nursing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"nurs","sideBox":"Learn more about [BMC Nursing](http://bmcnurs.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/nurs/default.aspx","title":"BMC Nursing","twitterHandle":"@BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"3719ddba-a790-4473-b8dc-a2655cd6f0ac","owner":[],"postedDate":"May 6th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-07-07T16:05:01+00:00","versionOfRecord":{"articleIdentity":"rs-5700089","link":"https://doi.org/10.1186/s12912-025-03304-5","journal":{"identity":"bmc-nursing","isVorOnly":false,"title":"BMC Nursing"},"publishedOn":"2025-07-01 15:58:01","publishedOnDateReadable":"July 1st, 2025"},"versionCreatedAt":"2025-05-06 09:29:31","video":"","vorDoi":"10.1186/s12912-025-03304-5","vorDoiUrl":"https://doi.org/10.1186/s12912-025-03304-5","workflowStages":[]},"version":"v1","identity":"rs-5700089","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5700089","identity":"rs-5700089","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}