Development and validation of a prediction model for the risk of relapse in psoriasis

Development and validation of a prediction model for the risk of relapse in psoriasis | 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 Article Development and validation of a prediction model for the risk of relapse in psoriasis Xiaoxue Zhang, Chen Zhao, Yu Luo, Hua He, Juan Gao, Xiaohua Tian, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8777210/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 11 Apr, 2026 Read the published version in Scientific Reports → Version 1 posted 13 You are reading this latest preprint version Abstract Background This study collected and analyzed clinical data from patients with psoriasis, developing and validating a risk prediction model for psoriasis relapse. The aim is to improve the efficiency and accuracy of early screening for psoriasis relapse in clinical practice and to provide a reference for implementing preventive measures. Objective To develop and validate a risk prediction model for psoriasis relapse. Methods A convenience sampling method was used to select 504 psoriasis patients admitted to a tertiary hospital in China between January 2022 and December 2024, including 353 cases in the training set and 151 cases in the test set. Independent risk factors for psoriasis relapse were identified through univariate analysis and logistic regression analysis to develop a prediction model. A nomogram and SHAP summary plot were generated for model visualization, and the model’s goodness of fit and discriminative ability were evaluated. Results The one-year relapse rate of psoriasis patients after treatment was 66.67%. Logistic regression analysis identified body mass index (BMI), diabetes, biologic agent use, smoking, upper respiratory tract infection (URTI), and non-standard medication as independent risk factors for psoriasis relapse, which were included in the model. The area under the ROC curve (AUC) values for the training and testing sets were 0.767 [95% CI: 0.715–0.818] and 0.704 [95% CI: 0.620–0.789], respectively. The model demonstrated good discrimination and calibration, and decision curve analysis (DCA) showed significant net benefit in both the training and testing sets. Conclusion The psoriasis relapse risk prediction model developed in this study demonstrated good predictive performance. This model can serve as an effective reference for assessing the risk of psoriasis relapse and provides valuable insights for developing personalized prevention strategies for patients. Biological sciences/Computational biology and bioinformatics Health sciences/Diseases Health sciences/Health care Health sciences/Medical research Health sciences/Risk factors Psoriasis relapse prediction model Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Highlights Currently, research on predictive models for psoriasis relapse primarily focuses on patients after discontinuation of biologic agents, with limited studies involving patient populations not using biologics or those transitioning from biologic therapy to other treatment regimens. This limitation restricts the applicability of such prediction models to a certain extent. This study developed and validated a one-year relapse risk prediction model for all psoriasis patients. The model serves as an effective reference for assessing relapse risk in psoriasis patients and provides valuable guidance for developing personalized prevention strategies. 1 Introduction Psoriasis is a chronic, relapsing, inflammatory, systemic skin disease mediated by the immune system, triggered by a combination of genetic and environmental factors. Its typical clinical manifestation is well-demarcated red plaques covered with silvery-white scales, which can be localized or widely distributed [1]. Patients with psoriasis often experience varying degrees of itching and pain, and some also have comorbidities such as cardiovascular and metabolic diseases [2,3,4]. Psoriasis is widely distributed worldwide. Epidemiological surveys show that there are approximately 125 million psoriasis patients globally, with a worldwide prevalence ranging from 0.51% to 11.43% [5]. The latest large-scale international study indicates that the global average prevalence of adult psoriasis is approximately 4.4%, with the prevalence in the East Asian region reaching as high as 5.7% [6]. Since psoriasis currently has no curative treatment, it exhibits a high relapse rate throughout its clinical course. Most patients experience multiple relapses during the disease progression, which significantly impacts their physical and mental health as well as quality of life [7]. However, there is currently a lack of highly specific and sensitive indicators for the diagnosis of psoriasis, and efficient screening tools for psoriasis relapse are also insufficient. Although many assessment scales related to psoriasis exist, these scales are typically used when patients already exhibit the characteristic features of psoriasis, meaning they have entered the recurrence stage. At this point, the patients have often already experienced negative physical and psychological effects, and interventions essentially become part of ongoing treatment rather than early prevention. Therefore, it is crucial for healthcare providers to shift psoriasis relapse management from a passive to an active approach by developing a multifactorial, rapid screening risk warning system. Early identification and warning of relevant risk factors before disease onset, along with predicting relapse trends, are of great importance for controlling psoriasis relapse and promoting patient recovery. In recent years, with the growing emphasis on precision medicine, the use of predictive models for early identification of disease risk and individualized intervention has become a research focus. Clinical prediction models are developed by utilizing existing clinical data to construct appropriate statistical models that summarize the regularity of the probability of a specific outcome occurring in particular clinical scenarios [8]. These models can provide patients and physicians with more accurate and scientific evidence to support earlier and better-informed decision-making. Current research on predictive models for psoriasis relapse risk primarily focuses on the specific clinical decision point of "post-discontinuation of biologic agents" [9,10]. Although biologic agents have demonstrated remarkable efficacy in the treatment of psoriasis, their actual global utilization remains restricted by multiple factors, including economic constraints, policies, and medical accessibility, resulting in limited access to biologic therapy for a significant proportion of patients [11,12]. However, there is a lack of effective quantitative prediction tools for the relapse risk in a large number of patients who do not use biologic agents, such as those receiving only conventional systemic drugs, phototherapy, or topical treatments. Therefore, it is necessary to develop a relapse risk prediction model applicable to all psoriasis patients, covering the entire population including both biologic users and those receiving conventional treatments, with the aim of enhancing the model's clinical applicability and generalizability. To address this limitation, the present study designed, developed, and validated a relapse risk prediction model based on psoriasis risk factors, applicable to all psoriasis patients. This model aims to improve the efficiency and accuracy of early screening for psoriasis relapse in clinical practice, provide a reference for preventive measures, and offer valuable guidance for the formulation of patient treatment plans. 2 Materials and methods 2.1 Study design This was a single-center, retrospective study conducted in the Department of Dermatology at a tertiary general hospital in China from January 2022 to December 2024. Patient data were collected via the Electronic Medical Record system and follow-up procedures. Informed consent was obtained from all patients upon admission, confirming their agreement to participate in the study. The study adhered to the Transparent Reporting of a Multivariate Prediction Model for Individual Prognosis or Diagnosis (TRIPOD) statement as a reporting guideline[13]. It was approved by the Ethics Committee of the Second Affiliated Hospital of Hunan University of Traditional Chinese Medicine (Approval Number: 2025-KY-024-01). All methods were performed in accordance with the relevant guidelines and regulations. 2.2 Study Population This study employed a convenience sampling method to select psoriasis patients admitted to a tertiary hospital in China between January 2022 and December 2024. Their relapse status within one year was obtained through follow-up. Patients meeting the inclusion criteria are required to fulfill the following conditions: (1) Diagnosis in accordance with the Guideline for the diagnosis and treatment of psoriasis in China (2023 edition) [14]; (2) Aged between 18 and 80 years at admission; (3) Clear consciousness, absence of cognitive impairment, and possession of basic communication and comprehension abilities; (4) Voluntary participation in this study and provide written informed consent; (5) Availability of complete clinical data and accessibility for follow-up. The exclusion criteria included the following: (1) History of severe psychiatric disorders or current use of psychotropic medications; (2) Presence of severe primary diseases affecting the cardiovascular, cerebrovascular, hepatic, renal, or hematopoietic systems with unstable conditions; (3) Presence of other autoimmune diseases, malignant tumors, or active infections; (4) Severe missing clinical data that affect the extraction of study variables and outcome assessment; (5) Lack of improvement or progressive deterioration of psoriasis after standardized treatment. The criteria for withdrawal and dropout included: (1) Patients voluntarily requesting to withdraw or being lost to follow-up during the study period; (2) Major discrepancies between provided clinical data and actual conditions that could not be corrected after verification; (3) Occurrence of serious adverse events, complications, or death during the follow-up period, rendering the patient unable to continue participation; (4) Use of non-protocol medications or therapeutic interventions during the study period that may affect disease relapse; (5) Missing data affecting the assessment of the primary outcome (relapse). 2.3 Sample Size calculation The sample size was estimated based on the principle of Events Per Variable (EPV). This method is commonly employed in the construction of clinical prediction models. It requires that the number of patients experiencing the target outcome must be at least ten times the number of predictor variables included in the final model. In other words, a minimum of ten outcome events per predictor variable is necessary to ensure the stability and reliability of the model parameters [15]. This study plans to include 35 independent variables. Research indicates that the one-year recurrence rate of psoriasis is as high as 86.1% [16]. Therefore, the minimum sample size is calculated as 35 × 10 ÷ 0.861 ≈ 407. A total of 504 patients with psoriasis were finally enrolled in this study and randomly divided into a training set (n = 353) and a testing set (n = 151) at a ratio of 7:3. 2.4 Outcome variables The outcome variable in this study was relapse. Relapse was defined as the reappearance of cutaneous lesions and histopathological features involving an area greater than 30% in patients with a history of psoriasis who had achieved clinical cure following treatment. After discharge, patients were followed up monthly by nursing staff, and the follow-up period lasted for one year. 2.5 Candidate variables Based on an analysis of previous relevant literature [17–23], integration with clinical experience, and group discussions, we identified potential risk factors for psoriasis recurrence. Accordingly, the following data were collected in this study: (1) Demographic and baseline characteristics: gender, age, body mass index (BMI), sleep disorders, smoking history, history of alcohol consumption, and anxiety; (2) Disease-related factors: duration of illness, severity of the condition, type of psoriasis, season of onset, family history, allergy history, history of diabetes, coronary heart disease, hypertension, hyperlipidemia, upper respiratory tract infection, irregular medication use, trauma/surgery, exposure to chemical agents (hair dyes, pesticides, etc.), and exposure to biological agents; (3) Laboratory parameters: presence of hypoproteinemia and whether biochemical indicators were normal (erythrocyte sedimentation rate, C-reactive protein, immunological indicators). 2.6 Data Collection This study retrospectively collected data from the hospital Electronic Medical Record (EMR) using a structured questionnaire. The questionnaire covered three specific domains, and patient recurrence within one year was obtained through follow-up. The data collection process strictly adhered to the predefined inclusion and exclusion criteria. Two trained researchers used a standardized questionnaire to ensure consistency in data collection and cross-verified the completeness, authenticity, and accuracy of the data. Concurrently, a specialized dermatology nurse conducted monthly follow-ups for a duration of one year. Strict quality control measures were implemented throughout the follow-up process to ensure the accuracy and completeness of the information. The data entry process strictly followed a double-entry system. After entry, data were promptly cross-checked against the original medical records to identify and resolve any discrepancies or missing information, ensuring high data quality and completeness. 2.7 Statistical analysis Statistical analyses were performed using R Studio (version 4.2.2). All hypothesis tests were two-sided with a significance level set at 0.05. Measurement data that follow a normal distribution are presented as mean ± standard deviation, and comparisons between groups are analyzed using the independent samples t-test. Measurement data that do not follow a normal distribution are presented as median (M) with interquartile range (P25, P75), and comparisons between groups are analyzed using the Mann-Whitney U test. Categorical data were analyzed using the chi-square test. Univariate analysis was performed to screen potential prognostic factors ( P < 0.05), which were then included in a multivariate logistic regression analysis to identify independent risk factors ( P < 0.05). A prediction model was subsequently constructed, and model visualization was conducted using a nomogram and SHAP summary plot. The Receiver Operating Characteristic (ROC) curve was plotted to evaluate the diagnostic performance of the model. The Hosmer-Lemeshow test was used to assess the goodness of fit. Calibration curves were plotted to evaluate the calibration of the model, and Decision Curve Analysis (DCA) was performed to assess the clinical utility of the model. 3 Results 3.1 Characteristics of the participants This study collected clinical data from a total of 504 patients, among whom 336 cases (66.67%) experienced relapse within one year after treatment. Based on the stratification of the dependent variable, all samples were randomly divided into a training set (n = 353) and a testing set (n = 151) at a 7:3 ratio. The training set included 233 relapsed and 120 non-relapsed cases, with a relapse rate of 66.0%, while the testing set had 103 relapsed and 48 non-relapsed cases, with a relapse rate of 68.2%. The analysis of baseline characteristic differences showed that, in the comparison of clinical data between the training and test sets, baseline features of C-reactive protein (CRP) and erythrocyte sedimentation rate (ESR) exhibited statistically significant differences. However, this was a result of random allocation and does not affect the model construction. No statistically significant differences were observed between the two groups in terms of demographics and disease-related factors. Detailed data are provided in Table 1. 3.2 Univariate analysis for relapse in psoriasis Table 2 summarizes the results of the univariate analysis. The training set was further divided into non-relapse and relapse groups according to the presence or absence of relapse. The results of this study showed that BMI, disease duration, diabetes, use of biologic agents, smoking, URTI, and non-standard medication use exhibited significant differences (all P < 0.05). 3.3 Logistic regression analysis for relapse in psoriasis Table 3 summarizes the results of the logistic regression analysis. A logistic regression model was constructed using the training set data. Backward stepwise logistic regression was performed for feature selection, with relapse within one year as the dependent variable and variables showing statistical significance in the univariate analysis as independent variables. The logistic regression results indicated that BMI, diabetes, use of biologic agents, smoking, URTI, and non-standard medication were independent risk factors for relapse (all P < 0.05). 3.4 Development of model 3.4.1 Nomogram for Clinical Risk Stratification The partial regression coefficients of the independent predictors identified by the logistic regression analysis were used to establish the model. The fitted regression equation of the prediction model for the risk of relapse within one year in patients with psoriasis is as follows: Logit p = -5.127 + 0.201 × BMI + 0.987 × Diabetes + 0.992 × Biologic agent + 0.843 × Smoking + 1.160 × URTI + 0.835 × Non-standard medication. The results are shown in Fig.1. 3.4.2 SHAP-based interpretability analysis This study evaluated the relative importance of various risk factors influencing relapse in patients with psoriasis, as shown in Fig.2. In the figure, each dot represents an individual sample. The color gradient from red to blue indicates the magnitude of the values ranging from low to high. The vertical axis arranges the risk factors in descending order of importance, while the horizontal axis shows the average SHAP value for each feature, along with the correlation and distribution between each feature and its SHAP values. The SHAP model not only elucidates the positive or negative contribution of each factor to individual predictions but also quantifies the magnitude of these effects. In the visualization, blue represents an increased risk of psoriasis relapse, while red denotes a decreased risk, thereby offering a personalized and transparent explanation for the model's decision-making process. The SHAP model results ranked the factors as follows: URTI > Smoking > Non-standard medication > Diabetes > BMI > Biologic agent, with URTI, Smoking, and Non-standard medication having key impacts on psoriasis relapse. 3.5 Prediction Model Performance 3.5.1 Model calibration The model demonstrated excellent calibration performance in both the training and testing sets. The Hosmer-Lemeshow goodness-of-fit test yielded a chi-square value of 7.577 with a P-value of 0.476 for the training set, and a chi-square value of 10.391 with a P-value of 0.239 for the testing set. The results demonstrated that the model exhibited good fitting performance, and the calibration curve showed a high degree of agreement between the predicted and observed outcomes. The bootstrap-corrected calibration results further confirmed good agreement, with the calibration curves (green and blue solid lines) closely aligning with the ideal reference line (black dashed line), as shown in Fig.3. 3.5.2 Model discrimination The ROC curves for the predictive model indicate that it has good discriminative ability in predicting relapse risk in psoriasis patients. The area under the curve (AUC) was 0.767 [95% CI: 0.715–0.818] for the training set (red solid line) and 0.704 [95% CI: 0.620–0.789] for the testing set (blue dashed line). The results are presented in Fig.4 and Table 4. 3.5.3 Clinical Utility Figure 5 presents the clinical Decision Curve Analysis (DCA). This curve circumvents the need to explicitly consider false positives and false negatives by directly calculating the Net Benefit (NB) and maximizing its value. The DCA plot displays the threshold probability on the x-axis and the Net Benefit (NB) on the y-axis. The horizontal reference line represents the "no treatment" strategy (treating all samples as negative while maintaining intervention for all patients), where the net benefit is zero. The vertical reference line represents the "treat all" strategy (treating all samples as positive and providing intervention to all patients), characterized by a negative slope. The DCA curves for the training set (red line) and the testing set (green line) both exhibited net benefits exceeding those of the "treat-none" (black horizontal line) and "treat-all" (light gray diagonal line) reference strategies within a threshold probability range of approximately 0 to 0.92. This indicates that the model has higher clinical utility within this threshold range. 4 Discussion Psoriasis is a chronic, recurrent, inflammatory skin disease, and its high relapse rate remains a major challenge and key focus in clinical management. Therefore, developing a prediction model capable of early identification of patients at high risk of relapse holds significant clinical value for facilitating personalized interventions and optimizing treatment strategies. Current research on prediction models for psoriasis relapse has predominantly focused on patients following the discontinuation of biological agents, with limited attention given to populations naive to biologics or those transitioning to alternative therapeutic regimens. This limitation restricts the applicability of existing models to a certain extent. This study developed and validated a prediction model for the risk of relapse within one year targeting the general population of psoriasis patients, identifying URTI, smoking, non-standard medication, diabetes, BMI, and biologic agents as independent predictors. The findings of this study indicate that URTI is an independent risk factor for psoriasis relapse. Upper respiratory streptococcal infection is recognized as one of the important triggers for psoriasis relapse [24]. Certain components of streptococcus, such as the M protein, exhibit molecular mimicry with human keratin, potentially initiating cross-immune reactions, activating T cells, and leading to the exacerbation of psoriatic skin lesions [25]. Additionally, upper respiratory tract infections caused by Staphylococcus aureus may also be associated with psoriasis relapse, as its superantigens can non-specifically activate a large number of T cells, triggering a strong inflammatory response and exacerbating psoriatic skin lesions [26]. Overall, infections can trigger abnormal immune responses that induce psoriasis recurrence. Therefore, preventing and promptly treating infections is of great significance in reducing the risk of recurrence. Relevant studies have also found that targeted vaccination can effectively reduce the risk of infection-induced relapse in patients with psoriasis [27]. This study found that smoking is an independent risk factor for psoriasis relapse, consistent with previous research [28,29]. The mechanism by which smoking induces relapse is relatively complex [20,30]. Components in tobacco, such as nicotine, can directly stimulate immune cells to release inflammatory factors (e.g., IL-6, TNF-α), thereby promoting the chemotaxis and activation of neutrophils. Meanwhile, oxidants and free radicals in smoke can damage the skin barrier, trigger oxidative stress responses, and activate inflammatory pathways such as NF-κB. Furthermore, smoking may also predispose the body to inflammatory responses by influencing gene expression (such as upregulating susceptibility genes like HLA-C*06:02) and epigenetic modifications. In clinical management, smoking cessation should be incorporated as an integral component of the comprehensive therapeutic strategy for psoriasis. Patients should be explicitly educated on the role of smoking in precipitating disease recurrence and the underlying inflammatory mechanisms, thereby fostering awareness of the necessity to quit. Furthermore, diversified cessation support should be provided to alleviate the challenges associated with smoking cessation, including encompassing behavioral interventions, psychological counseling, and pharmacological aids where indicated. Non-standard medication practices, including unauthorized discontinuation, dose reduction, or misuse of drugs, constitutes a critical factor leading to the recurrence of psoriasis relapse. Topical treatment requires patients to maintain long-term adherence. Sudden discontinuation or improper withdrawal may trigger disease rebound. For example, abrupt cessation after prolonged high-dose use of glucocorticoids can lead to rapid lesion spread within a short period and even induce severe forms such as erythrodermic or pustular psoriasis [31]. Additionally, drug resistance or reduced efficacy during treatment may also contribute to disease relapse. For example, long-term administration of the same biological agent in certain patients may induce the formation of anti-drug antibodies, resulting in diminished efficacy and the recurrence of skin lesions. Non-standard medication is also a modifiable factor contributing to psoriasis relapse. Adhering to standardized and continuous treatment is essential for preventing relapse. Studies have shown that implementing mobile health reminder systems, combined with smart pillboxes and SMS notifications, significantly improves patient medication adherence, which in turn helps reduce the risk of relapse [32]. The results of this study indicate that diabetes is an independent risk factor for psoriasis relapse. A population-based cohort study has shown that psoriasis patients with diabetes exhibit higher disease activity and an increased risk of relapse [33]. Diabetes, as a common comorbidity of psoriasis, promotes relapse through the IL-23/IL-17 axis: a hyperglycemic environment activates macrophages through advanced glycation end products (AGEs), leading to the upregulation of IL-23 secretion and subsequently exacerbating cutaneous inflammation [34]. In clinical practice, diabetes screening for psoriasis patients can be strengthened, especially by conducting regular blood glucose monitoring for high-risk groups such as individuals with obesity, to enable early identification and intervention. Furthermore, for psoriasis patients with established diabetes, glycemic control should be intensified through dietary regulation, regular exercise, and rational pharmacotherapy to maintain blood glucose levels within the target range, thereby reducing the hyperglycemia-induced release of inflammatory factors. This study found that increased BMI is an independent risk factor for psoriasis relapse. BMI, as a core indicator for assessing obesity, is defined by the World Health Organization as a BMI of 30 or higher in adults [35]. Research has shown that obesity can promote psoriasis relapse: adipose tissue secretes various pro-inflammatory cytokines (such as IL-6, TNF-α, leptin), which overlap with the inflammatory pathways involved in psoriasis and can lead to disease worsening and an increased risk of relapse [36,37]. For patients with elevated BMI, the prevention of psoriasis relapse can be achieved by prioritizing weight management and lifestyle interventions. This study found that a history of prior biologic agent exposure is an important treatment-related factor affecting psoriasis relapse. A study from Taiwan found that each additional prior exposure to biologics increases the risk of psoriasis relapse by 23% [38]. This phenomenon of "exposure-dependent relapse acceleration" may be related to the production of anti-drug antibodies (ADAs), which can accelerate drug clearance and reduce treatment efficacy [39]. For patients with a history of multiple exposures to biologic agents, greater caution should be exercised when selecting future treatment regimens. If necessary, rotating drugs with different mechanisms of action may be considered to reduce the risk of relapse. The model demonstrated good discriminative ability with AUC values of 0.767 in the training set and 0.704 in the testing set. The goodness-of-fit tests showed χ² = 7.577 ( P = 0.476) for the training set and χ² = 10.391 ( P = 0.239) for the testing set, indicating that the model has good overall consistency. Decision curve analysis (DCA) revealed significant net benefits in both the training and testing sets, supporting the clinical applicability of this model.Therefore, clinicians should utilize this model to promptly identify psoriasis patients at high risk of relapse and implement early preventive and effective interventions. These measures include but are not limited to: pthe prevention and timely treatment of upper respiratory tract infections; smoking cessation through measures such as nicotine replacement therapy; strict adherence to prescribed medication regimens; rigorous blood glucose monitoring and regulation for patients with comorbid diabetes; and scientific weight management via nutritional counseling and exercise prescriptions. In summary, early identification of high-risk patients and the implementation of timely and effective interventions are key steps in reducing the risk of psoriasis relapse. 5 Conclusion This study found that upper respiratory tract infection (URTI), smoking, non-standard medication use, diabetes, BMI, and biologic agent exposure are independent risk factors influencing psoriasis relapse. Therefore, early screening for relapse risk in psoriasis patients may be particularly important for reducing the rate of relapse. The psoriasis relapse risk prediction model established in this study demonstrates good predictive capability. This model serves as an effective reference for assessing the risk of psoriasis relapse and provides valuable guidance for the formulation of personalized preventive strategies for patients. 6 Limitations This study has several limitations that need to be addressed in future research. Firstly, this study is a single-center retrospective investigation, with all data derived from one medical center. Therefore, the representativeness of the sample may be limited, indicating that the study findings require further validation. Secondly, the predictive variables included in this study were all routine clinical indicators, without incorporating deeper biomarkers such as genetic factors, specific cytokines, or microbiomics. Future research could integrate multi-omics data to enhance the model’s predictive accuracy and scientific significance. Thirdly, this study only focused on relapse within one year and did not evaluate the longer-term risk of psoriasis relapse or the patterns of disease progression. Future research could extend the follow-up period to develop a more comprehensive disease trajectory prediction model. Finally, although internal validation of the model was performed, external validation was not conducted. Therefore, the predictive performance of this model should be continuously validated in future studies to achieve broader generalizability. Declarations Competing interests The authors declare no competing interests. Funding This study was supported by the 2025 Hunan Provincial Natural Science Foundation Project (2025JJ80911). Author Contribution XZ: Conceptualization, Methodology, Investigation, Data curation, Writing – original draft. CZ: Investigation, Data curation, Writing Original Draft. YL: Coordination, Formal analysis, Project administration, Writing – review & editing. HH: Coordination, Project administration, Writing – review & editing. JG: Project administration, Writing – review & editing. XT: Project administration, Writing – review & editing. GJ: Funding acquisition, Project administration, Writing – review & editing. All the authors have read and approved the final version of the manuscript. Data Availability The datasets generated during and/or analysed during the current study are available from the corresponding author on reasonable request. References Boehncke, W.-H. & Schön, M. P. Psoriasis. Lancet 386 , 983–994 (2015). Dubertret, L. et al. European patient perspectives on the impact of psoriasis: the EUROPSO patient membership survey. Br J Dermatol 155 , 729–736 (2006). Peng, C. et al. Epidemiological Variations in the Global Burden of Psoriasis, an Analysis With Trends From 1990 to 2017. Front Med (Lausanne) 8 , 585634 (2021). Takeshita, J. et al. Psoriasis and comorbid diseases: Epidemiology. J Am Acad Dermatol 76 , 377–390 (2017). World Health Organization. Global Report on Psoriasis . (2016). Skayem, C., Taieb, C., Halioua, B., Baissac, C. & Saint Aroman, M. Epidemiology of Psoriasis: A Worldwide Global Study. Acta Derm Venereol 105 , adv42945 (2025). Bu, J., Ding, R., Zhou, L., Chen, X. & Shen, E. Epidemiology of Psoriasis and Comorbid Diseases: A Narrative Review. Front Immunol 13 , 880201 (2022). Cadrin-Tourigny, J. et al. A new prediction model for ventricular arrhythmias in arrhythmogenic right ventricular cardiomyopathy. European Heart Journal 43 , e1–e9 (2022). Huang, S., Bai, Y., Qi, R., Yu, H. & Duan, X. Personalized prediction of psoriasis relapse post-biologic discontinuation: a machine learning-driven population cohort study. J Dermatolog Treat 36 , 2480743 (2025). Huang, S., Chen, B., Qi, Y., Duan, X. & Bai, Y. Development and external validation of a prediction model for the risk of relapse in psoriasis after discontinuation of biologics. Front Med (Lausanne) 11 , 1488096 (2024). Girolomoni, G. et al. Increasing Access to Effective Systemic Treatments in Patients with Moderate-to-Severe Psoriasis :: Narrative Review. Dermatology and Therapy 13 , 2171–2185 (2023). Wan, V. et al. Disparities and barriers to the access of biologics in moderate-to-severe adult psoriasis. Int J Dermatol 63 , 1293–1301 (2024). Collins, G. S., Reitsma, J. B., Altman, D. G. & Moons, K. G. M. Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement. BMJ 350 , g7594 (2015). Committee on Psoriasis, Chinese Society of Dermatology. Guideline for the diagnosis and treatment of psoriasis in China （2023 edition）. Chinese Journal of Dermatology 56 , 573–625 (2023). Riley, R. D. et al. Calculating the sample size required for developing a clinical prediction model. BMJ 368 , m441 (2020). Huang, Y.-W. & Tsai, T.-F. Remission Duration and Long-Term Outcomes in Patients with Moderate-to-Severe Psoriasis Treated by Biologics or Tofacitinib in Controlled Clinical Trials: A 15-Year Single-Center Experience. Dermatol Ther (Heidelb) 9 , 553–569 (2019). Francis, L., Capon, F., Smith, C. H., Haniffa, M. & Mahil, S. K. Inflammatory memory in psoriasis: From remission to recurrence. J Allergy Clin Immunol 154 , 42–50 (2024). Lee, E. B., Wu, K. K., Lee, M. P., Bhutani, T. & Wu, J. J. Psoriasis risk factors and triggers. Cutis 102 , 18–20 (2018). Zhang, L.-J. et al. Antimicrobial Peptide LL37 and MAVS Signaling Drive Interferon-β Production by Epidermal Keratinocytes during Skin Injury. Immunity 45 , 119–130 (2016). Liu, S. et al. Triggers for the onset and recurrence of psoriasis: a review and update. Cell Commun Signal 22 , 108 (2024). Stewart, T. J., Tong, W. & Whitfeld, M. J. The associations between psychological stress and psoriasis: a systematic review. Int J Dermatol 57 , 1275–1282 (2018). Potestio, L. et al. Risk Factors for Psoriasis Flares: A Narrative Review. Psoriasis (Auckl) 14 , 39–50 (2024). Yang, H., Li, X., Zhang, L., Xue, F. & Zheng, J. Immunomodulatory effects of sleep deprivation at different timing of psoriasiform process on skin inflammation. Biochem Biophys Res Commun 513 , 452–459 (2019). Thorleifsdottir, R. H. et al. Throat Infections are Associated with Exacerbation in a Substantial Proportion of Patients with Chronic Plaque Psoriasis. Acta Derm Venereol 96 , 788–791 (2016). Johnston, A., Gudjonsson, J. E., Sigmundsdottir, H., Love, T. J. & Valdimarsson, H. Peripheral blood T cell responses to keratin peptides that share sequences with streptococcal M proteins are largely restricted to skin-homing CD8(+) T cells. Clin Exp Immunol 138 , 83–93 (2004). Travers, J. B. et al. Epidermal HLA-DR and the enhancement of cutaneous reactivity to superantigenic toxins in psoriasis. J Clin Invest 104 , 1181–1189 (1999). Chiricozzi, A., Gisondi, P., Bellinato, F. & Girolomoni, G. Immune response to vaccination in patients with psoriasis treated with systemic therapies. Vaccines 8 , (2020). Shen, F. et al. Tobacco Smoking Was Positively Associated with Disease Relapse at week 24 and 48 Among Patients with Psoriasis Vulgaris in Shanghai: A Prospective Study. Psoriasis (Auckl) 15 , 261–272 (2025). Lee, E. J., Han, K. D., Han, J. H. & Lee, J. H. Smoking and risk of psoriasis: A nationwide cohort study. J Am Acad Dermatol 77 , 573–575 (2017). Armstrong, A. W., Armstrong, E. J., Fuller, E. N., Sockolov, M. E. & Voyles, S. V. Smoking and pathogenesis of psoriasis: a review of oxidative, inflammatory and genetic mechanisms. Br J Dermatol 165 , 1162–1168 (2011). Carey, W. et al. Relapse, rebound, and psoriasis adverse events: an advisory group report. J Am Acad Dermatol 54 , S171-181 (2006). Svendsen, M. T. et al. A smartphone application supporting patients with psoriasis improves adherence to topical treatment: a randomized controlled trial. Br J Dermatol 179 , 1062–1071 (2018). Armstrong, A. W., Harskamp, C. T. & Armstrong, E. J. Psoriasis and the risk of diabetes mellitus: a systematic review and meta-analysis. JAMA Dermatol 149 , 84–91 (2013). De Luca, D. A., Papara, C., Hawro, T. & Thaçi, D. Psoriasis and diabetes: a review of the pathophysiological and therapeutic interconnections. Minerva Med 116 , 195–222 (2025). World Health Organization. Obesity and overweight. https://www.who.int/news-room/fa-ct-sheets/detail/obesity-and-overweight (2025). Musumeci, M. L., Nasca, M. R., Boscaglia, S. & Micali, G. The role of lifestyle and nutrition in psoriasis: Current status of knowledge and interventions. Dermatol Ther 35 , e15685 (2022). Kunz, M., Simon, J. C. & Saalbach, A. Psoriasis: Obesity and Fatty Acids. Front Immunol 10 , 1807 (2019). Huang, Y.-H. et al. Predicting the Time to Relapse Following Withdrawal from Different Biologics in Patients with Psoriasis who Responded to Therapy: A 12-Year Multicenter Cohort Study. Am J Clin Dermatol 25 , 997–1008 (2024). Sun, X. et al. Formation and clinical effects of anti-drug antibodies against biologics in psoriasis treatment: An analysis of current evidence. Autoimmun Rev 23 , 103530 (2024). Tables Tables 1 to 4 are available in the Supplementary Files section. Additional Declarations No competing interests reported. Supplementary Files TABLES.docx Cite Share Download PDF Status: Published Journal Publication published 11 Apr, 2026 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 06 Mar, 2026 Reviews received at journal 03 Mar, 2026 Reviewers agreed at journal 16 Feb, 2026 Reviews received at journal 11 Feb, 2026 Reviews received at journal 11 Feb, 2026 Reviewers agreed at journal 10 Feb, 2026 Reviewers agreed at journal 10 Feb, 2026 Reviewers agreed at journal 10 Feb, 2026 Reviewers invited by journal 10 Feb, 2026 Editor assigned by journal 05 Feb, 2026 Editor invited by journal 05 Feb, 2026 Submission checks completed at journal 04 Feb, 2026 First submitted to journal 04 Feb, 2026 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-8777210","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":591745414,"identity":"4ef29820-633f-4cb8-8362-6b8655cf6ac3","order_by":0,"name":"Xiaoxue Zhang","email":"","orcid":"","institution":"Second Affiliated Hospital of Hunan University of Traditional Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Xiaoxue","middleName":"","lastName":"Zhang","suffix":""},{"id":591745415,"identity":"32350aaf-d686-4af2-99b1-871e35cf08ce","order_by":1,"name":"Chen Zhao","email":"","orcid":"","institution":"Hunan University of Traditional Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Chen","middleName":"","lastName":"Zhao","suffix":""},{"id":591745416,"identity":"d734594d-b0ba-4d9b-8fbe-f82e16f0f14d","order_by":2,"name":"Yu Luo","email":"","orcid":"","institution":"Second Affiliated Hospital of Hunan University of Traditional Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Yu","middleName":"","lastName":"Luo","suffix":""},{"id":591745417,"identity":"039e0ac2-4a4b-431b-acfd-2ff7bb8eb51d","order_by":3,"name":"Hua He","email":"","orcid":"","institution":"Second Affiliated Hospital of Hunan University of Traditional Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Hua","middleName":"","lastName":"He","suffix":""},{"id":591745418,"identity":"85ae70fa-baa7-40e4-8489-d4f272a11798","order_by":4,"name":"Juan Gao","email":"","orcid":"","institution":"Second Affiliated Hospital of Hunan University of Traditional Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Juan","middleName":"","lastName":"Gao","suffix":""},{"id":591745419,"identity":"f32f33bd-248a-4aff-8be1-727a2a39601b","order_by":5,"name":"Xiaohua Tian","email":"","orcid":"","institution":"Second Affiliated Hospital of Hunan University of Traditional Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Xiaohua","middleName":"","lastName":"Tian","suffix":""},{"id":591745420,"identity":"077ac60e-d648-4b8c-98f6-63a169c1235a","order_by":6,"name":"Gufen Jiang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAzklEQVRIiWNgGAWjYBACNvbGhoMfKmzq29ibDxCnhY/ncONhiTNpjP08xxKI0yIn4d58gLftMOPMGT4GRDpMgrHhgMQZZmaDGzwfb7xhsJPTbSCkRbqx4UBBBRubwe3ezZZzGJKNzQ4Q0iJzEGQLD4/BnbPbpHkYDiRuI6hFIrEB6BcJCYMbOc9I0mJgIDkjh41ILTwHG4CBnJDAz3PM2HKOARF+kW9vf/zxQ8X/BDb25oc33lTYyRHUggIkeIiMGmQtpOoYBaNgFIyCEQEAYUtHiMjVxi0AAAAASUVORK5CYII=","orcid":"","institution":"Second Affiliated Hospital of Hunan University of Traditional Chinese Medicine","correspondingAuthor":true,"prefix":"","firstName":"Gufen","middleName":"","lastName":"Jiang","suffix":""}],"badges":[],"createdAt":"2026-02-03 14:39:02","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8777210/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8777210/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-026-47802-1","type":"published","date":"2026-04-11T15:57:30+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":103049139,"identity":"52f1c1cd-f452-4b18-a256-b795aff3c153","added_by":"auto","created_at":"2026-02-20 07:34:56","extension":"jpeg","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":40437,"visible":true,"origin":"","legend":"\u003cp\u003eStatic nomogram for predicting relapse in psoriasis.\u003c/p\u003e","description":"","filename":"floatimage1.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8777210/v1/73ae16098f7045e1a1849569.jpeg"},{"id":102962615,"identity":"17f81892-8348-42cc-89a3-d59181387768","added_by":"auto","created_at":"2026-02-19 04:10:09","extension":"jpeg","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":36788,"visible":true,"origin":"","legend":"\u003cp\u003eSHAP-based interpretability analysis of the nomogram model.\u003c/p\u003e","description":"","filename":"floatimage2.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8777210/v1/8340df8dc949b7a158e93498.jpeg"},{"id":102962644,"identity":"f2f8e841-ea0c-4599-8759-19ca6840f1ae","added_by":"auto","created_at":"2026-02-19 04:10:15","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":45872,"visible":true,"origin":"","legend":"\u003cp\u003eCalibration curve of the relapse risk prediction model.\u003c/p\u003e","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-8777210/v1/ed5e8ce5b3d4c6947f828eaf.png"},{"id":102962646,"identity":"dba352f1-b9b4-4f26-8483-377f1bb1f174","added_by":"auto","created_at":"2026-02-19 04:10:16","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":27089,"visible":true,"origin":"","legend":"\u003cp\u003eReceiver operating characteristic (ROC) curve of the model.\u003c/p\u003e","description":"","filename":"floatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-8777210/v1/2206834055fa2789d99e8bce.png"},{"id":102791084,"identity":"2da3421d-4647-4517-b7e8-139ed7f1f204","added_by":"auto","created_at":"2026-02-16 17:17:30","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":39403,"visible":true,"origin":"","legend":"\u003cp\u003eDecision curve analysis (DCA) of the model.\u003c/p\u003e","description":"","filename":"floatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-8777210/v1/e42a004fcf31778113098acb.png"},{"id":106809205,"identity":"0cc4a85d-13fb-4139-8ebe-fa48a8903105","added_by":"auto","created_at":"2026-04-13 16:08:14","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":767621,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8777210/v1/0bf088ca-e1c8-4ae9-ae6f-7bd7840012b5.pdf"},{"id":102791081,"identity":"062453e0-32b2-4ef2-8367-38da2b521454","added_by":"auto","created_at":"2026-02-16 17:17:30","extension":"docx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":60072,"visible":true,"origin":"","legend":"","description":"","filename":"TABLES.docx","url":"https://assets-eu.researchsquare.com/files/rs-8777210/v1/2a8532efe5ad25fe475f82dc.docx"}],"financialInterests":"No competing interests reported.","formattedTitle":"Development and validation of a prediction model for the risk of relapse in psoriasis","fulltext":[{"header":"Highlights","content":"\u003cp\u003eCurrently, research on predictive models for psoriasis relapse primarily focuses on patients after discontinuation of biologic agents, with limited studies involving patient populations not using biologics or those transitioning from biologic therapy to other treatment regimens. This limitation restricts the applicability of such prediction models to a certain extent. This study developed and validated a one-year relapse risk prediction model for all psoriasis patients. The model serves as an effective reference for assessing relapse risk in psoriasis patients and provides valuable guidance for developing personalized prevention strategies.\u003c/p\u003e"},{"header":"1 Introduction","content":"\u003cp\u003ePsoriasis is a chronic, relapsing, inflammatory, systemic skin disease mediated by the immune system, triggered by a combination of genetic and environmental factors. Its typical clinical manifestation is well-demarcated red plaques covered with silvery-white scales, which can be localized or widely distributed [1]. Patients with psoriasis often experience varying degrees of itching and pain, and some also have comorbidities such as cardiovascular and metabolic diseases [2,3,4]. Psoriasis is widely distributed worldwide. Epidemiological surveys show that there are approximately 125\u0026nbsp;million psoriasis patients globally, with a worldwide prevalence ranging from 0.51% to 11.43% [5]. The latest large-scale international study indicates that the global average prevalence of adult psoriasis is approximately 4.4%, with the prevalence in the East Asian region reaching as high as 5.7% [6]. Since psoriasis currently has no curative treatment, it exhibits a high relapse rate throughout its clinical course. Most patients experience multiple relapses during the disease progression, which significantly impacts their physical and mental health as well as quality of life [7]. However, there is currently a lack of highly specific and sensitive indicators for the diagnosis of psoriasis, and efficient screening tools for psoriasis relapse are also insufficient. Although many assessment scales related to psoriasis exist, these scales are typically used when patients already exhibit the characteristic features of psoriasis, meaning they have entered the recurrence stage. At this point, the patients have often already experienced negative physical and psychological effects, and interventions essentially become part of ongoing treatment rather than early prevention. Therefore, it is crucial for healthcare providers to shift psoriasis relapse management from a passive to an active approach by developing a multifactorial, rapid screening risk warning system. Early identification and warning of relevant risk factors before disease onset, along with predicting relapse trends, are of great importance for controlling psoriasis relapse and promoting patient recovery.\u003c/p\u003e \u003cp\u003eIn recent years, with the growing emphasis on precision medicine, the use of predictive models for early identification of disease risk and individualized intervention has become a research focus. Clinical prediction models are developed by utilizing existing clinical data to construct appropriate statistical models that summarize the regularity of the probability of a specific outcome occurring in particular clinical scenarios [8]. These models can provide patients and physicians with more accurate and scientific evidence to support earlier and better-informed decision-making.\u003c/p\u003e \u003cp\u003eCurrent research on predictive models for psoriasis relapse risk primarily focuses on the specific clinical decision point of \"post-discontinuation of biologic agents\" [9,10]. Although biologic agents have demonstrated remarkable efficacy in the treatment of psoriasis, their actual global utilization remains restricted by multiple factors, including economic constraints, policies, and medical accessibility, resulting in limited access to biologic therapy for a significant proportion of patients [11,12]. However, there is a lack of effective quantitative prediction tools for the relapse risk in a large number of patients who do not use biologic agents, such as those receiving only conventional systemic drugs, phototherapy, or topical treatments. Therefore, it is necessary to develop a relapse risk prediction model applicable to all psoriasis patients, covering the entire population including both biologic users and those receiving conventional treatments, with the aim of enhancing the model's clinical applicability and generalizability.\u003c/p\u003e \u003cp\u003eTo address this limitation, the present study designed, developed, and validated a relapse risk prediction model based on psoriasis risk factors, applicable to all psoriasis patients. This model aims to improve the efficiency and accuracy of early screening for psoriasis relapse in clinical practice, provide a reference for preventive measures, and offer valuable guidance for the formulation of patient treatment plans.\u003c/p\u003e"},{"header":"2 Materials and methods","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e \u003ch2\u003e2.1 Study design\u003c/h2\u003e \u003cp\u003eThis was a single-center, retrospective study conducted in the Department of Dermatology at a tertiary general hospital in China from January 2022 to December 2024. Patient data were collected via the Electronic Medical Record system and follow-up procedures. Informed consent was obtained from all patients upon admission, confirming their agreement to participate in the study. The study adhered to the Transparent Reporting of a Multivariate Prediction Model for Individual Prognosis or Diagnosis (TRIPOD) statement as a reporting guideline[13]. It was approved by the Ethics Committee of the Second Affiliated Hospital of Hunan University of Traditional Chinese Medicine (Approval Number: 2025-KY-024-01). All methods were performed in accordance with the relevant guidelines and regulations.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec4\" class=\"Section2\"\u003e \u003ch2\u003e2.2 Study Population\u003c/h2\u003e \u003cp\u003eThis study employed a convenience sampling method to select psoriasis patients admitted to a tertiary hospital in China between January 2022 and December 2024. Their relapse status within one year was obtained through follow-up.\u003c/p\u003e \u003cp\u003ePatients meeting the inclusion criteria are required to fulfill the following conditions: (1) Diagnosis in accordance with the \u003cem\u003eGuideline for the diagnosis and treatment of psoriasis in China (2023 edition)\u003c/em\u003e [14]; (2) Aged between 18 and 80 years at admission; (3) Clear consciousness, absence of cognitive impairment, and possession of basic communication and comprehension abilities; (4) Voluntary participation in this study and provide written informed consent; (5) Availability of complete clinical data and accessibility for follow-up.\u003c/p\u003e \u003cp\u003eThe exclusion criteria included the following: (1) History of severe psychiatric disorders or current use of psychotropic medications; (2) Presence of severe primary diseases affecting the cardiovascular, cerebrovascular, hepatic, renal, or hematopoietic systems with unstable conditions; (3) Presence of other autoimmune diseases, malignant tumors, or active infections; (4) Severe missing clinical data that affect the extraction of study variables and outcome assessment; (5) Lack of improvement or progressive deterioration of psoriasis after standardized treatment.\u003c/p\u003e \u003cp\u003eThe criteria for withdrawal and dropout included: (1) Patients voluntarily requesting to withdraw or being lost to follow-up during the study period; (2) Major discrepancies between provided clinical data and actual conditions that could not be corrected after verification; (3) Occurrence of serious adverse events, complications, or death during the follow-up period, rendering the patient unable to continue participation; (4) Use of non-protocol medications or therapeutic interventions during the study period that may affect disease relapse; (5) Missing data affecting the assessment of the primary outcome (relapse).\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec5\" class=\"Section2\"\u003e \u003ch2\u003e2.3 Sample Size calculation\u003c/h2\u003e \u003cp\u003eThe sample size was estimated based on the principle of Events Per Variable (EPV). This method is commonly employed in the construction of clinical prediction models. It requires that the number of patients experiencing the target outcome must be at least ten times the number of predictor variables included in the final model. In other words, a minimum of ten outcome events per predictor variable is necessary to ensure the stability and reliability of the model parameters [15]. This study plans to include 35 independent variables. Research indicates that the one-year recurrence rate of psoriasis is as high as 86.1% [16]. Therefore, the minimum sample size is calculated as 35 \u0026times; 10\u0026thinsp;\u0026divide;\u0026thinsp;0.861\u0026thinsp;\u0026asymp;\u0026thinsp;407. A total of 504 patients with psoriasis were finally enrolled in this study and randomly divided into a training set (n\u0026thinsp;=\u0026thinsp;353) and a testing set (n\u0026thinsp;=\u0026thinsp;151) at a ratio of 7:3.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec6\" class=\"Section2\"\u003e \u003ch2\u003e2.4 Outcome variables\u003c/h2\u003e \u003cp\u003eThe outcome variable in this study was relapse. Relapse was defined as the reappearance of cutaneous lesions and histopathological features involving an area greater than 30% in patients with a history of psoriasis who had achieved clinical cure following treatment. After discharge, patients were followed up monthly by nursing staff, and the follow-up period lasted for one year.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec7\" class=\"Section2\"\u003e \u003ch2\u003e2.5 Candidate variables\u003c/h2\u003e \u003cp\u003eBased on an analysis of previous relevant literature [17\u0026ndash;23], integration with clinical experience, and group discussions, we identified potential risk factors for psoriasis recurrence. Accordingly, the following data were collected in this study: (1) Demographic and baseline characteristics: gender, age, body mass index (BMI), sleep disorders, smoking history, history of alcohol consumption, and anxiety; (2) Disease-related factors: duration of illness, severity of the condition, type of psoriasis, season of onset, family history, allergy history, history of diabetes, coronary heart disease, hypertension, hyperlipidemia, upper respiratory tract infection, irregular medication use, trauma/surgery, exposure to chemical agents (hair dyes, pesticides, etc.), and exposure to biological agents; (3) Laboratory parameters: presence of hypoproteinemia and whether biochemical indicators were normal (erythrocyte sedimentation rate, C-reactive protein, immunological indicators).\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec8\" class=\"Section2\"\u003e \u003ch2\u003e2.6 Data Collection\u003c/h2\u003e \u003cp\u003eThis study retrospectively collected data from the hospital Electronic Medical Record (EMR) using a structured questionnaire. The questionnaire covered three specific domains, and patient recurrence within one year was obtained through follow-up. The data collection process strictly adhered to the predefined inclusion and exclusion criteria. Two trained researchers used a standardized questionnaire to ensure consistency in data collection and cross-verified the completeness, authenticity, and accuracy of the data. Concurrently, a specialized dermatology nurse conducted monthly follow-ups for a duration of one year. Strict quality control measures were implemented throughout the follow-up process to ensure the accuracy and completeness of the information. The data entry process strictly followed a double-entry system. After entry, data were promptly cross-checked against the original medical records to identify and resolve any discrepancies or missing information, ensuring high data quality and completeness.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec9\" class=\"Section2\"\u003e \u003ch2\u003e2.7 Statistical analysis\u003c/h2\u003e \u003cp\u003eStatistical analyses were performed using R Studio (version 4.2.2). All hypothesis tests were two-sided with a significance level set at 0.05. Measurement data that follow a normal distribution are presented as mean\u0026thinsp;\u0026plusmn;\u0026thinsp;standard deviation, and comparisons between groups are analyzed using the independent samples t-test. Measurement data that do not follow a normal distribution are presented as median (M) with interquartile range (P25, P75), and comparisons between groups are analyzed using the Mann-Whitney U test. Categorical data were analyzed using the chi-square test. Univariate analysis was performed to screen potential prognostic factors (\u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.05), which were then included in a multivariate logistic regression analysis to identify independent risk factors (\u003cem\u003eP\u003c/em\u003e\u0026thinsp;\u0026lt;\u0026thinsp;0.05). A prediction model was subsequently constructed, and model visualization was conducted using a nomogram and SHAP summary plot. The Receiver Operating Characteristic (ROC) curve was plotted to evaluate the diagnostic performance of the model. The Hosmer-Lemeshow test was used to assess the goodness of fit. Calibration curves were plotted to evaluate the calibration of the model, and Decision Curve Analysis (DCA) was performed to assess the clinical utility of the model.\u003c/p\u003e \u003c/div\u003e"},{"header":"3 Results","content":"\u003cp\u003e3.1 Characteristics of the participants\u003c/p\u003e\n\u003cp\u003eThis study collected clinical data from a total of 504 patients, among whom 336 cases (66.67%) experienced relapse within one year after treatment. Based on the stratification of the dependent variable, all samples were randomly divided into a training set (n = 353) and a testing set (n = 151) at a 7:3 ratio. The training set included 233 relapsed and 120 non-relapsed cases, with a relapse rate of 66.0%, while the testing set had 103 relapsed and 48 non-relapsed cases, with a relapse rate of 68.2%. The analysis of baseline characteristic differences showed that, in the comparison of clinical data between the training and test sets, baseline features of C-reactive protein (CRP) and erythrocyte sedimentation rate (ESR) exhibited statistically significant differences. However, this was a result of random allocation and does not affect the model construction. No statistically significant differences were observed between the two groups in terms of demographics and disease-related factors. Detailed data are provided in Table 1.\u003c/p\u003e\n\u003cp\u003e3.2 Univariate analysis for relapse in psoriasis\u003c/p\u003e\n\u003cp\u003eTable 2 summarizes the results of the univariate analysis. The training set was further divided into non-relapse and relapse groups according to the presence or absence of relapse. The results of this study showed that BMI, disease duration, diabetes, use of biologic agents, smoking, URTI, and non-standard medication use exhibited significant differences (all \u003cem\u003eP\u003c/em\u003e \u0026lt; 0.05).\u003c/p\u003e\n\u003cp\u003e3.3 Logistic regression analysis for relapse in psoriasis\u003c/p\u003e\n\u003cp\u003eTable 3 summarizes the results of the logistic regression analysis. A logistic regression model was constructed using the training set data. Backward stepwise logistic regression was performed for feature selection, with relapse within one year as the dependent variable and variables showing statistical significance in the univariate analysis as independent variables. The logistic regression results indicated that BMI, diabetes, use of biologic agents, smoking, URTI, and non-standard medication were independent risk factors for relapse (all \u003cem\u003eP\u003c/em\u003e \u0026lt; 0.05).\u003c/p\u003e\n\u003cp\u003e3.4 Development of model\u003c/p\u003e\n\u003cp\u003e3.4.1 Nomogram for Clinical Risk Stratification\u003c/p\u003e\n\u003cp\u003eThe partial regression coefficients of the independent predictors identified by the logistic regression analysis were used to establish the model. The fitted regression equation of the prediction model for the risk of relapse within one year in patients with psoriasis is as follows: Logit \u003cem\u003ep\u003c/em\u003e = -5.127 + 0.201 \u0026times; BMI + 0.987 \u0026times; Diabetes + 0.992 \u0026times; Biologic agent + 0.843 \u0026times; Smoking + 1.160 \u0026times; URTI + 0.835 \u0026times; Non-standard medication. The results are shown in Fig.1.\u003c/p\u003e\n\u003cp\u003e3.4.2 SHAP-based interpretability analysis\u003c/p\u003e\n\u003cp\u003eThis study evaluated the relative importance of various risk factors influencing relapse in patients with psoriasis, as shown in Fig.2. In the figure, each dot represents an individual sample. The color gradient from red to blue indicates the magnitude of the values ranging from low to high. The vertical axis arranges the risk factors in descending order of importance, while the horizontal axis shows the average SHAP value for each feature, along with the correlation and distribution between each feature and its SHAP values. The SHAP model not only elucidates the positive or negative contribution of each factor to individual predictions but also quantifies the magnitude of these effects. In the visualization, blue represents an increased risk of psoriasis relapse, while red denotes a decreased risk, thereby offering a personalized and transparent explanation for the model\u0026apos;s decision-making process. The SHAP model results ranked the factors as follows: URTI \u0026gt; Smoking \u0026gt; Non-standard medication \u0026gt; Diabetes \u0026gt; BMI \u0026gt; Biologic agent, with URTI, Smoking, and Non-standard medication having key impacts on psoriasis relapse.\u003c/p\u003e\n\u003cp\u003e3.5 Prediction Model Performance\u003c/p\u003e\n\u003cp\u003e3.5.1 Model calibration\u003c/p\u003e\n\u003cp\u003eThe model demonstrated excellent calibration performance in both the training and testing sets. The Hosmer-Lemeshow goodness-of-fit test yielded a chi-square value of 7.577 with a P-value of 0.476 for the training set, and a chi-square value of 10.391 with a P-value of 0.239 for the testing set. The results demonstrated that the model exhibited good fitting performance, and the calibration curve showed a high degree of agreement between the predicted and observed outcomes. The bootstrap-corrected calibration results further confirmed good agreement, with the calibration curves (green and blue solid lines) closely aligning with the ideal reference line (black dashed line), as shown in Fig.3.\u003c/p\u003e\n\u003cp\u003e3.5.2 Model discrimination\u003c/p\u003e\n\u003cp\u003eThe ROC curves for the predictive model indicate that it has good discriminative ability in predicting relapse risk in psoriasis patients. The area under the curve (AUC) was 0.767 [95% CI: 0.715\u0026ndash;0.818] for the training set (red solid line) and 0.704 [95% CI: 0.620\u0026ndash;0.789] for the testing set (blue dashed line). The results are presented in Fig.4 and Table 4.\u003c/p\u003e\n\u003cp\u003e3.5.3 Clinical Utility\u003c/p\u003e\n\u003cp\u003eFigure 5 presents the clinical Decision Curve Analysis (DCA). This curve circumvents the need to explicitly consider false positives and false negatives by directly calculating the Net Benefit (NB) and maximizing its value. The DCA plot displays the threshold probability on the x-axis and the Net Benefit (NB) on the y-axis. The horizontal reference line represents the \u0026quot;no treatment\u0026quot; strategy (treating all samples as negative while maintaining intervention for all patients), where the net benefit is zero. The vertical reference line represents the \u0026quot;treat all\u0026quot; strategy (treating all samples as positive and providing intervention to all patients), characterized by a negative slope. The DCA curves for the training set (red line) and the testing set (green line) both exhibited net benefits exceeding those of the \u0026quot;treat-none\u0026quot; (black horizontal line) and \u0026quot;treat-all\u0026quot; (light gray diagonal line) reference strategies within a threshold probability range of approximately 0 to 0.92. This indicates that the model has higher clinical utility within this threshold range.\u003c/p\u003e"},{"header":"4 Discussion","content":"\u003cp\u003ePsoriasis is a chronic, recurrent, inflammatory skin disease, and its high relapse rate remains a major challenge and key focus in clinical management. Therefore, developing a prediction model capable of early identification of patients at high risk of relapse holds significant clinical value for facilitating personalized interventions and optimizing treatment strategies. Current research on prediction models for psoriasis relapse has predominantly focused on patients following the discontinuation of biological agents, with limited attention given to populations naive to biologics or those transitioning to alternative therapeutic regimens. This limitation restricts the applicability of existing models to a certain extent. This study developed and validated a prediction model for the risk of relapse within one year targeting the general population of psoriasis patients, identifying URTI, smoking, non-standard medication, diabetes, BMI, and biologic agents as independent predictors.\u003c/p\u003e\n\u003cp\u003eThe findings of this study indicate that URTI is an independent risk factor for psoriasis relapse. Upper respiratory streptococcal infection is recognized as one of the important triggers for psoriasis relapse [24]. Certain components of streptococcus, such as the M protein, exhibit molecular mimicry with human keratin, potentially initiating cross-immune reactions, activating T cells, and leading to the exacerbation of psoriatic skin lesions [25]. Additionally, upper respiratory tract infections caused by Staphylococcus aureus may also be associated with psoriasis relapse, as its superantigens can non-specifically activate a large number of T cells, triggering a strong inflammatory response and exacerbating psoriatic skin lesions [26]. Overall, infections can trigger abnormal immune responses that induce psoriasis recurrence. Therefore, preventing and promptly treating infections is of great significance in reducing the risk of recurrence. Relevant studies have also found that targeted vaccination can effectively reduce the risk of infection-induced relapse in patients with psoriasis [27].\u003c/p\u003e\n\u003cp\u003eThis study found that smoking is an independent risk factor for psoriasis relapse, consistent with previous research [28,29]. The mechanism by which smoking induces relapse is relatively complex [20,30]. Components in tobacco, such as nicotine, can directly stimulate immune cells to release inflammatory factors (e.g., IL-6, TNF-\u0026alpha;), thereby promoting the chemotaxis and activation of neutrophils. Meanwhile, oxidants and free radicals in smoke can damage the skin barrier, trigger oxidative stress responses, and activate inflammatory pathways such as NF-\u0026kappa;B. Furthermore, smoking may also predispose the body to inflammatory responses by influencing gene expression (such as upregulating susceptibility genes like HLA-C*06:02) and epigenetic modifications. In clinical management, smoking cessation should be incorporated as an integral component of the comprehensive therapeutic strategy for psoriasis. Patients should be explicitly educated on the role of smoking in precipitating disease recurrence and the underlying inflammatory mechanisms, thereby fostering awareness of the necessity to quit. Furthermore, diversified cessation support should be provided to alleviate the challenges associated with smoking cessation, including encompassing behavioral interventions, psychological counseling, and pharmacological aids where indicated.\u003c/p\u003e\n\u003cp\u003eNon-standard medication practices, including unauthorized discontinuation, dose reduction, or misuse of drugs, constitutes a critical factor leading to the recurrence of psoriasis relapse. Topical treatment requires patients to maintain long-term adherence. Sudden discontinuation or improper withdrawal may trigger disease rebound. For example, abrupt cessation after prolonged high-dose use of glucocorticoids can lead to rapid lesion spread within a short period and even induce severe forms such as erythrodermic or pustular psoriasis [31]. Additionally, drug resistance or reduced efficacy during treatment may also contribute to disease relapse. For example, long-term administration of the same biological agent in certain patients may induce the formation of anti-drug antibodies, resulting in diminished efficacy and the recurrence of skin lesions. Non-standard medication is also a modifiable factor contributing to psoriasis relapse. Adhering to standardized and continuous treatment is essential for preventing relapse. Studies have shown that implementing mobile health reminder systems, combined with smart pillboxes and SMS notifications, significantly improves patient medication adherence, which in turn helps reduce the risk of relapse [32].\u003c/p\u003e\n\u003cp\u003eThe results of this study indicate that diabetes is an independent risk factor for psoriasis relapse. A population-based cohort study has shown that psoriasis patients with diabetes exhibit higher disease activity and an increased risk of relapse [33]. Diabetes, as a common comorbidity of psoriasis, promotes relapse through the IL-23/IL-17 axis: a hyperglycemic environment activates macrophages through advanced glycation end products (AGEs), leading to the upregulation of IL-23 secretion and subsequently exacerbating cutaneous inflammation [34]. In clinical practice, diabetes screening for psoriasis patients can be strengthened, especially by conducting regular blood glucose monitoring for high-risk groups such as individuals with obesity, to enable early identification and intervention. Furthermore, for psoriasis patients with established diabetes, glycemic control should be intensified through dietary regulation, regular exercise, and rational pharmacotherapy to maintain blood glucose levels within the target range, thereby reducing the hyperglycemia-induced release of inflammatory factors.\u003c/p\u003e\n\u003cp\u003eThis study found that increased BMI is an independent risk factor for psoriasis relapse. BMI, as a core indicator for assessing obesity, is defined by the World Health Organization as a BMI of 30 or higher in adults [35]. Research has shown that obesity can promote psoriasis relapse: adipose tissue secretes various pro-inflammatory cytokines (such as IL-6, TNF-\u0026alpha;, leptin), which overlap with the inflammatory pathways involved in psoriasis and can lead to disease worsening and an increased risk of relapse\u0026nbsp;[36,37]. For patients with elevated BMI, the prevention of psoriasis relapse can be achieved by prioritizing weight management and lifestyle interventions.\u003c/p\u003e\n\u003cp\u003eThis study found that a history of prior biologic agent exposure is an important treatment-related factor affecting psoriasis relapse. A study from Taiwan found that each additional prior exposure to biologics increases the risk of psoriasis relapse by 23% [38]. This phenomenon of \u0026quot;exposure-dependent relapse acceleration\u0026quot; may be related to the production of anti-drug antibodies (ADAs), which can accelerate drug clearance and reduce treatment efficacy [39]. For patients with a history of multiple exposures to biologic agents, greater caution should be exercised when selecting future treatment regimens. If necessary, rotating drugs with different mechanisms of action may be considered to reduce the risk of relapse.\u003c/p\u003e\n\u003cp\u003eThe model demonstrated good discriminative ability with AUC values of 0.767 in the training set and 0.704 in the testing set. The goodness-of-fit tests showed\u0026nbsp;\u0026chi;\u0026sup2;\u0026nbsp;= 7.577 (\u003cem\u003eP\u003c/em\u003e = 0.476) for the training set and\u0026nbsp;\u0026chi;\u0026sup2;\u0026nbsp;= 10.391 (\u003cem\u003eP\u003c/em\u003e = 0.239) for the testing set, indicating that the model has good overall consistency. Decision curve analysis (DCA) revealed significant net benefits in both the training and testing sets, supporting the clinical applicability of this model.Therefore, clinicians should utilize this model to promptly identify psoriasis patients at high risk of relapse and implement early preventive and effective interventions. These measures include but are not limited to: pthe prevention and timely treatment of upper respiratory tract infections; smoking cessation through measures such as nicotine replacement therapy; strict adherence to prescribed medication regimens; rigorous blood glucose monitoring and regulation for patients with comorbid diabetes; and scientific weight management via nutritional counseling and exercise prescriptions. In summary, early identification of high-risk patients and the implementation of timely and effective interventions are key steps in reducing the risk of psoriasis relapse.\u003c/p\u003e"},{"header":"5 Conclusion","content":"\u003cp\u003eThis study found that upper respiratory tract infection (URTI), smoking, non-standard medication use, diabetes, BMI, and biologic agent exposure are independent risk factors influencing psoriasis relapse. Therefore, early screening for relapse risk in psoriasis patients may be particularly important for reducing the rate of relapse. The psoriasis relapse risk prediction model established in this study demonstrates good predictive capability. This model serves as an effective reference for assessing the risk of psoriasis relapse and provides valuable guidance for the formulation of personalized preventive strategies for patients.\u003c/p\u003e"},{"header":"6 Limitations","content":"\u003cp\u003eThis study has several limitations that need to be addressed in future research. Firstly, this study is a single-center retrospective investigation, with all data derived from one medical center. Therefore, the representativeness of the sample may be limited, indicating that the study findings require further validation. Secondly, the predictive variables included in this study were all routine clinical indicators, without incorporating deeper biomarkers such as genetic factors, specific cytokines, or microbiomics. Future research could integrate multi-omics data to enhance the model\u0026rsquo;s predictive accuracy and scientific significance. Thirdly, this study only focused on relapse within one year and did not evaluate the longer-term risk of psoriasis relapse or the patterns of disease progression. Future research could extend the follow-up period to develop a more comprehensive disease trajectory prediction model. Finally, although internal validation of the model was performed, external validation was not conducted. Therefore, the predictive performance of this model should be continuously validated in future studies to achieve broader generalizability.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e \u003ch2\u003eCompeting interests\u003c/h2\u003e \u003cp\u003eThe authors declare no competing interests.\u003c/p\u003e \u003c/p\u003e\u003ch2\u003eFunding\u003c/h2\u003e \u003cp\u003eThis study was supported by the 2025 Hunan Provincial Natural Science Foundation Project (2025JJ80911).\u003c/p\u003e\u003ch2\u003eAuthor Contribution\u003c/h2\u003e\u003cp\u003eXZ: Conceptualization, Methodology, Investigation, Data curation, Writing \u0026ndash; original draft. CZ: Investigation, Data curation, Writing Original Draft. YL: Coordination, Formal analysis, Project administration, Writing \u0026ndash; review \u0026amp; editing. HH: Coordination, Project administration, Writing \u0026ndash; review \u0026amp; editing. JG: Project administration, Writing \u0026ndash; review \u0026amp; editing. XT: Project administration, Writing \u0026ndash; review \u0026amp; editing. GJ: Funding acquisition, Project administration, Writing \u0026ndash; review \u0026amp; editing. All the authors have read and approved the final version of the manuscript.\u003c/p\u003e\u003ch2\u003eData Availability\u003c/h2\u003e\u003cp\u003eThe datasets generated during and/or analysed during the current study are available from the corresponding author on reasonable request.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\n \u003cli\u003eBoehncke, W.-H. \u0026amp; Sch\u0026ouml;n, M. P. Psoriasis. \u003cem\u003eLancet\u003c/em\u003e \u003cstrong\u003e386\u003c/strong\u003e, 983\u0026ndash;994 (2015).\u003c/li\u003e\n \u003cli\u003eDubertret, L. \u003cem\u003eet al.\u003c/em\u003e European patient perspectives on the impact of psoriasis: the EUROPSO patient membership survey. \u003cem\u003eBr J Dermatol\u003c/em\u003e \u003cstrong\u003e155\u003c/strong\u003e, 729\u0026ndash;736 (2006).\u003c/li\u003e\n \u003cli\u003ePeng, C. \u003cem\u003eet al.\u003c/em\u003e Epidemiological Variations in the Global Burden of Psoriasis, an Analysis With Trends From 1990 to 2017. \u003cem\u003eFront Med (Lausanne)\u003c/em\u003e \u003cstrong\u003e8\u003c/strong\u003e, 585634 (2021).\u003c/li\u003e\n \u003cli\u003eTakeshita, J. \u003cem\u003eet al.\u003c/em\u003e Psoriasis and comorbid diseases: Epidemiology. \u003cem\u003eJ Am Acad Dermatol\u003c/em\u003e \u003cstrong\u003e76\u003c/strong\u003e, 377\u0026ndash;390 (2017).\u003c/li\u003e\n \u003cli\u003eWorld Health Organization. \u003cem\u003eGlobal Report on Psoriasis\u003c/em\u003e. (2016).\u003c/li\u003e\n \u003cli\u003eSkayem, C., Taieb, C., Halioua, B., Baissac, C. \u0026amp; Saint Aroman, M. Epidemiology of Psoriasis: A Worldwide Global Study. \u003cem\u003eActa Derm Venereol\u003c/em\u003e \u003cstrong\u003e105\u003c/strong\u003e, adv42945 (2025).\u003c/li\u003e\n \u003cli\u003eBu, J., Ding, R., Zhou, L., Chen, X. \u0026amp; Shen, E. Epidemiology of Psoriasis and Comorbid Diseases: A Narrative Review. \u003cem\u003eFront Immunol\u003c/em\u003e \u003cstrong\u003e13\u003c/strong\u003e, 880201 (2022).\u003c/li\u003e\n \u003cli\u003eCadrin-Tourigny, J. \u003cem\u003eet al.\u003c/em\u003e A new prediction model for ventricular arrhythmias in arrhythmogenic right ventricular cardiomyopathy. \u003cem\u003eEuropean Heart Journal\u003c/em\u003e \u003cstrong\u003e43\u003c/strong\u003e, e1\u0026ndash;e9 (2022).\u003c/li\u003e\n \u003cli\u003eHuang, S., Bai, Y., Qi, R., Yu, H. \u0026amp; Duan, X. Personalized prediction of psoriasis relapse post-biologic discontinuation: a machine learning-driven population cohort study. \u003cem\u003eJ Dermatolog Treat\u003c/em\u003e \u003cstrong\u003e36\u003c/strong\u003e, 2480743 (2025).\u003c/li\u003e\n \u003cli\u003eHuang, S., Chen, B., Qi, Y., Duan, X. \u0026amp; Bai, Y. Development and external validation of a prediction model for the risk of relapse in psoriasis after discontinuation of biologics. \u003cem\u003eFront Med (Lausanne)\u003c/em\u003e \u003cstrong\u003e11\u003c/strong\u003e, 1488096 (2024).\u003c/li\u003e\n \u003cli\u003eGirolomoni, G. \u003cem\u003eet al.\u003c/em\u003e Increasing Access to Effective Systemic Treatments in Patients with Moderate-to-Severe Psoriasis :: Narrative Review. \u003cem\u003eDermatology and Therapy\u003c/em\u003e \u003cstrong\u003e13\u003c/strong\u003e, 2171\u0026ndash;2185 (2023).\u003c/li\u003e\n \u003cli\u003eWan, V. \u003cem\u003eet al.\u003c/em\u003e Disparities and barriers to the access of biologics in moderate-to-severe adult psoriasis. \u003cem\u003eInt J Dermatol\u003c/em\u003e \u003cstrong\u003e63\u003c/strong\u003e, 1293\u0026ndash;1301 (2024).\u003c/li\u003e\n \u003cli\u003eCollins, G. S., Reitsma, J. B., Altman, D. G. \u0026amp; Moons, K. G. M. Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement. \u003cem\u003eBMJ\u003c/em\u003e \u003cstrong\u003e350\u003c/strong\u003e, g7594 (2015).\u003c/li\u003e\n \u003cli\u003eCommittee on Psoriasis, Chinese Society of Dermatology. Guideline for the diagnosis and treatment of psoriasis in China\u0026nbsp;（2023 edition）. \u003cem\u003eChinese Journal of Dermatology\u003c/em\u003e \u003cstrong\u003e56\u003c/strong\u003e, 573\u0026ndash;625 (2023).\u003c/li\u003e\n \u003cli\u003eRiley, R. D. \u003cem\u003eet al.\u003c/em\u003e Calculating the sample size required for developing a clinical prediction model. \u003cem\u003eBMJ\u003c/em\u003e \u003cstrong\u003e368\u003c/strong\u003e, m441 (2020).\u003c/li\u003e\n \u003cli\u003eHuang, Y.-W. \u0026amp; Tsai, T.-F. Remission Duration and Long-Term Outcomes in Patients with Moderate-to-Severe Psoriasis Treated by Biologics or Tofacitinib in Controlled Clinical Trials: A 15-Year Single-Center Experience. \u003cem\u003eDermatol Ther (Heidelb)\u003c/em\u003e \u003cstrong\u003e9\u003c/strong\u003e, 553\u0026ndash;569 (2019).\u003c/li\u003e\n \u003cli\u003eFrancis, L., Capon, F., Smith, C. H., Haniffa, M. \u0026amp; Mahil, S. K. Inflammatory memory in psoriasis: From remission to recurrence. \u003cem\u003eJ Allergy Clin Immunol\u003c/em\u003e \u003cstrong\u003e154\u003c/strong\u003e, 42\u0026ndash;50 (2024).\u003c/li\u003e\n \u003cli\u003eLee, E. B., Wu, K. K., Lee, M. P., Bhutani, T. \u0026amp; Wu, J. J. Psoriasis risk factors and triggers. \u003cem\u003eCutis\u003c/em\u003e \u003cstrong\u003e102\u003c/strong\u003e, 18\u0026ndash;20 (2018).\u003c/li\u003e\n \u003cli\u003eZhang, L.-J. \u003cem\u003eet al.\u003c/em\u003e Antimicrobial Peptide LL37 and MAVS Signaling Drive Interferon-\u0026beta; Production by Epidermal Keratinocytes during Skin Injury. \u003cem\u003eImmunity\u003c/em\u003e \u003cstrong\u003e45\u003c/strong\u003e, 119\u0026ndash;130 (2016).\u003c/li\u003e\n \u003cli\u003eLiu, S. \u003cem\u003eet al.\u003c/em\u003e Triggers for the onset and recurrence of psoriasis: a review and update. \u003cem\u003eCell Commun Signal\u003c/em\u003e \u003cstrong\u003e22\u003c/strong\u003e, 108 (2024).\u003c/li\u003e\n \u003cli\u003eStewart, T. J., Tong, W. \u0026amp; Whitfeld, M. J. The associations between psychological stress and psoriasis: a systematic review. \u003cem\u003eInt J Dermatol\u003c/em\u003e \u003cstrong\u003e57\u003c/strong\u003e, 1275\u0026ndash;1282 (2018).\u003c/li\u003e\n \u003cli\u003ePotestio, L. \u003cem\u003eet al.\u003c/em\u003e Risk Factors for Psoriasis Flares: A Narrative Review. \u003cem\u003ePsoriasis (Auckl)\u003c/em\u003e \u003cstrong\u003e14\u003c/strong\u003e, 39\u0026ndash;50 (2024).\u003c/li\u003e\n \u003cli\u003eYang, H., Li, X., Zhang, L., Xue, F. \u0026amp; Zheng, J. Immunomodulatory effects of sleep deprivation at different timing of psoriasiform process on skin inflammation. \u003cem\u003eBiochem Biophys Res Commun\u003c/em\u003e \u003cstrong\u003e513\u003c/strong\u003e, 452\u0026ndash;459 (2019).\u003c/li\u003e\n \u003cli\u003eThorleifsdottir, R. H. \u003cem\u003eet al.\u003c/em\u003e Throat Infections are Associated with Exacerbation in a Substantial Proportion of Patients with Chronic Plaque Psoriasis. \u003cem\u003eActa Derm Venereol\u003c/em\u003e \u003cstrong\u003e96\u003c/strong\u003e, 788\u0026ndash;791 (2016).\u003c/li\u003e\n \u003cli\u003eJohnston, A., Gudjonsson, J. E., Sigmundsdottir, H., Love, T. J. \u0026amp; Valdimarsson, H. Peripheral blood T cell responses to keratin peptides that share sequences with streptococcal M proteins are largely restricted to skin-homing CD8(+) T cells. \u003cem\u003eClin Exp Immunol\u003c/em\u003e \u003cstrong\u003e138\u003c/strong\u003e, 83\u0026ndash;93 (2004).\u003c/li\u003e\n \u003cli\u003eTravers, J. B. \u003cem\u003eet al.\u003c/em\u003e Epidermal HLA-DR and the enhancement of cutaneous reactivity to superantigenic toxins in psoriasis. \u003cem\u003eJ Clin Invest\u003c/em\u003e \u003cstrong\u003e104\u003c/strong\u003e, 1181\u0026ndash;1189 (1999).\u003c/li\u003e\n \u003cli\u003eChiricozzi, A., Gisondi, P., Bellinato, F. \u0026amp; Girolomoni, G. Immune response to vaccination in patients with psoriasis treated with systemic therapies. \u003cem\u003eVaccines\u003c/em\u003e \u003cstrong\u003e8\u003c/strong\u003e, (2020).\u003c/li\u003e\n \u003cli\u003eShen, F. \u003cem\u003eet al.\u003c/em\u003e Tobacco Smoking Was Positively Associated with Disease Relapse at week 24 and 48 Among Patients with Psoriasis Vulgaris in Shanghai: A Prospective Study. \u003cem\u003ePsoriasis (Auckl)\u003c/em\u003e \u003cstrong\u003e15\u003c/strong\u003e, 261\u0026ndash;272 (2025).\u003c/li\u003e\n \u003cli\u003eLee, E. J., Han, K. D., Han, J. H. \u0026amp; Lee, J. H. Smoking and risk of psoriasis: A nationwide cohort study. \u003cem\u003eJ Am Acad Dermatol\u003c/em\u003e \u003cstrong\u003e77\u003c/strong\u003e, 573\u0026ndash;575 (2017).\u003c/li\u003e\n \u003cli\u003eArmstrong, A. W., Armstrong, E. J., Fuller, E. N., Sockolov, M. E. \u0026amp; Voyles, S. V. Smoking and pathogenesis of psoriasis: a review of oxidative, inflammatory and genetic mechanisms. \u003cem\u003eBr J Dermatol\u003c/em\u003e \u003cstrong\u003e165\u003c/strong\u003e, 1162\u0026ndash;1168 (2011).\u003c/li\u003e\n \u003cli\u003eCarey, W. \u003cem\u003eet al.\u003c/em\u003e Relapse, rebound, and psoriasis adverse events: an advisory group report. \u003cem\u003eJ Am Acad Dermatol\u003c/em\u003e \u003cstrong\u003e54\u003c/strong\u003e, S171-181 (2006).\u003c/li\u003e\n \u003cli\u003eSvendsen, M. T. \u003cem\u003eet al.\u003c/em\u003e A smartphone application supporting patients with psoriasis improves adherence to topical treatment: a randomized controlled trial. \u003cem\u003eBr J Dermatol\u003c/em\u003e \u003cstrong\u003e179\u003c/strong\u003e, 1062\u0026ndash;1071 (2018).\u003c/li\u003e\n \u003cli\u003eArmstrong, A. W., Harskamp, C. T. \u0026amp; Armstrong, E. J. Psoriasis and the risk of diabetes mellitus: a systematic review and meta-analysis. \u003cem\u003eJAMA Dermatol\u003c/em\u003e \u003cstrong\u003e149\u003c/strong\u003e, 84\u0026ndash;91 (2013).\u003c/li\u003e\n \u003cli\u003eDe Luca, D. A., Papara, C., Hawro, T. \u0026amp; Tha\u0026ccedil;i, D. Psoriasis and diabetes: a review of the pathophysiological and therapeutic interconnections. \u003cem\u003eMinerva Med\u003c/em\u003e \u003cstrong\u003e116\u003c/strong\u003e, 195\u0026ndash;222 (2025).\u003c/li\u003e\n \u003cli\u003eWorld Health Organization. Obesity and overweight. https://www.who.int/news-room/fa-ct-sheets/detail/obesity-and-overweight (2025).\u003c/li\u003e\n \u003cli\u003eMusumeci, M. L., Nasca, M. R., Boscaglia, S. \u0026amp; Micali, G. The role of lifestyle and nutrition in psoriasis: Current status of knowledge and interventions. \u003cem\u003eDermatol Ther\u003c/em\u003e \u003cstrong\u003e35\u003c/strong\u003e, e15685 (2022).\u003c/li\u003e\n \u003cli\u003eKunz, M., Simon, J. C. \u0026amp; Saalbach, A. Psoriasis: Obesity and Fatty Acids. \u003cem\u003eFront Immunol\u003c/em\u003e \u003cstrong\u003e10\u003c/strong\u003e, 1807 (2019).\u003c/li\u003e\n \u003cli\u003eHuang, Y.-H. \u003cem\u003eet al.\u003c/em\u003e Predicting the Time to Relapse Following Withdrawal from Different Biologics in Patients with Psoriasis who Responded to Therapy: A 12-Year Multicenter Cohort Study. \u003cem\u003eAm J Clin Dermatol\u003c/em\u003e \u003cstrong\u003e25\u003c/strong\u003e, 997\u0026ndash;1008 (2024).\u003c/li\u003e\n \u003cli\u003eSun, X. \u003cem\u003eet al.\u003c/em\u003e Formation and clinical effects of anti-drug antibodies against biologics in psoriasis treatment: An analysis of current evidence. \u003cem\u003eAutoimmun Rev\u003c/em\u003e \u003cstrong\u003e23\u003c/strong\u003e, 103530 (2024).\u003c/li\u003e\n\u003c/ol\u003e"},{"header":"Tables","content":"\u003cp\u003eTables 1 to 4 are available in the Supplementary Files section.\u003c/p\u003e\n"}],"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":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Psoriasis, relapse, prediction model","lastPublishedDoi":"10.21203/rs.3.rs-8777210/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8777210/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eBackground\u003c/h2\u003e \u003cp\u003eThis study collected and analyzed clinical data from patients with psoriasis, developing and validating a risk prediction model for psoriasis relapse. The aim is to improve the efficiency and accuracy of early screening for psoriasis relapse in clinical practice and to provide a reference for implementing preventive measures.\u003c/p\u003e\u003ch2\u003eObjective\u003c/h2\u003e \u003cp\u003eTo develop and validate a risk prediction model for psoriasis relapse.\u003c/p\u003e\u003ch2\u003eMethods\u003c/h2\u003e \u003cp\u003eA convenience sampling method was used to select 504 psoriasis patients admitted to a tertiary hospital in China between January 2022 and December 2024, including 353 cases in the training set and 151 cases in the test set. Independent risk factors for psoriasis relapse were identified through univariate analysis and logistic regression analysis to develop a prediction model. A nomogram and SHAP summary plot were generated for model visualization, and the model\u0026rsquo;s goodness of fit and discriminative ability were evaluated.\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e \u003cp\u003eThe one-year relapse rate of psoriasis patients after treatment was 66.67%. Logistic regression analysis identified body mass index (BMI), diabetes, biologic agent use, smoking, upper respiratory tract infection (URTI), and non-standard medication as independent risk factors for psoriasis relapse, which were included in the model. The area under the ROC curve (AUC) values for the training and testing sets were 0.767 [95% CI: 0.715\u0026ndash;0.818] and 0.704 [95% CI: 0.620\u0026ndash;0.789], respectively. The model demonstrated good discrimination and calibration, and decision curve analysis (DCA) showed significant net benefit in both the training and testing sets.\u003c/p\u003e\u003ch2\u003eConclusion\u003c/h2\u003e \u003cp\u003eThe psoriasis relapse risk prediction model developed in this study demonstrated good predictive performance. This model can serve as an effective reference for assessing the risk of psoriasis relapse and provides valuable insights for developing personalized prevention strategies for patients.\u003c/p\u003e","manuscriptTitle":"Development and validation of a prediction model for the risk of relapse in psoriasis","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-16 17:17:25","doi":"10.21203/rs.3.rs-8777210/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-03-06T23:35:13+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-04T02:10:37+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"181083523720883171120528249465963509798","date":"2026-02-16T16:04:43+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-02-11T15:27:49+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-02-11T15:17:43+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"315733854845667547096259847244398109793","date":"2026-02-10T23:42:47+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"61398149160514819240925424429042001024","date":"2026-02-10T17:57:31+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"89832287869760020357464043765197721206","date":"2026-02-10T17:56:34+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-02-10T17:51:27+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-02-05T16:19:47+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-02-05T11:15:12+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-02-04T14:37:37+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2026-02-04T14:27:51+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"1d8c0156-ae37-4ec8-9729-5381ef6b6297","owner":[],"postedDate":"February 16th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":62966085,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":62966086,"name":"Health sciences/Diseases"},{"id":62966087,"name":"Health sciences/Health care"},{"id":62966088,"name":"Health sciences/Medical research"},{"id":62966089,"name":"Health sciences/Risk factors"}],"tags":[],"updatedAt":"2026-04-13T16:05:04+00:00","versionOfRecord":{"articleIdentity":"rs-8777210","link":"https://doi.org/10.1038/s41598-026-47802-1","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2026-04-11 15:57:30","publishedOnDateReadable":"April 11th, 2026"},"versionCreatedAt":"2026-02-16 17:17:25","video":"","vorDoi":"10.1038/s41598-026-47802-1","vorDoiUrl":"https://doi.org/10.1038/s41598-026-47802-1","workflowStages":[]},"version":"v1","identity":"rs-8777210","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8777210","identity":"rs-8777210","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}