RESUMO
BACKGROUND: Psoriasis vulgaris (PsV) and psoriatic arthritis (PsA) are complex, multifactorial diseases significantly impacting health and quality of life. Predicting treatment response and disease progression is crucial for optimizing therapeutic interventions, yet challenging. Automated machine learning (AutoML) technology shows promise for rapidly creating accurate predictive models based on patient features and treatment data. OBJECTIVE: This study aims to develop highly accurate machine learning (ML) models using AutoML to address key clinical questions for PsV and PsA patients, including predicting therapy changes, identifying reasons for therapy changes, and factors influencing skin lesion progression or an abnormal Bath Ankylosing Spondylitis Disease Activity Index (BASDAI) score. METHODS: Clinical study data from 309 PsV and PsA patients were extensively prepared and analyzed using AutoML to build and select the most accurate predictive models for each variable of interest. RESULTS: Therapy change at 24 weeks follow-up was modeled using the extreme gradient boosted trees classifier with early stopping (area under the receiver operating characteristic curve [AUC] of 0.9078 and logarithmic loss [LogLoss] of 0.3955 for the holdout partition). Key influencing factors included the initial systemic therapeutic agent, the Classification Criteria for Psoriatic Arthritis score at baseline, and changes in quality of life. An average blender incorporating three models (gradient boosted trees classifier, ExtraTrees classifier, and Eureqa generalized additive model classifier) with an AUC of 0.8750 and LogLoss of 0.4603 was used to predict therapy changes for 2 hypothetical patients, highlighting the significance of these factors. Treatments such as methotrexate or specific biologicals showed a lower propensity for change. An average blender of a random forest classifier, an extreme gradient boosted trees classifier, and a Eureqa classifier (AUC of 0.9241 and LogLoss of 0.4498) was used to estimate PASI (Psoriasis Area and Severity Index) change after 24 weeks. Primary predictors included the initial PASI score, change in pruritus levels, and change in therapy. A lower initial PASI score and consistently low pruritus were associated with better outcomes. BASDAI classification at onset was analyzed using an average blender of a Eureqa generalized additive model classifier, an extreme gradient boosted trees classifier with early stopping, and a dropout additive regression trees classifier with an AUC of 0.8274 and LogLoss of 0.5037. Influential factors included initial pain, disease activity, and Hospital Anxiety and Depression Scale scores for depression and anxiety. Increased pain, disease activity, and psychological distress generally led to higher BASDAI scores. CONCLUSIONS: The practical implications of these models for clinical decision-making in PsV and PsA can guide early investigation and treatment, contributing to improved patient outcomes.
RESUMO
BACKGROUND: Psoriasis has a negative impact on patients' physical and mental health and can lead to anxiety and depression. Disease management strategies, including educational programs and eHealth devices, have been shown to improve health care for several chronic diseases. However, such disease management strategies are lacking in the routine care of patients with psoriasis. OBJECTIVE: This study aims to study the impact of a novel intervention that combines an educational program with a disease management smartphone app on the mental health of patients with psoriasis. METHODS: Patients with psoriasis in the intervention group received an educational program; attended visits on weeks 0, 12, 24, 36, and 60; and had access to the study app. Patients in the control group only attended the visits. The primary endpoint was a significant reduction of scores on the Hospital Anxiety and Depression Scale (HADS). Secondary end points were reductions in Dermatology Life Quality Index score, Psoriasis Area and Severity Index score, pruritus, and pain, as well as improvements in mood and daily activities. In addition, modulating effects of sex, age, disease duration, and app use frequency were evaluated. RESULTS: A total of 107 patients were included in the study and randomized into the control group (53/107, 49.5%) or intervention group (54/107, 50.5%). Approximately 71.9% (77/107) of the patients completed the study. A significant reduction in HADS-Depression (HADS-D) in the intervention group was found at weeks 12 (P=.04) and 24 (P=.005) but not at weeks 36 (P=.12) and 60 (P=.32). Patient stratification according to app use frequency showed a significant improvement in HADS-D score at weeks 36 (P=.004) and 60 (P=.04) and in HADS-Anxiety (HADS-A) score at weeks 36 (P=.04) and 60 (P=.05) in the group using the app less than once every 5 weeks. However, in patients using the app more than once every 5 weeks, no significant reduction in HADS-D (P=.84) or HADS-A (P=.20) score was observed over the 60-week study period compared with that observed in patients in the control group. All findings were independent of sex, age, and disease duration. CONCLUSIONS: These findings support the use of a disease management smartphone app as a valid tool to achieve long-term improvement in the mental health of patients with psoriasis if it is not used too frequently. Further studies are needed to analyze the newly observed influence of app use frequency. TRIAL REGISTRATION: Deutsches Register Klinischer Studien DRKS00020755; https://tinyurl.com/nyzjyvvk.