Development and assessment of a mobile app for early psoriasis symptom detection

Thesis Abstract

Psoriasis is a chronic inflammatory skin condition characterized by unpredictable flare-ups that significantly impact patients’ quality of life, yet early detection remains a challenge due to limited awareness and access to dermatological care, particularly in remote or resource-constrained settings. This study aims to develop and empirically assess a mobile application designed for the early detection of psoriasis symptoms to facilitate timely intervention and improve disease management. The primary objectives include designing a user-friendly app incorporating symptom recognition algorithms, evaluating its usability and accuracy, and determining its effectiveness in early diagnosis through a comprehensive field trial. The research adopts a mixed-methods approach, combining quantitative validation with qualitative usability assessment, underpinned by the Technology Acceptance Model (TAM) and the Health Belief Model (HBM) as the theoretical frameworks guiding user engagement and health behavior change. The study population comprises 500 adult participants within the dermatological outpatient clinics of urban tertiary hospitals, selected via stratified random sampling to ensure diverse demographic representation. The sample is divided into two groups 250 individuals with clinically diagnosed psoriasis and 250 healthy controls with no history of dermatological conditions. Data collection instruments include a customized symptom recognition questionnaire, usability and satisfaction surveys, and clinical dermatological assessments validated by expert dermatologists. The mobile app’s diagnostic accuracy will be evaluated through Receiver Operating Characteristic (ROC) curve analysis, sensitivity, specificity, and predictive values, while user acceptability and engagement will be analyzed using thematic analysis of interview transcripts and descriptive statistics. The study anticipates that the developed mobile app will demonstrate high diagnostic sensitivity (above 85%) and specificity (above 80%) in identifying early psoriasis symptoms, with a weighted kappa coefficient indicating moderate to substantial agreement with clinical diagnoses. Usability testing is expected to reveal positive user perceptions, with over 80% of participants rating the app as easy to use, engaging, and informative. Analysis of qualitative data will uncover key themes related to barriers and facilitators to app adoption, aligning with the constructs of TAM and HBM. The findings will also provide insights into user trust, perceived severity, and self-efficacy concerning psoriasis symptom recognition facilitated by digital health tools. This research will contribute novel evidence to the field of digital dermatology by demonstrating that mobile health interventions, grounded in behavioral theory, can enhance early disease detection and health literacy for psoriasis patients. It advances current knowledge by integrating diagnostic algorithms with user-centered design, ensuring practical relevance and scalability. The study's outcomes will inform policymakers and healthcare providers about the viability of mobile apps in augmenting dermatological services, especially in underserved populations. Additionally, it will lay the groundwork for future longitudinal studies examining the long-term impact of mobile-based early detection on disease progression, patient outcomes, and healthcare utilization. In conclusion, the study affirms that a systematically developed, theory-driven mobile app can effectively support early psoriasis symptom detection, foster user engagement, and promote timely clinical interventions. Recommendations include integrating the app into existing teledermatology platforms, prioritizing privacy and data security, and expanding app functionality based on user feedback to encompass educational resources and self-monitoring tools. Further research should explore scalability, cost-effectiveness, and integration with electronic health records to optimize the deployment of mobile health solutions across diverse healthcare settings.