Development and Assessment of a Mobile App for Early Psoriasis Detection

Thesis Abstract

Psoriasis, a chronic inflammatory skin condition characterized by distinctive scaling and erythematous plaques, often remains undiagnosed in its early stages, leading to delayed treatment and increased disease burden. This study addresses the critical need for an accessible, reliable, and user-friendly digital solution to facilitate early detection of psoriasis among high-risk populations. The primary aim is to develop, implement, and evaluate a mobile health application designed to assist laypersons and healthcare providers in the preliminary identification of psoriasis symptoms. Specific objectives include designing a user-centered mobile app incorporating symptom recognition algorithms, validating its diagnostic accuracy through empirical testing, and assessing its usability and acceptance among potential users. The study adopts a mixed-methods research design, combining quantitative validation with qualitative usability evaluation. The quantitative component involves a cross-sectional validation study with a sample size of 300 participants recruited from dermatology clinics and community health centers, comprising 150 confirmed psoriasis patients and 150 controls with other dermatological conditions or healthy skin. Data collection employed standardized dermatological assessments, high-resolution skin images, and the app's symptom-checking outputs. The app's diagnostic accuracy is evaluated through statistical techniques including sensitivity, specificity, positive predictive value, and negative predictive value, analyzed via Receiver Operating Characteristic (ROC) curve analysis and logistic regression modeling. Qualitative data on usability and user acceptance are gathered through semi-structured interviews with 30 participants, analyzed thematically using NVivo software. Key expected findings include a diagnostic accuracy exceeding 85% sensitivity and 80% specificity, demonstrating the app's potential as an early screening tool. The analysis is anticipated to reveal high user satisfaction and ease of use, corroborated by qualitative feedback emphasizing intuitive interface design and perceived usefulness. The validation process is also expected to identify specific symptom patterns and image features that contribute most significantly to accurate detection, informing future refinement of the algorithms. This research contributes new knowledge by integrating dermatological expertise, mobile health technology, and user-centered design to address a persistent gap in early psoriasis detection. It advances understanding of how mobile applications can support early diagnosis and management, particularly in resource-limited settings where access to dermatologists is constrained. Furthermore, the study proposes a conceptual framework grounded in the Health Belief Model and Technology Acceptance Model (TAM), elucidating factors influencing user engagement and adherence to app-guided screening. The study concludes that a well-designed mobile application can effectively support early psoriasis detection with satisfactory diagnostic performance and high user acceptability. Recommendations from the findings include integrating the app within primary healthcare workflows, conducting longitudinal studies to evaluate long-term impact, and expanding functionalities to include educational resources and teleconsultation features. Ultimately, the research emphasizes the potential of mobile health solutions to transform dermatological care by enabling timely diagnosis and empowering individuals for proactive skin health management.