Decision-Making Logic Model for Risk Stratification Using iALERTS (Informatics Analytics for Long-Term Evaluation and Repercussions Tracking Of SARS-Cov-2 Infection)

Background: Long COVID presents a significant public health challenge with its wide-ranging and persistent symptoms. However, there remains a lack of structured tools to identify, stratify, and manage individuals at risk of Long COVID. This study aims to develop the decision-making logic model for risk stratification using iALERTS platform. Methods: This is a mixed-methods, quasi-experimental study. Data were collected from 684 adults with confirmed COVID-19 who were at least 12 weeks post-recovery. A validated survey captured sociodemographic data, clinical history, anthropometry, vaccination status, and a comprehensive symptom profile. A rule-based decision-making logic model was embedded within iALERTS, incorporating ten key factors to generate individualized risk assessments. Results: Fatigue (80.8%), cough (83.3%), cognitive dysfunction (68.3%) and myalgia (74.3 %) were the most common persistent symptoms. High-risk groups included females, older adults, individuals with obesity, unvaccinated participants, and those hospitalized or admitted to ICU during acute infection. The logic model enabled automated risk stratification into low, moderate, or high categories, guiding clinical recommendations for monitoring, referrals, and rehabilitation. Conclusion: The iALERTS platform offers a novel informatics-driven solution for risk stratification and management of Long COVID. Its decision logic integrates validated clinical and demographic predictors with real-time symptom data.