iALERTS: A Pragmatic Pilot Study of a Clinical Decision Support System for Long COVID Care

Abstract

Background: Long COVID is a significant public health challenge due to its persistent multisystem symptoms. Few structured tools exist to support clinicians in identifying, stratifying, and managing patients at risk. This study reports the pilot implementation and evaluation of iALERTS, a clinical decision support system (CDSS) developed for real-time risk stratification and longitudinal management of Long COVID. Methods: In this mixed-methods pragmatic pilot study, 148 healthcare providers underwent structured training and readiness testing. Real-world data from 120 patients with post-COVID symptoms were entered into iALERTS. Evaluation, guided by PRISM and Content-Context-Process frameworks, included descriptive statistics as well as qualitative interviews and observations to assess technical accuracy, clinical integration, and user acceptance. Results: Data completeness exceeded 98%, with 100% concordance between system predictions and clinician judgment. Common symptoms were fatigue (72%), breathlessness (54%), brain fog (39%), headache (38%), and myalgia (36%). Providers reported high confidence in accuracy (mean = 4.3), positive workflow integration (mean = 4.0), and strong user acceptance (mean = 4.2). Conclusion: iALERTS demonstrated feasibility, reliability, and strong endorsement in this pilot. Limitations include its single-center design and short duration. Further multi-site studies are needed to validate scalability and long-term utility.

Publication Title

National Journal of Community Medicine

Link to Full Text

Share

COinS