Evaluating the Effectiveness of AI-Enhanced Telehealth Systems on Chronic Disease Management

The integration of artificial intelligence (AI) into telehealth platforms has emerged as a promising strategy to address the growing burden of chronic disease management worldwide. This review synthesizes evidence from researchers, examining AI-enhanced telehealth systems deployed for diabetes, cardiovascular disease, chronic respiratory conditions, and mental health comorbidities. Findings indicate that AI-augmented remote monitoring and decision-support tools are associated with clinically meaningful improvements in biomarker control, reduced hospital readmission rates, and enhanced patient self-management behaviors. AI-driven continuous glucose monitoring systems have shown potential to HbA1c reductions of 0.5 to 1.1% in randomized trials. Remote ECG analysis with machine-learning-based arrhythmia detection has reduced missed diagnoses of atrial fibrillation by up to 37% compared with standard care. Conversational AI agents for mental health management have shown modest but statistically significant reductions in Patient Health Questionnaire-9 (PHQ-9) depression scores. However, persistent barriers, including digital health literacy gaps, algorithmic bias, interoperability challenges, and short study follow-up periods, temper the strength of conclusions. Equity concerns demand urgent attention, as underserved populations risk being further marginalized by AI-telehealth deployment. This review calls for standardized evaluation frameworks, long-term real-world evidence, and an equity-centred research agenda.