Digital Health in clinical practice: an example of an expert system for heart failure management

Clinical Decision Support Systems (CDSS) are fundamental tools for assisting physicians in the decision-making process, thanks to their ability to analyze clinical data and provide diagnostic or therapeutic recommendations. The literature classifies them mainly as knowledge-based systems, which employ IF-THEN rules grounded in expert clinical experience, and machine learning systems, which use statistical models to identify data patterns. Despite their potential, CDSS face limitations hindering their effectiveness and adoption. Many focus solely on single pathologies, overlooking the complexity of comorbidities and the patient’s multidimensional nature. Moreover, a lack of interoperability often necessitates manual data entry, risking errors and incomplete information, which negatively impacts performance. Physician diffidence, stemming from technical issues and perceived limited control, further impedes their uptake. Addressing Digital Health (DH) needs requires evolving CDSS toward greater interoperability, telemedicine integration, multidisciplinary management, and personalized care. Of particular interest is the ongoing challenge of automatically and dynamically calculating individual patient risk for complications or worsening of clinical conditions. This relies on processing real-time data from vital signs, health records, and questionnaires. Integrating this information into a Medical Expert System (MES) could significantly enhance clinical decision support. This article focuses MES characteristics and their role in DH, showing a telemedicine application for managing complex chronic heart failure patients.