JMIR Human Factors · Published 2026-05-04 · DOI 10.2196/84802
Abstract BackgroundEffective health monitoring is essential for personalized care and comprehensive health assessment. Personal health indices and profiles offer a concise summary of an individual’s overall health, supporting both clinical decision-making and self-management. However, global standardization remains challenging due to diverse practices and data formats across countries. ObjectiveThis study aimed to present a novel model for computing a personal health index and health profile using the International Classification of Functioning, Disability and Health (ICF) framework. The model was designed to handle incomplete and heterogeneous datasets and aimed to provide standardized, interpretable health metrics. MethodsWe developed a recursive algorithm that calculates the health index based on the hierarchical structure of the ICF, using all available measurements. The model incorporates time decay and linkage reliability to weight input data. Preliminary validation was conducted on data from 505 individuals, using statistical correlation analyses with self-assessed health measures (EuroQol Visual Analogue Scale and pain ratings), and a sensitivity analysis was performed to assess model robustness. ResultsThe computed health index showed moderate positive correlations with EuroQol Visual Analogue Scale scores (all P ConclusionsThe proposed model offers a flexible and scientifically grounded approach to computing personal health indices and profiles within the ICF framework. It enables the integration of diverse health data sources and supports the visual representation for clinical and personal use. This model has potential applications in health monitoring, rehabilitation planning, and machine learning–based health informatics.
Abstract from DOAJ. Public domain (CC0 1.0).
Read the article at the publisher →