Currently submitted to: JMIR Human Factors
Date Submitted: Oct 8, 2025
(closed for review but you can still tweet)
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Monitoring Health Status: Development and Preliminary Validation of a Personal Health Index Based on the International Classification of Functioning, Disability and Health
ABSTRACT
Background:
Effective 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.
Objective:
This study presents 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 is designed to handle incomplete and heterogeneous datasets and aims to provide standardized, interpretable health metrics.
Methods:
We 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 using statistical correlation analyses with self-assessed health measures (EQ-VAS and pain ratings), and a sensitivity analysis was performed to assess model robustness.
Results:
The computed health index showed moderate positive correlations with EQ-VAS scores and negative correlations with maximum pain trajectories, supporting its validity. Sensitivity analysis confirmed predictable behavior in response to input changes, and the model demonstrated resilience to missing data.
Conclusions:
The proposed model offers a flexible and scientifically grounded approach to computing personal health indices and profiles within the ICF framework. It enables integration of diverse health data sources and supports visual representation for clinical and personal use. This model has potential applications in health monitoring, rehabilitation planning, and machine learning-based health informatics.
Citation
