Research map / Large language models / AI and society
A Hybrid AI Framework for Sensor-Based Personal Health Monitoring towards Precision Health
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes a hybrid neuro-symbolic AI framework (agent-based BDI architecture combining ML, ontologies, knowledge graphs and Bayesian networks) for sensor-based personal health monitoring, demonstrated on atrial fibrillation detection in a doctoral-symposium style progress report.
Problem
Sensor-based personal health monitoring systems lack interoperability of health data and processes, prediction of future health states, and uncertainty management.
Approach
A reusable hybrid AI architecture that integrates data-driven ML with knowledge-driven ontologies, fuzzy inference and Bayesian networks inside a Beliefs-Desires-Intentions agent framework, to detect and predict health situations and support decisions with explainability and uncertainty handling.
Key results
- Machine learning models were developed to detect atrial fibrillation and distinguish it from other arrhythmias from ECG signals, with no numeric results reported in this paper.
- A Bayesian network was shown to enhance explainability of ML outputs in prior work by the same group (Wanyana et al. 2022, 2023), per the paper.
Limitations
- Current progress is limited to the AF use case; the stress monitoring phase is future work.
- No quantitative evaluation results are reported in the paper.
Experimental setup
Builds on: Beliefs-Desires-Intentions neuro-symbolic AI
Closest papers by meaning
- Beyond Sensor Data: Foundation Models of Behavioral Data from Wearables Improve Health Predictions (ICML 2025 · similarity 0.84)
- OpenMHC: Accelerating the Science of Wearable Foundation Models (NeurIPS 2026 · similarity 0.83)
- Large-scale Training of Foundation Models for Wearable Biosignals (ICLR 2024 · similarity 0.81)
- SensorLM: Learning the Language of Wearable Sensors (NeurIPS 2025 · similarity 0.80)
- Scaling Wearable Foundation Models (ICLR 2025 · similarity 0.79)
- Statistically Valid Post-Deployment Monitoring Should Be Standard for AI-Based Digital Health (NeurIPS 2025 · similarity 0.79)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.