Interpretable Deep Learning for Biological Age Prediction: A Counterfactual Approach to Personalized Health Insights

DOI

10.2991/978-94-6463-948-3_8How to use a DOI?

Keywords

Deep Learning; Time Series; Extrinsic Regression; Coun- terfactuals; Explanations

Abstract

The accurate estimation of biological age from physical activ- ity data has the potential to revolutionize personalized health monitoring and early disease detection. However, existing deep learning models of- ten lack interpretability, limiting their practical application in real-world healthcare settings. In this study, we propose an Explainable Time Series Regression (XTSR) framework that integrates deep learning with coun- terfactual reasoning to enhance model transparency and user trust. Our approach employs a hybrid Time Series Extrinsic Regression (TSER) model, trained on large-scale wearable sensor data, to predict biologi- cal age while simultaneously generating counterfactual explanations. By identifying the most influential activity patterns contributing to aging predictions, our system offers actionable recommendations for person- alized health optimization. Experimental results demonstrate that our model outperforms traditional regression methods, achieving higher ac- curacy and interpretability. This research bridges the gap between pre- dictive analytics and human-centered AI, paving the way for intelligent and user-friendly health monitoring systems that provide actionable in- sights based on individual behavior patterns….

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Bhavana Nare
PY  - 2026
DA  - 2026/01/06
TI  - Interpretable Deep Learning for Biological Age Prediction: A Counterfactual Approach to Personalized Health Insights
BT  - Proceedings of the International Conference on Sustainable Innovation with Artificial Intelligence and Machine Learning 2025 (ICSIAIML 2025)
PB  - Atlantis Press
SP  - 99
EP  - 131
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-948-3_8
DO  - 10.2991/978-94-6463-948-3_8
ID  - Nare2026
ER  -