AdaCare: Explainable Clinical Health Status Representation Learning via Scale-Adaptive Feature Extraction and Recalibration

Authors

  • Liantao Ma Peking University
  • Junyi Gao Key Laboratory of High Confidence Software Technologies
  • Yasha Wang Peking University
  • Chaohe Zhang Peking University
  • Jiangtao Wang Lancaster University
  • Wenjie Ruan Lancaster University
  • Wen Tang Peking University Third Hospital
  • Xin Gao Peking University
  • Xinyu Ma Peking University

DOI:

https://doi.org/10.1609/aaai.v34i01.5427

Abstract

Deep learning-based health status representation learning and clinical prediction have raised much research interest in recent years. Existing models have shown superior performance, but there are still several major issues that have not been fully taken into consideration. First, the historical variation pattern of the biomarker in diverse time scales plays a vital role in indicating the health status, but it has not been explicitly extracted by existing works. Second, key factors that strongly indicate the health risk are different among patients. It is still challenging to adaptively make use of the features for patients in diverse conditions. Third, using prediction models as the black box will limit the reliability in clinical practice. However, none of the existing works can provide satisfying interpretability and meanwhile achieve high prediction performance. In this work, we develop a general health status representation learning model, named AdaCare. It can capture the long and short-term variations of biomarkers as clinical features to depict the health status in multiple time scales. It also models the correlation between clinical features to enhance the ones which strongly indicate the health status and thus can maintain a state-of-the-art performance in terms of prediction accuracy while providing qualitative interpretability. We conduct a health risk prediction experiment on two real-world datasets. Experiment results indicate that AdaCare outperforms state-of-the-art approaches and provides effective interpretability, which is verifiable by clinical experts.

Downloads

Published

2020-04-03

How to Cite

Ma, L., Gao, J., Wang, Y., Zhang, C., Wang, J., Ruan, W., Tang, W., Gao, X., & Ma, X. (2020). AdaCare: Explainable Clinical Health Status Representation Learning via Scale-Adaptive Feature Extraction and Recalibration. Proceedings of the AAAI Conference on Artificial Intelligence, 34(01), 825-832. https://doi.org/10.1609/aaai.v34i01.5427

Issue

Section

AAAI Technical Track: Applications