CDR-Detector: a chronic disease risk prediction model combining pre-training with deep reinforcement learning
Abstract Chronic disease risk prediction based on electronic health record (EHR) is an important research direction of Internet healthcare. Current studies mainly focused on developing well-designed deep learning models to predict the disease risk based on large-scale and high-quality longitudinal E...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2024-12-01
|
| Series: | Complex & Intelligent Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s40747-024-01697-5 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832571187960479744 |
|---|---|
| author | Shaofu Lin Shiwei Zhou Han Jiao Mengzhen Wang Haokang Yan Peng Dou Jianhui Chen |
| author_facet | Shaofu Lin Shiwei Zhou Han Jiao Mengzhen Wang Haokang Yan Peng Dou Jianhui Chen |
| author_sort | Shaofu Lin |
| collection | DOAJ |
| description | Abstract Chronic disease risk prediction based on electronic health record (EHR) is an important research direction of Internet healthcare. Current studies mainly focused on developing well-designed deep learning models to predict the disease risk based on large-scale and high-quality longitudinal EHR data. However, in real-world scenarios, people’s medical habits and low prevalence of diseases often lead to few-shot and imbalanced longitudinal EHR data. This has become an urgent challenge for chronic disease risk prediction based on EHR. Aiming at this challenge, this study combines EHR based pre-training and deep reinforcement learning to develop a novel chronic disease risk prediction model called CDR-Detector. The model adopts the Q-learning architecture with a custom reward function. In order to improve the few-shot learning ability of model, a self-adaptive EHR based pre-training model with two new pre-training tasks is developed to mine valuable dependencies from single-visit EHR data. In order to solve the problem of data imbalance, a dual experience replay strategy is realized to help the model select representative data samples and accelerate model convergence on the imbalanced EHR data. A group of experiments have been conducted on real personal physical examination data. Experimental results show that, compared with the existing state-of-art methods, the proposed CDR-Detector has better accuracy and robustness on the few-shot and imbalanced EHR data. |
| format | Article |
| id | doaj-art-a025377b1d8346eba0e1f8cb3e372773 |
| institution | Kabale University |
| issn | 2199-4536 2198-6053 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Springer |
| record_format | Article |
| series | Complex & Intelligent Systems |
| spelling | doaj-art-a025377b1d8346eba0e1f8cb3e3727732025-02-02T12:48:44ZengSpringerComplex & Intelligent Systems2199-45362198-60532024-12-0111111410.1007/s40747-024-01697-5CDR-Detector: a chronic disease risk prediction model combining pre-training with deep reinforcement learningShaofu Lin0Shiwei Zhou1Han Jiao2Mengzhen Wang3Haokang Yan4Peng Dou5Jianhui Chen6College of Computer Science, Beijing University of TechnologyCollege of Computer Science, Beijing University of TechnologyBeijing International Collaboration Base on Brain Informatics and Wisdom Services, Beijing University of TechnologyCyber Security and Informatization Office, Tianjin Chengjian UniversityCollege of Computer Science, Beijing University of TechnologyDepartment of Water Resources, Beijing Water Science and Technology InstituteBeijing International Collaboration Base on Brain Informatics and Wisdom Services, Beijing University of TechnologyAbstract Chronic disease risk prediction based on electronic health record (EHR) is an important research direction of Internet healthcare. Current studies mainly focused on developing well-designed deep learning models to predict the disease risk based on large-scale and high-quality longitudinal EHR data. However, in real-world scenarios, people’s medical habits and low prevalence of diseases often lead to few-shot and imbalanced longitudinal EHR data. This has become an urgent challenge for chronic disease risk prediction based on EHR. Aiming at this challenge, this study combines EHR based pre-training and deep reinforcement learning to develop a novel chronic disease risk prediction model called CDR-Detector. The model adopts the Q-learning architecture with a custom reward function. In order to improve the few-shot learning ability of model, a self-adaptive EHR based pre-training model with two new pre-training tasks is developed to mine valuable dependencies from single-visit EHR data. In order to solve the problem of data imbalance, a dual experience replay strategy is realized to help the model select representative data samples and accelerate model convergence on the imbalanced EHR data. A group of experiments have been conducted on real personal physical examination data. Experimental results show that, compared with the existing state-of-art methods, the proposed CDR-Detector has better accuracy and robustness on the few-shot and imbalanced EHR data.https://doi.org/10.1007/s40747-024-01697-5Chronic risk predictionData imbalanceElectronic health recordsFew-shot learningReinforcement learning |
| spellingShingle | Shaofu Lin Shiwei Zhou Han Jiao Mengzhen Wang Haokang Yan Peng Dou Jianhui Chen CDR-Detector: a chronic disease risk prediction model combining pre-training with deep reinforcement learning Complex & Intelligent Systems Chronic risk prediction Data imbalance Electronic health records Few-shot learning Reinforcement learning |
| title | CDR-Detector: a chronic disease risk prediction model combining pre-training with deep reinforcement learning |
| title_full | CDR-Detector: a chronic disease risk prediction model combining pre-training with deep reinforcement learning |
| title_fullStr | CDR-Detector: a chronic disease risk prediction model combining pre-training with deep reinforcement learning |
| title_full_unstemmed | CDR-Detector: a chronic disease risk prediction model combining pre-training with deep reinforcement learning |
| title_short | CDR-Detector: a chronic disease risk prediction model combining pre-training with deep reinforcement learning |
| title_sort | cdr detector a chronic disease risk prediction model combining pre training with deep reinforcement learning |
| topic | Chronic risk prediction Data imbalance Electronic health records Few-shot learning Reinforcement learning |
| url | https://doi.org/10.1007/s40747-024-01697-5 |
| work_keys_str_mv | AT shaofulin cdrdetectorachronicdiseaseriskpredictionmodelcombiningpretrainingwithdeepreinforcementlearning AT shiweizhou cdrdetectorachronicdiseaseriskpredictionmodelcombiningpretrainingwithdeepreinforcementlearning AT hanjiao cdrdetectorachronicdiseaseriskpredictionmodelcombiningpretrainingwithdeepreinforcementlearning AT mengzhenwang cdrdetectorachronicdiseaseriskpredictionmodelcombiningpretrainingwithdeepreinforcementlearning AT haokangyan cdrdetectorachronicdiseaseriskpredictionmodelcombiningpretrainingwithdeepreinforcementlearning AT pengdou cdrdetectorachronicdiseaseriskpredictionmodelcombiningpretrainingwithdeepreinforcementlearning AT jianhuichen cdrdetectorachronicdiseaseriskpredictionmodelcombiningpretrainingwithdeepreinforcementlearning |