Comorbidity network analysis and deep learning prediction of medical expenses based on health insurance data
10.3969/j.issn.1671-8348.2024.24.002
- VernacularTitle:基于健康保险数据的医疗费用共病网络分析及深度学习预测
- Author:
Yuwen CAO
1
;
Hao MEI
;
Jiayi SUN
;
Jiongyu HU
;
Yaqing XU
Author Information
1. 中国人民大学应用统计科学研究中心,北京 100872;中国人民大学统计学院,北京 100872
- Keywords:
chronic disease management;
health insurance data;
disease network;
deep learning;
medical expenses prediction
- From:
Chongqing Medicine
2024;53(24):3686-3691
- CountryChina
- Language:Chinese
-
Abstract:
Objective To construct a comorbidity network for medical expenses by analyzing the rele-vant medical records,and to construct a deep learning prediction model by combining with the disease net-works and long short-term memory neural networks in order to improve the accuracy of individual medical ex-pense prediction and provide the assistance for optimizing the medical policies and enhancing the patient health management level.Methods Based on the medical records of Taiwan,China Health Insurance Research Data-base during 2000-2013,the data of 5.84 million visits from 9 963 patients were analyzed,and a comorbidity network of medical expenses for 104 common diseases was constructed.The network structure was analyzed and the potential comorbidity was predicted,and the deep learning model of individual medical cost was con-structed by combining the input of patient's gender,age,medical history and other information.Results The constructed medical cost comorbidity network consists of 104 nodes,3 390 edges and 6 modules,and is a high-ly connected network with nodes,indicating that the medical costs possesses the high correlation between dis-eases.The constructed deep learning prediction model significantly improves the prediction accuracy compared to the traditional regression models and deep learning models that do not fully consider the comorbidity infor-mation.Conclusion The constructed model provides a new theoretical perspective for understanding the co-morbidity of diseases,as well as an effective tool for accurately predicting medical costs,optimizing medical re-source allocation and achieving the personalized medical services.
