Prediction of Chronic Diseases With Multi-Label Neural Network

Ruiquan Ge,Pu Wang,Renfeng Zhang

doi:10.1109/access.2020.3011374

Abstract

Chronic diseases have seriously affected human activities, especially in many developing countries and underdeveloped countries. The long duration of chronic diseases and the high cost of medical care have placed a huge economic burden on society and families. Meanwhile, chronic patients tend to have a variety of complications over time. So, it is difficult for doctors to find effective diagnosis and appropriate treatment. Machine learning techniques can integrate their heterogeneous data of various body indicators. Meanwhile, for chronic patients, multi-label learning methods can be used to help doctors identify the types of the chronic diseases. This paper proposes a novel multi-label neural network method (ML-NN) to predict the chronic diseases combining neural network and multi-label learning technology based on cross entropy lost function and backward propagation algorithm. Compared with 14 traditional multi-label learning methods on 10 chronic diseases and 19733 patients, the proposed method achieved a consistently best in 5 performance measurements. The results demonstrate the proposed method can effectively predict chronic diseases and assist doctors to diagnose and treat patients.

Highlights

Chronic diseases are known as noncommunicable diseases (NCDs), which are distinguished by a long duration and slow development
The burden of diseases caused by chronic diseases accounts a large proportion of the total diseases, and the number of deaths caused by chronic diseases is gradually increasing [4]
Just like the data preprocessing in [19], the experimental dataset was randomly divided into three subsets according to the standard machine learning algorithm, in which the training set was used for model learning, the verification set for parameter adjustment and model selection, and the test set for results comparison between models [44]

Summary

Introduction

Chronic diseases are known as noncommunicable diseases (NCDs), which are distinguished by a long duration and slow development. The long duration of chronic diseases and the high cost of medical care have placed a huge economic burden on society and families [2]. The situation of prevention and treatment of chronic diseases in all countries is still severe, especially in low- and middle-income countries [3]. The burden of diseases caused by chronic diseases accounts a large proportion of the total diseases, and the number of deaths caused by chronic diseases is gradually increasing [4]. Because chronic diseases with complex causes often develop into complications, it is difficult for doctors to find appropriate treatment.

Methods

Results

Conclusion