Optimal treatment recommendations for diabetes patients using the Markov decision process along with the South Korean electronic health records

Sang-Ho Oh,Su Jin Lee,Jeonghoon Mo,Juhwan Noh

doi:10.1038/s41598-021-86419-4

Sang-Ho Oh, Su Jin Lee + Show 2 more

Open Access

https://doi.org/10.1038/s41598-021-86419-4

Copy DOI

Journal: Scientific Reports	Publication Date: Mar 25, 2021
Citations: 8	License type: open-access

Affiliation: Yonsei University, Korean Red Cross

Abstract

The extensive utilization of electronic health records (EHRs) and the growth of enormous open biomedical datasets has readied the area for applications of computational and machine learning techniques to reveal fundamental patterns. This study’s goal is to develop a medical treatment recommendation system using Korean EHRs along with the Markov decision process (MDP). The sharing of EHRs by the National Health Insurance Sharing Service (NHISS) of Korea has made it possible to analyze Koreans’ medical data which include treatments, prescriptions, and medical check-up. After considering the merits and effectiveness of such data, we analyzed patients’ medical information and recommended optimal pharmaceutical prescriptions for diabetes, which is known to be the most burdensome disease for Koreans. We also proposed an MDP-based treatment recommendation system for diabetic patients to help doctors when prescribing diabetes medications. To build the model, we used the 11-year Korean NHISS database. To overcome the challenge of designing an MDP model, we carefully designed the states, actions, reward functions, and transition probability matrices, which were chosen to balance the tradeoffs between reality and the curse of dimensionality issues.

Highlights

Medical treatment can be viewed as a series of interactions between patients and doctors
We proposed an Markov decision process (MDP)-based treatment recommendation system for diabetic patients
To overcome the challenge of designing an MDP model, we carefully designed the states, actions, reward functions, and transition probability matrices, that were chosen to balance the trade-offs between reality and the curse of dimensionality issues

Summary

Introduction

Medical treatment can be viewed as a series of interactions between patients and doctors. The system decides to recommend whether to use single, double, or triple therapy of diabetes medication according to the state of diabetes patient. While a few previous studies have evaluated the medical recommendations for diabetes through M DP8–11,21, despite the challenges of MDP, their models only considered a few states and actions while proposing recommendations. To overcome these challenges, we increased the number of states and actions to as many as possible, so as to contain more information on patients and to provide various choices of recommendations for treating diabetes. We recommended appropriate medication according to the state of patient by our MDP model. We proved diabetic complication occurrence can be delayed by our MDP medical recommendations

Objectives

Methods

Results

Conclusion