Method and System for Predicting Recurrence Risk of Myocardial Infarction in Cardiac Rehabilitation Patients by using Clinical data Lifelog data and Machine Learning Algorithm

• Main Authors: RAH HYUNG CHUL, SOMAKHAMIXAY OUI, KANG GIL WON, BANG HEUI JE
• Format: Patent
• Language: English; Korean
• Published: 29.04.2021
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATIONTECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING ORPROCESSING OF MEDICAL OR HEALTHCARE DATA; INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTEDFOR SPECIFIC APPLICATION FIELDS; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

Disclosed are a method and system for predicting the risk of recurrence of myocardial infarction in cardiac rehabilitation patients using machine learning techniques. According to an embodiment, a computer implemented method for predicting the risk of recurrence of myocardial infarction in cardiac rehabilitation patients, includes the steps of: acquiring an electronic medical record (EMR) of the cardiac rehabilitation patient and lifelog data of the cardiac rehabilitation patient measured during cardiac rehabilitation; generating a dataset to be input to a machine learning-based risk prediction model by extracting preset features from the electronic medical record and the lifelog data; determining whether the myocardial infarction of the cardiac rehabilitation patient reoccurs or myocardial infarction recurrence risk index of the cardiac rehabilitation patient from the dataset by using the machine learning-based risk prediction model; and providing a determined risk of myocardial infarction recurrence or a risk index of myocardial infarction recurrence. 머신러닝 기법을 이용하여 심장재활 환자의 심근경색 재발 위험을 예측하는 방법 및 시스템을 개시한다. 본 실시예의 일 측면에 의하면, 심장재활 환자의 심근경색 재발 위험을 예측하는 컴퓨터 구현 방법에 있어서, 심장재활 환자의 전자의무기록(electronic medical record: EMR)과 심장재활 동안에 측정된 상기 심장재활 환자의 라이프로그(lifelog) 데이터를 획득하는 단계; 상기 전자의무기록과 상기 라이프로그 데이터로부터 기설정된 특징들을 추출하여 머신러닝 기반의 위험 예측 모델에 입력할 데이터셋을 생성하는 단계; 상기 머신러닝 기반의 위험 예측 모델을 이용하여, 상기 데이터셋으로부터 상기 심장재활 환자의 심근경색 재발 위험 여부 또는 심근경색 재발 위험 지수를 결정하는 단계; 및 결정된 심근경색 재발 위험 여부 또는 심근경색 재발 위험 지수를 제공하는 단계를 제공하는 단계를 포함하는 컴퓨터 구현 방법을 제공한다.