EMR 데이터를 활용한 욕창 발생 방지 및 데이터 처리 방법
Method of preventing Pressure Ulcer and EMR data preprocess
4
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
본 논문에서는 MIMIC-IV(Medical Information Mart for Intensive Care) v2.0 데이터를 이용한 시계열 데이터의 정제 및 가공 방법을 제안한다. 더불어 해당 가공법을 기반으로 정제한 데이터셋을활용하여 구축한 기계학습 기반의 욕창 조기 경보 시스템을 통해 해당 가공 방법의 유의성을 검증하였다. 구현된 욕창 조기 경보 시스템은 병변이 발생하기 전 12, 24시간에 미리 의료진에게 경보를 주는 시스템이다. 전자의무기록(Electronic Medical Record; EMR) 시스템과 연동하여 실시간으로 환자의 욕창 발생 위험도를 의료진에게 알려 중환자 의사결정을 지원하고, 나아가 효율적인의료 자원 배분을 가능하게 한다. 여러 기계학습 모델 중 GRU 모델을 사용하였을 때, AUROC 평가지표를 기준으로 발생 전 12시간이 0.831, 24시간이 0.822로 가장 좋은 성능을 보였다.
Abstract
This paper proposes a method of refining and processing time-series data using Medical Information Mart for Intensive Care (MIMIC-IV) v2.0 data. In addition, the significance of the processing method was validated through a machine learning-based pressure ulcer early warning system using a dataset processed based on the proposed method. The implemented system alerts medical staff in advance 12 and 24 hours before a lesion occurs. In conjunction with the Electronic Medical Record (EMR) system, it informs the medical staff of the risk of a patient's pressure ulcer development in real-time to support a clinical decision, and further, it enables the efficient allocation of medical resources. Among several machine learning models, the GRU model showed the best performance with AUROC of 0.831 for 12 hours and 0.822 for 24 hours.
참고문헌 (15)
- In Sook Cho, "Formative Evaluation of Standard Terminology-based Electronic Nursing Record System in Clinical Setting", Journal of Korean Socirety of Medical Informatics, 9(4), pp.413~421 (2003)[DOI]
- Chung Hee Lee, "A Study on the Effects of EMR on Nursing Documentation", Journal of Korean Society of Medical Informatics, 6(4), pp.87~97 (2000)[DOI]
- Johnson, A, "MIMIC-III, a freely accessible critical care database", Sci Data, 3, pp.160035~ (2016)[DOI]
- Alistair E W Johnson, "The MIMIC Code Repository: enabling reproducibility in critical care research", Journal of the American Medical Informatics Association, 25(1), pp.32~39 (2018)[DOI]
- Sanjay Purushotham, "Benchmarking deep learning models on large healthcare datasets", Journal of Biomedical Informatics, 83, pp.112~134 (2018)[DOI]
- Shirly Wang, "MIMIC-Extract: a data extraction, preprocessing, and representation pipeline for MIMIC-III", Association for Computing Machinery, CHIL '20, pp.222~235 (2020)
- Shengpu Tang, "Democratizing EHR analyses with FIDDLE: a flexible data-driven preprocessing pipeline for structured clinical data", Journal of the American Medical Informatics Association, 27(12), pp.1921~1934 (2020)[DOI]
- 박슬기, "전자건강기록 데이터 기반 욕창 발생 예측모델의 개발 및 평가", Journal of Korean Academy of Nursing, 49(5), pp.575~585 (2019), 한국간호과학회[DOI]
- Walther, F, "Prediction of inpatient pressure ulcers based on routine healthcare data using machine learning methodology", Sci Rep, 12(5044) (2022)[DOI]
- Cramer EM, "Predicting the Incidence of Pressure Ulcers in the Intensive Care Unit Using Machine Learning", EGEMS, 7(1), pp.49~ (2019)[DOI]
- Knaus WA, "APACHE II: a severity of disease classification system", Critical Care Medicine, 13(10), pp.818~829 (1985)
- Nassar, A.P, "Evaluation of simplified acute physiology score 3 performance: a systematic review of external validation studies", Crit Care, 18, pp.R117~ (2014)[DOI]
- Simon Lebech Cichosz, "Prediction of In-Hospital Pressure Ulcer Development", Advances in Wound Care, 8(1), pp.1~6 (2019)[DOI]
- 조인숙, "욕창발생 예측도구 개발을 위한 전자간호기록데이터 이용 가능성", Healthcare Informatics Research, 14(2), pp.161~168 (2008), 대한의료정보학회
- Goldberger, A, "MIMIC-IV (version 2.0)", PhysioNet, ~