대한신장학회

Skip Navigation: Skip to contents

KOR
ENG
전체메뉴보기

간행물 검색

현재 페이지 경로

HOME
간행물
간행물 검색

논문분류	춘계학술대회 초록집
제목	Interpretable Machine Learning Approach for Mortality Risk Assessment in ICU Patients with Heart Failure Complicated by Acute Kidney Injury
저자	Xinyao Luo
출판정보	2024; 2024(1):
키워드
초록	Objectives: Heart failure (HF) complicated by acute kidney injury (AKI) significantly impacts patient outcomes, making early prediction of short-term mortality crucial. This study focuses on developing an interpretable machine learning model to enhance prediction accuracy in such clinical scenarios. Methods: This retrospective cohort study utilized the Medical Information Mart for Intensive Care IV (MIMIC-IV, version 2.0) database. Data from the initial 24 hours of ICU admission was extracted and divided into a training set (70%) and a validation set (30%). We utilized the SHapley Additive exPlanation (SHAP) method to interpret the workings of an extreme gradient boosting (XGBoost) model and identify key prognostic factors. The XGBoost model's predictive ability was evaluated against three other machine learning models using the area under the curve (AUC) metric, and its interpretation was enhanced using the SHAP method. Results: The study included 8,028 patients with HF complicated AKI. The XGBoost model outperformed others, achieving an AUC of 0.93 (Accuracy=0.89), while neural network showed the lowest performance (AUC=0.79, Accuracy=0.82). Decision curve analysis indicated the superior net benefit of the XGBoost model within 9% to 60% threshold probabilities. SHAP analysis identified the top 20 predictors, with age emerging as the most significant. Conclusions: Our interpretable model offers an enhanced ability to predict mortality risk in HF patients with AKI in ICUs. This model not only aids in formulating effective treatment plans but also optimizes resource allocation. The interpretability of the model adds to its transparency, making it a reliable tool for medical practitioners.
원문(PDF)	PDF 원문보기

목록

위로가기