대한신장학회

Skip Navigation: Skip to contents

KOR
ENG
전체메뉴보기

간행물 검색

현재 페이지 경로

HOME
간행물
간행물 검색

논문분류	춘계학술대회 초록집
제목	Prediction and management of acute kidney injury with explainable artificial intelligence (prime): a study protocol for a randomized controlled trial
저자	Giae Yun
출판정보	2023; 2023(1):
키워드
초록	Objectives: Acute kidney injury (AKI) is a common but harmful clinical syndrome that requires immediate management. There are many studies on the early detection of AKI, but only some studies have performed management proactively before AKI occurs. We established an artificial intelligence (AI) prediction model through our previous study, and the actual AKI predictive power was about 95%. In this study, we will utilize explainable AI to predict the development of AKI in hospitalized patients and determine whether the incidence of AKI may be decreased by proactively managing risk factors. Methods: We designed a prospective, investigator-initiated, single-center, single-blinded, randomized controlled study with two experimental groups. A total of 1438 participants with hospitalized patients will be enrolled and randomized into two groups; intervention or usual-care groups. We will apply an AKI prediction model based on the patient's demographic. We will collect data on vital signs, laboratory test results, medication history, and surgical records. We provide information on whether AKI develops within 48 hours and the top 10 explanatory factors for predicting AKI to the physician. Intervention group receives the prediction results daily until the patient is discharged or up to 7 days after admission. Usual-care group does not receive analysis results. Primary outcome is the incidence of AKI. Secondary outcomes include severe AKI (stage 2 or 3), renal replacement therapy, and death during hospitalization. We calculated the required sample size for a two-sided significance level ofα = 0.05, a power of 80%; thus, determined that 719 participants would be necessary for each group. Results: The Institutional Review Boards of Seoul National University Bundang Hospital approved this study (No. B-2301-804-301). Patient enrollment will initiate on March 1, 2023. Conclusions: This study will be the first randomized controlled trial to apply the technology of predicting AKI using Explainable AI to clinical practice in adult inpatients.
원문(PDF)	PDF 원문보기

목록

위로가기