대한신장학회

Skip Navigation: Skip to contents

KOR
ENG
전체메뉴보기

간행물 검색

현재 페이지 경로

HOME
간행물
간행물 검색

논문분류	춘계학술대회 초록집
제목	Prediction of Acute Kidney Failure based on Machine Learning with the Fuzzy Decision Tree Implementation Technique
저자	Rifaldy Fajar, Prihantini Jupri, Nana Indri Kurniastuti
출판정보	2020; 2020(1):
키워드	Acute Kidney Failure \| Fuzzy Desicion Tree \| Machine Learning
초록	Acute kidney failure is one type of disease that can cause death. Until now, acute kidney failure has no antidote, so the disease cannot be cured, but can be made more slowly or stopped development. Early diagnosis of this disease will help to prevent these fatal consequences. In an effort to diagnose this disease several laboratory tests are needed in which the results of these tests will be calculated and concluded the results by a doctor or medical practitioner. The development of science and technology, especially in the field of computers will help the work of doctors to analyze the results of laboratory tests become easier and faster. Through some data as training data and implementing the Fuzzy Decision classification algorithm is expected to obtain high accuracy results so that it can be used as a reference for predicting acute kidney failure and avoiding fatal consequences that will occur. The flow of the research method consists of several steps such as; make system design, form attribute identification, data transformation, algorithm compilation, test scenario and system testing. This study uses data sets taken from the UCI Machine Learning Repository. Data was collected from the hospital for approximately two months. This data set includes a total of 400 samples with numeric attributes totaling 11 columns and nominal totaling 14 columns. Data samples were provided as many as 400 rows with 250 samples being positive for acute renal failure and 150 samples being negative for acute renal failure. The trial was conducted using several predetermined thresholds and the most optimal accuracy was 98.3%, which showed a very high degree of accuracy. It was concluded that the Fuzzy Decision Tree algorithm can be said to be able to predict acute kidney failure with an accuracy rate of 98.3%
원문(PDF)	PDF 원문보기

목록

위로가기