인문학
사회과학
자연과학
공학
의약학
농수해양학
예술체육학
복합학
DBpia AI
AI 에이전트
AI 아이디어
AI 리더
AI 뷰어
Citeasy
크롬 서지관리 다운로드
지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
초록·키워드
I would like to discuss the article recently published entitled “Predicting the mortality of patients with Covid-19: A machine learning approach”.1 This work is done by training classifiers (Random Forest, Regression Logistic, Gradient Boosted Trees, and Support Vector Machine) on a relatively big data set from five hospitals. The First and major concern raised is: it seems in Figure 4B there is a clear cut based on the D-Dimer test that could be used to determine the class (Discharge and Death). If Figure 4B is representative of the data it seems that the performance of a simple rule (if D-Dimer > 500 then class = Death else class=Discharge) should outperform the classifiers introduce in the manuscript. Second, in the preprocessing section, the authors stated they have used the KNN technique for replacing missing values however the K is mentioned to be 30 and (simultaneously) 50. It is not clear how the authors used two K numbers (30 and 50) for this purpose although the number of the K is better to be an odd number that the majority vote of neighbors was clear (if the distance does not affect the weight). Third, In the limitation part, the authors stated that one of the limitations of the study is that it is conducted on one database while in the methods section in the samples definition sub-section, it is noted that the data set contains the data of five hospitals and it seems this limitation is not valid. Seyed Mohammad Ayyoubzadeh: Conceptualization; writing—original draft; writing—review and editing. The author declares no conflict of interest. Data available on request from the authors.
#Artificial intelligence
#Logistic regression
#Machine learning
#Random forest
#Set (abstract data type)
#Class (philosophy)
#Computer science
#Conceptualization
#Coronavirus disease 2019 (COVID-19)
#Preprocessor
#Support vector machine
#Section (typography)
#Test set
#Data set
#Statistics
#Mathematics
#Medicine
인공지능 문자 인식 모델을 통해 추출된 텍스트로, 일부 오타나 오류가 포함될 수 있으나 지속적으로 개선 중입니다.
오류를 발견하셨다면 해당 부분을 드래그한 후 ' 를 통해 신고해주세요.
오류를 발견하셨다면 해당 부분을 드래그한 후 ' 를 통해 신고해주세요.
최근 본 자료 전체보기
