0 273

Cited 5 times in

Predicting survival in heart failure: a risk score based on machine-learning and change point algorithm

Authors
 Wonse Kim  ;  Jin Joo Park  ;  Hae-Young Lee  ;  Kye Hun Kim  ;  Byung-Su Yoo  ;  Seok-Min Kang  ;  Sang Hong Baek  ;  Eun-Seok Jeon  ;  Jae-Joong Kim  ;  Myeong-Chan Cho  ;  Shung Chull Chae  ;  Byung-Hee Oh  ;  Woong Kook  ;  Dong-Ju Choi 
Citation
 CLINICAL RESEARCH IN CARDIOLOGY, Vol.110(8) : 1321-1333, 2021-08 
Journal Title
CLINICAL RESEARCH IN CARDIOLOGY
ISSN
 1861-0684 
Issue Date
2021-08
MeSH
Aged ; Female ; Heart Failure / mortality* ; Humans ; Machine Learning* ; Male ; Middle Aged ; Predictive Value of Tests ; Prognosis ; Registries ; Republic of Korea ; Risk Assessment* ; Survival Rate
Keywords
Change-point analysis ; Grouped Lasso ; Heart failure ; Machine learning ; Mortality ; Prognostic model
Abstract
Objective: Machine learning (ML) algorithm can improve risk prediction because ML can select features and segment continuous variables effectively unbiased. We generated a risk score model for mortality with ML algorithms in East-Asian patients with heart failure (HF).

Methods: From the Korean Acute Heart Failure (KorAHF) registry, we used the data of 3683 patients with 27 continuous and 44 categorical variables. Grouped Lasso algorithm was used for the feature selection, and a novel continuous variable segmentation algorithm which is based on change-point analysis was developed for effectively segmenting the ranges of the continuous variables. Then, a risk score was assigned to each feature reflecting nonlinear relationship between features and survival times, and an integer score of maximum 100 was calculated for each patient.

Results: During 3-year follow-up time, 32.8% patients died. Using grouped Lasso, we identified 15 highly significant independent clinical features. The calculated risk score of each patient ranged between 1 and 71 points with a median of 36 (interquartile range: 27-45). The 3-year survival differed according to the quintiles of the risk score, being 80% and 17% in the 1st and 5th quintile, respectively. In addition, ML risk score had higher AUCs than MAGGIC-HF score to predict 1-year mortality (0.751 vs. 0.711, P < 0.001).

Conclusions: In East-Asian patients with HF, a novel risk score model based on ML and the new continuous variable segmentation algorithm performs better for mortality prediction than conventional prediction models.

Clinical trial registration: Unique identifier: INCT01389843 https://clinicaltrials.gov/ct2/show/NCT01389843 .
Full Text
https://link.springer.com/article/10.1007/s00392-021-01870-7
DOI
10.1007/s00392-021-01870-7
Appears in Collections:
1. College of Medicine (의과대학) > Dept. of Internal Medicine (내과학교실) > 1. Journal Papers
Yonsei Authors
Kang, Seok Min(강석민) ORCID logo https://orcid.org/0000-0001-9856-9227
URI
https://ir.ymlib.yonsei.ac.kr/handle/22282913/187822
사서에게 알리기
  feedback

qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Browse

Links