On Expert-Machine Partnership to Predict Mortality of Congestive Heart Failure Patients

Ofir Ben-Assuli; Tsipi Heart; Nan Yin; Robert Klempfner; Rema Padman

doi:10.1080/10580530.2024.2312380

On Expert-Machine Partnership to Predict Mortality of Congestive Heart Failure Patients

Ofir Ben-Assuli, Tsipi Heart, Nan Yin, Robert Klempfner, Rema Padman

Research output: Contribution to journal › Article › peer-review

Abstract

This study examines the combined use of machine learning (ML) and expert judgment in predicting 30-day mortality for congestive heart failure (CHF) patients. It compares models using either expert-selected, ML-selected, or integrated features. The integrated model, merging expert and ML insights, outperforms others in predicting mortality risk, underscoring the value of combining human expertise and ML in clinical decision-making.

Original language	English
Journal	Information Systems Management
DOIs	https://doi.org/10.1080/10580530.2024.2312380
State	Accepted/In press - 1 Jan 2024
Externally published	Yes

Keywords

congestive heart failure (CHF)
expert-machine collaboration
feature selection
Health risk assessment
XGBoost

ASJC Scopus subject areas

Information Systems
Computer Science Applications
Library and Information Sciences

Access to Document

10.1080/10580530.2024.2312380

Cite this

@article{42202285595c4ed99db241870548549c,

title = "On Expert-Machine Partnership to Predict Mortality of Congestive Heart Failure Patients",

abstract = "This study examines the combined use of machine learning (ML) and expert judgment in predicting 30-day mortality for congestive heart failure (CHF) patients. It compares models using either expert-selected, ML-selected, or integrated features. The integrated model, merging expert and ML insights, outperforms others in predicting mortality risk, underscoring the value of combining human expertise and ML in clinical decision-making.",

keywords = "congestive heart failure (CHF), expert-machine collaboration, feature selection, Health risk assessment, XGBoost",

author = "Ofir Ben-Assuli and Tsipi Heart and Nan Yin and Robert Klempfner and Rema Padman",

note = "Publisher Copyright: {\textcopyright} 2024 Taylor & Francis.",

year = "2024",

month = jan,

day = "1",

doi = "10.1080/10580530.2024.2312380",

language = "English",

journal = "Information Systems Management",

issn = "1058-0530",

publisher = "Taylor and Francis Ltd.",

}

TY - JOUR

T1 - On Expert-Machine Partnership to Predict Mortality of Congestive Heart Failure Patients

AU - Ben-Assuli, Ofir

AU - Heart, Tsipi

AU - Yin, Nan

AU - Klempfner, Robert

AU - Padman, Rema

PY - 2024/1/1

Y1 - 2024/1/1

N2 - This study examines the combined use of machine learning (ML) and expert judgment in predicting 30-day mortality for congestive heart failure (CHF) patients. It compares models using either expert-selected, ML-selected, or integrated features. The integrated model, merging expert and ML insights, outperforms others in predicting mortality risk, underscoring the value of combining human expertise and ML in clinical decision-making.

AB - This study examines the combined use of machine learning (ML) and expert judgment in predicting 30-day mortality for congestive heart failure (CHF) patients. It compares models using either expert-selected, ML-selected, or integrated features. The integrated model, merging expert and ML insights, outperforms others in predicting mortality risk, underscoring the value of combining human expertise and ML in clinical decision-making.

KW - congestive heart failure (CHF)

KW - expert-machine collaboration

KW - feature selection

KW - Health risk assessment

KW - XGBoost

UR - http://www.scopus.com/inward/record.url?scp=85185263640&partnerID=8YFLogxK

U2 - 10.1080/10580530.2024.2312380

DO - 10.1080/10580530.2024.2312380

M3 - Article

AN - SCOPUS:85185263640

SN - 1058-0530

JO - Information Systems Management

JF - Information Systems Management

ER -

On Expert-Machine Partnership to Predict Mortality of Congestive Heart Failure Patients

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this