Clinical Record Analysis of Heart Failure Identification of Key Features and Disease Prediction

Xiaoqing Yao

2023

Abstract

In contemporary society, disease prediction has become an important healthcare domain. Various advanced techniques have been utilized to enhance the accuracy and efficiency of disease prediction. This paper employs machine learning techniques, specifically logistic regression and random forest models, to predict mortality rates associated with heart failure using a clinical dataset. The findings highlight the importance of key physiological measures in predicting outcomes, including age, ejection fraction, serum creatinine, serum sodium, and time. Both models showed highly accurate predictive power, with logistic regression slightly better than random forest on the Area Under the Curve (AUC) indicator. The study contributes to the existing literature on heart failure risk prediction and underscores the transformative potential of machine learning for improving patient outcomes via precise risk stratification and early intervention. This study plays an essential role in understanding how machine learning technology can be used to investigate the key features and disease prediction of heat failure based on the previous clinical record.

Paper Citation

in Harvard Style

Yao X. (2023). Clinical Record Analysis of Heart Failure Identification of Key Features and Disease Prediction. In Proceedings of the 1st International Conference on Data Analysis and Machine Learning - Volume 1: DAML; ISBN 978-989-758-705-4, SciTePress, pages 297-304. DOI: 10.5220/0012803900003885

in Bibtex Style

@conference{daml23,
author={Xiaoqing Yao},
title={Clinical Record Analysis of Heart Failure Identification of Key Features and Disease Prediction},
booktitle={Proceedings of the 1st International Conference on Data Analysis and Machine Learning - Volume 1: DAML},
year={2023},
pages={297-304},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012803900003885},
isbn={978-989-758-705-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Data Analysis and Machine Learning - Volume 1: DAML
TI - Clinical Record Analysis of Heart Failure Identification of Key Features and Disease Prediction
SN - 978-989-758-705-4
AU - Yao X.
PY - 2023
SP - 297
EP - 304
DO - 10.5220/0012803900003885
PB - SciTePress