Multimorbidity in Heart Failure Patients: Application of Machine Learning Algorithms to Predict Imminent Health Outcomes

Jorge Cerejo, Jorge Cerejo, Rui Lopes Baeta, Simão Gonçalves, Bernardo Neves, Bernardo Neves, Pedro Morais Sarmento, José Maria Moreira, Nuno André da Silva, Francisca Leite, Bruno Martins, Mário J. Silva

2025

Abstract

As populations age and life expectancy increases, multimorbidity, which is the simultaneous presence of two or more chronic conditions, has become increasingly common, especially among older adults. Heart failure, a widespread and heterogeneous syndrome, has sparked research into multimorbidity to deepen our understanding of its pathophysiology and improve clinical management approaches. This paper offers a detailed characterization of a heart failure patient cohort, utilizing clinical data from a Portuguese tertiary hospital. Based on this characterization, we developed a clinical tool for identification of high-risk patients and prediction of imminent hospital admissions based on laboratory tests. Our models for predicting imminent hospitalization showed reasonable effectiveness (AUROC of 0.79 with lab test prescriptions and 0.72 with lab test results). These findings emphasize the significant predictive value of laboratory tests in the context of HF. Additionally, we investigated the explainability of our models using SHAP values, in collaboration with clinical experts, providing insights into factors influencing the models’ predictions. These results highlight the importance of secondary clinical data analysis assisting healthcare professionals in identifying patients at high risk of adverse events, and improving patient care and outcomes.

Paper Citation

in Harvard Style

Cerejo J., Baeta R., Gonçalves S., Neves B., Sarmento P., Moreira J., da Silva N., Leite F., Martins B. and Silva M. (2025). Multimorbidity in Heart Failure Patients: Application of Machine Learning Algorithms to Predict Imminent Health Outcomes. In Proceedings of the 18th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 2: HEALTHINF; ISBN 978-989-758-731-3, SciTePress, pages 330-339. DOI: 10.5220/0013381800003911

in Bibtex Style

@conference{healthinf25,
author={Jorge Cerejo and Rui Baeta and Simão Gonçalves and Bernardo Neves and Pedro Sarmento and José Moreira and Nuno da Silva and Francisca Leite and Bruno Martins and Mário Silva},
title={Multimorbidity in Heart Failure Patients: Application of Machine Learning Algorithms to Predict Imminent Health Outcomes},
booktitle={Proceedings of the 18th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 2: HEALTHINF},
year={2025},
pages={330-339},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013381800003911},
isbn={978-989-758-731-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 18th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 2: HEALTHINF
TI - Multimorbidity in Heart Failure Patients: Application of Machine Learning Algorithms to Predict Imminent Health Outcomes
SN - 978-989-758-731-3
AU - Cerejo J.
AU - Baeta R.
AU - Gonçalves S.
AU - Neves B.
AU - Sarmento P.
AU - Moreira J.
AU - da Silva N.
AU - Leite F.
AU - Martins B.
AU - Silva M.
PY - 2025
SP - 330
EP - 339
DO - 10.5220/0013381800003911
PB - SciTePress