Provisionally accepted

Pei-Hsuan Chang1

Feng-Ching Liao1

Yi-Ching Wu1

Fang-Ju Sun1

Yen-Yu Liu2

Hung-I Yeh2

Chung-Lieh Hung3*

Kun-Pin Wu1

• 1National Yang Ming Chiao Tung University, Taipei, Taiwan
• 2Mackay Memorial Hospital, Taipei City, Taiwan
• 3Mackay Medical College, New Taipei, Taiwan

The final, formatted version of the article will be published soon.

Notify me

Select one of your emails

You have multiple emails registered with Frontiers:

Notify me

Notify me on publication

Please enter your email address:

Email

If you already have an account, please login

You don't have a Frontiers account ? You can register here

Notify me

ABSTRACT Background Heart failure (HF), with its distinct phenotypes, poses significant public health challenges. Early diagnosis of specific HF phenotypes is crucial for timely therapeutic intervention. Objectives We employed random forests to predict acute HF (AHF) phenotypes (HFrEF, HFmrEF, and HFpEF) during admission, using structured and unstructured data types while blinded to left ventricular ejection fraction (LVEF) information. Methods We investigated the predictive performance of integrated natural language processing (NLP) and machine learning (ML)-based models in AHF phenotype classification by random forests, leveraging clinical text and laboratory data from the MIMIC-III database. Feature selection for unstructured textual data and biochemical test data was performed using the LASSO method, with selected textual features converted into structured data using one-hot encoding. The areas under the ROC and PRC curves (AUROC and AUPRC) assessed overall performance. Results Our final study cohort comprised 1,192 training datasets and 513 independent validating datasets with primary data types and LVEF information available. The overall model from the training dataset showed the best performance with combined datasets (accuracy: 0.70±0.03, AUROC: 0.76±0.02) compared to the textual or laboratory dataset alone, which was replicated in the independent validating dataset. Our model achieved optimal performance by selecting up to 100 combined features from both textual and laboratory data. Reducing features to 20 did not substantially attenuate the overall model performance until only 10 features were selected. Conclusions Our study enhances HF phenotype classification and underscores the value of multifaceted data analysis in clinical informatics, enabling more personalized heart failure treatment. Early identification of AHF phenotypes may support timely, phenotype-specific management and inform treatment decisions.

Keywords: Heart Failure, Heart failure phenotypes, Natural Language Processing, Machine learning model, random forest

Received: 12 Jul 2025; Accepted: 24 Sep 2025.

Copyright: © 2025 Chang, Liao, Wu, Sun, Liu, Yeh, Hung and Wu. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

* Correspondence: Chung-Lieh Hung, jotaro3791@gmail.com

Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.