EUVIMEDEUVIMED entdecken
Open Access

Predicting Left Ventricular Ejection Fraction Recovery After Percutaneous Coronary Intervention in Patients With Chronic Coronary Syndrome by Using Interpretable Machine Learning Models: Retrospective Study

Jiayi Ding iD, Guanqi Lyu iD, Masaharu Nakayama iD, Kotaro Nochioka iD, Jun Takahashi iD, Satoshi Yasuda iD, Tetsuya Matoba iD, Takahide Kohro iD, Naoyuki Akashi iD, Hideo Fujita iD, Yusuke Oba iD, Tomoyuki Kabutoya iD und 11 weitere

JMIR Medical Informatics · 2025

DOI: 10.2196/77839 ↗

Kurz gefasst

Fachartikel in der Zeitschrift JMIR Medical Informatics, 2025. Verfasst von Jiayi Ding und 22 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medical Informatics, Graduate School of Medicine, Tohoku University, Sendai, Japan. Hauptthemen laut MEDLINE: Machine Learning, Percutaneous Coronary Intervention, Stroke Volume, Ventricular Function, Left. Die Arbeit nennt 52 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Accurately predicting left ventricular ejection fraction (LVEF) recovery after percutaneous coronary intervention (PCI) in patients with chronic coronary syndrome (CCS) is crucial for clinical decision-making.

Objective

This study aimed to develop and compare multiple machine learning (ML) models to predict LVEF recovery and identify key contributing features.

Methods

We retrospectively analyzed 520 patients with CCS from the Clinical Deep Data Accumulation System database. Patients were categorized into 4 binary classification tasks based on baseline LVEF (≥50% or 10% compared with ≤0%; and (2) normal recovery, defined as an LVEF increase of 0% to 10% compared with ≤0%. For each task, 3 feature selection strategies (all features, least absolute shrinkage and selection operator [LASSO] regression, and recursive feature elimination [RFE]) were combined with 4 ML algorithms (extreme gradient boosting [XGBoost], categorical boosting, light gradient boosting machine, and random forest), resulting in 48 models. Models were evaluated using 10-fold cross-validation and assessed by the area under the curve (AUC), decision curve analysis, and calibration plots.

Results

The highest AUCs were achieved by RFE combined with XGBoost (AUC=0.93) for preserved LVEF with good recovery, LASSO combined with XGBoost (AUC=0.79) for preserved LVEF with normal recovery, LASSO combined with XGBoost (AUC=0.88) for reduced LVEF with good recovery, and RFE combined with XGBoost (AUC=0.84) for reduced LVEF with normal recovery. Shapley Additive Explanation analysis identified uric acid, platelets, hematocrit, brain natriuretic peptide, glycated hemoglobin, glucose, creatinine, baseline LVEF, left ventricular end-diastolic internal diameter, heart rate, R wave amplitude in V5, and R wave amplitude in V6 as important predictive factors of LVEF recovery.

Conclusions

ML models incorporating feature selection strategies demonstrated strong predictive performance for LVEF recovery after PCI. These interpretable models may support clinical decision-making and can improve the management of patients with CCS after PCI.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningPercutaneous Coronary InterventionStroke VolumeVentricular Function, LeftHumansRetrospective StudiesMaleFemaleMiddle AgedAgedRecovery of Function

Stichwörter der Autor:innen

chronic coronary syndromeleft ventricular ejection fractionmachine learningpercutaneous coronary interventionprognostic modeling

Autor:innen und Institutionen

  • Department of Medical Informatics, Graduate School of Medicine, Tohoku University, Sendai, Japan.
  • Division of Cardiovascular Medicine, Tohoku University Hospital, Sendai, Japan.
  • Department of Cardiovascular Medicine, Graduate School of Medical Sciences, Kyushu University, Fukuoka, Japan.
  • Department of Clinical Informatics, School of Medicine, Jichi Medical University, Tochigi, Japan.
  • Division of Cardiovascular Medicine, Jichi Medical University Saitama Medical Center, Saitama, Japan.
  • Department of Medicine, School of Medicine, Jichi Medical University, Tochigi, Japan.

ORCID-Profile: Jiayi Ding, Guanqi Lyu, Masaharu Nakayama, Kotaro Nochioka, Jun Takahashi, Satoshi Yasuda, Tetsuya Matoba, Takahide Kohro, Naoyuki Akashi, Hideo Fujita, Yusuke Oba, Tomoyuki Kabutoya, Kazuomi Kario, Yasushi Imai, Arihiro Kiyosue, Yoshiko Mizuno, Takamasa Iwai, Yoshihiro Miyamoto, Masanobu Ishii, Kenichi Tsujita, Taishi Nakamura, Hisahiko Sato, Ryozo Nagai

Zitieren

APA

Ding, J., Lyu, G., Nakayama, M., Nochioka, K., Takahashi, J., Yasuda, S., Matoba, T., Kohro, T., Akashi, N., Fujita, H., Oba, Y., Kabutoya, T., Kario, K., Imai, Y., Kiyosue, A., Mizuno, Y., Iwai, T., Miyamoto, Y., Ishii, M., …, & Nagai, R. (2025). Predicting Left Ventricular Ejection Fraction Recovery After Percutaneous Coronary Intervention in Patients With Chronic Coronary Syndrome by Using Interpretable Machine Learning Models: Retrospective Study. JMIR Medical Informatics. https://doi.org/10.2196/77839

Vancouver

Ding J, Lyu G, Nakayama M, Nochioka K, Takahashi J, Yasuda S, et al. Predicting Left Ventricular Ejection Fraction Recovery After Percutaneous Coronary Intervention in Patients With Chronic Coronary Syndrome by Using Interpretable Machine Learning Models: Retrospective Study. JMIR Medical Informatics. 2025. doi:10.2196/77839

BibTeX
@article{Ding2025,
  author = {Ding, Jiayi and Lyu, Guanqi and Nakayama, Masaharu and Nochioka, Kotaro and Takahashi, Jun and Yasuda, Satoshi and Matoba, Tetsuya and Kohro, Takahide and Akashi, Naoyuki and Fujita, Hideo and Oba, Yusuke and Kabutoya, Tomoyuki and Kario, Kazuomi and Imai, Yasushi and Kiyosue, Arihiro and Mizuno, Yoshiko and Iwai, Takamasa and Miyamoto, Yoshihiro and Ishii, Masanobu and Tsujita, Kenichi and Nakamura, Taishi and Sato, Hisahiko and Nagai, Ryozo},
  title = {Predicting Left Ventricular Ejection Fraction Recovery After Percutaneous Coronary Intervention in Patients With Chronic Coronary Syndrome by Using Interpretable Machine Learning Models: Retrospective Study},
  journal = {JMIR Medical Informatics},
  year = {2025},
  doi = {10.2196/77839}
}
Kostenlos starten →