EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Acute myocardial infarction prognosis prediction with reliable and interpretable artificial intelligence system

Minwook Kim, Donggil Kang, Min Sun Kim, Jeong Cheon Choe, Sun-Hack Lee, Jin Hee Ahn, Jun-Hyok Oh, Jung Hyun Choi, Han Cheol Lee, Kwang Soo Cha, Kyungtae Jang, WooR I Bong und 2 weitere

Journal of the American Medical Informatics Association · 20.06.2024 · 31 (7) · 1540-1550

DOI: 10.1093/jamia/ocae114 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of the American Medical Informatics Association, online erschienen am 28.05.2024. Verfasst von Minwook Kim und 13 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Engineering, Pusan National University, Busan 46421, Republic of Korea. Hauptthemen laut MEDLINE: Myocardial Infarction, Artificial Intelligence. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Foundation of Korea, Korea Government, Pusan National University Hospital Clinical Research.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

Predicting mortality after acute myocardial infarction (AMI) is crucial for timely prescription and treatment of AMI patients, but there are no appropriate AI systems for clinicians. Our primary goal is to develop a reliable and interpretable AI system and provide some valuable insights regarding short, and long-term mortality. Materials and methods We propose the RIAS framework, an end-to-end framework that is designed with reliability and interpretability at its core and automatically optimizes the given model. Using RIAS, clinicians get accurate and reliable predictions which can be used as likelihood, with global and local explanations, and “what if” scenarios to achieve desired outcomes as well.

Results

We apply RIAS to AMI prognosis prediction data which comes from the Korean Acute Myocardial Infarction Registry. We compared FT-Transformer with XGBoost and MLP and found that FT-Transformer has superiority in sensitivity and comparable performance in AUROC and F1 score to XGBoost. Furthermore, RIAS reveals the significance of statin-based medications, beta-blockers, and age on mortality regardless of time period. Lastly, we showcase reliable and interpretable results of RIAS with local explanations and counterfactual examples for several realistic scenarios.

Discussion

RIAS addresses the “black-box” issue in AI by providing both global and local explanations based on SHAP values and reliable predictions, interpretable as actual likelihoods. The system’s “what if” counterfactual explanations enable clinicians to simulate patient-specific scenarios under various conditions, enhancing its practical utility.

Conclusion

The proposed framework provides reliable and interpretable predictions along with counterfactual examples.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Myocardial InfarctionArtificial IntelligenceHumansPrognosisMaleRegistriesFemaleRepublic of KoreaReproducibility of ResultsAgedMiddle Aged

Stichwörter der Autor:innen

acute myocardial infarctioncounterfactual explanationelectronic health records (EHR)explainable artificial intelligence (XAI)interpretable machine learning

Autor:innen und Institutionen

  • School of Computer Science and Engineering, Pusan National University, Busan 46421, Republic of Korea.
  • Department of Cardiology, Medical Research Institute, Pusan National University Hospital, Busan 49241, Republic of Korea.
  • College of Medicine, Pusan National University, Gyeongsangnam-do 50612, Republic of Korea.
  • Gupo Sungshim Hospital, Busan 46581, Republic of Korea.
  • Division of Cardiology, Department of Medicine, Busan Veterans Hospital, Busan 46996, Republic of Korea.
  • Center for Artificial Intelligence Research, Pusan National University, Busan 46421, Republic of Korea.

ORCID-Profile: Giltae Song

Förderung

  • National Research Foundation of Korea
  • Korea Government
  • Pusan National University Hospital Clinical Research
  • Basic Science Research Program
  • Institute of Information & Communications Technology Planning & Evaluation
  • Artificial Intelligence Convergence Innovation Human Resources Development
  • Pusan National University Hospital Clinical Research Funding

Zitieren

APA

Kim, M., Kang, D., Kim, M. S., Choe, J. C., Lee, S. H., Ahn, J. H., Oh, J. H., Choi, J. H., Lee, H. C., Cha, K. S., Jang, K., Bong, W. I., Song, G., & Lee, H. (2024). Acute myocardial infarction prognosis prediction with reliable and interpretable artificial intelligence system. Journal of the American Medical Informatics Association, 31(7), 1540-1550. https://doi.org/10.1093/jamia/ocae114

Vancouver

Kim M, Kang D, Kim MS, Choe JC, Lee SH, Ahn JH, et al. Acute myocardial infarction prognosis prediction with reliable and interpretable artificial intelligence system. Journal of the American Medical Informatics Association. 2024;31(7):1540-1550. doi:10.1093/jamia/ocae114

BibTeX
@article{Kim2024,
  author = {Kim, Minwook and Kang, Donggil and Kim, Min Sun and Choe, Jeong Cheon and Lee, Sun-Hack and Ahn, Jin Hee and Oh, Jun-Hyok and Choi, Jung Hyun and Lee, Han Cheol and Cha, Kwang Soo and Jang, Kyungtae and Bong, WooR I and Song, Giltae and Lee, Hyewon},
  title = {Acute myocardial infarction prognosis prediction with reliable and interpretable artificial intelligence system},
  journal = {Journal of the American Medical Informatics Association},
  year = {2024},
  volume = {31},
  number = {7},
  pages = {1540--1550},
  doi = {10.1093/jamia/ocae114}
}
Kostenlos starten →