Multimodal deep learning to predict postoperative major adverse cardiac and cerebrovascular events after noncardiac surgery
A multimodal deep learning model combining raw ECG waveforms with minimal clinical data yielded superior 30-day MACCE risk prediction compared to that of the conventional indices. This approach could facilitate broad clinical adoption by minimizing data collection requirements while enhancing perioperative risk stratification.
Authors
- Soo‐Hyuk Yoon (ORCID: https://orcid.org/0000-0002-8484-5777)
- Hyung‐Chul Lee (ORCID: https://orcid.org/0000-0003-0048-7958)
- Hyeonhoon Lee (ORCID: https://orcid.org/0000-0002-9426-823X)
- Hyun‐Kyu Yoon (ORCID: https://orcid.org/0000-0001-5424-3559)
- Byeol Yi Kim (ORCID: https://orcid.org/0009-0008-8875-1111)
- Hee‐Pyoung Park (ORCID: https://orcid.org/0000-0002-4772-0780)
- Jang Ho Ahn (ORCID: https://orcid.org/0000-0003-1058-812X)
- Woo-Young Jo
Institutions
- Seoul National University (KR)
- Seoul National University Hospital (KR)
Publication Details
- Journal
- International Journal of Surgery
- Published
- 2025-08-27
- DOI
- https://doi.org/10.1097/js9.0000000000003143
- Citations
- 2
- Primary Topic
- Cardiac, Anesthesia and Surgical Outcomes
- Type
- article
- Field-Weighted Citation Impact
- 2.78