Deep learning-based electrocardiographic differentiation of Takotsubo syndrome from acute anterior myocardial infarction: explainability, human-AI interaction, and a utilization bias hypothesis

@misc{kagawa2026deep,
  title = {{Deep learning-based electrocardiographic differentiation of Takotsubo syndrome from acute anterior myocardial infarction: explainability, human-AI interaction, and a utilization bias hypothesis}},
  author = {E. Kagawa and M. Kato and T. Hidaka and E. Kunita and N. Hironobe and S. Matsui and Y. Kobayashi and Y. Uotani and T. Teramoto and K. Yoshii and T. Okumoto and M. Tani and K. Dote},
  howpublished = {medRxiv},
  year = {2026},
  month = oct,
  doi = {10.64898/2026.10.15.26365116},
  url = {https://www.medrxiv.org/content/10.64898/2026.10.15.26365116v1},
  note = {CC BY-NC},
}

TY  - UNPB
TI  - Deep learning-based electrocardiographic differentiation of Takotsubo syndrome from acute anterior myocardial infarction: explainability, human-AI interaction, and a utilization bias hypothesis
AU  - E. Kagawa
AU  - M. Kato
AU  - T. Hidaka
AU  - E. Kunita
AU  - N. Hironobe
AU  - S. Matsui
AU  - Y. Kobayashi
AU  - Y. Uotani
AU  - T. Teramoto
AU  - K. Yoshii
AU  - T. Okumoto
AU  - M. Tani
AU  - K. Dote
PY  - 2026
DA  - 2026/10/15
PB  - medRxiv
DO  - 10.64898/2026.10.15.26365116
UR  - https://www.medrxiv.org/content/10.64898/2026.10.15.26365116v1
AB  - Background: Artificial intelligence (AI) may improve electrocardiographic differentiation of Takotsubo syndrome from acute anterior ST-segment elevation myocardial infarction (STEMI), but its impact on human diagnostic performance, the added value of visual explanations, and differences by reader background and experience remain uncertain. Methods: Using 12-lead electrocardiogram (ECG) images from two hospitals, we developed and externally validated an ensemble of three deep learning models after self-supervised pretraining and fine-tuning. The diagnostic task used ECGs recorded within 14 days after symptom onset, regardless of reperfusion status. We conducted a four-phase reader study. Phases 1-3 compared unaided interpretation, a reference sheet, and additional AI assistance. In Phase 4, readers evaluated a new ECG set after randomization to reference-sheet support alone, with AI predictions, or with AI predictions plus gradient-weighted class activation mapping (Grad-CAM) heatmaps. Diagnostic correctness was analyzed using generalized linear mixed-effects models. Exploratory analyses examined differences by cardiologist status and experience. Results: Development and external-validation cohorts, including healthy controls, comprised 832 and 95 participants, respectively. For Takotsubo-STEMI discrimination, external-validation accuracy was 0.914, with areas under the receiver operating characteristic and precision-recall curves of 0.970 and 0.984. Seventy healthcare providers completed the reader study. The estimated probability of correct diagnosis increased from 0.632 without assistance to 0.864 with AI assistance (odds ratio [OR], 3.71; P<0.001). In randomized Phase 4, AI assistance improved accuracy vs reference-sheet support alone (OR, 4.28; 95% CI, 3.08-5.95; P<0.001), and Grad-CAM provided additional benefit (OR, 1.53; 95% CI, 1.04-2.25; P=0.033). Exploratory analyses showed greater improvement among less experienced readers; with AI assistance, non-cardiologists outperformed cardiologists. AI-assisted readers remained less accurate overall than the model alone. Conclusions: An ECG image-based ensemble differentiated Takotsubo syndrome from anterior STEMI and improved reader accuracy. Visual explanations provided additional benefit, while experience-related differences highlight the importance of effective human-AI interaction.
ER  -