Multi-modal cardiovascular classification on PhysioNet 2016
97.77AccuracyW. P. Li, et al. (2025)
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| W. P. Li, et al. (2025)Params=11.7M, FLOPs=3.14G2025.10 | 97.77 | 97.99 | 97.28 | 98.79 | 98.39 | 99.67 | |
| Multi-Modal Tiny-CNNParams=16K, FLOPs=3.74M2025.10 | 97.48 | 98.2 | 96.75 | 96.98 | 97.52 | 97.61 | |
| J. Li, et al. (2022)Params=5.8M, FLOPs=3.0G2025.10 | 96.13 | 98.48 | 90.8 | 96.04 | 97.24 | — | |
| M. Morshed, et al. (2023)Params=19.16M, FLOPs=1.69G2025.10 | 95.06 | 95.06 | 90.92 | 95.08 | 95 | 99 | |
| H. Zhang, et al. (2024)Params=25.3M, FLOPs=3.84G2025.10 | 94.41 | 94.85 | 93.97 | — | — | 97.3 | |
| P. Qi, et al. (2023)Params=11.25M, FLOPs=2.92G2025.10 | 94.34 | 97.69 | 90.92 | — | — | — | |
| R. Hettiarachchi, et al. (2021)Params=711K, FLOPs=532M2025.10 | 90.41 | 94.74 | 75 | — | — | 91.06 | |
| P. Li, et al. (2021)Params=446K, FLOPs=59.1M2025.10 | 87.3 | 90.3 | 84.5 | — | 87.4 | 93.6 |