Clinical Diagnosis Identification on MIMIC-IV-Ext Cardiac Disease
84.98Primary AccuracyDxChain
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| DxChainBackbone=GPT-4.1-Mini2026.04 | 84.98 | 46.03 | 46.93 | 53.42 | 54.47 | |
| DxChainBackbone=GPT-5-Nano2026.04 | 82.91 | 36.67 | 43.07 | 40.17 | 47.19 | |
| Base-model + CoTBackbone=GPT-5-Nano2026.04 | 78.27 | 21.88 | 31.84 | 25.48 | 37.08 | |
| KAMACBackbone=GPT-5-Nano2026.04 | 78.05 | 31.91 | 39.06 | 35.71 | 43.71 | |
| Base-modelBackbone=GPT-5-Nano2026.04 | 77.93 | 21.89 | 31.85 | 25.53 | 37.14 | |
| KAMACBackbone=GPT-4.1-Mini2026.04 | 77.05 | 34.18 | 38.31 | 39.93 | 44.75 | |
| MAMBackbone=GPT-5-Nano2026.04 | 75.94 | 30.14 | 39.29 | 33.91 | 44.21 | |
| MDagentsBackbone=GPT-4.1-Mini2026.04 | 75.36 | 35.73 | 42.32 | 40.03 | 47.42 | |
| Base-modelBackbone=GPT-4.1-Mini2026.04 | 74.08 | 23.22 | 31.69 | 27.62 | 37.69 | |
| Base-model + CoTBackbone=GPT-4.1-Mini, Prompting Strategy=Chain-of-Thought2026.04 | 74.04 | 23.88 | 32.43 | 28.51 | 38.72 | |
| MAMBackbone=GPT-4.1-Mini2026.04 | 73.78 | 34.2 | 40.23 | 41.47 | 48.78 | |
| MedagentsBackbone=GPT-4.1-Mini2026.04 | 72.21 | 29.79 | 35.65 | 35.96 | 43.03 | |
| MDagentsBackbone=GPT-5-Nano2026.04 | 70.68 | 23.72 | 33.29 | 24.88 | 34.92 | |
| MedagentsBackbone=GPT-5-Nano2026.04 | 68.08 | 29.47 | 35.25 | 30.96 | 37.04 |