Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Average Final Diagnosis Prediction on MIMIC, MedCaseReasoning, and ER-Reason

62.1Average Accuracy

Counterfactual Multi-agent Diagnostic Framework

21.85232.30142.7553.199Mar 29, 2026
Updated 19d ago

Evaluation Results

MethodLinks
2026.03
62.1
2026.03
58.1
2026.03
55.2
2026.03
52
2026.03
52
2026.03
51.1
2026.03
51.1
2026.03
50.7
2026.03
50.2
2026.03
48.7
2026.03
48.6
2026.03
48.6
2026.03
48.5
2026.03
46.7
2026.03
43.9
2026.03
42.9
2026.03
40.9
2026.03
40.2
2026.03
39
2026.03
37.6
2026.03
37.5
2026.03
37.1
2026.03
37.1
2026.03
36.8
2026.03
36.6
2026.03
36.5
2026.03
35.8
2026.03
35.5
2026.03
35.4
2026.03
35.2
2026.03
35
2026.03
34.6
2026.03
34.5
2026.03
34.4
2026.03
34.1
2026.03
34.1
2026.03
33.3
2026.03
33.1
2026.03
32.9
2026.03
32.5
2026.03
31.5
2026.03
31.5
2026.03
31
2026.03
30.9
2026.03
29.3
2026.03
29
2026.03
27.7
2026.03
27.3
2026.03
27.3
2026.03
26.9
2026.03
25.8
2026.03
25.5
2026.03
25.3
2026.03
24.5
2026.03
24.4
2026.03
23.4