Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Patient Eligibility Classification on N2C2 Track 1 2018
Loading...
92.2
Accuracy
MAKAR
83.88
86.04
88.2
90.36
Nov 22, 2024
Accuracy
F1 Score
Abdominal Criterion
Advanced CAD Criterion
Alcohol Abuse Criterion
Aspirin for MI Criterion
Creatinine Criterion
Dietary Support (2 Months) Criterion
Drug Abuse Criterion
English Language Criterion
HbA1c Criterion
Ketoacidosis (1 Year) Criterion
Major Diabetes Criterion
Makes Decisions Criterion
MI (6 Months) Criterion
Average Score
Updated 9d ago
Evaluation Results
Method
Method
Links
Accuracy
F1 Score
Abdominal Criterion
Advanced CAD Criterion
Alcohol Abuse Criterion
Aspirin for MI Criterion
Creatinine Criterion
Dietary Support (2 Months) Criterion
Drug Abuse Criterion
English Language Criterion
HbA1c Criterion
Ketoacidosis (1 Year) Criterion
Major Diabetes Criterion
Makes Decisions Criterion
MI (6 Months) Criterion
Average Score
MAKAR
Backbone=GPT-4o, Crite...
2024.11
92.2
85.4
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Wornow et al.
Approach=two-stage ret...
2024.11
88.4
80.2
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Beattie et al.
Approach=chain-of-thou...
2024.11
88.4
78.7
-
-
-
-
-
-
-
-
-
-
-
-
-
-
TrialGPT
Criterion=Average
2024.11
84.2
75.3
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Feedback
Search any
task
Search any
task