# Patient eligibility classification on ClinicalTrial Dataset

Source: [Patient eligibility classification on ClinicalTrial Dataset](<https://www.sota2.com/research/sota/patient-eligibility-classification-on-clinicaltrial-dataset>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-10T07:28:46.017Z

Evaluation of patient eligibility classification performance using the ClinicalTrial Dataset.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Patient eligibility classification |
| Dataset (including any stated split) | ClinicalTrial Dataset |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Accuracy](<https://www.sota2.com/research/sota/patient-eligibility-classification-on-clinicaltrial-dataset.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [F1 Score](<https://www.sota2.com/research/sota/patient-eligibility-classification-on-clinicaltrial-dataset.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

- [CT-IN](<https://www.sota2.com/research/sota/patient-eligibility-classification-on-clinicaltrial-dataset.md?metric=CT-IN>): Higher is better; unit: SCALAR.

- [CT-EX](<https://www.sota2.com/research/sota/patient-eligibility-classification-on-clinicaltrial-dataset.md?metric=CT-EX>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| MAKAR | 98.7 | Not recorded | 68fa79d81e209131cea7fb1f |
| MAKAR | 98.7 | Not recorded | 68fa79d81e209131cea7fb1f |
| Beattie et al. | 96.7 | Not recorded | 68fa79d81e209131cea7fb1f |
| Beattie et al. | 94.7 | Not recorded | 68fa79d81e209131cea7fb1f |
| TrialGPT | 90 | Not recorded | 68fa79d81e209131cea7fb1f |
| TrialGPT | 90 | Not recorded | 68fa79d81e209131cea7fb1f |

### MAKAR

Accuracy: 98.7. Result ID: 69d8a51647f34ce924c11f8f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79d81e209131cea7fb1f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79d81e209131cea7fb1f.md>)

Recorded evaluation configuration: {"Backbone":"GPT-4o","Criteria":"CT-IN (Inclusion)"}. This record does not assert independent reproduction.

### MAKAR

Accuracy: 98.7. Result ID: 69d8a51647f34ce924c11f90.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79d81e209131cea7fb1f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79d81e209131cea7fb1f.md>)

Recorded evaluation configuration: {"Backbone":"GPT-4o","Criteria":"CT-EX (Exclusion)"}. This record does not assert independent reproduction.

### Beattie et al.

Accuracy: 96.7. Result ID: 69d8a51647f34ce924c11f8d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79d81e209131cea7fb1f.md>)

Recorded evaluation configuration: {"Approach":"chain-of-thought (CoT)","Criteria":"CT-IN (Inclusion)"}. This record does not assert independent reproduction.

### Beattie et al.

Accuracy: 94.7. Result ID: 69d8a51647f34ce924c11f8e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79d81e209131cea7fb1f.md>)

Recorded evaluation configuration: {"Approach":"chain-of-thought (CoT)","Criteria":"CT-EX (Exclusion)"}. This record does not assert independent reproduction.

### TrialGPT

Accuracy: 90. Result ID: 69d8a51647f34ce924c11f8b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79d81e209131cea7fb1f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75bc1e209131cea699c2.md>)

Recorded evaluation configuration: {"Criteria":"CT-IN (Inclusion)"}. This record does not assert independent reproduction.

### TrialGPT

Accuracy: 90. Result ID: 69d8a51647f34ce924c11f8c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79d81e209131cea7fb1f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75bc1e209131cea699c2.md>)

Recorded evaluation configuration: {"Criteria":"CT-EX (Exclusion)"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
