# Rare Disease Identification (Text-to-ORDO) on MIMIC-III discharge summaries (val)

Source: [Rare Disease Identification (Text-to-ORDO) on MIMIC-III discharge summaries (val)](<https://www.sota2.com/research/sota/rare-disease-identification-text-to-ordo-on-mimic-iii-discharge-summaries-val>)

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

Data updated: 2026-02-26T05:58:23.193Z

Evaluation of model performance on identifying rare diseases, specifically mapping to ORDO codes, using the validation split of MIMIC-III discharge summaries. Metrics include Precision, Recall, and F1 scores.

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 | Rare Disease Identification (Text-to-ORDO) |
| Dataset (including any stated split) | MIMIC-III discharge summaries (val) |
| Metric | Precision |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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

- [Precision](<https://www.sota2.com/research/sota/rare-disease-identification-text-to-ordo-on-mimic-iii-discharge-summaries-val.md?metric=Precision>): Higher is better; unit: PERCENT.

- [Recall](<https://www.sota2.com/research/sota/rare-disease-identification-text-to-ordo-on-mimic-iii-discharge-summaries-val.md?metric=Recall>): Higher is better; unit: PERCENT.

- [F1 Score](<https://www.sota2.com/research/sota/rare-disease-identification-text-to-ordo-on-mimic-iii-discharge-summaries-val.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Precision | Result date | Report paper |
| --- | --- | --- | --- |
| SemEHR + WS (rules+BERT) | 67.6 | Not recorded | 68fa6f2e1e209131cea4445b |
| SemEHR + rules | 53.9 | Not recorded | 68fa6f2e1e209131cea4445b |
| SemEHR | 18.7 | Not recorded | 68fa6f2e1e209131cea4445b |

### SemEHR + WS (rules+BERT)

Precision: 67.6. Result ID: 69909b203a6c31484901d0de.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f2e1e209131cea4445b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f2e1e209131cea4445b.md>)

[Implementation](<https://github.com/acadTags/Rare-disease-identification>)

Recorded evaluation configuration: {"Methodology":"Weak supervision","BERT Model":"BlueBERT-base","Rules included":"true"}. This record does not assert independent reproduction.

### SemEHR + rules

Precision: 53.9. Result ID: 69909b203a6c31484901d0dd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f2e1e209131cea4445b.md>)

Recorded evaluation configuration: {"Rules-based enhancement":"true"}. This record does not assert independent reproduction.

### SemEHR

Precision: 18.7. Result ID: 69909b203a6c31484901d0dc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f2e1e209131cea4445b.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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