| Title | Datasets for testing agentic LLM in diagnosis |
|---|---|
| Description | Three datasets for testing the diagnostic efficacy of agentic LLM, including Xinhua_phenotypeOnly (978 cases), Xinhua_with_Gene (168 cases) and Hunan_with_Gene (162 cases). Each dataset contains phenotypic features (HPOs), age, sex and diagnostic conclusion (ICD_10, ORPHA_ID). |
| Organism | Homo sapiens |
| Data Type | Clinical Research data |
| Data Accessibility | Controlled-access |
| BioProject | PRJCA052720 |
| Release Date | 2026-03-06 |
| Submitter | Yanjie Fan (fanyanjie13@163.com) |
| Organization | Xinhua Hospital Affiliated to Shanghai Jiao Tong University School of Medicine |
| Submission Date | 2025-12-05 |
HTTP download speed may be slow. It is highly recommended that you download the dataset using a dedicated FTP tool (such as FileZilla Client).
| File ID | File Title | Number/Samples | File Type | File Size | File Suffix | Download |
|---|---|---|---|---|---|---|
| OMIX013512-01 | Xinhua_168cases_with_Gene | 168 | Clinical Research data | 26.97 KB | csv | Controlled |
| OMIX013512-04 | Xinhua_978cases_PhenotypeOnly | 978 | Clinical Research data | 189.77 KB | csv | Controlled |
| OMIX013512-05 | Hunan_162cases_with_Gene | 162 | Clinical Research data | 42.33 KB | csv | Controlled |
| Paper Title | Journal Name | Publish Time | Accession | Citing Type |
|---|---|---|---|---|
| An agentic system for rare disease diagnosis with traceable reasoning | Nature | 2026-02 | OMIX013512 | Deposit |