Dataset · gretelai
Symptom descriptions and 22 medical diagnoses in English
gretelai/symptom_to_diagnosis
A set of 1,065 textual descriptions of patient complaints labeled with 22 diagnoses for training classifiers.
What's inside
The dataset consists of 1,065 English examples where each symptom text description (input_text) corresponds to a specific diagnosis (output_text). A total of 22 diagnoses are represented in the sample. The data is intended for text classification tasks in the medical domain.
What you can do with it
- Training or fine-tuning a text classifier for primary sorting of medical complaints
- Testing LLMs on the accuracy of matching symptoms and diagnoses in a narrow domain
- Tasks
- Text classification
- Languages
- English
- Size
- 1K–10K rows
- Downloads this month
- 2.1K
- Likes
- 55
Models trained on it
- mradermacher/SympQwen-0.5B-GGUF 338
- samratduttaofficial/WaterSheepZero shot classification 81
- khazarai/SympQwen-0.5BText generation 43
- ITLL/WaterSheepZero shot classification 33
- chrisvoncsefalvay/dx-reasoning-qwen2.5-grpoText generation 30
- Zabihin/Symptom_to_DiagnosisText classification 29
- dumbequation/Qwen2.5-3B-reasoning-medical-symptoms-GRPO-f16Text generation 6
- kechemale/eng-am-symptom-nerText classification 6
How to load it
from datasets import load_dataset
ds = load_dataset("gretelai/symptom_to_diagnosis")