sb-ai-lab/MedBench
https://arxiv.org/abs/2201.06499
This project helps medical professionals, researchers, and data scientists evaluate how well AI models understand Russian medical texts and ECG signals. It takes raw medical text (like patient symptoms or complaints) and ECG data, then measures how accurately an AI can predict diagnoses, recommend symptoms, answer medical questions, identify key medical terms, or classify ECG pathologies. This is for anyone who needs to assess or improve AI systems working with Russian medical information.
Use this if you need to benchmark the performance of Natural Language Processing (NLP) models or machine learning models on specific medical tasks using Russian language data or ECG signals.
Not ideal if you are looking for a ready-to-use AI application for direct patient care or clinical decision support, as this is a benchmark for evaluating models.
Stars
11
Forks
1
Language
Jupyter Notebook
License
Apache-2.0
Category
Last pushed
Feb 02, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/sb-ai-lab/MedBench"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
fidelity/textwiser
[AAAI 2021] TextWiser: Text Featurization Library
RandolphVI/Multi-Label-Text-Classification
About Muti-Label Text Classification Based on Neural Network.
ThilinaRajapakse/pytorch-transformers-classification
Based on the Pytorch-Transformers library by HuggingFace. To be used as a starting point for...
ntumlgroup/LibMultiLabel
A library for multi-class and multi-label classification
xuyige/BERT4doc-Classification
Code and source for paper ``How to Fine-Tune BERT for Text Classification?``