New MMTClinic benchmark tests LLMs on multilingual clinical time-series data

Researchers have introduced MMTClinic, a new benchmark designed to evaluate large language models (LLMs) on clinical time-series data. This benchmark incorporates text, medical images, and physiological signals, featuring 30,000 question-answer pairs across five languages: English, Hindi, Bengali, Marathi, and Tamil. MMTClinic aims to assess LLMs on critical clinical tasks such as mortality prediction, heart rate forecasting, and SOFA score estimation, with evaluations showing significant performance differences across models, languages, and data modalities. AI

IMPACT This benchmark could accelerate the development of more inclusive and capable AI systems for clinical decision-making.

RANK_REASON The item describes a new benchmark for evaluating AI models on clinical data, presented in an academic paper. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• arXiv
• Bangla
• English
• heart rate forecasting
• Hindi
• Hugging Face
• Marathi
• MMTClinic
• Mortality prediction and acuity assessment in critical care
• SOFA score estimation
• Tamil

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →