Why 'Zero-Shot' Clinical Predictions Are Risky

Stanford HAI·Jan 7

This story is reported by Stanford HAI. Read what other outlets are saying below, then open the original report for full details.

Full coverage

1

ClinicRealm: Re-evaluating large language models with conventional machine learning for non-generative clinical prediction tasks

Nature·Apr 8

2

Understanding Uncertainty in Large Language Model Predictions of Early Death in Critically Ill Patients: A Conformal Prediction Approach

medRxiv·Dec 15

3

Cancer mortality prediction: Trained ML leads, but zero-shot LLMs approach clinical performance

Vera Health·May 31

4

Tempus Announces Initial Results from its Multimodal Foundation Model Efforts for Novel and Scalable Insight Generation in Oncology

Business Wire·May 29

5

AI and health care: Professor’s paper explores how systems assess patient risks and medical coding

News at IU·Aug 6

6

An ECG biomarker for sudden cardiac death discovered with deep learning

Nature·Jun 24

7

Integrating large language models for enhanced predictive analytics in healthcare | npj Digital Medicine

Nature·Apr 2

8

Large language models improve transferability of electronic health record-based predictions across countries and coding systems | npj Digital Medicine

Nature·Jan 22