welcome
Science News

Science News

Technology

Technology

Medical AI tools are growing, but are they being tested properly?

Science News
Summary
Nutrition label

86% Informative

A review of studies evaluating health care AI models, specifically LLMs, found that only 5 percent used real patient data.

The current benchmarks are distracting, computer scientist Deborah Raji and colleagues argue.

Raji: These benchmarks are not indicative of the types of applications people are aspiring to, so the field should not obsess about them.

Right now, evaluation is very much an afterthought, says Raji .

Raji: We should be more thoughtful about the evaluations that we focus on or that we overly base our performance on.

He says hospitals should share the full list of different AI products that they make use of as part of their clinical practice.

VR Score

91

Informative language

93

Neutral language

47

Article tone

informal

Language

English

Language complexity

55

Offensive language

not offensive

Hate speech

not hateful

Attention-grabbing headline

not detected

Known propaganda techniques

not detected

Time-value

long-living

Affiliate links

no affiliate links