Tratopedia
Side N繁中
Settings

Text size

Language

Theme

High contrast

Version

v1.177.0

The release this page was built from. It is what the service worker caches under.

Side N

The Rise of Biomedical Foundation Models — 220 Models Surveyed

Which sources back which section of this article, and what its evidence base looks like.

Which sources back which section

SectionSources behind it
What HappenedChang, Cheng, Modi et al., Nature Biotechnology (2026); the same paper’s open-access text, PubMed Central
TimelineChang, Cheng, Modi et al., Nature Biotechnology (2026); the same paper’s open-access text, PubMed Central; Lee et al., Bioinformatics (2020); Rives et al., PNAS (2021); Cui et al., Nature Methods (2024); Chen et al., Nature Medicine (2024); Hayes et al., Science (2025); Brixi et al., Nature (2026)
The ArgumentChang, Cheng, Modi et al., Nature Biotechnology (2026); the same paper’s open-access text, PubMed Central
What Others AddChang, Cheng, Modi et al., Nature Biotechnology (2026); the same paper’s open-access text, PubMed Central; Lee et al., Bioinformatics (2020); Rives et al., PNAS (2021); Chen et al., Nature Medicine (2024); Cui et al., Nature Methods (2024); Hayes et al., Science (2025); Brixi et al., Nature (2026)
ConclusionChang, Cheng, Modi et al., Nature Biotechnology (2026); the same paper’s open-access text, PubMed Central

What the evidence base looks like

  • 8Sources behind this article
  • 5Sections, every one of them sourced
  • 2Read in full
  • 6Read at the abstract only
What the source isHow manyHow they were read
The survey itself, at its publisher and in its open-access copy2Read in full, the image of its main figure included, because the citation counts appear nowhere else
The original papers behind six of the models it names6All six read at the abstract, with their full citation records

Reliable

Reliable, but with an interestWorth believing and reliableWeak on both, and used with careHonest, but thin

Worth believing

Each point is one source used, placed by two judgements on a six-step scale. Points carry no names: the chart shows the shape of the evidence, not a verdict on any publisher.