How medical AI devices are evaluated: limitations and recommendations from an analysis of FDA approvals
Paper cited by one bottleneck page and 22 idea pages, indexed on Europe PMC as PubMed record 33820998 and published in Nature Medicine; the citing pages link this DOI, which is how the record was matched.
Overview
Europe PMC indexes no abstract for this record; the title is the only text available.
Indexed on Europe PMC as PubMed record 33820998 (DOI 10.1038/s41591-021-01312-x). Matched by DOI alone: one bottleneck page and 22 idea pages cite this DOI among their external links (the pages are listed under Related), and this page was written so that the citation resolves inside OnCo. No figure has been checked by an editor.
One bottleneck page and 22 idea pages on OnCo cite this paper by its DOI; this record gives the citation a page of its own so a reader can follow it without leaving OnCo. Read the abstract above alongside the citing pages listed under Related; the record was created automatically from the Europe PMC entry and its figures have not been checked by hand.
- Matched to the citing OnCo records by DOI alone; the summary reproduces the Europe PMC abstract and no figure has been verified against the full paper.
Similar pages
not linked directly; found by shared links- IdeaA public registry of every AI model used in cancer care
Shares A liability framework for clinical AI: safe harbour for clinicians, liability for makers, Patients told which AI is used in their care, in plain language, Rules for retiring cancer AI when performance drops or the standard of care moves, Mandatory post-market performance reporting for cancer AI.
- IdeaSequestered, prospectively collected benchmark datasets that no one can train on
Shares A neutral public evaluator for cancer AI, on the model of NIST, Red-team programmes that attack cancer AI before patients do, External validation at five or more sites in two countries before clearance, AI that is built but not validated or deployed.
- IdeaPatient-level multimodal foundation models for treatment selection
Shares Digital twins for treatment selection, validated by predicting before observing, Whole-patient digital twins validated in prospective randomised trials, A pre-competitive consortium to train a shared multimodal cancer foundation model, AI that is built but not validated or deployed.
- CompanyPathAI
Shares A standard evaluation pathway for AI-assisted pathology, from reader study to deployment, A pre-competitive consortium to train a shared multimodal cancer foundation model, AI that is built but not validated or deployed.
- IdeaA dedicated fund for randomised trials of cancer AI with patient outcomes
Shares Pay for cancer AI only when it has outcome evidence, then pay properly, AI that is built but not validated or deployed.
- CompanyPaige AI
Shares A standard evaluation pathway for AI-assisted pathology, from reader study to deployment, A pre-competitive consortium to train a shared multimodal cancer foundation model, AI that is built but not validated or deployed.
- IdeaDecision support that cites the exact trial and guideline line it relies on
Shares A randomised trial of AI-generated treatment recommendations versus tumour boards, AI that is built but not validated or deployed.
- IdeaAn open foundation model of the cancer cell trained on perturbation data
Shares In silico trials to prioritise combinations, scored against later real trials, AI that is built but not validated or deployed.