Deep Learning to Estimate RECIST in Patients with NSCLC Treated with PD-1 Blockade
Source check: Source checked. Not independent scientific confirmation.
Finding: A supervised deep-learning NLP model estimated RECIST response/progression from NSCLC radiology reports, enabling scalable measurement of treatment-specific outcomes. Blinded internal holdout plus independent external institution and expert RECIST ground truth; authors limit use to retrospective research, not real-time care.
Technology: A fully connected network used tokenized longitudinal report text and radiologist RECIST labels to predict response and progression timing.
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- A fully connected network used tokenized longitudinal report text and radiologist RECIST labels to predict response and progression timing.
- Test and result
- Internal and external test cohorts showed response classification and progression-date agreement with radiologist RECIST; external test included 97 patients.
- Limitation / still unknown
- Blinded internal holdout plus independent external institution and expert RECIST ground truth; authors limit use to retrospective research, not real-time care. The source does not establish benefits beyond the reported evaluation.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://pmc.ncbi.nlm.nih.gov/articles/PMC7981277/ · https://pmc.ncbi.nlm.nih.gov/articles/PMC7981277/#methods · https://pmc.ncbi.nlm.nih.gov/articles/PMC7981277/#results
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: other. Paper: not linked in this catalog; this does not mean no paper exists.
Review date: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..
No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.
Editorial assessment: Impact 2/5 · Validation 2/5 · Novelty 2/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.