Following this puts new work involving it at the top of your briefing, with a note saying why it is there. Links are taken from the source record, never inferred.
A systematic review of 102 AI prediction studies showing that most lack external validation, prospective evidence, or workflow integration; none demonstrate interventional benefit for treatment tailoring in breast cancer neoadjuvant therapy.
A narrative review synthesizing evidence from phase III trials and biomarker studies to inform clinical decision-making about adjuvant immunotherapy after neoadjuvant chemoimmunotherapy in resectable NSCLC, without reporting original trial data or meta-analysis.
Single-center machine learning model with reasonable test-set performance (AUC 0.894) and independent temporal validation, but surrogate endpoints (biochemical markers and imaging classification) rather than hard clinical outcomes, and no comparison to standard risk stratification.
Retrospective single-centre imaging cohort with exploratory endpoints and modest sample size; key finding (delta torso fat volume) failed validation in temporally aligned subgroup analysis and authors acknowledge need for further validation.
This is a methodological comparison study using simulation and observational radiomics data to evaluate machine learning algorithms for confounder selection; it does not test a clinical hypothesis or report a patient outcome.
A retrospective multi-centre radiomics study with internal and external validation showing moderate discriminatory performance (AUC 0.790–0.818 on external cohorts) for a clinically relevant surrogate endpoint, but lacking prospective design, hard clinical outcomes, or demonstration of impact on treatment decisions.
Retrospective, single-centre study with modest sample size and surrogate endpoint (mutation status prediction); requires prospective multicentre validation before clinical use, as stated by the authors.
A retrospective single-center study using cross-validation in a small, heterogeneous cohort (152 patients, split by treatment) that reports surrogate endpoints (AUC) rather than clinical outcomes; radiomic findings did not improve on baseline models, limiting clinical utility.