Radiomics Models Predict NSCLC Recurrence Risk
A systematic review and meta-analysis published April 2, 2026, evaluates radiomics-based machine learning models predicting recurrence risk in non–small cell lung cancer (NSCLC), synthesizing 30 studies covering 7,964 patients. Pooled c‑indices were 0.850 (training) and 0.878 (validation); combined models with clinical features achieved 0.833–0.854. Authors report low average Radiomics Quality Score (27.4%) and call for standardized, multicenter validation.
Scoring Rationale
This is the first large meta-analysis confirming solid predictive performance of radiomics-based ML for NSCLC recurrence, boosting novelty and credibility (peer-reviewed JMIR). Score reduced slightly for limited methodological quality (average RQS 27.4%) and NSCLC-specific scope, but overall high relevance and actionable guidance for further validation.
Practice with real Ad Tech data
90 SQL & Python problems · 15 industry datasets
250 free problems · No credit card
See all Ad Tech problemsStep-by-step roadmaps from zero to job-ready — curated courses, salary data, and the exact learning order that gets you hired.
Sources
- Read OriginalAccuracy of Radiomics-Based Machine Learning for Predicting Risk of Recurrence in Non–Small Cell Lung Cancer: Systematic Review and Meta-Analysisjmir.org
