{"id":"W4378801059","doi":"10.1016/s2589-7500(23)00082-1","title":"Predicting benefit from immune checkpoint inhibitors in patients with non-small-cell lung cancer by CT-based ensemble deep learning: a retrospective study","year":2023,"lang":"en","type":"article","venue":"The Lancet Digital Health","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":109,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; National Cancer Institute; NGM Biopharmaceuticals; Novartis Institutes for BioMedical Research; University of Texas MD Anderson Cancer Center; EMD Serono; AstraZeneca; Genentech; NIH Clinical Center; Sun Pharma; Amgen; STCube; Daiichi Sankyo Europe; Innovent Biologics; European Society for Medical Oncology; Université de Montréal; Clovis Oncology; Bayer HealthCare; Astellas Pharma; Rexanna's Foundation; Seagen; MacroGenics; Jounce Therapeutics; ViewRay; Ribon Therapeutics; BeiGene; Helsinn; Mirati Therapeutics; American College of Radiology Imaging Network; Society for Immunotherapy of Cancer; Jazz Pharmaceuticals; Conquer Cancer Foundation; National Institutes of Health; Natera; RefleXion Medical; Regeneron Pharmaceuticals; McGill University; Merck KGaA; Varian Medical Systems; Damon Runyon Cancer Research Foundation; ECOG-ACRIN Cancer Research Group; Eli Lilly and Company; Calithera Biosciences; Gilead Sciences; Exelixis; Sanofi; Arrowhead Pharmaceuticals; Foundation Medicine; GlaxoSmithKline; Bristol-Myers Squibb; Moderna; Pfizer","keywords":"Medicine; Context (archaeology); Immune checkpoint; Lung cancer; Oncology; Internal medicine; Univariate analysis; Cancer; Retrospective cohort study; Multivariate analysis; Immunotherapy; Biology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009948735,0.0003672564,0.0003578571,0.0005367768,0.0001987233,0.0005212414,0.0006227773,0.0004177622,0.0006630727],"category_scores_gemma":[0.002779139,0.0003202402,0.0006743332,0.0006160259,0.0003043932,0.0005819735,0.0004796422,0.0006097476,0.0002273596],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006674601,"about_ca_system_score_gemma":0.000415873,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005249289,"about_ca_topic_score_gemma":0.005514729,"domain_scores_codex":[0.9996545,0.00008344853,0.00004291361,0.0001325764,0.00004872827,0.00003779817],"domain_scores_gemma":[0.9982154,0.0005317482,0.0004633523,0.0003482117,0.0002708347,0.000170429],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005364468,0.00008707869,0.9927909,0.00001238749,0.000165558,0.0001149386,0.00003075053,0.002040974,0.0003300575,0.00004697776,0.0003010618,0.003542831],"study_design_scores_gemma":[0.0001043388,0.001057015,0.9335586,0.00004315959,0.0005160319,0.001515493,0.0002558788,0.05994583,0.001176567,0.0003889719,0.001395186,0.00004276996],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9979766,0.0001778914,0.0007833497,0.00003861282,0.000004182942,0.0000128762,0.0008438405,0.000006954939,0.0001555522],"genre_scores_gemma":[0.997905,0.00009612914,0.0003065198,0.0000206388,0.000005594613,0.00001113714,0.001587757,0.000003354824,0.00006386688],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005249289,"threshold_uncertainty_score":0.01043749,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008714826560307552,"score_gpt":0.2745603073552363,"score_spread":0.2658454807949288,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}