{"id":"W4416945183","doi":"10.1038/s41598-025-26365-7","title":"Foundation model based prediction of lung cancer survival using temporal changes in dual time point CT scans","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia, Okanagan Campus; Kelowna General Hospital; University of British Columbia; Artificial Intelligence in Medicine (Canada)","funders":"National Cancer Institute; National Institutes of Health; National Instruments Corporation","keywords":"Feature (linguistics); Lung cancer; Time point; Radiation therapy; Computed tomography; Pattern recognition (psychology); Point (geometry); Survival analysis","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001952245,0.00009713919,0.0002485666,0.0004321657,0.000105899,0.00004857481,0.00003312891,0.00003724079,0.0001010435],"category_scores_gemma":[0.0003035316,0.00008871357,0.00004951064,0.000618936,0.000167233,0.00009316702,0.00003183723,0.0001801411,4.541925e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002085682,"about_ca_system_score_gemma":0.000809964,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006807728,"about_ca_topic_score_gemma":0.0001035759,"domain_scores_codex":[0.9984887,0.00004627698,0.0004319919,0.0004031796,0.0004343126,0.000195511],"domain_scores_gemma":[0.999231,0.00002516427,0.000214171,0.0003138318,0.0001476162,0.00006824188],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007808871,0.0002584077,0.6443316,0.0004604478,0.00007094547,0.0004313572,0.0003955734,0.1135466,0.2254734,0.00006354417,0.005826135,0.009063927],"study_design_scores_gemma":[0.0004188317,0.00001230111,0.007288706,0.0005387928,0.00006850476,0.00003846191,0.00002229861,0.9867916,0.003955562,0.0002390021,0.0005671441,0.00005877379],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9782349,0.000084839,0.01557018,0.001500593,0.003214239,0.0003506067,0.00000531038,0.00004169384,0.000997627],"genre_scores_gemma":[0.9958421,0.000003175736,0.001715669,0.00008471269,0.00006612088,0.00001304253,0.0001302484,0.00001142473,0.002133505],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8732451,"threshold_uncertainty_score":0.3617634,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02363825058324953,"score_gpt":0.3287521262320547,"score_spread":0.3051138756488052,"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."}}