{"id":"W4406384062","doi":"10.1186/s41747-024-00547-w","title":"Can ChatGPT4-vision identify radiologic progression of multiple sclerosis on brain MRI?","year":2025,"lang":"en","type":"article","venue":"European Radiology Experimental","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Science Foundation Ireland; Health Service Executive; Royal College of Surgeons in Ireland; Wellcome Trust; Canadian Institute for Theoretical Astrophysics","keywords":"Multiple sclerosis; Neuroradiology; Medicine; Neurology; Neuroscience; Radiology; Psychology; Psychiatry","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005052586,0.0001744075,0.0003249636,0.0002191002,0.0001625979,0.00001018501,0.0001563242,0.0001074578,0.0001206451],"category_scores_gemma":[0.0003627432,0.0001438985,0.0001097617,0.0002040569,0.0002919557,0.00004254967,0.00006777608,0.0002303446,0.00008737275],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001603766,"about_ca_system_score_gemma":0.00008027602,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000688099,"about_ca_topic_score_gemma":0.00000442492,"domain_scores_codex":[0.9981917,0.0004768198,0.0005077127,0.0004086898,0.0001311474,0.0002839482],"domain_scores_gemma":[0.9990143,0.0003070057,0.0001432142,0.0003639626,0.00006274717,0.0001087573],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001332454,0.001292224,0.09916423,0.00009366153,0.00009392034,0.0000620757,0.004516313,0.00003086749,0.7796763,0.001198,0.04948771,0.06305223],"study_design_scores_gemma":[0.000556844,0.003208262,0.1553481,0.0006447436,0.00002615175,0.00006364407,0.003179722,0.0002725231,0.8331242,0.0001086543,0.003271674,0.0001955413],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.984363,0.001505928,0.0000894621,0.006295579,0.001121213,0.0005551435,0.000005646966,0.00007739975,0.005986594],"genre_scores_gemma":[0.9962273,0.00009602307,0.000414956,0.002376817,0.0002463739,0.00002713858,0.00007715702,0.00002208098,0.0005121995],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06285669,"threshold_uncertainty_score":0.5868012,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1282998897865956,"score_gpt":0.4370250659856302,"score_spread":0.3087251761990346,"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."}}