{"id":"W4405971752","doi":"10.46475/asean-jr.v25i3.901","title":"Reliability and radiologists’ concordance of artificial intelligence (AI)-calculated Alberta Stroke Program Early CT Score (ASPECTS)","year":2025,"lang":"en","type":"article","venue":"The ASEAN Journal of Radiology","topic":"Acute Ischemic Stroke Management","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Concordance; Reliability (semiconductor); Medical physics; Computer science; Artificial intelligence; Medicine; Psychology; Reliability engineering; Engineering; Internal medicine","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001140015,0.000182528,0.0007205646,0.000161497,0.00005930785,0.00001207687,0.0003707087,0.00007640906,0.00003965142],"category_scores_gemma":[0.001291392,0.0001149192,0.000178116,0.0002735526,0.001143903,0.00005855816,0.0001219162,0.0005964321,0.000002931389],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009277557,"about_ca_system_score_gemma":0.0001759708,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001118802,"about_ca_topic_score_gemma":0.00001019803,"domain_scores_codex":[0.9981335,0.0002768069,0.0008765589,0.000242165,0.0001818984,0.0002890696],"domain_scores_gemma":[0.9980266,0.000637475,0.0004960446,0.0004741779,0.00026106,0.0001046589],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.01374088,0.001610778,0.4821866,0.0007929843,0.004812646,0.001599576,0.001826014,0.001308301,0.07254831,0.03682322,0.04011923,0.3426314],"study_design_scores_gemma":[0.008057143,0.02254476,0.757198,0.00211932,0.004695884,0.01914769,0.003531226,0.01387194,0.108677,0.02947519,0.0295087,0.001173122],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9860266,0.001240113,0.004971672,0.004726098,0.0003363718,0.0005751362,0.000005151941,0.00001708302,0.002101783],"genre_scores_gemma":[0.9971529,0.0002199771,0.001714731,0.000422968,0.0001472611,0.000007185856,0.000002987811,0.00001012712,0.0003218235],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3414583,"threshold_uncertainty_score":0.4686267,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01917430277253407,"score_gpt":0.3027942467108905,"score_spread":0.2836199439383564,"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."}}