{"id":"W4404065884","doi":"10.1148/radiol.241421","title":"Laterality: A Potential Pitfall in Applying Multimodal Large Language Models to Radiology","year":2024,"lang":"en","type":"letter","venue":"Radiology","topic":"Interpreting and Communication in Healthcare","field":"Health Professions","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"London Health Sciences Centre; Western University","funders":"","keywords":"Medicine; Laterality; Radiology; Medical physics; Linguistics; Audiology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01660355,0.0007764657,0.0008692627,0.001318485,0.001675611,0.004893366,0.002560778,0.006453142,0.01322972],"category_scores_gemma":[0.1274987,0.0007868715,0.00117117,0.0007391977,0.003125279,0.007801448,0.002985314,0.007623082,0.006836094],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001762105,"about_ca_system_score_gemma":0.003431523,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01079984,"about_ca_topic_score_gemma":0.01601609,"domain_scores_codex":[0.9894925,0.007082753,0.0006175358,0.0005169052,0.001996417,0.0002939291],"domain_scores_gemma":[0.884964,0.0972572,0.001717404,0.005358997,0.009841189,0.0008611309],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0006660504,0.0002089175,0.01269295,0.0008280518,0.0002536248,0.003601118,0.004983206,0.01450787,0.003639924,0.1856675,0.4488603,0.3240905],"study_design_scores_gemma":[0.0001318287,0.000178403,0.001956907,0.0008397984,0.0001451331,0.008130691,0.004353454,0.2116305,0.004776911,0.5122479,0.2553878,0.0002206335],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.01688724,0.001248862,0.2006332,0.7249324,0.00463659,0.0002302714,0.002048862,0.002624797,0.04675776],"genre_scores_gemma":[0.4710488,0.002546728,0.22135,0.2507832,0.01251239,0.0009856267,0.00117702,0.001486825,0.03810938],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.01660355,"threshold_uncertainty_score":0.08780897,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05654591465774114,"score_gpt":0.4125511802588636,"score_spread":0.3560052656011225,"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."}}