{"id":"W4411145114","doi":"10.1101/2025.06.08.25328588","title":"Application of deep learning and explainable AI-supported medical decision-making for facial phenotyping in genetic syndromes","year":2025,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; Leibniz-Gemeinschaft; Deutsche Forschungsgemeinschaft","keywords":"CLARITY; Interpretability; Relevance (law); Artificial intelligence; Computer science; Intervention (counseling); Psychology; Machine learning; Biology; Psychiatry","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001526659,0.0005107978,0.000293597,0.0003297573,0.0002070919,0.0006416173,0.000574157,0.0007362239,0.001756618],"category_scores_gemma":[0.009855472,0.0002244345,0.0004187845,0.0001646191,0.0003032222,0.0006677725,0.0008337498,0.0009890392,0.0001583601],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000889779,"about_ca_system_score_gemma":0.0007407865,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00556125,"about_ca_topic_score_gemma":0.007323603,"domain_scores_codex":[0.9993187,0.0003630387,0.00003564356,0.0001269023,0.00009001208,0.00006571891],"domain_scores_gemma":[0.995695,0.003475109,0.0003070318,0.0001615833,0.0002108702,0.0001502587],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002252263,0.001807574,0.02810645,0.0004153846,0.0002836226,0.0005358647,0.002281522,0.3041231,0.0214413,0.002617399,0.003156825,0.6329787],"study_design_scores_gemma":[0.00005422291,0.0002649929,0.004982394,0.00002950203,0.00003889228,0.00005525298,0.000136867,0.9856668,0.003567588,0.00462604,0.0005547914,0.00002269804],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.8043532,0.0004814557,0.1879297,0.001682979,0.00006816996,0.0002899578,0.0003017945,0.001397813,0.003494881],"genre_scores_gemma":[0.9604979,0.00006598049,0.03875665,0.0001208566,0.00001044089,0.00005653312,0.00009691283,0.00001172227,0.0003829502],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.00556125,"threshold_uncertainty_score":0.01105779,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05353951657763775,"score_gpt":0.4209902471859076,"score_spread":0.3674507306082698,"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."}}