{"id":"W4401868171","doi":"10.3389/fncom.2024.1434421","title":"Deep learning for detecting prenatal alcohol exposure in pediatric brain MRI: a transfer learning approach with explainability insights","year":2024,"lang":"en","type":"article","venue":"Frontiers in Computational Neuroscience","topic":"Neonatal and fetal brain pathology","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Alberta Children's Hospital; University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Children's Hospital Research Institute; Kids Brain Health Network; Canadian Institutes of Health Research; Alberta Innovates","keywords":"Prenatal alcohol exposure; Transfer of learning; Prenatal exposure; Deep learning; Computer science; Artificial intelligence; Neuroimaging; Neuroscience; Psychology; Alcohol; Pregnancy; Chemistry; Biology","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":[0.0008911208,0.000897829,0.0005100342,0.0006136233,0.000206822,0.0004902114,0.0008578872,0.0008734447,0.00100505],"category_scores_gemma":[0.002409614,0.0002492273,0.0006689226,0.0003712366,0.0003533668,0.0007329202,0.0009832376,0.001413998,0.0002453896],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005229229,"about_ca_system_score_gemma":0.0007890587,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004133768,"about_ca_topic_score_gemma":0.003783841,"domain_scores_codex":[0.9997643,0.0000783292,0.00001291012,0.00006975658,0.00003519295,0.00003956918],"domain_scores_gemma":[0.9993321,0.0004037495,0.00006059104,0.00005686804,0.0001095094,0.00003716485],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.0003045573,0.0004127385,0.0220083,0.0001512756,0.0002965807,0.0005751259,0.0002302646,0.5382764,0.01081304,0.005903738,0.004357104,0.4166708],"study_design_scores_gemma":[0.000005408167,0.00004916345,0.00103018,0.0000096144,0.00001975249,0.00003245319,0.00001678501,0.9942958,0.001152039,0.003029397,0.0003538536,0.000005567393],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2372164,0.002052672,0.7548665,0.00159268,0.0000814058,0.0001117657,0.000526343,0.001376594,0.002175647],"genre_scores_gemma":[0.9219462,0.0007097119,0.07354178,0.0003277397,0.00007818331,0.0001328676,0.0009011025,0.00006250729,0.002300007],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004133768,"threshold_uncertainty_score":0.008219421,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01474016794008214,"score_gpt":0.2517821544881344,"score_spread":0.2370419865480523,"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."}}