{"id":"W4411485357","doi":"10.1038/s41746-025-01749-1","title":"Few shot learning for phenotype-driven diagnosis of patients with rare genetic diseases","year":2025,"lang":"en","type":"article","venue":"npj Digital Medicine","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Wellcome Trust; National Human Genome Research Institute; National Center for Advancing Translational Sciences; National Institute of Neurological Disorders and Stroke; U.S. Air Force; European Bioinformatics Institute; Harvard Data Science Initiative, Harvard University; Common Fund; Microsoft Research; AstraZeneca; National Institutes of Health; National Science Foundation","keywords":"Disease; Clinical phenotype; Medicine; Rare disease; Medical diagnosis; Machine learning; Phenotype; Artificial intelligence; Bioinformatics; Computer science; Pathology; Gene; Biology; Genetics","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":[0.001563375,0.0006654204,0.0007713689,0.002022039,0.0005681181,0.000715151,0.001574385,0.001543885,0.001823618],"category_scores_gemma":[0.009127267,0.0003773542,0.0006891251,0.0008288871,0.0006795708,0.0009908165,0.001535361,0.001660633,0.000551866],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001195946,"about_ca_system_score_gemma":0.001273355,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01064563,"about_ca_topic_score_gemma":0.01584637,"domain_scores_codex":[0.9992589,0.0002558888,0.00005200154,0.0002854553,0.00008196367,0.00006569029],"domain_scores_gemma":[0.99692,0.002174702,0.0002134654,0.0002390547,0.000201834,0.0002510289],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00140237,0.001072838,0.1587118,0.0006585238,0.0007216333,0.001908437,0.0008108219,0.3026716,0.0065449,0.009854445,0.03548471,0.4801578],"study_design_scores_gemma":[0.0001069881,0.00009955686,0.004530101,0.00004987763,0.00006815123,0.0003117441,0.000118905,0.9576365,0.00230132,0.03286438,0.001887809,0.00002471126],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5398793,0.004108828,0.4291228,0.006441168,0.0002668143,0.0003787655,0.00924293,0.005286459,0.005272779],"genre_scores_gemma":[0.92791,0.0003029644,0.06247847,0.001062776,0.0001094258,0.00008596474,0.006965679,0.00006317316,0.001021555],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01064563,"threshold_uncertainty_score":0.02116734,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005285920508350112,"score_gpt":0.2271593874211226,"score_spread":0.2218734669127725,"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."}}