{"id":"W3090220574","doi":"10.2196/18395","title":"Phenotypically Similar Rare Disease Identification from an Integrative Knowledge Graph for Data Harmonization: Preliminary Study","year":2020,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Genomics and Rare Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Center for Advancing Translational Sciences; National Institutes of Health","keywords":"Disease; Clinical phenotype; Computer science; Similarity (geometry); Rare disease; Computational biology; Phenotype; Biology; Medicine; Artificial intelligence; Genetics; Gene; Pathology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007240749,0.0005868649,0.0005290338,0.005040299,0.0008490887,0.001921476,0.001380213,0.0007039962,0.001313469],"category_scores_gemma":[0.0252103,0.0001901105,0.001252891,0.003776168,0.000601323,0.002496493,0.002537882,0.0006019071,0.0003131757],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001350894,"about_ca_system_score_gemma":0.002411728,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005362119,"about_ca_topic_score_gemma":0.007261874,"domain_scores_codex":[0.9941338,0.002837806,0.000460604,0.001194973,0.001193904,0.0001788964],"domain_scores_gemma":[0.9774375,0.01474907,0.001261116,0.00292495,0.00302615,0.0006012996],"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":[0.001211647,0.002071044,0.231223,0.00372577,0.001083782,0.001861867,0.004134556,0.04537503,0.03109283,0.01685237,0.01145855,0.6499095],"study_design_scores_gemma":[0.0003321772,0.001555394,0.1665878,0.0008918376,0.001452799,0.003335895,0.008291925,0.6947368,0.04046433,0.03298971,0.04917352,0.0001877998],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6543416,0.001347,0.3240871,0.001135485,0.00006595376,0.001811832,0.009225081,0.002667481,0.005318414],"genre_scores_gemma":[0.5757982,0.0004774388,0.4067755,0.0001877066,0.00002564265,0.0006695954,0.01544753,0.0001265147,0.0004917865],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007240749,"threshold_uncertainty_score":0.03829318,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02802310562233928,"score_gpt":0.3251037446507462,"score_spread":0.2970806390284069,"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."}}