{"id":"W4313290006","doi":"10.1101/2022.12.27.521999","title":"A 3D Clinical Face Phenotype Space of Genetic Syndromes using a Triplet-Based Singular Geometric Autoencoder","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Face recognition and analysis","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Alberta Children's Hospital; University of Calgary","funders":"National Institutes of Health; Vlaamse regering; KU Leuven; Fonds Wetenschappelijk Onderzoek","keywords":"Autoencoder; Orthogonality; Artificial intelligence; Face (sociological concept); Space (punctuation); Pattern recognition (psychology); Computer science; Metric (unit); Matching (statistics); Similarity (geometry); Singular value decomposition; Encoder; Deep learning; Machine learning; Mathematics; Image (mathematics); Engineering; Statistics","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001561422,0.0006302138,0.001261309,0.001563091,0.0002562189,0.0003306791,0.001938406,0.000471901,0.0002625072],"category_scores_gemma":[0.0007016947,0.0007061734,0.0006594136,0.00427437,0.0001841609,0.0001902192,0.001431206,0.00108101,0.0000442592],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003533104,"about_ca_system_score_gemma":0.001886399,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001063171,"about_ca_topic_score_gemma":0.00000117534,"domain_scores_codex":[0.9946148,0.0006809507,0.001315007,0.001650643,0.001054156,0.0006844652],"domain_scores_gemma":[0.9951813,0.000299974,0.001207782,0.002307156,0.0006255768,0.0003782725],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002936667,0.009811187,0.1458097,0.007692675,0.007670116,0.002891841,0.0002286906,0.4784475,0.3411887,0.003051162,0.001683278,0.001231533],"study_design_scores_gemma":[0.001386321,0.0002463989,0.04079098,0.0004286365,0.000600315,1.027847e-7,0.000006667137,0.9399359,0.01213557,0.000007468778,0.002858841,0.001602801],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3475207,0.001835056,0.6483712,0.0002092444,0.001119928,0.0004760679,0.00009428726,0.0003678896,0.000005608836],"genre_scores_gemma":[0.7001326,0.0001394947,0.2993025,0.0001969114,0.00009817912,0.00004918226,3.93682e-7,0.00007410108,0.000006679245],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4614884,"threshold_uncertainty_score":0.999539,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03980533946498525,"score_gpt":0.2747575349028761,"score_spread":0.2349521954378908,"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."}}