{"id":"W4200297453","doi":"10.1101/2021.12.17.473215","title":"MixEHR-Guided: A guided multi-modal topic modeling approach for large-scale automatic phenotyping using the electronic health record","year":2021,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Canada First Research Excellence Fund","keywords":"Computer science; Machine learning; Artificial intelligence; Health informatics; Inference; Data mining; Health care","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"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":[0.003704106,0.0008908684,0.001201659,0.0003468222,0.001176823,0.0009777187,0.002820437,0.0005933212,0.000009285661],"category_scores_gemma":[0.0005657854,0.0008573089,0.0004327763,0.001026798,0.00005170616,0.0003864173,0.001913523,0.002200774,0.000004194868],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002040329,"about_ca_system_score_gemma":0.004591499,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001506504,"about_ca_topic_score_gemma":0.00006390726,"domain_scores_codex":[0.9923723,0.0009988185,0.001539617,0.002295497,0.0007185896,0.002075148],"domain_scores_gemma":[0.9939195,0.0001877057,0.001072125,0.003475188,0.0009389864,0.0004065047],"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":[0.00005759576,0.002103213,0.01957213,0.02642843,0.001582065,0.0000749219,0.003853062,0.8765736,0.03100547,0.0372699,0.0006712573,0.0008084185],"study_design_scores_gemma":[0.0006751723,0.00004710964,0.0008428547,0.0006469844,0.00005475165,2.941852e-7,0.00003121082,0.9958283,0.0005218752,0.00001498195,0.0005083849,0.000828057],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.208558,0.002753791,0.7832711,0.001168367,0.001250665,0.002134121,0.00003420819,0.0008280877,0.000001596542],"genre_scores_gemma":[0.5266122,0.00008381779,0.4714589,0.0008706328,0.0004194967,0.0004196645,0.000001441469,0.000130299,0.000003584081],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.3180542,"threshold_uncertainty_score":0.9993877,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04947228149419877,"score_gpt":0.3040285454588539,"score_spread":0.2545562639646551,"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."}}