{"id":"W4285796460","doi":"10.1371/journal.pdig.0000074","title":"Conditional generation of medical time series for extrapolation to underrepresented populations","year":2022,"lang":"en","type":"article","venue":"PLOS Digital Health","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Advanced Research","funders":"","keywords":"Health records; Extrapolation; Longitudinal data; Representation (politics); Health care; Computer science; Missing data; Synthetic data; Population; Medicine; Data science; Data mining; Machine learning; Artificial intelligence; Statistics; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.0003947492,0.00007136582,0.0001362653,0.0001352855,0.0004390312,0.0000635032,0.0003439874,0.00002738395,0.0001212388],"category_scores_gemma":[0.0003381186,0.00008002863,0.00003942555,0.0003238432,0.00001731113,0.0004324395,0.0001931322,0.0001515205,0.000009498429],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001479016,"about_ca_system_score_gemma":0.0004802035,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000792741,"about_ca_topic_score_gemma":0.00003299689,"domain_scores_codex":[0.998224,0.0001383443,0.0003614977,0.0002552588,0.0008281393,0.0001927267],"domain_scores_gemma":[0.9991946,0.0001420128,0.000143577,0.0002328869,0.0001018033,0.0001851802],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008973226,0.001103631,0.01924701,0.0005509684,0.00004546158,0.000006066624,0.004307467,0.05165496,0.000143119,0.8401689,0.02633191,0.05635078],"study_design_scores_gemma":[0.0003358268,0.0009566597,0.0119154,0.00002309939,0.00000193043,0.00003787277,0.00005772307,0.9674785,0.0000395176,0.0152129,0.003796416,0.0001441657],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06890402,0.00007586964,0.8312431,0.09680054,0.0003896374,0.00122039,0.0005764875,0.0002441157,0.000545865],"genre_scores_gemma":[0.9856463,0.000001226485,0.01187448,0.0009614877,0.0001098632,0.0001375516,0.001041348,0.00001014855,0.0002175991],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9167423,"threshold_uncertainty_score":0.3376717,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1213832634115292,"score_gpt":0.3772623873423903,"score_spread":0.255879123930861,"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."}}