{"id":"W4379197097","doi":"10.1177/14604582231180581","title":"Breaking the 80:20 rule in health research using large administrative data sets","year":2023,"lang":"en","type":"article","venue":"Health Informatics Journal","topic":"Artificial Intelligence in Healthcare","field":"Health Professions","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Alberta Bone and Joint Health Institute; University of Calgary","funders":"Canadian Institutes of Health Research; Canada Foundation for Innovation","keywords":"Online analytical processing; Data warehouse; Computer science; Data cube; Data mining; Leverage (statistics); Data science; Analytics; Health care; Population; Database; Medicine","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":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.06138014,0.0002513011,0.0006000457,0.0008620396,0.009140385,0.0001326986,0.001514073,0.00026034,0.0002227351],"category_scores_gemma":[0.003312415,0.0001876209,0.00005741656,0.002491782,0.0001827809,0.001015719,0.001102511,0.006700483,0.0009846569],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002026188,"about_ca_system_score_gemma":0.0149903,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003378045,"about_ca_topic_score_gemma":0.01124495,"domain_scores_codex":[0.9837883,0.005465956,0.005252387,0.0002794653,0.00171619,0.003497736],"domain_scores_gemma":[0.9916103,0.003394404,0.002111654,0.001223837,0.0007643925,0.000895392],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.000240862,0.0002159708,0.136782,0.007205485,0.00006184643,0.0001066682,0.524058,0.002340227,0.000003624507,0.007920501,0.2558748,0.06519],"study_design_scores_gemma":[0.0006539316,0.0003510055,0.01079172,0.004763647,0.000004057987,0.000199612,0.4495917,0.3501725,0.000002560127,0.01185907,0.1712969,0.0003132716],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7275057,0.002721318,0.005861538,0.2385736,0.007772114,0.009151293,0.001773702,0.0004912671,0.006149538],"genre_scores_gemma":[0.9484671,0.005682431,0.01073775,0.03156264,0.002205434,0.0001535693,0.0004930801,0.0001564421,0.0005415893],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3478323,"threshold_uncertainty_score":0.9997932,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8455603265902553,"score_gpt":0.6929477354375245,"score_spread":0.1526125911527307,"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."}}