{"id":"W2922053026","doi":"10.5206/uwomj.v87i2.1140","title":"Challenges to Using Big Data in Health Services Research","year":2019,"lang":"en","type":"article","venue":"University of Western Ontario Medical Journal","topic":"Medical Coding and Health Information","field":"Health Professions","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Data science; Health care; Database; Digitization; Big data; Health data; Representation (politics); External Data Representation; Data mining; Political science","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01054964,0.00007511557,0.0003236175,0.0004156033,0.0004979261,0.000006364546,0.000950708,0.0002169892,0.001344561],"category_scores_gemma":[0.0001229409,0.00007066462,0.00002164083,0.0001852631,0.0000521682,0.0002600965,0.0006559069,0.00233194,0.0002730281],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009514813,"about_ca_system_score_gemma":0.005160513,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.1524976,"about_ca_topic_score_gemma":0.6513615,"domain_scores_codex":[0.9964142,0.0008432827,0.000581135,0.0001979303,0.001377754,0.0005856254],"domain_scores_gemma":[0.9978033,0.0004010317,0.0002831226,0.0003968678,0.0002033163,0.0009123417],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003559813,0.0001228507,0.7392077,0.00233999,0.000022231,0.00007193343,0.1608796,0.00001972981,0.000004257191,0.0001531981,0.001160719,0.09566189],"study_design_scores_gemma":[0.002768732,0.0004290585,0.4829335,0.01178449,0.000005770999,0.00003944709,0.07126629,0.001463897,2.987305e-7,0.000110535,0.4290638,0.0001341519],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9768577,0.0001929221,0.001042817,0.01612354,0.0009194649,0.0003918639,0.000006147466,0.00001270694,0.004452882],"genre_scores_gemma":[0.9916376,0.001422579,0.001202371,0.003253946,0.0004985793,1.496126e-7,0.00002083278,0.0000102706,0.001953652],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.498864,"threshold_uncertainty_score":0.9999697,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6081707880321395,"score_gpt":0.5113574672410477,"score_spread":0.09681332079109184,"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."}}