{"id":"W2345564273","doi":"10.1177/1460458216647089","title":"Under-coding of secondary conditions in coded hospital health data: Impact of co-existing conditions, death status and number of codes in a record","year":2016,"lang":"en","type":"article","venue":"Health Informatics Journal","topic":"Medical Coding and Health Information","field":"Health Professions","cited_by":53,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Coding (social sciences); Logistic regression; Medicine; Diagnosis code; Hospital discharge; Environmental health; Statistics; Mathematics; Intensive care medicine; Internal medicine","routes":{"ca_aff":true,"ca_fund":false,"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":[],"consensus_categories":[],"category_scores_codex":[0.006840819,0.0001875096,0.0009546964,0.0006051162,0.0004925641,0.00001006227,0.0002252991,0.0001821995,0.0003758339],"category_scores_gemma":[0.001232238,0.0001384554,0.00005970385,0.0003409001,0.0001767218,0.00106097,0.0001085606,0.001130789,0.00001033222],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000926742,"about_ca_system_score_gemma":0.00704143,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002073867,"about_ca_topic_score_gemma":0.0005451527,"domain_scores_codex":[0.9924732,0.0006144662,0.005435648,0.0001118688,0.0004750714,0.0008897876],"domain_scores_gemma":[0.9923099,0.001586501,0.004840357,0.0003334308,0.0003209306,0.0006089299],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000160145,0.0001825811,0.9351888,0.008353647,0.0000467121,0.000001444818,0.02815846,0.00004533081,0.00001152022,0.007427521,0.007803499,0.01262029],"study_design_scores_gemma":[0.00890953,0.001417665,0.9337045,0.01698455,0.00001409168,0.00007255669,0.02669934,0.004966447,0.000009851477,0.005794931,0.001134723,0.0002918393],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9879491,0.0001982945,0.004734582,0.001901697,0.0003121958,0.000879636,0.002320609,0.00001849574,0.001685438],"genre_scores_gemma":[0.989656,0.0045509,0.004580226,0.0008409832,0.00005830479,0.00001613075,0.000266837,0.0000145577,0.00001609056],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01232845,"threshold_uncertainty_score":0.9985877,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2550043989605879,"score_gpt":0.5275920358680678,"score_spread":0.2725876369074799,"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."}}