{"id":"W3174779648","doi":"10.21203/rs.3.rs-505934/v1","title":"The ICD-11 Field Trial: Creating a Large Dually Coded Database","year":2021,"lang":"en","type":"preprint","venue":"Research Square","topic":"Medical Coding and Health Information","field":"Health Professions","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"Canadian Institutes of Health Research; University of Calgary","keywords":"Coding (social sciences); ICD-10; Medicine; Database; Data quality; Medical diagnosis; Diagnosis code; Data mining; Computer science; Statistics; Engineering; Pathology; Operations management","routes":{"ca_aff":true,"ca_fund":true,"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":["metaresearch","sts","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02554563,0.000243685,0.0005410011,0.0002317217,0.006203273,0.0002094068,0.0008004468,0.0009120677,0.002035257],"category_scores_gemma":[0.03881672,0.0001683089,0.0001589431,0.0004476507,0.00009391439,0.0001410269,0.002987051,0.009108473,0.000397587],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004425142,"about_ca_system_score_gemma":0.005964052,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002734327,"about_ca_topic_score_gemma":0.003667489,"domain_scores_codex":[0.9883003,0.00563398,0.001444798,0.0005258875,0.002294572,0.001800489],"domain_scores_gemma":[0.9800519,0.01567149,0.0004496432,0.001564508,0.001653127,0.0006093585],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0159149,0.0005680616,0.007942538,0.04429255,0.0001715916,0.0001680101,0.05075479,0.00002635961,0.00002965085,0.03770385,0.8262151,0.01621258],"study_design_scores_gemma":[0.02714241,0.0009823334,0.001868535,0.0237606,0.00004457062,0.000002429487,0.08198793,0.015149,0.00005380601,0.001694899,0.8466607,0.0006527469],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.548386,0.008260986,0.02062456,0.1531156,0.01638266,0.03590975,0.00188845,0.001370008,0.2140619],"genre_scores_gemma":[0.9184858,0.01094468,0.0021008,0.008694516,0.009273096,0.009965567,0.005648461,0.0001861437,0.03470092],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3700998,"threshold_uncertainty_score":0.9996712,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4802990170877911,"score_gpt":0.607431988734799,"score_spread":0.1271329716470079,"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."}}