{"id":"W4417223250","doi":"10.48550/arxiv.2504.00052","title":"Assessing Validity of ICD-10 Administrative Data in Coding Comorbidities","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Medical Coding and Health Information","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Comorbidity; Coding (social sciences); Chart; Health informatics; Diagnosis code; Informatics; Diabetes mellitus","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1179028,0.0005561395,0.0006349322,0.005748529,0.001289914,0.003350368,0.002084933,0.001023035,0.0006172689],"category_scores_gemma":[0.3556592,0.0006698843,0.001797241,0.006228425,0.002226051,0.002158278,0.003120428,0.001087622,0.0002032037],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00413086,"about_ca_system_score_gemma":0.006573291,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.07175966,"about_ca_topic_score_gemma":0.06809028,"domain_scores_codex":[0.8919778,0.05940513,0.01427427,0.007464375,0.02449048,0.002387934],"domain_scores_gemma":[0.5914227,0.2164387,0.1046123,0.021749,0.06322823,0.002549072],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00004122775,0.00001350634,0.9958236,0.00005289101,0.0001668101,0.00001053022,0.0003398626,0.0003162629,0.00002609125,0.0001199727,0.0002447111,0.002844555],"study_design_scores_gemma":[0.00001926643,0.00009233021,0.9891221,0.0004174275,0.0001543663,0.0001130992,0.0008242958,0.006736184,0.0003309138,0.0004099026,0.001750915,0.00002917338],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9760005,0.002001089,0.01177598,0.001345869,0.00023354,0.0003926837,0.003768458,0.00005463,0.004427276],"genre_scores_gemma":[0.9919323,0.0002472829,0.005212572,0.0002158935,0.00007790043,0.0001568457,0.002002124,0.00001449799,0.0001406393],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8820972,"threshold_uncertainty_score":0.6235369,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7906320805313973,"score_gpt":0.5919478072159695,"score_spread":0.1986842733154278,"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."}}