{"id":"W4414396056","doi":"10.1093/ajeadv/uuaf010","title":"ICD-10 code embedding for patient matching: a first step toward applications in causal inference from hospital discharge data","year":2025,"lang":"en","type":"article","venue":"AJE Advances Research in Epidemiology","topic":"Medical Coding and Health Information","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"University of Bern","keywords":"Propensity score matching; Causal inference; Matching (statistics); Set (abstract data type); Inference; Observational study; Population; Pooling; Code (set theory)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01077907,0.0006864514,0.0007387098,0.002118389,0.000449284,0.001521854,0.001173049,0.001011069,0.007540751],"category_scores_gemma":[0.06083006,0.0004478061,0.0009617895,0.001851642,0.0005539429,0.001671206,0.003058439,0.002050578,0.001913639],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004928565,"about_ca_system_score_gemma":0.001889817,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002118496,"about_ca_topic_score_gemma":0.003035651,"domain_scores_codex":[0.9928902,0.004976811,0.0004398926,0.0007399825,0.0008217813,0.0001312556],"domain_scores_gemma":[0.9807967,0.01349688,0.0008623033,0.00323406,0.001274161,0.0003358914],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006582465,0.0004632606,0.03898327,0.0005851646,0.0008566644,0.000214208,0.0004884484,0.04776252,0.004292028,0.0415308,0.0342577,0.8299077],"study_design_scores_gemma":[0.000299652,0.000340338,0.008209698,0.0002532006,0.0001180163,0.0003782978,0.0002009019,0.8501323,0.004677325,0.1122121,0.02309474,0.00008343508],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01391714,0.0004101807,0.9786472,0.001243603,0.0001915193,0.0002868197,0.001805031,0.0027741,0.0007242984],"genre_scores_gemma":[0.1117454,0.0002680761,0.882879,0.000544061,0.0002035658,0.0004799596,0.002793267,0.0004118348,0.0006748354],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01077907,"threshold_uncertainty_score":0.05700582,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4973699652473476,"score_gpt":0.628304726194639,"score_spread":0.1309347609472914,"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."}}