{"id":"W4399616485","doi":"10.2139/ssrn.4863974","title":"Robustly Measuring Multiple Long-Term Health Conditions Using Disparate Linked Datasets in UK Biobank","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"Institute of Population and Public Health","funders":"Medical Research Council","keywords":"Biobank; Term (time); Data science; Computer science; Geography; Biology; Bioinformatics; Physics","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":[0.005845218,0.0008738389,0.00120118,0.006667946,0.0007141788,0.004324181,0.001109916,0.002190355,0.001886196],"category_scores_gemma":[0.03527711,0.0004856294,0.001147943,0.009356169,0.0006094371,0.002787329,0.004047764,0.001202509,0.001432966],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001656986,"about_ca_system_score_gemma":0.00195832,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0248946,"about_ca_topic_score_gemma":0.03262983,"domain_scores_codex":[0.9935126,0.001866961,0.0009172155,0.0019784,0.001284182,0.0004407657],"domain_scores_gemma":[0.9767208,0.01323937,0.00381506,0.003451893,0.002282989,0.0004899267],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002076842,0.0004529241,0.8067747,0.001616509,0.00287428,0.001142329,0.001649852,0.01866106,0.01072,0.003745769,0.02537514,0.1249106],"study_design_scores_gemma":[0.0001676258,0.0002127407,0.9089301,0.0007288792,0.001237551,0.0009695816,0.002311567,0.03906535,0.005424374,0.01273526,0.0280721,0.0001448999],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7709218,0.004782342,0.03484686,0.004056502,0.000350557,0.0002966647,0.1784205,0.0009213522,0.005403395],"genre_scores_gemma":[0.7923222,0.001195124,0.0246465,0.0005884459,0.0001617169,0.0003195225,0.1791809,0.00008774053,0.00149792],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0248946,"threshold_uncertainty_score":0.04949939,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04653986490803771,"score_gpt":0.3385454665720985,"score_spread":0.2920056016640608,"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."}}