{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.001606579,0.0003703633,0.0004413133,0.0002270331,0.0001939629,0.0001249655,0.0005287557,0.0005331006,0.000009048142],"category_scores_gemma":[0.0001759811,0.0003389216,0.0002171461,0.0001468919,0.000154839,0.000003564127,0.0007214895,0.004001913,0.00001149363],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007445979,"about_ca_system_score_gemma":0.005224314,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002904341,"about_ca_topic_score_gemma":0.005828435,"domain_scores_codex":[0.9961986,0.0002226347,0.0006087313,0.0006609565,0.0002532575,0.002055842],"domain_scores_gemma":[0.9989851,0.00002429371,0.0003167982,0.0004533513,0.00004208769,0.0001783653],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.002293294,0.0030883,0.2452567,0.004906176,0.01260866,0.001453611,0.001815143,0.03508428,0.2930322,0.003912415,0.02239913,0.37415],"study_design_scores_gemma":[0.03878472,0.01408132,0.2815818,0.03508195,0.003667285,0.02966443,0.008713293,0.04581346,0.03737481,0.4535189,0.02930311,0.022415],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9295323,0.05941853,0.008498015,0.0008493749,0.0009646166,0.0002744436,0.000405195,0.00003654799,0.00002094343],"genre_scores_gemma":[0.9851761,0.01159073,0.0005401429,0.0001265431,0.0006573042,0.00001713537,0.001707337,0.00004984434,0.000134799],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4496064,"threshold_uncertainty_score":0.9999063,"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."}}