{"id":"W4405621264","doi":"10.48550/arxiv.2408.11861","title":"Speaking the Same Language: Leveraging LLMs in Standardizing Clinical Data for AI","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Artificial Intelligence in Law","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Health and Medical Research Council; Canadian Institutes of Health Research; Genentech; National Institutes of Health; IXICO; H. Lundbeck A/S; National Cancer Institute; Servier; Vetenskapsrådet; Eisai; Lunds Universitet; University of Melbourne; Royal Swedish Academy of Sciences; Commonwealth Scientific and Industrial Research Organisation; Northern California Institute for Research and Education; State Government of Victoria; BioClinica; Biogen; Pfizer; Novartis Pharmaceuticals Corporation; University of Southern California; Dementia Collaborative Research Centres, Australia; Edith Cowan University; Bristol-Myers Squibb; Eli Lilly and Company; Torsten Söderbergs Stiftelse; Alzheimer's Disease Neuroimaging Initiative; Medical Research Council; Meso Scale Diagnostics; Science and Industry Endowment Fund; Alzheimer's Association","keywords":"Computer science; Data science","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03745456,0.000606427,0.0006109605,0.003506904,0.001095629,0.00791335,0.002103527,0.001459064,0.002361215],"category_scores_gemma":[0.1186398,0.0005624402,0.001799576,0.002913937,0.003547432,0.01093366,0.006911512,0.00307461,0.001353572],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002272257,"about_ca_system_score_gemma":0.007808885,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004146086,"about_ca_topic_score_gemma":0.005603595,"domain_scores_codex":[0.95561,0.03278164,0.003644631,0.003328341,0.004130426,0.0005049586],"domain_scores_gemma":[0.8930743,0.06363455,0.007580795,0.02589175,0.008536076,0.001282565],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004255906,0.0004828653,0.01529415,0.0008175405,0.0002450363,0.0006557264,0.01368989,0.04125285,0.01011307,0.4810184,0.01015665,0.4258483],"study_design_scores_gemma":[0.00009712417,0.0002969818,0.002991431,0.0008897706,0.0002182628,0.0006170624,0.004209299,0.3477222,0.01613808,0.5477891,0.07883712,0.0001935668],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01174016,0.0001745348,0.9765638,0.00525746,0.0000928873,0.0003685954,0.0003663956,0.001397417,0.004038854],"genre_scores_gemma":[0.1262417,0.0001757979,0.8703958,0.0009530539,0.00007239483,0.000367438,0.0007070998,0.0002735007,0.0008130543],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03745456,"threshold_uncertainty_score":0.198081,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3928649249160623,"score_gpt":0.3865061568719257,"score_spread":0.006358768044136598,"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."}}