{"id":"W4399070329","doi":"10.1038/s41598-024-62567-1","title":"ClinicalGAN: powering patient monitoring in clinical trials with patient digital twins","year":2024,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; Pfizer; Novartis Pharmaceuticals Corporation; University of Southern California; Biogen; Eli Lilly and Company; Bristol-Myers Squibb; BioClinica; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; National Institute on Aging; Alzheimer's Association","keywords":"Computer science; Key (lock); Generative model; Clinical trial; Machine learning; Artificial intelligence; Generative grammar; Medicine","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":[0.01152935,0.0007356759,0.0009182815,0.0009533859,0.0004128813,0.001285603,0.001765669,0.001245439,0.004901604],"category_scores_gemma":[0.0307135,0.0006867782,0.0008039058,0.0007271937,0.00114879,0.00206588,0.002923936,0.001773738,0.001021065],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008543346,"about_ca_system_score_gemma":0.001666483,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001233664,"about_ca_topic_score_gemma":0.002052258,"domain_scores_codex":[0.9951799,0.003242134,0.0001883462,0.0007671865,0.0004757826,0.00014673],"domain_scores_gemma":[0.9864787,0.009220232,0.0009164407,0.002218649,0.0007496686,0.0004162894],"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":[0.0011787,0.0003067124,0.01655813,0.000497009,0.0002552592,0.0005581807,0.0006501814,0.4639015,0.005821862,0.03094475,0.01206274,0.467265],"study_design_scores_gemma":[0.0001522254,0.0002452342,0.001419246,0.00006339709,0.00005625796,0.000198609,0.00007393192,0.9446357,0.003299762,0.04176574,0.00806154,0.00002840376],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04187806,0.001063655,0.9439883,0.002566994,0.0002490657,0.0006860194,0.0008011045,0.00452251,0.004244385],"genre_scores_gemma":[0.6328758,0.000539124,0.3587187,0.001510852,0.000213419,0.0007822685,0.001320401,0.0004174256,0.003621927],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01152935,"threshold_uncertainty_score":0.0609737,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08468100225353671,"score_gpt":0.4142625346760938,"score_spread":0.3295815324225571,"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."}}