{"id":"W4405441807","doi":"10.1093/braincomms/fcae445","title":"Deep learning-based patient stratification for prognostic enrichment of clinical dementia trials","year":2024,"lang":"en","type":"article","venue":"Brain Communications","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":20,"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; F. Hoffmann-La Roche; University of Southern California; Biogen; Eli Lilly and Company; Bristol-Myers Squibb; BioClinica; European Commission; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Pfizer; National Institute on Aging; Alzheimer's Association","keywords":"Stratification (seeds); Dementia; Clinical trial; Risk stratification; Medicine; Environmental science; Intensive care medicine; Internal medicine; Disease; Biology","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005070078,0.000122775,0.000333426,0.0001517105,0.0002652866,0.0001444211,0.00147751,0.00009228811,0.00001882049],"category_scores_gemma":[0.007247053,0.0001142247,0.0002315621,0.0004394756,0.00009498889,0.0001389061,0.000270346,0.0003956974,0.0000145932],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000357146,"about_ca_system_score_gemma":0.0003736297,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003802915,"about_ca_topic_score_gemma":0.00005099854,"domain_scores_codex":[0.9954348,0.002328565,0.001427264,0.0003618677,0.0002565515,0.000190911],"domain_scores_gemma":[0.9814844,0.01587445,0.0004890623,0.001844759,0.0002190821,0.0000882916],"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":[0.00001876417,0.0005320287,0.01001989,0.0004017206,0.0001852732,7.805615e-7,0.001739592,0.01053854,0.0001404176,0.2616679,0.002821273,0.7119339],"study_design_scores_gemma":[0.0002455653,0.0003957163,0.005272246,0.0001114454,0.00004737308,9.265731e-7,0.00004899425,0.9157234,0.00005505958,0.002617781,0.0753662,0.0001152833],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001340288,0.003916126,0.9593604,0.03266469,0.0004136457,0.001541526,0.00001118283,0.0003258842,0.0004262854],"genre_scores_gemma":[0.8351281,0.00006222803,0.1637993,0.0002630769,0.00004115404,0.0005295401,0.0001253236,0.00001382489,0.00003748566],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9051849,"threshold_uncertainty_score":0.8675922,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.159637736019877,"score_gpt":0.4578348148462694,"score_spread":0.2981970788263923,"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."}}