{"id":"W4254465874","doi":"10.21203/rs.3.rs-38213/v1","title":"Quantitative longitudinal predictions of Alzheimer's disease by multi-modal predictive learning","year":2020,"lang":"en","type":"preprint","venue":"Research Square (Research Square)","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Kuopion Yliopistollinen Sairaala; Servier; Tekniikan Edistämissäätiö; Eisai; F. Hoffmann-La Roche; Pfizer; Biogen; BioClinica; Eli Lilly and Company; U.S. Department of Defense; Meso Scale Diagnostics; Academy of Finland; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Bristol-Myers Squibb; National Institute on Aging; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Modal; Disease; Psychology; Computer science; Artificial intelligence; Medicine; Internal medicine; Chemistry","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":["metaresearch","metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":["sts"],"category_scores_codex":[0.01212026,0.001100195,0.001932034,0.003608386,0.001657842,0.0005049335,0.001613709,0.0008888094,0.001936098],"category_scores_gemma":[0.01404043,0.001056314,0.001138314,0.00396372,0.004316435,0.0005135007,0.005938172,0.01595891,0.0006882097],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001279657,"about_ca_system_score_gemma":0.007571557,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001835367,"about_ca_topic_score_gemma":0.00005885873,"domain_scores_codex":[0.9694304,0.008096419,0.001698538,0.003359746,0.01352211,0.003892805],"domain_scores_gemma":[0.9769458,0.003471211,0.0004235975,0.001853038,0.01328105,0.004025309],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.03335169,0.02027497,0.7625014,0.0224281,0.009590843,0.004506559,0.008022962,0.002067058,0.01993028,0.002709317,0.105292,0.009324877],"study_design_scores_gemma":[0.01048377,0.03114128,0.7741237,0.009514656,0.001444844,0.00003682528,0.01632907,0.1343316,0.009344821,0.003548508,0.007905365,0.001795645],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8077698,0.04485063,0.04584523,0.02731445,0.001033694,0.04278881,0.01238179,0.001571853,0.01644372],"genre_scores_gemma":[0.9847565,0.00344287,0.001115082,0.0000358342,0.0006393812,0.003606847,0.003569146,0.000310093,0.002524251],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1769867,"threshold_uncertainty_score":0.9996418,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.184338295171937,"score_gpt":0.4794871697402634,"score_spread":0.2951488745683264,"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."}}