{"id":"W4409263895","doi":"10.21203/rs.3.rs-4619161/v2","title":"Predicting cognitive decline in prodromal synucleinopathies using clinical markers and machine learning","year":2025,"lang":"en","type":"preprint","venue":"Research Square","topic":"Parkinson's Disease Mechanisms and Treatments","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Montréal; Montreal General Hospital; Hôpital du Sacré-Cœur de Montréal; Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Alliance de recherche numérique du Canada; Fonds de Recherche du Québec - Santé; Institut de Valorisation des Données","keywords":"Synucleinopathies; Cognition; Cognitive impairment; Psychology; Cognitive decline; Artificial intelligence; Machine learning; Medicine; Neuroscience; Cognitive psychology; Computer science; Internal medicine; Disease; Dementia","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001405202,0.0008241177,0.0006223162,0.001723262,0.000203406,0.001538836,0.0003506211,0.0008206391,0.00124858],"category_scores_gemma":[0.005702892,0.0001781873,0.0005505447,0.0007211352,0.0002526004,0.0007354061,0.0004342207,0.00074628,0.0004910551],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003694973,"about_ca_system_score_gemma":0.0004075856,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00330704,"about_ca_topic_score_gemma":0.003238524,"domain_scores_codex":[0.9997303,0.00009779581,0.00002656738,0.00006962912,0.00004043468,0.00003527791],"domain_scores_gemma":[0.9979147,0.001130705,0.0003754809,0.0001283844,0.0002886548,0.0001621062],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002019896,0.000420437,0.9176363,0.0000764064,0.0003028963,0.0002542388,0.00007071924,0.008376434,0.001206288,0.000412113,0.001920308,0.067304],"study_design_scores_gemma":[0.0001516793,0.001032982,0.8180534,0.0001016682,0.0004375148,0.0008874199,0.0002961564,0.1621676,0.003290572,0.01190159,0.001630671,0.00004882583],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.990475,0.00141693,0.003915187,0.0005886454,0.00006074559,0.00003140713,0.001587028,0.0001092242,0.001815814],"genre_scores_gemma":[0.9954613,0.0004041276,0.002115106,0.00005766519,0.0000679326,0.00001476201,0.001155228,0.00001024891,0.0007137267],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00330704,"threshold_uncertainty_score":0.007431448,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1213206781275133,"score_gpt":0.4526765454036756,"score_spread":0.3313558672761622,"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."}}