{"id":"W4403365098","doi":"10.1101/2024.10.11.24315328","title":"Discovering Subtypes with Imaging Signatures in the Motoric Cognitive Risk Syndrome Consortium using Weakly-Supervised Clustering","year":2024,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Institut Universitaire de Gériatrie de Montréal; Université du Québec à Montréal","funders":"Cure Alzheimer's Fund; National Institute on Aging; National Institutes of Health; Alzheimer's Association","keywords":"Cluster analysis; Cognition; Artificial intelligence; Computer science; Psychology; Neuroscience","routes":{"ca_aff":true,"ca_fund":false,"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":[0.005265111,0.0005176135,0.0008925484,0.002821351,0.001144145,0.001809568,0.001117222,0.0007609798,0.001583189],"category_scores_gemma":[0.01550997,0.0002290787,0.001118449,0.001795318,0.0004888074,0.0003931972,0.001802103,0.000551941,0.000475567],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007341366,"about_ca_system_score_gemma":0.001625482,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01857848,"about_ca_topic_score_gemma":0.02039029,"domain_scores_codex":[0.9978807,0.0008446757,0.0002515566,0.0005153938,0.0003440851,0.0001635428],"domain_scores_gemma":[0.9958483,0.001041531,0.0008901048,0.0008642998,0.0009041284,0.0004515626],"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":[0.0007781959,0.0001241154,0.9678707,0.00007058465,0.0006472651,0.0002391838,0.0007294627,0.001961855,0.00196636,0.0003942843,0.002254563,0.02296356],"study_design_scores_gemma":[0.0002471245,0.0001915279,0.95868,0.00009124453,0.0004451828,0.0009283655,0.001530155,0.03005968,0.001657252,0.00393291,0.002172316,0.0000642769],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9908941,0.0001624786,0.005607092,0.0001918031,0.00001101717,0.0001407341,0.002358381,0.00007969287,0.0005548611],"genre_scores_gemma":[0.9834782,0.00005452893,0.008640258,0.00005313416,0.00001883564,0.0002250238,0.007030013,0.00004542179,0.0004545846],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01857848,"threshold_uncertainty_score":0.03694063,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01926687181532404,"score_gpt":0.3037480600078023,"score_spread":0.2844811881924783,"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."}}