{"id":"W3123995491","doi":"10.1111/jon.12835","title":"Differentiating Dementia with Lewy Bodies and Alzheimer's Disease by Deep Learning to Structural MRI","year":2021,"lang":"en","type":"article","venue":"Journal of Neuroimaging","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"SNC-Lavalin (Canada)","funders":"","keywords":"Dementia with Lewy bodies; Medicine; Artificial intelligence; Deep learning; Voxel; Dementia; Convolutional neural network; Atrophy; Temporal lobe; Voxel-based morphometry; Pattern recognition (psychology); Pathology; Radiology; Magnetic resonance imaging; Disease; White matter; Computer science; Psychiatry; Epilepsy","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001487658,0.0001335596,0.0002345648,0.0001252652,0.0001684032,0.0001506345,0.0000576158,0.00001092526,0.0001125446],"category_scores_gemma":[0.0001652403,0.0001008807,0.00006577558,0.0000947637,0.0000466895,0.0002168419,0.000103352,0.0003695789,0.000001988138],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001552417,"about_ca_system_score_gemma":0.00007575183,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000264916,"about_ca_topic_score_gemma":0.000001959664,"domain_scores_codex":[0.9986584,0.0001054931,0.0002621935,0.0001922771,0.0005003359,0.0002812901],"domain_scores_gemma":[0.9989903,0.00006657066,0.0001399657,0.00008230244,0.0003331198,0.0003877216],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002920337,0.0000512877,0.9553172,0.00005121211,0.0003456511,0.001413518,0.0003732589,0.00003192279,0.02261744,0.000003304688,0.0002490524,0.01925415],"study_design_scores_gemma":[0.001766212,0.000501562,0.9870926,0.000258267,0.0008845101,0.0008124434,0.0009329934,0.001515772,0.00484294,0.00003329445,0.001224292,0.0001351676],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9898586,0.00450705,0.00163821,0.003558301,0.00006864193,0.00010906,0.000001571701,0.00001183473,0.0002467459],"genre_scores_gemma":[0.9975443,0.0001544776,0.001423947,0.0006053526,0.0001009825,0.000001863414,0.000005339691,0.00002142693,0.0001422491],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03177537,"threshold_uncertainty_score":0.4113796,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01423797291670344,"score_gpt":0.2966099226224678,"score_spread":0.2823719497057644,"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."}}