{"id":"W3133955102","doi":"10.1016/j.compbiomed.2021.104312","title":"Improved motor outcome prediction in Parkinson's disease applying deep learning to DaTscan SPECT images","year":2021,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Parkinson's Disease Mechanisms and Treatments","field":"Medicine","cited_by":41,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"Directorate for Engineering; Michael J. Fox Foundation for Parkinson's Research","keywords":"Rating scale; Convolutional neural network; Parkinson's disease; Spect imaging; Dopamine transporter; Artificial intelligence; Nuclear medicine; Medicine; Computer science; Pattern recognition (psychology); Disease; Mathematics; Statistics; Internal medicine; Dopamine; Dopaminergic","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":[0.0003340632,0.0006412257,0.0004890265,0.0004806625,0.0001327373,0.0005535218,0.000310889,0.0005860458,0.00100362],"category_scores_gemma":[0.001012343,0.0001696518,0.0003963636,0.0002571957,0.00009724625,0.0002864832,0.0003627737,0.0004753404,0.0003057477],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000306007,"about_ca_system_score_gemma":0.0004171899,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008533577,"about_ca_topic_score_gemma":0.01222168,"domain_scores_codex":[0.9999157,0.0000181911,0.000006363616,0.00002172569,0.00001534422,0.00002266862],"domain_scores_gemma":[0.9998152,0.00007000619,0.0000193752,0.00001627977,0.00005811737,0.00002100865],"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":[0.00205386,0.0005645548,0.05567164,0.0003236092,0.0005288211,0.001101981,0.00008891873,0.1326534,0.03724753,0.0008999292,0.01121229,0.7576535],"study_design_scores_gemma":[0.0000359232,0.0002124922,0.01744402,0.00003881614,0.0001086404,0.000279364,0.00002923754,0.9701311,0.009265706,0.0015569,0.0008752533,0.00002258846],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8849469,0.004230241,0.1028735,0.0009362093,0.000190362,0.00006870932,0.002344042,0.001673612,0.002736431],"genre_scores_gemma":[0.9861437,0.0004626418,0.01051784,0.00007588533,0.00003854427,0.00001559321,0.001086655,0.00002812088,0.001631016],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008533577,"threshold_uncertainty_score":0.01696777,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01810844040961531,"score_gpt":0.3047388359028246,"score_spread":0.2866303954932093,"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."}}