{"id":"W3165101924","doi":"10.1038/s41467-021-23311-9","title":"Predicting optimal deep brain stimulation parameters for Parkinson’s disease using functional MRI and machine learning","year":2021,"lang":"en","type":"article","venue":"Nature Communications","topic":"Neurological disorders and treatments","field":"Medicine","cited_by":301,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Brain Institute; Toronto Western Hospital; University of Toronto; University Health Network","funders":"Michael J. Fox Foundation for Parkinson's Research","keywords":"Deep brain stimulation; Functional magnetic resonance imaging; Stimulation; Neuroimaging; Brain stimulation; Parkinson's disease; Medicine; Neuroscience; Magnetic resonance imaging; Functional connectivity; Machine learning; Biomarker; Observational study; Physical medicine and rehabilitation; Artificial intelligence; Computer science; Psychology; Disease; Internal medicine; Radiology; Biology","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":[0.00008145102,0.00009292581,0.000122824,0.00004093585,0.0003993061,0.00002623766,0.00006276308,0.0001015525,0.00001592863],"category_scores_gemma":[0.0007803178,0.00008364915,0.00006807615,0.0001243913,0.00005470519,0.0000615452,0.000106927,0.0004522116,7.359791e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003012571,"about_ca_system_score_gemma":0.0000462523,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006654705,"about_ca_topic_score_gemma":0.00004240952,"domain_scores_codex":[0.9993541,0.0000922309,0.0001326985,0.0001979879,0.0001051779,0.0001178602],"domain_scores_gemma":[0.998796,0.0005737853,0.00005807833,0.0003649723,0.0001011086,0.0001059919],"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":[0.0003648681,0.0004824402,0.9808058,0.00003898935,0.000149809,0.00001411766,0.0001114194,0.01125002,0.0007166678,0.001044402,0.0001930657,0.004828392],"study_design_scores_gemma":[0.001731076,0.0001141615,0.3758385,0.0000320519,0.0002629611,0.00001519577,0.00006836411,0.6135009,0.00003400458,0.0006395392,0.007667019,0.00009617285],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9546639,0.01555596,0.01312095,0.01569805,0.00009011565,0.0005580508,0.00005586065,0.00009393398,0.0001631818],"genre_scores_gemma":[0.9577827,0.0002688752,0.03953965,0.001488052,0.00002258002,0.00003981721,0.000766548,0.00001381986,0.0000779879],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6049672,"threshold_uncertainty_score":0.3411113,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05153399375685683,"score_gpt":0.3227030667317585,"score_spread":0.2711690729749016,"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."}}