{"id":"W4399390361","doi":"10.3390/tomography10060068","title":"Causal Forest Machine Learning Analysis of Parkinson’s Disease in Resting-State Functional Magnetic Resonance Imaging","year":2024,"lang":"en","type":"article","venue":"Tomography","topic":"Parkinson's Disease Mechanisms and Treatments","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. Michael's Hospital; University of Toronto","funders":"Avid Radiopharmaceuticals; Jazz Pharmaceuticals; Genentech; Celgene; Allergan; Bristol-Myers Squibb; Eli Lilly and Company; Biogen","keywords":"Interpretability; Functional magnetic resonance imaging; Artificial intelligence; Machine learning; Feature selection; Logistic regression; Magnetic resonance imaging; Disease; Computer science; Random forest; Population; F1 score; Pattern recognition (psychology); Psychology; Medicine; Pathology; 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":[0.001740076,0.0004307843,0.0004204301,0.00204769,0.0002974847,0.0004105134,0.0003011602,0.0003887858,0.0007346376],"category_scores_gemma":[0.003799315,0.000119898,0.000676339,0.0007813809,0.0002302431,0.0004042303,0.0002397371,0.0003394755,0.0001403005],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002895993,"about_ca_system_score_gemma":0.0004628025,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006356595,"about_ca_topic_score_gemma":0.005595767,"domain_scores_codex":[0.9995767,0.0001534197,0.00002761513,0.00008568312,0.00008714206,0.00006945225],"domain_scores_gemma":[0.9988086,0.0007679475,0.0001283569,0.00007682012,0.0001879344,0.00003034034],"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":[0.0008679151,0.0004456969,0.1383138,0.0002428144,0.0005457107,0.001518547,0.000313575,0.3109984,0.02059003,0.009920735,0.004658859,0.5115839],"study_design_scores_gemma":[0.000009910589,0.00005828466,0.0290087,0.00001410605,0.000043357,0.0002409387,0.00003849425,0.9622825,0.002629701,0.005035535,0.0006219925,0.0000165748],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3674836,0.001289624,0.6278006,0.0003821366,0.00008298402,0.00009458463,0.0006959228,0.001074424,0.001096196],"genre_scores_gemma":[0.9456822,0.0002134418,0.05298585,0.00003638586,0.00004105617,0.00004486314,0.0005455496,0.00002025684,0.0004303196],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006356595,"threshold_uncertainty_score":0.01263922,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01072477280159449,"score_gpt":0.2463795980748687,"score_spread":0.2356548252732742,"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."}}