{"id":"W3109500069","doi":"10.1016/j.compbiomed.2020.104142","title":"Robust identification of Parkinson's disease subtypes using radiomics and hybrid machine learning","year":2020,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Parkinson's Disease Mechanisms and Treatments","field":"Medicine","cited_by":58,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Michael J. Fox Foundation for Parkinson's Research","keywords":"Radiomics; Identification (biology); Parkinson's disease; Machine learning; Artificial intelligence; Computer science; Disease; Medicine; Pathology; Biology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001329328,0.0007430366,0.001000461,0.002348404,0.0002629388,0.001165586,0.0006761073,0.000903152,0.0009847038],"category_scores_gemma":[0.002715105,0.0002485173,0.0008866633,0.001076318,0.0003305533,0.000792367,0.0006949718,0.0006473353,0.001219494],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002308338,"about_ca_system_score_gemma":0.0003664066,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001227246,"about_ca_topic_score_gemma":0.002272801,"domain_scores_codex":[0.9992404,0.0002387541,0.00005116475,0.0002151,0.0001690447,0.00008557393],"domain_scores_gemma":[0.9988569,0.0004647149,0.000183652,0.0001297277,0.000328832,0.00003614274],"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":[0.001209426,0.0002687364,0.03483983,0.0003451868,0.000517672,0.0003931774,0.0001526892,0.03876228,0.1124531,0.002162701,0.003579433,0.8053157],"study_design_scores_gemma":[0.0001218193,0.0005419594,0.06398421,0.00009223229,0.0005847724,0.001795225,0.0002351011,0.8724455,0.04594981,0.007330668,0.006759588,0.0001591903],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1907125,0.003060539,0.7979521,0.0003152811,0.0002269434,0.0001529201,0.001267413,0.002076789,0.004235612],"genre_scores_gemma":[0.769736,0.0008701209,0.2237859,0.0002294912,0.0002167171,0.0001418817,0.002085513,0.0002098442,0.002724531],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002348404,"threshold_uncertainty_score":0.007030249,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03620372923167545,"score_gpt":0.2890472018985741,"score_spread":0.2528434726668986,"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."}}