{"id":"W3199719950","doi":"10.21037/qims-21-425","title":"Longitudinal clustering analysis and prediction of Parkinson’s disease progression using radiomics and hybrid machine learning","year":2021,"lang":"en","type":"article","venue":"Quantitative Imaging in Medicine and Surgery","topic":"Parkinson's Disease Mechanisms and Treatments","field":"Medicine","cited_by":47,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Massachusetts Department of Agricultural Resources","keywords":"Artificial intelligence; Cluster analysis; Computer science; Machine learning; Principal component analysis; Pattern recognition (psychology); Linear discriminant analysis","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":[0.002112142,0.0005134729,0.0004794964,0.002229614,0.000297212,0.0006130499,0.0004210207,0.0004112439,0.0006816855],"category_scores_gemma":[0.002618856,0.000161576,0.0008942296,0.0009728182,0.0002527931,0.0003677497,0.0004331963,0.0003814803,0.0003115346],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006894052,"about_ca_system_score_gemma":0.0005824047,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00523068,"about_ca_topic_score_gemma":0.005572826,"domain_scores_codex":[0.9994212,0.000221616,0.00005100845,0.0001804362,0.00007802658,0.00004774407],"domain_scores_gemma":[0.9985583,0.0005260344,0.0002764957,0.0001431523,0.0004166474,0.00007930207],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001533553,0.0004782682,0.3142382,0.00033594,0.0009877846,0.0002930844,0.0005906443,0.2624523,0.02798559,0.002561942,0.002735115,0.3858077],"study_design_scores_gemma":[0.00002515499,0.000346825,0.1143547,0.00003138973,0.0001220146,0.0002319915,0.00009672219,0.8743175,0.007277506,0.002037372,0.00108515,0.00007367998],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7266415,0.0006770352,0.2691862,0.0001695596,0.00003599506,0.0001275022,0.001189292,0.001012922,0.0009599659],"genre_scores_gemma":[0.9037779,0.0001040003,0.09442042,0.00002275867,0.00002049121,0.00009531622,0.001121758,0.00004138688,0.0003960454],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00523068,"threshold_uncertainty_score":0.01117015,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05209418235196464,"score_gpt":0.3335347539425118,"score_spread":0.2814405715905471,"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."}}