{"id":"W4225319089","doi":"10.1016/j.ebiom.2022.104027","title":"Identifying neuroimaging biomarkers of major depressive disorder from cortical hemodynamic responses using machine learning approaches","year":2022,"lang":"en","type":"article","venue":"EBioMedicine","topic":"Optical Imaging and Spectroscopy Techniques","field":"Medicine","cited_by":60,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; University Health Network","funders":"Kementerian Pendidikan Malaysia; Universiti Teknologi Petronas; National University of Singapore","keywords":"Major depressive disorder; Support vector machine; Artificial intelligence; Machine learning; Neuroimaging; Cross-validation; Verbal fluency test; Computer science; Test set; Biomarker; Cognition; Medicine; Neuropsychology; Psychiatry","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":[0.0005132126,0.0002400399,0.0005694572,0.0004611887,0.0003693853,0.00002023216,0.0001827288,0.00004818123,0.0003598477],"category_scores_gemma":[0.0004695247,0.0002146508,0.0001316525,0.0006007481,0.0004335876,0.00008720272,0.0003130568,0.000840285,0.000002010522],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001436338,"about_ca_system_score_gemma":0.00008745281,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001150074,"about_ca_topic_score_gemma":0.000004680261,"domain_scores_codex":[0.9976746,0.0002988878,0.000517523,0.0004951576,0.00062277,0.0003910223],"domain_scores_gemma":[0.9988601,0.0003439271,0.000200244,0.0003754175,0.00005354721,0.0001667567],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00116041,0.0003790956,0.2305371,0.0001347084,0.0002599811,0.0003466118,0.0005699471,0.00005073051,0.7636677,0.0001146832,0.00007464572,0.002704395],"study_design_scores_gemma":[0.008339539,0.001849336,0.1118931,0.0006812568,0.00171997,0.0009418003,0.004372092,0.8087409,0.05813115,0.001214491,0.001307677,0.0008087186],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9599103,0.002635978,0.03427143,0.001950064,0.0001897906,0.0003517081,0.0000501597,0.0002558735,0.0003846514],"genre_scores_gemma":[0.9778106,0.00003102301,0.02136526,0.0002163793,0.00008861219,0.00002458035,0.000178957,0.00006124996,0.0002232935],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8086902,"threshold_uncertainty_score":0.8753207,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04284955916327272,"score_gpt":0.3245025951146293,"score_spread":0.2816530359513565,"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."}}