{"id":"W2982362945","doi":"10.1016/j.neuroimage.2019.116316","title":"Pharmacologically informed machine learning approach for identifying pathological states of unconsciousness via resting-state fMRI","year":2019,"lang":"en","type":"article","venue":"NeuroImage","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"National Institute of General Medical Sciences; Medical School, University of Michigan; National Institutes of Health","keywords":"Unconsciousness; Wakefulness; Artificial intelligence; Consciousness; Machine learning; Resting state fMRI; Receiver operating characteristic; Sedation; Persistent vegetative state; Artificial neural network; Support vector machine; Level of consciousness; Computer science; Minimally conscious state; Psychology; Neuroscience; Medicine; Electroencephalography; Anesthesia","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":[0.0009422326,0.000614667,0.000551965,0.0007722718,0.0002025493,0.0006214342,0.0005659987,0.0007323128,0.0004919492],"category_scores_gemma":[0.001832446,0.0002143469,0.000519519,0.0003171464,0.0002465009,0.0004527643,0.0003248221,0.0008372759,0.0002261058],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000279945,"about_ca_system_score_gemma":0.0004865273,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008094835,"about_ca_topic_score_gemma":0.001407025,"domain_scores_codex":[0.9997515,0.0001010732,0.00001897076,0.00006739928,0.00003721159,0.00002385938],"domain_scores_gemma":[0.9996313,0.0002036944,0.00006180666,0.00003429475,0.00005489428,0.00001397596],"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":[0.0008115732,0.00111193,0.02873478,0.0003511318,0.0006991906,0.000452384,0.0001838523,0.2562851,0.1408806,0.004507184,0.002476784,0.5635055],"study_design_scores_gemma":[0.00001749508,0.0002351531,0.008454089,0.00001559002,0.00006204344,0.0001258367,0.00002423978,0.9782293,0.00911297,0.003192871,0.0005071055,0.00002333882],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2369915,0.002061214,0.757122,0.0006233061,0.0000495951,0.0002070244,0.0003767269,0.0008652415,0.001703304],"genre_scores_gemma":[0.8692765,0.00060865,0.1281364,0.0002852328,0.00007711327,0.0002531818,0.0004478679,0.00003522922,0.0008797467],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0009422326,"threshold_uncertainty_score":0.004983068,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0692314549494197,"score_gpt":0.3165707767076514,"score_spread":0.2473393217582318,"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."}}