{"id":"W4362703920","doi":"10.1016/j.jbi.2023.104357","title":"Deep learning prediction of motor performance in stroke individuals using neuroimaging data","year":2023,"lang":"en","type":"article","venue":"Journal of Biomedical Informatics","topic":"Stroke Rehabilitation and Recovery","field":"Medicine","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University Health Centre; Centre Intégré de Santé et de Services Sociaux des Laurentides; Jewish Rehabilitation Hospital; McGill University","funders":"Canadian Institutes of Health Research; Fonds de Recherche du Québec - Santé; Université de Genève; University of British Columbia; Türkiye Bilimsel ve Teknolojik Araştırma Kurumu; UCL Institute of Neurology, University College London; Canada Foundation for Innovation","keywords":"Artificial intelligence; Fractional anisotropy; Support vector machine; Diffusion MRI; Convolutional neural network; Neuroimaging; Computer science; Machine learning; Naive Bayes classifier; Pattern recognition (psychology); Cross-validation; Population; Magnetic resonance imaging; Medicine; Psychology; Neuroscience; Radiology","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001457765,0.00008040833,0.0003261111,0.0009876192,0.00003442011,0.00001440888,0.0001775155,0.00008529982,0.00002611499],"category_scores_gemma":[0.001152783,0.00006120933,0.00007667039,0.0006123412,0.0001193135,0.0005826759,0.0001117449,0.0004902988,0.000006524839],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006268693,"about_ca_system_score_gemma":0.000180947,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002036986,"about_ca_topic_score_gemma":1.212665e-7,"domain_scores_codex":[0.9977626,0.00004078748,0.001245831,0.00004992773,0.0007242802,0.0001765678],"domain_scores_gemma":[0.998723,0.0002457459,0.0005909259,0.0001673312,0.0001345717,0.0001383665],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000154132,0.000226472,0.9076453,0.001638079,0.000160896,0.00003154594,0.004718127,0.004074771,0.007019637,0.000005543365,0.000770236,0.07355527],"study_design_scores_gemma":[0.001456047,0.0006261652,0.360114,0.0006475877,0.00006065659,0.0002258447,0.003129927,0.627943,0.00009935351,0.000004399908,0.005645321,0.0000476401],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9964479,0.00007579392,0.002487561,0.0002290093,0.0004742056,0.0001098903,0.00002480684,0.00001643867,0.0001344118],"genre_scores_gemma":[0.9886428,0.0005586442,0.01040711,0.00008338327,0.000197922,5.203515e-7,0.00005532745,0.00000978283,0.00004454267],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6238682,"threshold_uncertainty_score":0.2496044,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0531152743285396,"score_gpt":0.3218665079062785,"score_spread":0.2687512335777389,"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."}}