{"id":"W2960026766","doi":"10.1016/j.compbiomed.2019.103355","title":"Prediction of epileptic seizures with convolutional neural networks and functional near-infrared spectroscopy signals","year":2019,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Optical Imaging and Spectroscopy Techniques","field":"Medicine","cited_by":59,"is_retracted":false,"has_abstract":false,"ca_institutions":"Montreal Heart Institute; Hôpital Notre-Dame; Polytechnique Montréal","funders":"Université de Montréal; Consejo Nacional de Ciencia y Tecnología","keywords":"Functional near-infrared spectroscopy; Convolutional neural network; Electroencephalography; Modality (human–computer interaction); Computer science; Artificial intelligence; Pattern recognition (psychology); Epileptic seizure; Epilepsy; Artificial neural network; Predictive value; Neuroscience; Psychology; Medicine; Cognition","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":[0.0001887523,0.0001194053,0.0003655795,0.00009974781,0.00003584012,0.000003649911,0.00002792796,0.0001023545,0.0000648427],"category_scores_gemma":[0.00002703361,0.00008059809,0.00001655144,0.0001089095,0.0007963958,0.00003714327,0.00002731833,0.0002424746,4.413913e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002137018,"about_ca_system_score_gemma":0.0000297478,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001730302,"about_ca_topic_score_gemma":0.000001016304,"domain_scores_codex":[0.9992416,0.00004321839,0.0002180361,0.0002429489,0.00007952072,0.0001746888],"domain_scores_gemma":[0.9995164,0.0001851274,0.00005808457,0.0001067749,0.0000519744,0.00008160196],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001178073,0.00009424592,0.9629653,0.0001114886,0.0000908918,0.00002094815,0.0001186253,0.0001710772,0.02597971,0.005792132,0.002402509,0.001074972],"study_design_scores_gemma":[0.004348846,0.005883338,0.7685173,0.0005392362,0.00008550627,0.0004635952,0.00005738337,0.2162449,0.0006324375,0.002779037,0.0003233425,0.0001250854],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9460405,0.001521017,0.04921738,0.001587016,0.0002935684,0.0003167148,0.000004374908,0.00006012768,0.0009593161],"genre_scores_gemma":[0.9914873,0.0001836165,0.007269902,0.000748473,0.0001657559,0.000006420858,0.00005997378,0.000006830784,0.00007175019],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2160738,"threshold_uncertainty_score":0.3286695,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01384531842985202,"score_gpt":0.2842485224829542,"score_spread":0.2704032040531021,"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."}}