{"id":"W3170809055","doi":"10.1016/j.artmed.2021.102118","title":"The Physiological Deep Learner: First application of multitask deep learning to predict hypotension in critically ill patients","year":2021,"lang":"en","type":"article","venue":"Artificial Intelligence in Medicine","topic":"Hemodynamic Monitoring and Therapy","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Deep learning; Mean arterial pressure; Hemodynamics; Artificial intelligence; Computer science; Confidence interval; Task (project management); Critically ill; Blood pressure; Medicine; Heart rate; Machine learning; Cardiology; Internal medicine","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":[0.0006533549,0.0001469653,0.0003766311,0.0001174375,0.0001052137,0.000007353663,0.000141338,0.0001204579,0.00003828727],"category_scores_gemma":[0.008326693,0.0001002673,0.00004923434,0.0006188645,0.0002301465,0.00003411577,0.00005610514,0.0004546285,0.00003500749],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009578536,"about_ca_system_score_gemma":0.0000330897,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002864784,"about_ca_topic_score_gemma":0.000565129,"domain_scores_codex":[0.9980358,0.0001445154,0.0007228658,0.0003684286,0.0003986823,0.0003297089],"domain_scores_gemma":[0.997979,0.0006345508,0.00007614891,0.0003100852,0.0008660554,0.0001341695],"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":[0.0005367966,0.0007086861,0.069174,0.00007671007,0.00002002996,0.00005929578,0.002648661,0.007028781,0.04007177,0.001461774,0.00002642898,0.8781871],"study_design_scores_gemma":[0.001100984,0.003347656,0.3814241,0.001732747,0.00006894633,0.00002079906,0.01682478,0.5439284,0.03834448,0.008614299,0.004117335,0.0004754302],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9733884,0.0003462019,0.01936511,0.005900217,0.0003041082,0.0004568551,7.127791e-7,0.00003242579,0.0002059161],"genre_scores_gemma":[0.9974953,0.0004946687,0.0009972937,0.00067235,0.000220688,0.00004899512,0.00002372594,0.00001565072,0.00003133752],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8777117,"threshold_uncertainty_score":0.996843,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03182161579942656,"score_gpt":0.3253607468909631,"score_spread":0.2935391310915365,"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."}}