{"id":"W2964037754","doi":"10.48550/arxiv.1802.02511","title":"DeepHeart: Semi-Supervised Sequence Learning for Cardiovascular Risk Prediction","year":2018,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Non-Invasive Vital Sign Monitoring","field":"Engineering","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Wearable computer; Artificial intelligence; Machine learning; Computer science; Wearable technology; Supervised learning; Heuristic; Blood pressure; Medicine; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002148926,0.001452341,0.0006904142,0.0006036691,0.000277876,0.0005348726,0.001528662,0.001254442,0.002002012],"category_scores_gemma":[0.005601446,0.0004621454,0.0007165771,0.0005157979,0.000345625,0.0008964857,0.001132565,0.001815884,0.001419971],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004977913,"about_ca_system_score_gemma":0.0009497658,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005221245,"about_ca_topic_score_gemma":0.00957682,"domain_scores_codex":[0.9992802,0.000294213,0.00004459494,0.0002142087,0.00009211234,0.00007475552],"domain_scores_gemma":[0.9977258,0.001356874,0.0001386987,0.0003105555,0.0003669939,0.0001011063],"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":[0.001135103,0.001375798,0.01931227,0.0004133788,0.0007590384,0.0003227362,0.0002651626,0.3783879,0.01345087,0.001377636,0.02839528,0.5548049],"study_design_scores_gemma":[0.00003465508,0.0001310953,0.001661822,0.00001748426,0.00002546564,0.00004916783,0.00001411824,0.9923769,0.003668013,0.001307467,0.0006972232,0.00001641719],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3425371,0.002685374,0.6210097,0.001082857,0.0007210411,0.0002591136,0.00668862,0.02182295,0.00319317],"genre_scores_gemma":[0.829863,0.0003921698,0.1527291,0.0006298214,0.0001660382,0.0002806314,0.01156987,0.0002528337,0.004116677],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005221245,"threshold_uncertainty_score":0.01136476,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04567829106625716,"score_gpt":0.1668266726598555,"score_spread":0.1211483815935984,"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."}}