{"id":"W2785925437","doi":"10.1609/aaai.v32i1.11891","title":"DeepHeart: Semi-Supervised Sequence Learning for Cardiovascular Risk Prediction","year":2018,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"ECG Monitoring and Analysis","field":"Medicine","cited_by":142,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Wearable computer; Computer science; Machine learning; Supervised learning; Wearable technology; Artificial intelligence; Blood pressure; Sleep apnea; Classifier (UML); Medicine; Cardiology; Internal medicine; Embedded system","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":[0.0008531984,0.0001990185,0.0004001065,0.0001217734,0.0004002733,0.0000681802,0.0003100203,0.0001231781,0.00006237933],"category_scores_gemma":[0.001452265,0.0001486821,0.0005564796,0.0004980019,0.0003547957,0.0001269514,0.00006943107,0.0003775101,0.00005922511],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006336461,"about_ca_system_score_gemma":0.00008408833,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001039731,"about_ca_topic_score_gemma":0.000004332459,"domain_scores_codex":[0.9982362,0.00002254783,0.0004639692,0.00045508,0.0005011822,0.0003210455],"domain_scores_gemma":[0.9979117,0.0000788299,0.0002362286,0.0002592313,0.001401812,0.0001121881],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001402413,0.0004875649,0.07323688,0.0005886884,0.001638122,0.000001804193,0.004544125,0.001114922,0.4112216,0.02500914,0.0004720143,0.4802827],"study_design_scores_gemma":[0.0001350301,0.001213345,0.001021082,0.0007321463,0.0008854966,0.00001099919,0.001818016,0.1920491,0.7890638,0.01147319,0.001352377,0.0002454275],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9742509,0.0001202355,0.01886896,0.0008817779,0.0006051221,0.0007858882,0.00001756522,0.0001677923,0.004301766],"genre_scores_gemma":[0.9963192,0.0001560636,0.002108847,0.00004859319,0.0007584422,0.00005046454,0.000002614152,0.0000237382,0.0005320084],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4800373,"threshold_uncertainty_score":0.6063079,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0954081901217702,"score_gpt":0.3158907397834265,"score_spread":0.2204825496616563,"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."}}