{"id":"W3202889383","doi":"10.12688/wellcomeopenres.17148.1","title":"Using self-supervised feature learning to improve the use of pulse oximeter signals to predict paediatric hospitalization","year":2021,"lang":"en","type":"preprint","venue":"Wellcome Open Research","topic":"Non-Invasive Vital Sign Monitoring","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; BC Children's Hospital","funders":"Alliance for Accelerating Excellence in Science in Africa; African Academy of Sciences; New Partnership for Africa's Development; Government of the United Kingdom; Wellcome Trust","keywords":"Artificial intelligence; Deep learning; Machine learning; Computer science; Initialization; Logistic regression; Feature (linguistics); Supervised learning; Pattern recognition (psychology); Feature engineering; Feature extraction; Artificial neural network","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":[0.001643544,0.0006404695,0.0004090782,0.0006132427,0.0001871152,0.0004998025,0.0007980307,0.0007962981,0.001642367],"category_scores_gemma":[0.009510974,0.0002322092,0.0006414304,0.0002914617,0.0002691954,0.0007848454,0.0005975242,0.001012482,0.001074745],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005131129,"about_ca_system_score_gemma":0.000774089,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003593421,"about_ca_topic_score_gemma":0.005521134,"domain_scores_codex":[0.9993628,0.0002500537,0.00004418282,0.0001874952,0.0001016075,0.00005382228],"domain_scores_gemma":[0.9970543,0.001434961,0.0003382834,0.0002845277,0.0007687313,0.0001190857],"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":[0.001315203,0.001088168,0.1810228,0.0002702373,0.0004620542,0.0004068761,0.0002668056,0.2183614,0.02033848,0.0009906349,0.02668397,0.5487933],"study_design_scores_gemma":[0.00002402277,0.0001551106,0.01311252,0.00003349818,0.00003104594,0.00007651468,0.00002591537,0.9774132,0.007576945,0.0007808889,0.0007458717,0.00002439],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.7357166,0.001220045,0.2484419,0.002283613,0.0004454907,0.0001422766,0.002411768,0.005368951,0.003969506],"genre_scores_gemma":[0.9575734,0.000134955,0.03821791,0.000330512,0.00008190659,0.00008197278,0.002388049,0.0001134589,0.001077834],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.003593421,"threshold_uncertainty_score":0.008691967,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1114603563819283,"score_gpt":0.3392080182658952,"score_spread":0.2277476618839669,"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."}}