{"id":"W4392377510","doi":"10.3390/bioengineering11030251","title":"Contactless Blood Oxygen Saturation Estimation from Facial Videos Using Deep Learning","year":2024,"lang":"en","type":"article","venue":"Bioengineering","topic":"Non-Invasive Vital Sign Monitoring","field":"Engineering","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"RGB color model; Deep learning; Convolutional neural network; Computer science; Artificial intelligence; Pulse oximetry; Mean squared error; Benchmark (surveying); Mean absolute percentage error; Mean absolute error; Oxygen saturation; Pattern recognition (psychology); Computer vision; Artificial neural network; Statistics; Mathematics; Medicine; Oxygen","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":[0.0003986504,0.0006881938,0.0003816094,0.0003797431,0.0001215363,0.0003203786,0.0005334482,0.0004045617,0.0009403836],"category_scores_gemma":[0.001337967,0.0001490029,0.0002747296,0.0002479671,0.000142162,0.0005536518,0.000474957,0.000470564,0.0003620365],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003987453,"about_ca_system_score_gemma":0.0004166192,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005504621,"about_ca_topic_score_gemma":0.006481302,"domain_scores_codex":[0.9998129,0.00003265309,0.000008766395,0.00005673729,0.0000608165,0.00002810557],"domain_scores_gemma":[0.9997883,0.00007250219,0.000030757,0.00002571376,0.00007006756,0.00001264697],"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":[0.0006682831,0.0005037432,0.0118615,0.0001722031,0.0001555824,0.0001730186,0.00006639674,0.2050923,0.05876592,0.001074858,0.005647557,0.7158186],"study_design_scores_gemma":[0.000006285314,0.00006162308,0.001909204,0.00000821989,0.00001373406,0.0000456222,0.00001074814,0.9872147,0.009999743,0.0003683009,0.0003560566,0.000005732478],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3760789,0.001189449,0.6153522,0.0003354485,0.0001505214,0.0001074169,0.0008790059,0.002146178,0.003760873],"genre_scores_gemma":[0.9433308,0.0003886127,0.05145811,0.000132823,0.00003445363,0.0000610868,0.00109425,0.00004300601,0.003456787],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005504621,"threshold_uncertainty_score":0.01094514,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01135073409625562,"score_gpt":0.2204411282148402,"score_spread":0.2090903941185846,"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."}}