{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00008548083,0.0002666474,0.0001934295,0.000212142,0.00008284683,0.0002695814,0.000115453,0.0001376079,0.00003064059],"category_scores_gemma":[0.0000540187,0.0003058292,0.00007940744,0.0003067392,0.00001158397,0.0005548996,0.00003595333,0.000336481,0.00006783788],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002110481,"about_ca_system_score_gemma":0.00001487143,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007543548,"about_ca_topic_score_gemma":0.000007404251,"domain_scores_codex":[0.9989109,0.00001477879,0.0002729994,0.0002656588,0.0002084072,0.0003272484],"domain_scores_gemma":[0.9996196,0.00009998283,0.00002058777,0.0001397519,0.00002669324,0.00009335665],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001559485,0.000002663384,0.0002691603,0.00009356653,0.00007534328,0.00002799712,0.0002721622,0.4061042,0.5830475,0.00005651174,0.000003593706,0.01004569],"study_design_scores_gemma":[0.0001589558,0.00001619641,0.0007652264,0.00027593,0.00007163206,0.0000127261,0.00006330182,0.8213497,0.1763951,0.00005615843,0.0004870017,0.0003480636],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5930905,0.002439347,0.4011127,0.000005562099,0.001748308,0.0001299486,0.00001060202,0.001334507,0.0001285276],"genre_scores_gemma":[0.9861663,0.00005040867,0.01267607,0.000002527637,0.0009184813,0.00001799226,0.00004983272,0.0001073895,0.00001098668],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4152454,"threshold_uncertainty_score":0.9999394,"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."}}