{"id":"W4416266498","doi":"10.1016/j.bspc.2025.109071","title":"Towards mapping low-cost BCG to ECG using deep learning","year":2025,"lang":"en","type":"article","venue":"Biomedical Signal Processing and Control","topic":"ECG Monitoring and Analysis","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Mastercard Foundation; Carnegie Mellon University","keywords":"Deep learning; Key (lock); Convolutional neural network; Ground truth; Correlation; Artificial neural network; Mean squared error; Correlation coefficient","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004340765,0.0001858889,0.0004525463,0.0003323805,0.0003655167,0.0001102199,0.00008734476,0.0001505331,0.0000394751],"category_scores_gemma":[0.0002242241,0.0001499545,0.00009716224,0.0007358975,0.0001218268,0.00005901838,0.00004640794,0.000348726,0.00000882222],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008242228,"about_ca_system_score_gemma":0.0002130761,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007709798,"about_ca_topic_score_gemma":8.935352e-7,"domain_scores_codex":[0.9984676,0.00005557309,0.0003399251,0.0003778332,0.0003630215,0.0003961015],"domain_scores_gemma":[0.9992402,0.00007104946,0.00007106474,0.00009562598,0.0001359744,0.0003860735],"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":[0.0001180037,0.000085827,0.01096628,0.0003124892,0.0001131262,0.00004072144,0.000165513,0.00005337247,0.03615731,0.00000468243,0.00003964037,0.951943],"study_design_scores_gemma":[0.006323637,0.0003420635,0.01274394,0.004868235,0.0009892484,0.00006234496,0.001671628,0.9372125,0.002411299,0.0002028753,0.03258185,0.0005903353],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1910319,0.002478151,0.8019806,0.003315266,0.0001254085,0.0002287616,0.000001991818,0.0001564326,0.0006815045],"genre_scores_gemma":[0.9948366,0.00001876163,0.00293372,0.001063577,0.0004726172,0.00001985629,0.000006876405,0.00001522083,0.0006328069],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9513527,"threshold_uncertainty_score":0.6114968,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01327302442100376,"score_gpt":0.2889853337105556,"score_spread":0.2757123092895519,"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."}}