{"id":"W4379742578","doi":"10.1145/3555776.3577747","title":"The Case for tinyML in Healthcare: CNNs for Real-Time On-Edge Blood Pressure Estimation","year":2023,"lang":"en","type":"article","venue":"","topic":"Non-Invasive Vital Sign Monitoring","field":"Engineering","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Convolutional neural network; Edge device; Edge computing; Inference; Cloud computing; Pruning; Enhanced Data Rates for GSM Evolution; Quantization (signal processing); Computation; Analytics; Artificial intelligence; Real-time computing; Data mining; Computer engineering; Distributed computing; Algorithm","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":[0.000972795,0.0007795658,0.0005147103,0.0002992832,0.0001801441,0.0009915375,0.001384571,0.001202278,0.002825323],"category_scores_gemma":[0.006481876,0.0003784436,0.0003360051,0.0003192389,0.0008478392,0.003452098,0.00148398,0.001736663,0.0009489829],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005625163,"about_ca_system_score_gemma":0.0003156815,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002521379,"about_ca_topic_score_gemma":0.002867484,"domain_scores_codex":[0.9995155,0.0001289235,0.00002935808,0.0001140325,0.0001595461,0.00005271518],"domain_scores_gemma":[0.9990925,0.0004032956,0.00006428933,0.0002261947,0.0001539746,0.00005971669],"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":[0.00153153,0.0001592163,0.006643913,0.0008011562,0.0002723422,0.0008416945,0.0003814021,0.1105444,0.04018249,0.03887701,0.06147366,0.7382911],"study_design_scores_gemma":[0.00008885463,0.0003581036,0.003392018,0.0002022558,0.0001070514,0.0006990198,0.000142,0.8497949,0.04297088,0.04775556,0.05440501,0.00008429275],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06316019,0.005950989,0.8985332,0.01263679,0.001251218,0.00009978651,0.0008898078,0.008556391,0.008921649],"genre_scores_gemma":[0.7542307,0.003070313,0.2291096,0.005410834,0.000403459,0.0001288798,0.001135772,0.0005615071,0.005949077],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002825323,"threshold_uncertainty_score":0.009451628,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02050523940172084,"score_gpt":0.2755929272339533,"score_spread":0.2550876878322325,"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."}}