{"id":"W4294974799","doi":"10.1109/ichi54592.2022.00047","title":"tinyCare: A tinyML-based Low-Cost Continuous Blood Pressure Estimation on the Extreme Edge","year":2022,"lang":"en","type":"article","venue":"2022 IEEE 10th International Conference on Healthcare Informatics (ICHI)","topic":"Non-Invasive Vital Sign Monitoring","field":"Engineering","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Robustness (evolution); Microcontroller; Photoplethysmogram; Edge computing; Inference; Enhanced Data Rates for GSM Evolution; Edge device; Blood pressure; Inference engine; Cloud computing; Artificial intelligence; Real-time computing; Embedded system; Computer vision; Medicine","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0005620265,0.0003771342,0.000297134,0.000327101,0.0004588342,0.0002152256,0.000944054,0.0001036687,0.0008652104],"category_scores_gemma":[0.0001961464,0.0003474687,0.0001254467,0.0003415159,0.00005324707,0.0002766858,0.0001245544,0.001165141,0.0001823993],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000317192,"about_ca_system_score_gemma":0.0002243512,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006602499,"about_ca_topic_score_gemma":0.00002937744,"domain_scores_codex":[0.9969684,0.0001386836,0.0008512479,0.0002370886,0.001321664,0.0004829057],"domain_scores_gemma":[0.9982601,0.0004005406,0.0003155275,0.0005403685,0.0003146084,0.0001688176],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005633266,0.0007398532,0.005571742,0.001879646,0.001132,0.0001102402,0.009417607,0.787421,0.006870137,0.1058081,0.02489939,0.05558695],"study_design_scores_gemma":[0.001680012,0.0006706622,0.0006231444,0.0006248774,0.00009181263,0.00004237662,0.002409926,0.9640447,0.01497585,0.00134385,0.01257114,0.0009216795],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7691849,0.0006391378,0.03870064,0.02113432,0.03451523,0.009621041,0.006570184,0.003136666,0.1164978],"genre_scores_gemma":[0.9964401,0.00003023988,0.0005081118,0.00142469,0.0003016515,0.0006934955,0.0002676615,0.00005822677,0.0002757944],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2272552,"threshold_uncertainty_score":0.9998977,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05255181983516453,"score_gpt":0.2728664704811051,"score_spread":0.2203146506459405,"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."}}