{"id":"W4403220176","doi":"10.1101/2024.10.08.24314844","title":"Using machine learning and centrifugal microfluidics at the point-of-need to predict clinical deterioration of patients with suspected sepsis within the first 24 h.","year":2024,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Sepsis Diagnosis and Treatment","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. Michael's Hospital; University of British Columbia; National Research Council Canada; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Groupe canadien de recherche en soins intensifs; University of Toronto; Killam Trusts; Génome Québec; California HIV/AIDS Research Program; Public Health Agency; Public Health Agency of Canada","keywords":"Sepsis; Point (geometry); Microfluidics; Intensive care medicine; Computer science; Artificial intelligence; Machine learning; Medicine; Nanotechnology; Internal medicine; Mathematics; Materials science","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001194006,0.0003853629,0.0004385102,0.0008184529,0.000181583,0.000763715,0.0002846609,0.0004610175,0.0004726093],"category_scores_gemma":[0.002025192,0.0001639286,0.0003261359,0.0004785308,0.0003117164,0.0002521543,0.0004004742,0.0005387042,0.0002676678],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000346127,"about_ca_system_score_gemma":0.0004210082,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005880755,"about_ca_topic_score_gemma":0.0007626531,"domain_scores_codex":[0.999164,0.0002057223,0.00006111588,0.0002570715,0.0002468124,0.00006532697],"domain_scores_gemma":[0.9991946,0.0003256116,0.000234691,0.00007962869,0.0001050087,0.00006048398],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002324997,0.0006126954,0.702065,0.0002347609,0.0004438029,0.0004223423,0.0002650844,0.008277436,0.1336359,0.0004626956,0.002277174,0.1489781],"study_design_scores_gemma":[0.0001960481,0.003243606,0.6879373,0.00008836025,0.0003660344,0.002219252,0.0002273277,0.1435792,0.1563037,0.001346223,0.004387632,0.0001052919],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9816399,0.001494886,0.01399144,0.0003096542,0.0001151387,0.0001048197,0.0009350463,0.0002551931,0.001153957],"genre_scores_gemma":[0.9855796,0.0003330343,0.01232541,0.0002441101,0.0000627581,0.00005670349,0.0008119679,0.000009215035,0.0005772856],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.001194006,"threshold_uncertainty_score":0.006314576,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06366868667173471,"score_gpt":0.3373579205866765,"score_spread":0.2736892339149418,"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."}}