OBJECTIVE Use machine-learning (ML) algorithms to classify alerts as real or artifacts in online noninvasive vital sign (VS) data streams to reduce alarm fatigue and missed true instability. METHODS Using a 24-bed trauma step-down unit’s non-invasive VS monitoring data (heart rate [HR], respiratory rate [RR], peripheral oximetry [SpO2]) recorded at 1/20Hz, and noninvasive oscillometric blood pressure [BP] less frequently, we partitioned data into training/validation (294 admissions; 22,980 monitoring hours) and test sets (2,057 admissions; 156,177 monitoring hours). Alerts were VS deviations beyond stability thresholds. A four-member expert committee annotated a subset of alerts (576 in training/validation set, 397 in test set) as real or artifact selected by active learning, upon which we trained ML algorithms. The best model was evaluated on alerts in the test set to enact online alert classification as signals evolve over time. MAIN RESULTS The Random Forest model discriminated between real and artifact as the alerts evolved online in the test set with area under the curve (AUC) performance of 0.79 (95% CI 0.67-0.93) for SpO2 at the instant the VS first crossed threshold and increased to 0.87 (95% CI 0.71-0.95) at 3 minutes into the alerting period. BP AUC started at 0.77 (95%CI 0.64-0.95) and increased to 0.87 (95% CI 0.71-0.98), while RR AUC started at 0.85 (95%CI 0.77-0.95) and increased to 0.97 (95% CI 0.94–1.00). HR alerts were too few for model development. CONCLUSIONS ML models can discern clinically relevant SpO2, BP and RR alerts from artifacts in an online monitoring dataset (AUC>0.87).
A closed-book, multiple-choice examination following this article tests your under standing of the following objectives:1. Describe the medical indications for the use of extracorporeal membrane oxygenation (ECMO ACNP-BCBackground Extracorporeal membrane oxygenation (ECMO) is used for critically ill patients when conventional treatments for cardiac or respiratory failure are unsuccessful. Objectives To describe patient and treatment characteristics and discharge outcome for ECMO patients, determine which characteristics are associated with good (survival) versus poor (death before hospital discharge) outcomes, and compare characteristics of patients with cardiac versus respiratory failure indicating ECMO. Methods Single-center, retrospective review of all adult patients treated with ECMO from 2005 through 2009. Results A total of 212 patients received ECMO for cardiac (n = 126) or respiratory (n = 86) failure. Mean age was 51 (SD, 14.5) years; support duration was 135 (SD, 149) hours. Survival to discharge was 33% overall; 50% for respiratory indication and 21% for cardiac indication patients. Patients with poor outcomes were older (53 vs 47 years, P = .007), more likely to require cardiovascular support before ECMO (99% vs 91%; P = .02), and had more transfusions (48 vs 24 units, P = .005) and complications (99% vs 87%; P < .001) than did patients with good outcomes. For cardiac patients, older age was associated with poor outcome (poor, 55 vs good, 48 years; P = .01). For respiratory patients, poor outcome was associated with more ventilator days before ECMO (poor, 6 vs good, 3; P = .01), higher peak inspiratory pressure (poor, 39 vs good, 35 cm H 2 O; P = .02), and lower pulmonary compliance (poor, 19 vs good, 25 mL/cm H 2 O; P = .008). Conclusions Patients with respiratory indications for ECMO experienced better survival than did cardiac patients. Increasing age was associated with poor outcome. Complications, regardless of ECMO indication, were common and associated with poor outcome.
Background: The quick-Sequential Organ Failure Assessment (qSOFA) criteria are recommended for identifying non–intensive care unit (ICU) patients at risk for sepsis but are underutilized. Local Problem: We hypothesized that education on recognizing sepsis using qSOFA criteria and empowering nurses to trigger rapid response team (RRT) calls based on positive qSOFA scores would reduce time to recognition and time to intervention and improve treatment compliance in non–ICU patients. Methods: The methods involved a descriptive retrospective review of 60 sepsis patients (30 pre- and 30 posteducation) to determine sepsis recognition time (qSOFA-to-RRT); time-to-sepsis interventions (reported as median [interquartile range] hours); and percent compliance with interventions. Interventions: We provided qSOFA and sepsis education to more than 1000 nurses, physicians, and advanced practice providers in a large tertiary hospital. Results: Posteducation, time to recognition (qSOFA-to-RRT) improved from 11.8 hours (3.4, 34.3) pre to 1.7 (0, 11.7) post (P = .005). Time from qSOFA to antibiotics improved from 1.4 hours (2.4, 6.2) pre to −4.7 (−25.4, 1.8) hours post (P < .01). Using qSOFA, compliance improved for antibiotics from 60% pre to 87% post (P = .02).
Background and purpose: The use of pulmonary ultrasound (US) in the critical care setting has been increasing over the past 2 decades. The use of advanced practice providers (APPs) in the critical care setting is also increasing. Limited data exist regarding the clinical and educational impact of a formal pulmonary US training course for APPs working in critical care settings. Methods: A preimplementation and postimplementation comparative design focused on the development and implementation of a formal pulmonary US course for novice critical care APPs. Conclusions: Eleven APPs underwent formal pulmonary US training. There was a significant increase in pulmonary US knowledge after the course, with pretest median of 13 and posttest median of 22 (p < .001; maximum score = 23). Presurvey and postsurvey comparison showed overall increase in skill and clinical use of pulmonary US. After the course, participating APPs reported a greater frequency of clinical decision-making based on US examination as measured by presurvey and postsurvey results. Implications for practice: Implementation of a formal pulmonary US course for critical care APPs improved pulmonary US knowledge, skill, and utilization, and impacted clinical decision-making and should be a highly recommended addition to the practice setting.
The ICU period is only one time point among many in the complex, multidisciplinary postoperative management required for patient survival and improved QOL. The care required on step-down units and after discharge to home each has unique care aspects that impact successful patient outcomes.
Background Development of contrast-induced acute kidney injury (CI-AKI) is associated with increased morbidity, mortality, hospital length of stay, and overall health care costs. Objectives The purpose of this project was to evaluate a clinical practice change—the addition of high-dose statin therapy to standard renal protection measures—in adults undergoing acute cardiac catheterization procedures and assessing its effect on CI-AKI. Method The evaluation was a pretest/posttest descriptive design. Adult patients undergoing acute cardiac catheterization procedures were evaluated for the rate of CI-AKI before (10 months preimplementation, N = 283) and after (10 months postimplementation, N = 286) a recent practice change that added high-dose statin therapy (within 24 hours of dye exposure) to a standard renal protection bundle (intravenous fluids, maximum dye calculations, and avoidance of nephrotoxic medications). Outcomes included the rate of CI-AKI, stage of acute kidney injury, need for new hemodialysis, discharge disposition (alive or died in the hospital), and hospital length of stay. Results Patients in the postintervention group that received renal protection bundle with high-dose statin had significantly lower incidence of CI-AKI (10.1% pre vs 3.2% post; P < .001). There were no significant differences in hospital length of stay, need for new hemodialysis, or mortality. Administration of high-dose statin within 24 hours of the cardiac catheterization procedure improved significantly (19.4% pre vs 74.1% post; P < .001). Adherence to all 5 components of the renal bundle improved post intervention (17% pre vs 73.4% post; P < .001). Discussion The addition of a high-dose statin in addition to existing renal protective measures in patients with acute cardiac procedures is associated with a decreased incidence of CI-AKI.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.