-
Quantifying the Impact of Infusion Alerts and Alarms on Nursing Workflows: A Retrospective Analysis.Applied Clinical Informatics May 2021Smart infusion pumps affect workflows as they add alerts and alarms in an information-rich clinical environment where alarm fatigue is already a major concern. An...
BACKGROUND
Smart infusion pumps affect workflows as they add alerts and alarms in an information-rich clinical environment where alarm fatigue is already a major concern. An analytic approach is needed to quantify the impact of these alerts and alarms on nursing workflows and patient safety.
OBJECTIVES
To analyze a detailed infusion dataset from a smart infusion pump system and identify contributing factors for infusion programming alerts, operational alarms, and alarm resolution times.
METHODS
We analyzed detailed infusion pump data across four hospitals in a health system for up to 1 year. The prevalence of alerts and alarms was grouped by infusion type and a selected list of 32 high-alert medications (HAMs). Logistic regression was used to explore the relationship between a set of risk factors and the occurrence of alerts and alarms. We used nonparametric tests to explore the relationship between alarm resolution times and a subset of predictor variables.
RESULTS
The study dataset included 745,641 unique infusions with a total of 3,231,300 infusion events. Overall, 28.7% of all unique infusions had at least one operational alarm, and 2.1% of all unique infusions had at least one programming alert. Alarms averaged two per infusion, whereas at least one alert happened in every 48 unique infusions. Eight percent of alarms took over 4 minutes to resolve. Intravenous fluid infusions had the highest rate of error-state occurrence. HAMs had 1.64 more odds for alerts than the rest of the infusions. On average, HAMs had a higher alert rate than maintenance fluids.
CONCLUSION
Infusion pump alerts and alarms impact clinical care, as alerts and alarms by design interrupt clinical workflow. Our study showcases how hospital system leadership teams can leverage infusion pump informatics to prioritize quality improvement and patient safety initiatives pertaining to infusion practices.
Topics: Humans; Infusion Pumps; Medication Errors; Patient Safety; Retrospective Studies; Workflow
PubMed: 34192773
DOI: 10.1055/s-0041-1730031 -
Frontiers in Neuroscience 2023Epilepsy is a neurological disease characterized by sudden, unprovoked seizures. The unexpected nature of epileptic seizures is a major component of the disease burden....
INTRODUCTION
Epilepsy is a neurological disease characterized by sudden, unprovoked seizures. The unexpected nature of epileptic seizures is a major component of the disease burden. Predicting seizure onset and alarming patients may allow timely intervention, which would improve clinical outcomes and patient quality of life. Currently, algorithms aiming to predict seizures suffer from a high false alarm rate, rendering them unsuitable for clinical use.
METHODS
We adopted here a calibration method called Learn then Test to reduce false alarm rates of seizure prediction. This method calibrates the output of a "black-box" model to meet a specified false alarm rate requirement. The method was initially validated on synthetic data and subsequently tested on publicly available (EEG) records from 15 patients with epilepsy by calibrating the outputs of a deep learning model.
RESULTS AND DISCUSSION
Validation showed that the calibration method rigorously controlled the false alarm rate at a user-desired level after our adaptation. Real data testing showed an average of 92% reduction in the false alarm rate, at the cost of missing four of nine seizures of six patients. Better-performing prediction models combined with the proposed method may facilitate the clinical use of real-time seizure prediction systems.
PubMed: 37790590
DOI: 10.3389/fnins.2023.1184990 -
Sensors (Basel, Switzerland) Oct 2021Real-time and accurate longitudinal rip detection of a conveyor belt is crucial for the safety and efficiency of an industrial haulage system. However, the existing...
Real-time and accurate longitudinal rip detection of a conveyor belt is crucial for the safety and efficiency of an industrial haulage system. However, the existing longitudinal detection methods possess drawbacks, often resulting in false alarms caused by tiny scratches on the belt surface. A method of identifying the longitudinal rip through three-dimensional (3D) point cloud processing is proposed to solve this issue. Specifically, the spatial point data of the belt surface are acquired by a binocular line laser stereo vision camera. Within these data, the suspected points induced by the rips and scratches were extracted. Subsequently, a clustering and discrimination mechanism was employed to distinguish the rips and scratches, and only the rip information was used as alarm criterion. Finally, the direction and maximum width of the rip can be effectively characterized in 3D space using the principal component analysis (PCA) method. This method was tested in practical experiments, and the experimental results indicate that this method can identify the longitudinal rip accurately in real time and simultaneously characterize it. Thus, applying this method can provide a more effective and appropriate solution to the identification scenes of longitudinal rip and other similar defects.
PubMed: 34640970
DOI: 10.3390/s21196650 -
Epilepsy & Behavior Reports 2024We consider the disorders of arousal and sleep-related hypermotor epilepsy as genetic twin-conditions, one without, one with epilepsy. They share an augmented... (Review)
Review
We consider the disorders of arousal and sleep-related hypermotor epilepsy as genetic twin-conditions, one without, one with epilepsy. They share an augmented arousal-activity during NREM sleep with sleep-wake dissociations, culminating in sleep terrors and sleep-related hypermotor seizures with similar symptoms. The known mutations underlying the two spectra are different, but there are multifold population-genetic-, family- and even individual (the two conditions occurring in the same person) overlaps supporting common genetic roots. In the episodes of disorders of arousal, the anterior cingulate, anterior insular and pre-frontal cortices (shown to be involved in fear- and emotion processing) are activated within a sleeping brain. These regions overlap with the seizure-onset zones of successfully operated sleep-related hypermotor seizures, and notably, belong to the salience network being consistent with its hubs. The arousal-relatedness and the similar fearful confusion occurring in sleep terrors and hypermotor seizures, make them alike acute stress-responses emerging from sleep; triggered by false alarms. The activation of the anterior cingulate, prefrontal and insular regions in the episodes of both conditions, can easily mobilize the hypothalamo-pituitary-adrenal axis (preparing fight-flight responses in wakefulness); through its direct pathways to and from the salience network. This hypothesis has never been studied.
PubMed: 38328672
DOI: 10.1016/j.ebr.2024.100650 -
Scientific Reports May 2021In very preterm infants, cardio-respiratory events and associated hypoxemia occurring during early postnatal life have been associated with risks of retinopathy, growth... (Observational Study)
Observational Study
In very preterm infants, cardio-respiratory events and associated hypoxemia occurring during early postnatal life have been associated with risks of retinopathy, growth alteration and neurodevelopment impairment. These events are commonly detected by continuous cardio-respiratory monitoring in neonatal intensive care units (NICU), through the associated bradycardia. NICU nurse interventions are mainly triggered by these alarms. In this work, we acquired data from 52 preterm infants during NICU monitoring, in order to propose an early bradycardia detector which is based on a decentralized fusion of three detectors. The main objective is to improve automatic detection under real-life conditions without altering performance with respect to that of a monitor commonly used in NICU. We used heart rate lower than 80 bpm during at least 10 sec to define bradycardia. With this definition we observed a high rate of false alarms (64%) in real-life and that 29% of the relevant alarms were not followed by manual interventions. Concerning the proposed detection method, when compared to current monitors, it provided a significant decrease of the detection delay of 2.9 seconds, without alteration of the sensitivity (97.6% vs 95.2%) and false alarm rate (63.7% vs 64.1%). We expect that such an early detection will improve the response of the newborn to the intervention and allow for the development of new automatic therapeutic strategies which could complement manual intervention and decrease the sepsis risk.
Topics: Bradycardia; Humans; Infant, Extremely Premature; Infant, Newborn; Infant, Premature, Diseases; Intensive Care Units, Neonatal; Monitoring, Physiologic
PubMed: 34006917
DOI: 10.1038/s41598-021-89468-x -
BMJ Open Quality Jul 2023Physiological monitoring systems, like Masimo, used during inpatient hospitalisation, offer a non-invasive approach to capture critical vital signs data. These systems...
BACKGROUND
Physiological monitoring systems, like Masimo, used during inpatient hospitalisation, offer a non-invasive approach to capture critical vital signs data. These systems trigger alarms when measurements deviate from preset parameters. However, often non-urgent or potentially false alarms contribute to 'alarm fatigue,' a form of sensory overload that can have adverse effects on both patients and healthcare staff. The Joint Commission, in 2021, announced a target to mitigate alarm fatigue-related fatalities through improved alarm management. Yet, no established guidelines are presently available. This study aims to address alarm fatigue at the Mayo Clinic to safeguard patient safety, curb staff burnout and improve the sensitivity of oxygen saturation monitoring to promptly detect emergencies.
METHODS
A quality improvement project was conducted to combat minimise the false alarm burden, with data collected 2 months prior to intervention commencement. The project's goal was to decrease the total alarm value by 20% from 55%-85% to 35%-75% within 2 months, leveraging quality improvement methodologies.
INTERVENTIONS
February to April 2021, we implemented a two-pronged intervention: (1) instituting a protocol to evaluate patients' continuous monitoring needs and discontinuing it when appropriate, and (2) introducing educational signage for patients and Mayo Clinic staff on monitoring best practices.
RESULTS
Baseline averages of red alarms (158.6), manual snoozes (37.8) and self-resolves (120.7); the first postintervention phase showed reductions in red alarms (125.5), manual snoozes (17.8) and self-resolves (107.8). Second postintervention phase recorded 138 red alarms, 13 manual snoozes and 125 self-resolves. Baseline comparison demonstrated an average of 16.92% reduction of alarms among both interventions (p value: 0.25).
CONCLUSION
Simple interventions like education and communication techniques proved instrumental in lessening the alarm burden for patients and staff. The findings underscore the practical use and efficacy of these methods in any healthcare setting, thus contributing to mitigating the prevalent issue of alarm fatigue.
Topics: Humans; Patient Safety; Clinical Alarms; Monitoring, Physiologic; Health Facilities; Burnout, Professional
PubMed: 37474134
DOI: 10.1136/bmjoq-2023-002262 -
Sensors (Basel, Switzerland) Jul 2023Fault alarm time lag is one of the difficulties in fault diagnosis of wind turbine generators (WTGs), and the existing methods are insufficient to achieve accurate and...
Fault alarm time lag is one of the difficulties in fault diagnosis of wind turbine generators (WTGs), and the existing methods are insufficient to achieve accurate and rapid fault diagnosis of WTGs, and the operation and maintenance costs of WTGs are too high. To invent a new method for fast and accurate fault diagnosis of WTGs, this study constructs a stacking integration model based on the machine learning algorithms light gradient boosting machine (LightGBM), extreme gradient boosting (XGBoost), and stochastic gradient descent regressor (SGDRegressor) using publicly available datasets from Energias De Portugal (EDP). This model is automatically tuned for hyperparameters during training using Bayesian tuning, and the coefficient of determination (R) and root mean square error (RMSE) were used to evaluate the model to determine its applicability and accuracy. The fitted residuals of the test set were calculated, the Pauta criterion (3σ) and the temporal sliding window were applied, and a final adaptive threshold method for accurate fault diagnosis and alarming was created. The model validation results show that the adaptive threshold method proposed in this study is better than the fixed threshold for diagnosis, and the alarm times for the GENERATOR fault type, GENERATOR_BEARING fault type, and TRANSFORMER fault type are 1.5 h, 5.8 h, and 3 h earlier, respectively.
Topics: Bayes Theorem; Algorithms; Electric Power Supplies; Machine Learning; Portugal
PubMed: 37448048
DOI: 10.3390/s23136198 -
International Journal of Medical... Apr 2024Sepsis is a life-threatening condition in the ICU and requires treatment in time. Despite the accuracy of existing sepsis prediction models, insufficient focus on...
OBJECTIVE
Sepsis is a life-threatening condition in the ICU and requires treatment in time. Despite the accuracy of existing sepsis prediction models, insufficient focus on reducing alarms could worsen alarm fatigue and desensitisation in ICUs, potentially compromising patient safety. In this retrospective study, we aim to develop an accurate, robust, and readily deployable method in ICUs, only based on the vital signs and laboratory tests.
METHODS
Our method consists of a customised down-sampling process and a specific dynamic sliding window and XGBoost to offer sepsis prediction. The down-sampling process was applied to the retrospective data for training the XGBoost model. During the testing stage, the dynamic sliding window and the trained XGBoost were used to predict sepsis on the retrospective datasets, PhysioNet and FHC.
RESULTS
With the filtered data from PhysioNet, our method achieved 80.74% accuracy (77.90% sensitivity and 84.42% specificity) and 83.95% (84.82% sensitivity and 82.00% specificity) on the test set of PhysioNet-A and PhysioNet-B, respectively. The AUC score was 0.89 for both datasets. On the FHC dataset, our method achieved 92.38% accuracy (88.37% sensitivity and 95.16% specificity) and 0.98 AUC score on the test set of FHC.
CONCLUSION
Our results indicate that the down-sampling process and the dynamic sliding window with XGBoost brought robust and accurate performance to give sepsis prediction under various hospital settings. The localisation and robustness of our method can assist in sepsis diagnosis in different ICU settings.
Topics: Humans; Retrospective Studies; Sepsis; Machine Learning; Vital Signs; Intensive Care Units
PubMed: 38350181
DOI: 10.1016/j.ijmedinf.2024.105365 -
Journal of Assisted Reproduction and... Apr 2019To study the relationship between liquid nitrogen loss and temperature in cryostorage dewars and develop an early-warning alarm for impending tank failure.
PURPOSE
To study the relationship between liquid nitrogen loss and temperature in cryostorage dewars and develop an early-warning alarm for impending tank failure.
METHODS
Cryostorage dewars were placed on custom-engineered scales, and weight and temperature data were continuously monitored in the setting of slow, medium, and fast rate-loss of LN to simulate three scenarios of tank failure.
RESULTS
LN Tank weights and temperatures were continuously monitored and recorded, with a calculated alarm trigger set at 10% weight loss and temperature of - 185 °C. With an intact tank, a 10% loss in LN occurred in 4.2-4.9 days. Warming to - 185 °C occurred in 37.8-43.7 days, over 30 days after the weight-based alarm was triggered. Full evaporation of LN required ~ 36.8 days. For the medium rate-loss simulation, a 10% loss in LN occurred in 0.8 h. Warming to - 185 °C occurred in 3.7-4.8 h, approximately 3 h after the weight-based alarm was triggered. For the fast rate-loss simulation, a 10% weight loss occurred within 15 s, and tanks were depleted in under 3 min. Tank temperatures began to rise immediately and at a relatively constant rate of 43.9 °C/h and 51.6 °C/h. Temperature alarms would have sounded within 0.37 and 0.06 h after the breech.
CONCLUSIONS
This study demonstrates that a weight-based alarm system can detect tank failures prior to a temperature-based system. Weight-based monitoring could serve as a redundant safety mechanism for added protection of cryopreserved reproductive tissues.
Topics: Cryopreservation; Female; Humans; Nitrogen; Semen Preservation; Sperm Motility
PubMed: 30834464
DOI: 10.1007/s10815-019-01402-3 -
Biomedical Instrumentation & Technology 2023Continuous physiologic monitoring commonly is used in pediatric medical-surgical (med-surg) units and is associated with high alarm burden for clinicians....
Continuous physiologic monitoring commonly is used in pediatric medical-surgical (med-surg) units and is associated with high alarm burden for clinicians. Characteristics of pediatric patients generating high rates of alarms on med-surg units are not known. To describe the demographic and clinical characteristics of pediatric med-surg patients associated with high rates of clinical alarms. We conducted a cross-sectional, single-site, retrospective study using existing clinical and alarm data from a children's hospital. Continuously monitored patients from med-surg units who had available alarm data were included. Negative binomial regression models were used to test the association between patient characteristics and the rate of clinical alarms per continuously monitored hour. Our final sample consisted of 1,569 patients with a total of 38,501 continuously monitored hours generating 265,432 clinical alarms. Peripheral oxygen saturation (SpO) low alarms accounted for 57.5% of alarms. Patients with medical complexity averaged 11% fewer alarms per hour than those without medical complexity ( < 0.01). Patients older than 5 years had up to 30% fewer alarms per hour than those who were younger than 5 years ( < 0.01). Patients using supplemental oxygen averaged 39% more alarms per hour compared with patients who had no supplemental oxygen use ( < 0.01). Patients at high risk for deterioration averaged 19% more alarms per hour than patients who were not high risk ( = 0.01). SpO alarms were the most common type of alarm in this study. The results highlight patient populations in pediatric medical-surgical units that may be high yield for interventions to reduce alarms. Most physiologic monitor alarms in pediatric medical-surgical (med-surg) units are not informative and likely could be safely eliminated to reduce noise and alarm fatigue. However, identifying and sustaining successful alarm-reduction strategies is a challenge. Research shows that 25% of patients in pediatric med-surg units produce almost three-quarters of all alarms. These patients are a potential high-yield target for alarm-reduction strategies; however, we are not aware of studies describing characteristics of pediatric patients generating high rates of alarms. The patient populations seen on pediatric med-surg units are diverse. Children of all ages are cared for on these units, with diagnoses ranging from acute respiratory infections, to management of chronic conditions, and to psychiatric conditions. Not all patients on pediatric med-surg units have physiologic parameters continuously monitored, but among those who do, understanding patient characteristics associated with high rates of alarms may help clinicians, healthcare technology management (HTM) professionals, and others working on alarm management strategies to develop targeted interventions. We conducted an exploratory retrospective study to describe patient characteristics associated with high rates of alarms in pediatric med-surg units.
Topics: Humans; Child; Cross-Sectional Studies; Retrospective Studies; Clinical Alarms; Monitoring, Physiologic; Oxygen
PubMed: 38170941
DOI: 10.2345/0899-8205-57.4.171