Alarm Safety and Alarm Fatigue

The Alarm Fatigue Challenge in the Neonatal Intensive Care Unit: A "before" and "after" Study

OBJECTIVE

 Alarm fatigue (AF) happens when professionals are exposed to many alarms and they become desensitized to them. It is related to proliferation of devices, not standardized alarm limits, and high prevalence of "nonactionable alarms," i.e., false alarms (triggered by equipment issues) or nuisance alarms (physiological change not requiring clinical action). When AF happens, response time seems to be longer and important alarms could be dismissed. After evaluating the situation in our neonatal intensive care unit (NICU), an alarm management program (AMP) was developed to reduce AF. The objective of this study were to compare the proportion of true alarms, nonactionable alarms, and to measure response time to alarms in the NICU before and after implementing an AMP and also to determine variables associated with nonactionable alarms and response time.

STUDY DESIGN

 This was a cross-sectional study. A total of 100 observations were collected between December 2019 and January 2020. After an AMP was implemented, 100 new observations were collected between June 2021 and August 2021. We estimated the true and nonactionable alarms proportion. Univariate analyses were performed to determine variables associated with nonactionable alarms and response time. Logistic regression was performed to assess independent variables.

RESULTS

 The proportion of true alarms before and after AMP was 31 versus 57% (p = 0.001), whereas the proportion of nonactionable alarms was 69 versus 43% (p = 0.001). Median response time was significantly reduced (35 versus 12 seconds; p = 0.001). Before AMP, neonates with less intensive care needs had a higher proportion of nonactionable alarms and a longer response time. After AMP, response time was similar for true and nonactionable alarms. For both periods, the need of respiratory support was significantly associated with true alarms (p = 0.001). In the adjusted analysis, response time (p = 0.001) and respiratory support (p = 0.003) remained associated with nonactionable alarms.

CONCLUSION

 AF was highly prevalent in our NICU. This study shows that after the implementation of an AMP, response time to alarms and the proportion of nonactionable alarms can be significantly reduced.

KEY POINTS

· AF happens when professionals are exposed to many alarms and they become desensitized to them.. · The presence of AF can compromise patients' safety.. · The implementation of an AMP can reduce AF..

The mental workload of ICU nurses performing human-machine tasks and associated factors: A cross-sectional questionnaire survey

AIMS

To assess the level of mental workload (MWL) of intensive care unit (ICU) nurses in performing different human-machine tasks and examine the predictors of the MWL.

DESIGN

A cross-sectional questionnaire study.

METHODS

Between January and February 2021, data were collected from ICU nurses (n = 427) at nine tertiary hospitals selected from five (east, west, south, north, central) regions in China through an electronic questionnaire, including sociodemographic questions, the National Aeronautics and Space Administration Task Load Index, General Self-Efficacy Scale, Difficulty-assessing Index System of Nursing Operation Technique, and System Usability Scale. Descriptive statistics, t-tests, one-way ANOVA and multiple linear regression models were used.

RESULTS

ICU nurses experienced a medium level of MWL (score 52.04 on a scale of 0-100) while performing human-machine tasks. ICU nurses' MWL was notably higher in conducting first aid and life support tasks (using defibrillators or ventilators). Predictors of MWL were task difficulty, system usability, professional title, age, self-efficacy, ICU category, and willingness to study emerging technology actively. Task difficulty and system usability were the strongest predictors of nearly all typical tasks.

CONCLUSION

ICU nurses experience a medium MWL while performing human-machine tasks, but higher mental, temporal, and effort are perceived compared to physical demands. The MWL varied significantly across different human-machine tasks, among which are significantly higher: first aid and life support and information-based human-machine tasks. Task difficulty and system availability are decisive predictors of MWL.

IMPACT

This is the first study to investigate the level of MWL of ICU nurses performing different representative human-machine tasks and to explore its predictors, which provides a reference for future research. These findings suggest that healthcare organizations should pay attention to the MWL of ICU nurses and develop customized management strategies based on task characteristics to maintain a moderate level of MWL, thus enabling ICU nurses to perform human-machine tasks better.

PATIENT OR PUBLIC CONTRIBUTION

No patient or public contribution.

Qualitative Exploration of Anesthesia Providers' Perceptions Regarding Philips Visual Patient Avatar in Clinical Practice

The Philips Visual Patient Avatar, a user-centered visualization technology, offers an alternative approach to patient monitoring. Computer-based simulation studies indicate that it increases diagnostic accuracy and confidence, while reducing perceived workload. About three months after the technology's integration into clinical practice, we conducted an assessment among anesthesia providers to determine their views on its strengths, limitations, and overall perceptions. This single-center qualitative study at the University Hospital of Zurich examined anesthesia providers' perceptions of the Philips Visual Patient Avatar after its implementation. The study included an online survey to identify medical personnel's opinions on the technology's strengths and areas for improvement, which were analyzed using thematic analysis. A total of 63 of the 377 invited anesthesia providers (16.7%) responded to the survey. Overall, 163 comments were collected. The most prevalent positive themes were good presentation of specific parameters (16/163; 9.8%) and quick overview/rapid identification of problems (15/163; 9.2%). The most common perceived area for improvement was the ability to adjust the visualization thresholds of Visual Patient Avatar, which represent the physiological upper and lower vital-sign limits (33/163; 20.3%). The study showed that users consider Philips Visual Patient Avatar a valuable asset in anesthesia, allowing for easier identification of underlying problems. However, the study also revealed a user desire for the ability to freely adjust the thresholds of the Visual Patient Avatar by the handling caregivers, which were fixed to the departmental standard during the study.

Factors Influencing Medication Administration Outcomes Among New Graduate Nurses Using Bar Code-Assisted Medication Administration

Paramount to patient safety is the ability for nurses to make clinical decisions free from human error. Yet, the dynamic clinical environment in which nurses work is characterized by uncertainty, urgency, and high consequence, necessitating that nurses make quick and critical decisions. The aim of this study was to examine the influence of human and environmental factors on the decision to administer among new graduate nurses in response to alert generation during bar code-assisted medication administration. The design for this study was a descriptive, longitudinal, observational cohort design using EHR audit log and administrative data. The study was set at a large, urban medical center in the United States and included 132 new graduate nurses who worked on adult, inpatient units. Research variables included human and environmental factors. Data analysis included descriptive and inferential analyses. This study found that participants continued with administration of a medication in 90.75% of alert encounters. When considering the response to an alert, residency cohort, alert category, and previous exposure variables were associated with the decision to proceed with administration. It is important to continue to study factors that influence nurses' decision-making, particularly during the process of medication administration, to improve patient safety and outcomes.

Novel interventions significantly reduce falls with fractures: A meta-analysis and systematic review

INTRODUCTION

Worldwide, falls lead to possible complications such as prolonged hospitalization, prolonged bed rest, pressure injuries, fractures and mortality.

AIMS

The study aimed to evaluate the effectiveness of novel fall prevention strategies that utilized technology in preventing falls.

METHODS

The meta-analysis and systematic review was guided by the Cochrane guidelines for systematic reviews of interventions. The authors searched databases for specified keywords.

RESULTS

A total of 22 studies were included. Interventions included multi-modal fall prevention interventions, camera surveillance, motion sensors and bed/chair exit alarms. Video monitoring was equivocal in reducing fall rates. Exit alarms statistically significantly reduce falls between groups but not within groups. The interventions were not statistically significant in reducing falls with minor injuries but they were statistically significant in reducing falls with serious injuries including fractures.

CONCLUSION

A comprehensive fall prevention care plan, rather than one specific intervention, is necessary to prevent falls effectively.

Human-centered visualization technologies for patient monitoring are the future: a narrative review

Medical technology innovation has improved patient monitoring in perioperative and intensive care medicine and continuous improvement in the technology is now a central focus in this field. Because data density increases with the number of parameters captured by patient-monitoring devices, its interpretation has become more challenging. Therefore, it is necessary to support clinicians in managing information overload while improving their awareness and understanding about the patient's health status. Patient monitoring has almost exclusively operated on the single-sensor-single-indicator principle-a technology-centered way of presenting data in which specific parameters are measured and displayed individually as separate numbers and waves. An alternative is user-centered medical visualization technology, which integrates multiple pieces of information (e.g., vital signs), derived from multiple sensors into a single indicator-an avatar-based visualization-that is a meaningful representation of the real-world situation. Data are presented as changing shapes, colors, and animation frequencies, which can be perceived, integrated, and interpreted much more efficiently than other formats (e.g., numbers). The beneficial effects of these technologies have been confirmed in computer-based simulation studies; visualization technologies improved clinicians' situation awareness by helping them effectively perceive and verbalize the underlying medical issue, while improving diagnostic confidence and reducing workload. This review presents an overview of the scientific results and the evidence for the validity of these technologies.

Retrospective cohort observation on psychotropic drug-drug interaction and identification utility from 3 databases: Drugs.com®, Lexicomp®, and Epocrates®

BACKGROUND

Pharmacotherapy is necessary for many people with psychiatric disorders and polypharmacy is common. The psychotropic drug-drug interaction (DDI) should be concerned and efficiently monitored by a proper instrument.

OBJECTIVES

This study aimed to investigate the prevalence and associated factors of psychotropic DDI and to compare the identification utility from three databases: Drugs.com®, Lexicomp®, and Epocrates®.

METHODS

This was a retrospective cohort design. We collected demographic and clinical data of all patients hospitalised in the psychiatric inpatient unit in 2020. Psychotropic DDI profiles were examined through three databases. Descriptive statistics were used to report comprehensiveness of each database and prevalence of psychotropic DDI. The Fleiss' kappa index would be analysed to indicate agreement strength of DDI severity classification among three databases.

RESULTS

From 149 total admissions, the psychotropic DDIs were found in 148 admissions (99.3%). Thorough the study, there were 182 of both psychotropic and other agents prescribed under 1,357 prescriptions. In total, 2,825 psychotropic DDIs were identified by using Drugs.com® 2,500 times, Epocrates® 2,269 times, and Lexicomp® 2,265 times. Interactions with clonazepam was the three most frequent agents when co-administrated with quetiapine (n = 56), risperidone (n = 36), and valproic acid and derivatives (n = 36). Serious DDIs were comparatively lower in incidence and there was no evidence of its association with reported clinical adverse consequences. The study revealed slight and fair agreement regarding severity classification among the three databases was found. DDI events detected by Drugs.com® were greatest in number, but Lexicomp® provided the broadest list of medications prescribed in our study.

CONCLUSION

Among three databases, interactions detected by Drugs.com® were greatest in number, whereas Lexicomp® provided the broadest list of medications. Development of such databases, based on both theoretical and clinical conceptions, should be focused to balance safety of patients and weariness of healthcare providers.

Polish Adaptation of the Alarm Fatigue Assessment Questionnaire as an Element of Improving Patient Safety

Medical personnel, working in medical intensive care units, are exposed to fatigue associated with alarms emitted by numerous medical devices used for diagnosing, treating, and monitoring patients. Alarm fatigue is a safety and quality problem in patient care and actions should be taken to reduce this by, among other measures, building an effective safety culture. In the present study, an adaptation of a questionnaire to assess alarm fatigue was carried out. The study obtained good reliability of the questionnaire at Cronbach's alpha level of 0.88. The Polish research team has successfully adapted the Alarm Fatigue Assessment Questionnaire so that it can be used in healthcare settings as a tool to improve patient safety.

Determinants of Medical Equipment Alarm Fatigue in Practicing Nurses: A Systematic Review

Objective

This study aimed to systematically evaluate the level of medical equipment alarm fatigue and its influencing factors among clinical nurses.

Methods

PubMed, Embase, CNKI, and Wanfang databases were systematically searched to identify articles on alarm fatigue of clinical nurses published before September 25, 2022. According to the evaluation criteria of prevalence studies recommended by JBI Evidence-Based Health Care Center, the quality of the literature meeting the inclusion criteria was evaluated, and Stata MP17 software was used for meta-analysis.

Results

A total of 14 cross-sectional studies were included, with a total sample of 2,848 nurses. The results showed that the alarm fatigue score of clinical nurses was 21.76 (95% CI [20.27, 23.25]). Subgroup analysis showed that the nurses who worked night shift and had lower professional title had higher alarm fatigue.

Conclusion

The alarm fatigue of clinical nurses was at a moderate level. To reduce the alarm fatigue level of clinical nurses, nursing managers should strengthen the alarm safety awareness of nurses, rationally arrange nurse manpower, carry out training to actively improve the alarm management ability of nurses, and optimize the alarm level and frequency of alarm equipment.

Impact of Obstetric Communication on Decision-to-Delivery Time

OBJECTIVE

In obstetric emergencies, care coordination is critical in achieving a "decision-to-delivery" time of 30 minutes. Reliable communication is essential to optimize coordinated care of mother and baby. Clinical mobility (CM) platforms have been shown to improve communication during medical emergencies; however, their impact on improving decision-to-delivery times has not been shown. This study aimed to determine the impact of a new CM platform on decision-to-delivery time.

STUDY DESIGN

A multidisciplinary team designed a CM platform that employs a wall-mounted panel paired with mobile technology to alert all relevant clinical staff. This new platform uses in-room preprogrammed messages that alert predetermined responders matching the emergency. For example, the "STAT section" button summons doctors (obstetrics, anesthesiology, and neonatology), obstetric nurses, and newborn resuscitation staff via smartphones. Impact of this platform was assessed with process and outcome data: cord artery pH, 5-minute Apgar's score; and decision for cesarean section to time of: skin incision, uterine incision, and delivery. This pre- and postimplementation study (October-September 2018 vs. January-December 2019) centered on the opening of our new Obstetric Care Unit. Data were analyzed with Chi-square and Mann-Whitney U-test.

RESULTS

Emergent cesarean delivery was performed in 172 women pre- and 124 postimplementation of the new CM platform. In postimplementation, we observed a 7.4-minute reduction in time from decision-to-delivery (26 pre- vs. 18.6 minutes postimplementation, p = 0.001). Delivery within 30 minutes improved by 15.2% (p = 0.018). Times to skin and uterine incision were also significantly reduced. The two groups had similar neonatal outcomes: birth weight, Apgar's score at 5 minutes, and cord artery pH did not differ, but the study was underpowered to compare these outcomes.

CONCLUSION

This new CM platform significantly reduced decision-to-delivery time, in turn improving compliance with the "30-minute rule." All relevant personnel were contacted specifically, while avoiding overhead paging and other unnecessary messages.

KEY POINTS

· Obstetric communication via a clinical mobility platform shortens the delivery to delivery interval. · Obstetric communication systems via an information technology (IT)-system results in a higher frequency of deliveries within 30 minutes.. · Communication systems may be a useful tools to synchronously call multiple services to respond..

Computational approaches to alleviate alarm fatigue in intensive care medicine: A systematic literature review

Patient monitoring technology has been used to guide therapy and alert staff when a vital sign leaves a predefined range in the intensive care unit (ICU) for decades. However, large amounts of technically false or clinically irrelevant alarms provoke alarm fatigue in staff leading to desensitisation towards critical alarms. With this systematic review, we are following the Preferred Reporting Items for Systematic Reviews (PRISMA) checklist in order to summarise scientific efforts that aimed to develop IT systems to reduce alarm fatigue in ICUs. 69 peer-reviewed publications were included. The majority of publications targeted the avoidance of technically false alarms, while the remainder focused on prediction of patient deterioration or alarm presentation. The investigated alarm types were mostly associated with heart rate or arrhythmia, followed by arterial blood pressure, oxygen saturation, and respiratory rate. Most publications focused on the development of software solutions, some on wearables, smartphones, or headmounted displays for delivering alarms to staff. The most commonly used statistical models were tree-based. In conclusion, we found strong evidence that alarm fatigue can be alleviated by IT-based solutions. However, future efforts should focus more on the avoidance of clinically non-actionable alarms which could be accelerated by improving the data availability.

Systematic Review Registration:https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42021233461, identifier: CRD42021233461.

Clinical feasibility of an advanced neonatal epidermal multiparameter continuous monitoring technology in a large public maternity hospital in Nairobi, Kenya

Clinically feasible multiparameter continuous physiological monitoring technologies are needed for use in resource-constrained African healthcare facilities to allow for early detection of critical events and timely intervention for major morbidities in high-risk neonates. We conducted a prospective clinical feasibility study of a novel multiparameter continuous physiological monitoring technology in neonates at Pumwani Maternity Hospital in Nairobi, Kenya. To assess feasibility, we compared the performance of Sibel's Advanced Neonatal Epidermal (ANNE) technology to reference technologies, including Masimo's Rad-97 pulse CO-oximeter with capnography technology for heart rate (HR), respiratory rate (RR), and oxygen saturation (SpO₂) measurements and Spengler's Tempo Easy non-contact infrared thermometer for temperature measurements. We evaluated key performance criteria such as up-time, clinical event detection performance, and the agreement of measurements compared to those from the reference technologies in an uncontrolled, real-world setting. Between September 15 and December 15, 2020, we collected and analyzed 503 h of ANNE data from 109 enrolled neonates. ANNE's up-time was 42 (11%) h more for HR, 77 (25%) h more for RR, and 6 (2%) h less for SpO₂ compared to the Rad-97. However, ANNE's ratio of up-time to total attached time was less than Rad-97's for HR (0.79 vs 0.86), RR (0.68 vs. 0.79), and SpO₂ (0.69 vs 0.86). ANNE demonstrated adequate performance in identifying high and low HR and RR and high temperature events; however, showed relatively poor performance for low SpO₂ events. The normalized spread of limits of agreement were 8.4% for HR and 52.2% for RR and the normalized root-mean-square deviation was 4.4% for SpO₂. Temperature agreement showed a spread of limits of agreement of 2.8 °C. The a priori-identified optimal limits were met for HR and temperature but not for RR or SpO₂. ANNE was clinically feasible for HR and temperature but not RR and SpO₂ as demonstrated by the technology's up-time, clinical event detection performance, and the agreement of measurements compared to those from the reference technologies.

Prediction of postoperative cardiac events in multiple surgical cohorts using a multimodal and integrative decision support system

Postoperative patients are at risk of life-threatening complications such as hemodynamic decompensation or arrhythmia. Automated detection of patients with such risks via a real-time clinical decision support system may provide opportunities for early and timely interventions that can significantly improve patient outcomes. We utilize multimodal features derived from digital signal processing techniques and tensor formation, as well as the electronic health record (EHR), to create machine learning models that predict the occurrence of several life-threatening complications up to 4 hours prior to the event. In order to ensure that our models are generalizable across different surgical cohorts, we trained the models on a cardiac surgery cohort and tested them on vascular and non-cardiac acute surgery cohorts. The best performing models achieved an area under the receiver operating characteristic curve (AUROC) of 0.94 on training and 0.94 and 0.82, respectively, on testing for the 0.5-hour interval. The AUROCs only slightly dropped to 0.93, 0.92, and 0.77, respectively, for the 4-hour interval. This study serves as a proof-of-concept that EHR data and physiologic waveform data can be combined to enable the early detection of postoperative deterioration events.

Alarm fatigue in nurses working in intensive care units: A multicenter study

BACKGROUND: Technological progress improves health care efficiency, quality, safety, and cost, supporting clinical activity in various scenarios, such as Intensive Care Unit (ICU). A timely response to alarms from monitors and other ICU electromedical devices is therefore crucial. The number of false alarms tend to desensitize care providers increasing the risk of experiencing alarm fatigue and, at times, lead to severe consequences for patients. OBJECTIVES: To assess the psychometric properties of the Italian version of the Alarm Fatigue Questionnaire and to explore the phenomenon of alarm fatigue among nurses working in intensive care settings. METHODS: The CVI-I was calculated to evaluate the validity of the content of the tool. Construct validity was investigated through exploratory factor analysis. Cronbach’s alpha coefficient (α) was used to examine the internal consistency of the scale and Spearman’s rho coefficient to test for stability. We designed a multicentre cross-sectional survey. A convenience sample of nurses from 4 Major Italian hospitals was recruited. The nurses completed the Italian version of the Alarm Fatigue Questionnaire. RESULTS: The content validity index CVI-S of the scale (CVI-S) was 91.11%; Cronbach’s alpha coefficient was 0.71. The Italian version of the tool explained 67.18%of the overall variance. 396 nurses were enrolled (79.84%). The overall level of alarm fatigue was Me = 29 [22;30]. 42.17%of the sample reported prior experience with alarm fatigue incidents. CONCLUSIONS: The extension of alarm fatigue requires the adoption of a preventive intervention plan. The Italian version of the Alarm Fatigue Questionnaire shows promising psychometric properties.

Reducing False Alarms and Alarm Fatigue from Pulse Oximeters in a Neonatal Care Unit: A Quality Improvement Study

Background:

Pulse oximeters play a vital role in monitoring sick newborns, but majority of the times, their alarms are of little clinical significance. False alarms from pulse oximeters were frequent in our neonatal intensive care unit, causing desensitization of staff and inattention to clinically important alarms.

Objectives:

The objective of the study was to reduce the burden of false alarms and alarm fatigue.

Methods:

This was a quality improvement (QI) study. During the baseline phase, alarms for heart rate and SPO2 (percentage of oxygenated blood) were evaluated. Response to them within 30 s was checked. Major causes of false alarms were the movement of the newborns, inappropriate alarm limits, and loose probe. Fishbone chart was prepared, and Plan-Do-Study-Act (PDSA) model was designed using point of care quality improvement (POCQI) principles. During the first PDSA (implementation phase), the staff was trained to adjust alarm limits using the reference chart. A lecture on noise hazards, emphasis on muting the alarms, and advice to change probe site at beginning of their duty was given. In the second PDSA (sustenance phase), components of the first PDSA were strengthened by supportive supervision and guidance and the training of new staff.

Results:

Total 494, 329, and 162 alarms were observed during baseline, implementation, and sustenance phases, respectively. In the baseline phase majority, 364 (73.7%) were false alarms, which occurred at a frequency of 0.39 alarms/patient/h. More than one-third of the alarms were not responded timely. After QI, false alarms reduced to 214 (65%; 0.22 alarms/patient/h) and 100 (61.7%; 0.16 alarms/patient/h) in implementation and sustenance phases, respectively. Response to true alarms improved from 101 (77.7%) to 104 (90.4%) to 62 (100%) during the 3 phases consecutively.

Conclusion:

Frequent false alarms lead to desensitization of health care workers. POCQI principles can be a practical approach for reducing false alarms and improving alarm safety.

An E-Textile Respiration Sensing System for NICU Monitoring: Design and Validation

The world is witnessing a rising number of preterm infants who are at significant risk of medical conditions. These infants require continuous care in Neonatal Intensive Care Units (NICU). Medical parameters are continuously monitored in premature infants in the NICU using a set of wired, sticky electrodes attached to the body. Medical adhesives used on the electrodes can be harmful to the baby, causing skin injuries, discomfort, and irritation. In addition, respiration rate (RR) monitoring in the NICU faces challenges of accuracy and clinical quality because RR is extracted from electrocardiogram (ECG). This research paper presents a design and validation of a smart textile pressure sensor system that addresses the existing challenges of medical monitoring in NICU. We designed two e-textile, piezoresistive pressure sensors made of Velostat for noninvasive RR monitoring; one was hand-stitched on a mattress topper material, and the other was embroidered on a denim fabric using an industrial embroidery machine. We developed a data acquisition system for validation experiments conducted on a high-fidelity, programmable NICU baby mannequin. We designed a signal processing pipeline to convert raw time-series signals into parameters including RR, rise and fall time, and comparison metrics. The results of the experiments showed that the relative accuracies of hand-stitched sensors were 98.68 (top sensor) and 98.07 (bottom sensor), while the accuracies of embroidered sensors were 99.37 (left sensor) and 99.39 (right sensor) for the 60 BrPM test case. The presented prototype system shows promising results and demands more research on textile design, human factors, and human experimentation.

Does alarm fatigue start in nursing school?

PURPOSE

Alarm fatigue among working nurses is a well-documented, high-priority safety issue. This article describes a study to learn whether alarm fatigue develops in undergraduate nursing student populations.

METHODS

This longitudinal quantitative study employed survey data from a single cohort of nursing students in the Southeastern US over a period of 18 months to assess nursing students' level of sensitivity to alarms, including the call bell, bathroom, fall and safety, I.V. infusion pumps, and telemetry alarms.

RESULTS

These data were significant for I.V. infusion pump alarms and indicated a general decrease in sensitivity over an 18-month period. Nursing students with previous healthcare experience also noted decreased sensitivity to bathroom call bells and fall and safety alarms.

CONCLUSION

Alarm fatigue was recognized among the surveyed nursing students. Nurse educators also identified a performance-based strategy to increase student awareness of alarm fatigue and evidence-based strategies to minimize desensitization to alarms in both education and practice.

Management of oxygen saturation monitoring in preterm newborns in the NICU: the Italian picture

Background

Although many studies emphasize the importance of using oxygen saturation (SpO₂) targets in the NICUs, there is a wide variability in used saturation ranges among centers. Primary aim was to draw a representative picture on how the management of oxygen monitoring is performed in the Italian NICUs. Second aim was to identify healthcare-professionals related factors associated with oxygen targeting in the preterm population.

Methods

Cross-sectional study with data collection via an electronic survey form. A questionnaire containing pre-piloted and open questions on monitoring and management of the SpO₂ was administered to neonatologists across the network of the Italian Society of Neonatology. The questions focused on: the infrastructure, specific training, healthcare professionals and patients-related factors. The results of the survey were anonymously collected, summarized and analyzed.

Results

Out of 378 questionnaires, 93 were correctly filled. Thirty-six different SpO₂ ranges were observed. Centers using written standard operating procedures on oxygen management and SpO₂ monitoring maintained a correct average range of SpO₂ 90–95%, avoided hyperoxia and reconsidered saturation targets in relation to comorbidities. 39.8% of responders disabled alarms during neonatal care. One center used biomarkers for complete monitoring of neonatal oxygenation status.

Conclusions

There is considerable variation in SpO₂ targets for preterm infants in the Italian NICUs. Standard operating procedures and specific training for health care personnel are the main factors playing a role for the correct maintenance of the recommended oxygen targets in preterms.

Nurse Cognition, Decision Support, and Barcode Medication Administration: A Conceptual Framework for Research, Practice, and Education

This article synthesizes theoretical perspectives related to nurse cognition. We present a conceptual model that can be used by multiple stakeholders to study and contemplate how nurses use clinical decision support systems, and specifically, Barcode-Assisted Medication Administration, to make decisions during the delivery of care. Theoretical perspectives integrated into the model include dual process theory, the Cognitive Continuum Theory, human factors engineering, and the Recognition-Primed Decision model. The resulting framework illustrates the process of nurse cognition during Barcode-Assisted Medication Administration. Additionally, the model includes individual or human and environmental factors that may influence nurse cognition and decision making. It is important to consider the influence of individual, human, and environmental factors on the process of nurse cognition and decision making. Specifically, it is necessary to explore the impact of heuristics and biases on clinician decision making, particularly related to the development of alarm and alert fatigue. Aided by the proposed framework, stakeholders may begin to identify heuristics and cognitive biases that influence the decision of clinicians to accept or override a clinical decision support system alert and whether heuristics and biases are associated with inappropriate alert override.

Bridging the Chasm between Pregnancy and Health over the Life Course: A National Agenda for Research and Action

BACKGROUND

Many pregnant people find no bridge to ongoing specialty or primary care after giving birth, even when clinical and social complications of pregnancy signal need. Black, indigenous, and all other women of color are especially harmed by fragmented care and access disparities, coupled with impacts of racism over the life course and in health care.

METHODS

We launched the initiative "Bridging the Chasm between Pregnancy and Health across the Life Course" in 2018, bringing together patients, advocates, providers, researchers, policymakers, and systems innovators to create a National Agenda for Research and Action. We held a 2-day conference that blended storytelling, evidence analysis, and consensus building to identify key themes related to gaps in care and root causes of inequities. In 2019, more than 70 stakeholders joined six working groups to reach consensus on strategic priorities based on equity, innovation, effectiveness, and feasibility.

FINDINGS

Working groups identified six key strategic areas for bridging the chasm. These include: 1) progress toward eliminating institutional and interpersonal racism and bias as a requirement for accreditation of health care institutions, 2) infrastructure support for community-based organizations, 3) extension of holistic team-based care to the postpartum year and beyond, with integration of doulas and community health workers on the team, 4) extension of Medicaid coverage and new quality and pay-for-performance metrics to link maternity care and primary care, 5) systems to preserve maternal narratives and data across providers, and 6) alignment of research with women's lived experiences.

CONCLUSIONS

The resulting agenda presents a path forward to remedy the structural chasms in women's health care, with key roles for advocates, policymakers, researchers, health care leaders, educators, and the media.

Optimisation of clinical workflow and monitor settings safely reduces alarms in the NICU

Aim

To address alarm fatigue, a new alarm management system which ensures a quicker delivery of alarms together with waveform information on nurses' handheld devices was implemented and settings optimised. The effects of this clinical implementation on alarm rates and nurses' responsiveness were measured in an 18‐bed single family rooms neonatal intensive care unit (NICU).

Methods

The technical implementation of the alarm management system was followed by clinical workflow optimisation. Alarms and vital parameters from October 2017 to December 2019 were analysed. Measures included monitoring alarms, nurses' response to alarms and time spent by patients in different saturation ranges. A survey among nurses was performed to evaluate changes in alarm rate and use of protocols.

Results

A significant reduction of monitoring alarms per patient days was detected after the optimisation phase (in particular for SpO2 ≤ 80%, P < .001). More time was spent by infants within the optimal peripheral oxygen saturation range (88% < SpO2 < 95%, P < .001). Results from the surveys showed that false alarms are less likely to cause an inappropriate response after the optimisation phase.

Conclusion

The implementation of an alarm management solution and an optimisation programme can safely reduce the alarm burden inside of the NICU environment.

Reducing Alarm Burden in a Level IV Neonatal Intensive Care Unit

Introduction

Excessive alarm burden contributes to alarm fatigue, causing staff to ignore or delay response to clinically significant alarms. The objective of this quality improvement project was to reduce yellow self-resolving SpO2 alarms from a mean of 14 alarms/patient-hour (APH) to 7 APH (a 50% reduction) within a 6-month period, without significantly decreasing the amount of time spent in target SpO2 range (90%-95%).

Methods

A multidisciplinary team used Define-Measure-Analyze-Improve-Control methodology to identify etiologies of alarm frequency and design improvement interventions to reduce alarm burden in a single-site Level IV NICU. Data-driven changes in alarm limit settings, alarm delay, and trial of a new pulse oximeter probe were used. Alarm data from the bedside monitor were analyzed following each improvement cycle. As a balancing measure, histograms monitored time spent in target SpO2 range.

Results

SpO2 alarm data were collected for 4,320 patient-hours (180 patient-days) on 40 neonatal intensive care unit patients meeting inclusion criteria. Corresponding histograms were obtained for each patient day. Following 5 Plan-Do-Study-Act cycles, the mean number of yellow self-resolving SpO2 alarms decreased from 14 to 5 APH, a 64% decrease. There was no difference in time spent in target SpO2 range (50% versus 50%, P = 0.93). After achieving the project aim, 2 control phase measurements demonstrated sustained improvement (mean APH = 6).

Conclusions

Yellow self-resolving SpO2 alarm frequency was reduced by 64% through the implementation of data-driven changes in alarm limit settings, alarm delays, and trial of a more sensitive oximeter probe without introducing harm to patients.

Compatibility and Safety Implications Associated with Interfacing Medical Devices in Neonatal Respiratory Care: A Case Example Using the Inhaled Nitric Oxide Delivery System

Over the past decade, international organizations have instituted strict regulations for the safe use of connected medical devices. The International Organization for Standardization and the Medical Device Single Audit Program instituted certifications to ensure that connected devices are compatible and operate within their proper clinical parameters. These efforts came about, in part, as a consequence of clinicians’ decisions to use nonstandard, modified, or improvised devices for purposes outside the original manufacturers’ approved parameters. Unapproved device modifications can be associated with increased risk of dosing errors, monitoring errors, tubing misconnections and serious or potentially fatal adverse events; furthermore, health care providers who implement unapproved device modifications may assume legal and financial liability should harm come to patients as a consequence of the modification. Using the inhaled nitric oxide delivery system as an example, the objective of this paper is to raise awareness of the potential dangers associated with unapproved modification and interfacing of therapeutic gas delivery systems and ventilators in the neonatal intensive care unit setting. The paper also highlights the rationale and necessity for rigorous validation processes that ensure that interfaced medical devices perform as intended in the clinical setting.

Are We Ready for Video Recognition and Computer Vision in the Intensive Care Unit? A Survey

OBJECTIVE

Video recording and video recognition (VR) with computer vision have become widely used in many aspects of modern life. Hospitals have employed VR technology for security purposes, however, despite the growing number of studies showing the feasibility of VR software for physiologic monitoring or detection of patient movement, its use in the intensive care unit (ICU) in real-time is sparse and the perception of this novel technology is unknown. The objective of this study is to understand the attitudes of providers, patients, and patient's families toward using VR in the ICU.

DESIGN

A 10-question survey instrument was used and distributed into two groups of participants: clinicians (MDs, advance practice providers, registered nurses), patients and families (adult patients and patients' relatives). Questions were specifically worded and section for free text-comments created to elicit respondents' thoughts and attitudes on potential issues and barriers toward implementation of VR in the ICU.

SETTING

The survey was conducted at Mayo Clinic in Minnesota and Florida.

RESULTS

A total of 233 clinicians' and 50 patients' surveys were collected. Both cohorts favored VR under specific circumstances (e.g., invasive intervention and diagnostic manipulation). Acceptable reasons for VR usage according to clinicians were anticipated positive impact on patient safety (70%), and diagnostic suggestions and decision support (51%). A minority of providers was concerned that artificial intelligence (AI) would replace their job (14%) or erode professional skills (28%). The potential use of VR in lawsuits (81% clinicians) and privacy breaches (59% patients) were major areas of concern. Further identified barriers were lack of trust for AI, deterioration of the patient-clinician rapport. Patients agreed with VR unless it does not reduce nursing care or record sensitive scenarios.

CONCLUSION

The survey provides valuable information on the acceptance of VR cameras in the critical care setting including an overview of real concerns and attitudes toward the use of VR technology in the ICU.

Assessment of Outliers and Detection of Artifactual Network Segments Using Univariate and Multivariate Dispersion Entropy on Physiological Signals

Network physiology has emerged as a promising paradigm for the extraction of clinically relevant information from physiological signals by moving from univariate to multivariate analysis, allowing for the inspection of interdependencies between organ systems. However, for its successful implementation, the disruptive effects of artifactual outliers, which are a common occurrence in physiological recordings, have to be studied, quantified, and addressed. Within the scope of this study, we utilize Dispersion Entropy (DisEn) to initially quantify the capacity of outlier samples to disrupt the values of univariate and multivariate features extracted with DisEn from physiological network segments consisting of synchronised, electroencephalogram, nasal respiratory, blood pressure, and electrocardiogram signals. The DisEn algorithm is selected due to its efficient computation and good performance in the detection of changes in signals for both univariate and multivariate time-series. The extracted features are then utilised for the training and testing of a logistic regression classifier in univariate and multivariate configurations in an effort to partially automate the detection of artifactual network segments. Our results indicate that outlier samples cause significant disruption in the values of extracted features with multivariate features displaying a certain level of robustness based on the number of signals formulating the network segments from which they are extracted. Furthermore, the deployed classifiers achieve noteworthy performance, where the percentage of correct network segment classification surpasses 95% in a number of experimental setups, with the effectiveness of each configuration being affected by the signal in which outliers are located. Finally, due to the increase in the number of features extracted within the framework of network physiology and the observed impact of artifactual samples in the accuracy of their values, the implementation of algorithmic steps capable of effective feature selection is highlighted as an important area for future research.

Multimodal tensor-based method for integrative and continuous patient monitoring during postoperative cardiac care

Patients recovering from cardiovascular surgeries may develop life-threatening complications such as hemodynamic decompensation, making the monitoring of patients for such complications an essential component of postoperative care. However, this need has given rise to an inexorable increase in the number and modalities of data points collected, making it challenging to effectively analyze in real time. While many algorithms exist to assist in monitoring these patients, they often lack accuracy and specificity, leading to alarm fatigue among healthcare practitioners. In this study we propose a multimodal approach that incorporates salient physiological signals and EHR data to predict the onset of hemodynamic decompensation. A retrospective dataset of patients recovering from cardiac surgery was created and used to train predictive models. Advanced signal processing techniques were employed to extract complex features from physiological waveforms, while a novel tensor-based dimensionality reduction method was used to reduce the size of the feature space. These methods were evaluated for predicting the onset of decompensation at varying time intervals, ranging from a half-hour to 12 h prior to a decompensation event. The best performing models achieved AUCs of 0.87 and 0.80 for the half-hour and 12-h intervals respectively. These analyses evince that a multimodal approach can be used to develop clinical decision support systems that predict adverse events several hours in advance.

Reducing medical device alarms by an order of magnitude: A human factors approach

The intensive care unit (ICU) is one of the most technically advanced environments in healthcare, using a multitude of medical devices for drug administration, mechanical ventilation and patient monitoring. However, these technologies currently come with disadvantages, namely noise pollution, information overload and alarm fatigue—all caused by too many alarms. Individual medical devices currently generate alarms independently, without any coordination or prioritisation with other devices, leading to a cacophony where important alarms can be lost amongst trivial ones, occasionally with serious or even fatal consequences for patients. We have called this approach to the design of medical devices the single-device paradigm, and believe it is obsolete in modern hospitals where patients are typically connected to several devices simultaneously. Alarm rates of one alarm every four minutes for only the physiological monitors (as recorded in the ICUs of two hospitals contributing to this paper) degrades the quality of the patient’s healing environment and threatens patient safety by constantly distracting healthcare professionals. We outline a new approach to medical device design involving the application of human factors principles which have been successful in eliminating alarm fatigue in commercial aviation. Our approach comprises the networked-device paradigm, comprehensive alarms and humaniform information displays. Instead of each medical device alarming separately at the patient’s bedside, our proposed approach will integrate, prioritise and optimise alarms across all devices attached to each patient, display information more intuitively and hence increase alarm quality while reducing the number of alarms by an order of magnitude below current levels.

Analysis: Protocol for a New Method to Measure Physiologic Monitor Alarm Responsiveness

Evaluating the clinical impacts of healthcare alarm management systems plays a critical role in assessing newly implemented monitoring technology, exposing latent threats to patient safety, and identifying opportunities for system improvement. We describe a novel, accurate, rapidly implementable, and readily reproducible in situ simulation approach to measure alarm response times and rates without the challenges and expense of video analysis. An interprofessional team consisting of biomedical engineers, human factors engineers, information technology specialists, nurses, physicians, facilitators from the hospital's simulation center, clinical informaticians, and hospital administrative leadership worked with three units at a pediatric hospital to design and conduct the simulations. Existing hospital technology was used to transmit a simulated, unambiguously critical alarm that appeared to originate from an actual patient to the nurse's mobile device, and discreet observers measured responses. Simulation observational data can be used to design and evaluate quality improvement efforts to address alarm responsiveness and to benchmark performance of different alarm communication systems.

Generalizability of SuperAlarm via Cross-Institutional Performance Evaluation

Bedside patient monitors are ubiquitous tools in modern critical care units to provide timely patient status. However, current systems suffer from high volume of false alarms leading to alarm fatigue, one of top technical hazards in clinical settings. Many studies are racing to develop improved algorithms towards precision patient monitoring, while little has been done to investigate the aspect of algorithm generalizability across different health institutions. Our group has been developing an evolving framework termed SuperAlarm that extracts multivariate patterns in data streams (monitor alarms, electronic health records and physiologic waveforms) of modern health enterprise to predict patient deterioration and has demonstrated great potential in mitigating alarm fatigue. In this study, we further investigate the generalizability of SuperAlarm by designing a comprehensive approach to achieve performance comparison in predicting in-hospital code blue (CB) events across two health institutions. SuperAlarm model trained with alarm data in one institution is tested on both internal and external test sets. Results show comparable performance with sensitivity up to 80% within one-hour window of events and over 90% in reduction of false alarms in both institutions. Cross-institutional performance agreement can be further improved by predicting a more stringent CB subtype (cardiopulmonary arrest), with internal sensitivity lying within 95% confident interval of external one up to 8-hour before event onset. The cross-institutional performance comparison offers first-hand knowledge on both advantages and challenges in generalizing a prediction algorithm across different institutions, which hold key information to guide the design of model training and deployment strategy.

Textile Based Sensing Blanket for ECG Monitoring in the Intensive Care Unit

Multiple designs of textile-based sensors were developed and integrated into blankets for the measurement of Electrocardiogram (ECG) signals. Once the patient makes direct skin contact with the electrodes, the ECG signals are acquired and transmitted wirelessly by a wireless data acquisition unit to an associated computer for analysis, assessment and storage. A variety of designs and manufacturing methods were tested. An adult human subjects' study was conducted to test the feasibility of these measurements as well as to test the different design types and manufacturing methods. The heart rate and Signal to Noise ratio (SNR) are comparable to the gold standard adhesive lead measurements.

A two-pronged approach to reduce noise levels in the neonatal intensive care unit

OBJECTIVES

The aim of this study was to assess the efficacy of a visual noise feedback system and "quiet time" in reducing noise levels in the neonatal intensive care unit (NICU).

DESIGN

A prospective cross-sectional study was performed in a combined level II/III NICU at a Canadian tertiary care hospital. Noise levels were recorded continuously for three weeks without and then three weeks with visual noise feedback system. Noise levels were compared after one year of using visual feedback, and subsequently with the addition of two "quiet times."

RESULTS

Visual feedback reduced noise levels from 54.2 dB (95% CI 53.8-54.7 dB) to 49.4 dB (95% CI 48.9-49.8 dB; P < 0.0001) and increased the amount of time spent under 45 dB from 0 to 25% (P < 0.0001) after three weeks of use. However, this effect was not sustained at one year of visual feedback, with noise levels at 54.7 dB (95% CI 54.5-55.0 dB, P = 0.55). Quiet Time did not further reduce daily noise in the NICU (average noise levels 54.7, 95% CI 54.4-55.0 dB, P = 0.836).

CONCLUSIONS

While visual noise feedback system reduced noise levels in the short term, these effects were not sustainable at one year and could not be remediated with the addition of a Quiet Time initiative. Continuing education regarding the detrimental effects of noise is paramount to ensure persistent noise reduction in the NICU.

Thresholds for oximetry alarms and target range in the NICU: an observational assessment based on likely oxygen tension and maturity

BACKGROUND

Continuous monitoring of SpO₂ in the neonatal ICU is the standard of care. Changes in SpO₂ exposure have been shown to markedly impact outcome, but limiting extreme episodes is an arduous task. Much more complicated than setting alarm policy, it is fraught with balancing alarm fatigue and compliance. Information on optimum strategies is limited.

METHODS

This is a retrospective observational study intended to describe the relative chance of normoxemia, and risks of hypoxemia and hyperoxemia at relevant SpO₂ levels in the neonatal ICU. The data, paired SpO₂-PaO₂ and post-menstrual age, are from a single tertiary care unit. They reflect all infants receiving supplemental oxygen and mechanical ventilation during a 3-year period. The primary measures were the chance of normoxemia (PaO₂ 50-80 mmHg), risks of severe hypoxemia (PaO₂ ≤ 40 mmHg), and of severe hyperoxemia (PaO₂ ≥ 100 mmHg) at relevant SpO₂ levels.

RESULTS

Neonates were categorized by postmenstrual age: < 33 (n = 155), 33-36 (n = 192) and > 36 (n = 1031) weeks. From these infants, 26,162 SpO₂-PaO₂ pairs were evaluated. The post-menstrual weeks (median and IQR) of the three groups were: 26 (24-28) n = 2603; 34 (33-35) n = 2501; and 38 (37-39) n = 21,058. The chance of normoxemia (65, 95%-CI 64-67%) was similar across the SpO₂ range of 88-95%, and independent of PMA. The increasing risk of severe hypoxemia became marked at a SpO₂ of 85% (25, 95%-CI 21-29%), and was independent of PMA. The risk of severe hyperoxemia was dependent on PMA. For infants < 33 weeks it was marked at 98% SpO₂ (25, 95%-CI 18-33%), for infants 33-36 weeks at 97% SpO₂ (24, 95%-CI 14-25%) and for those > 36 weeks at 96% SpO₂ (20, 95%-CI 17-22%).

CONCLUSIONS

The risk of hyperoxemia and hypoxemia increases exponentially as SpO₂ moves towards extremes. Postmenstrual age influences the threshold at which the risk of hyperoxemia became pronounced, but not the thresholds of hypoxemia or normoxemia. The thresholds at which a marked change in the risk of hyperoxemia and hypoxemia occur can be used to guide the setting of alarm thresholds. Optimal management of neonatal oxygen saturation must take into account concerns of alarm fatigue, staffing levels, and FiO₂ titration practices.

Evaluation of clinician interaction with alerts to enhance performance of the tele-critical care medical environment

OBJECTIVE

Identify opportunities to improve the interaction between clinicians and Tele-Critical Care (Tele-CC) programs through an analysis of alert occurrence and reactivation in a specific Tele-CC application.

MATERIALS AND METHODS

Data were collected automatically through the Philips eCaremanager® software system used at multiple hospitals in the Avera health system. We evaluated the distribution of alerts per patient, frequency of alert types, time between consecutive alerts, and Tele-CC clinician choice of alert reactivation times.

RESULTS

Each patient generated an average of 79.8 alerts during their ICU stay (median 31.0; 25th - 75th percentile 10.0-89.0) with 46.4 for blood pressure and 38.4 for oxygenation. The most frequent alerts for continuous physiological parameters were: MAP limit (28.9 %), O₂/RR (26.4 %), MAP trend (16.5 %), HR trend (12.1 %), and HR limit (11.3 %). The median time between consecutive alerts for one parameter was less than 10 min for 86 % of patients. Tele-CC providers responded to all alert types with immediate reactivation 47-88 % of the time. Limit alerts had longer reactivation times than their trend alert counterparts (p-value < .001).

CONCLUSIONS

The alert type specific differences in frequency, time occurrence and provider choice of reactivation time provide insight into how clinicians interact with the Tele-CC system. Systems engineering enhancements to Tele-CC software algorithms may reduce alert burden and thereby decrease clinicians' cognitive workload for alert assessment. Further study of Tele-CC alert generation, alert presentation to clinicians, and the clinicians' options to respond to these alerts may reduce provider workload, minimize alert desensitization, and optimize the ability of Tele-CC clinicians to provide efficient and timely critical care management.

Alarm Fatigue in the Intensive Care Unit: Relevance and Response Time

OBJECTIVE

To establish the presence of alarm fatigue, the clinical relevance of alarms and the stimulus-response time of the health team in an Adult Intensive Care Unit.

METHOD

Descriptive, quantitative, observational study, developed in the Multipurpose Adult Intensive Care Unit. Population made up of health personnel and the ICU teams. The method used was non-participant observation. Follow-up was carried out over 120 hours in three months. The variables studied were number of alarms activated, time elapsed between the alert sound of the blood pressure parameter, heart rate and oximetry and the response of the health personnel who attended the alarm. A descriptive statistical analysis was carried out.

RESULTS

5,147 alarms were detected, on average 43 alarms / hour, of these 52.8% corresponded to multiparameter monitors and the rest to other equipment. Of those generated by multiparameter monitors, 37.3% were blood pressure, 33.4% oximetry and 29.3% heart rate. The clinical relevance was low in 42.7%, medium in 49.8% and high in 7.5%. The stimulus response time was between 0 and 60 seconds for 37% of the alarms; however, 42.5% had no response, which is why they are considered fatigued. A statistically significant relationship was found between the response time and the clinical relevance of the alarms (p = .000).

CONCLUSIONS

The presence of alarm fatigue was evident; with predominance of clinical relevance in the middle and low ranges. The health personnel responded within the time established for timely attention to the non-fatigued alarms.

Augmentation of Dispersion Entropy for Handling Missing and Outlier Samples in Physiological Signal Monitoring

Entropy quantification algorithms are becoming a prominent tool for the physiological monitoring of individuals through the effective measurement of irregularity in biological signals. However, to ensure their effective adaptation in monitoring applications, the performance of these algorithms needs to be robust when analysing time-series containing missing and outlier samples, which are common occurrence in physiological monitoring setups such as wearable devices and intensive care units. This paper focuses on augmenting Dispersion Entropy (DisEn) by introducing novel variations of the algorithm for improved performance in such applications. The original algorithm and its variations are tested under different experimental setups that are replicated across heart rate interval, electroencephalogram, and respiratory impedance time-series. Our results indicate that the algorithmic variations of DisEn achieve considerable improvements in performance while our analysis signifies that, in consensus with previous research, outlier samples can have a major impact in the performance of entropy quantification algorithms. Consequently, the presented variations can aid the implementation of DisEn to physiological monitoring applications through the mitigation of the disruptive effect of missing and outlier samples.

Sleeping Soundlessly in the Intensive Care Unit

An estimated 70% of patients who have been in the Intensive Care Unit (ICU) experience some form of Post-Intensive Care Syndrome (PICS). As a stressful environment, the ICU can be traumatic for any patient; however, the disruption of sleep experienced by patients in ICU negatively impacts their mental status and recovery. One of the most significant contributors to sleep disruption is the constant blare of monitor alarms, many of which are false or redundant. Through multisensory approaches and procedural redesign, the hostile acoustic environment of the ICU that causes so many to suffer from PICS may be alleviated. In this paper, we present suggestions for improving the ICU acoustic environment to possibly reduce the incidence of post-ICU complications such as PICS.

Reducing False Alarm Rates in Neonatal Intensive Care: A New Machine Learning Approach

In neonatal intensive care units (NICUs), 87.5% of alarms by the monitoring system are false alarms, often caused by the movements of the neonates. Such false alarms are not only stressful for the neonates as well as for their parents and caregivers, but may also lead to longer response times in real critical situations. The aim of this project was to reduce the rates of false alarms by employing machine learning algorithms (MLA), which intelligently analyze data stemming from standard physiological monitoring in combination with cerebral oximetry data (in-house built, OxyPrem).

MATERIALS & METHODS

Four popular MLAs were selected to categorize the alarms as false or real: (i) decision tree (DT), (ii) 5-nearest neighbors (5-NN), (iii) naïve Bayes (NB) and (iv) support vector machine (SVM). We acquired and processed monitoring data (median duration (SD): 54.6 (± 6.9) min) of 14 preterm infants (gestational age: 26 6/7 (± 2 5/7) weeks). A hybrid method of filter and wrapper feature selection generated the candidate subset for training these four MLAs.

RESULTS

A high specificity of >99% was achieved by all four approaches. DT showed the highest sensitivity (87%). The cerebral oximetry data improved the classification accuracy.

DISCUSSION & CONCLUSION

Despite a (as yet) low amount of data for training, the four MLAs achieved an excellent specificity and a promising sensitivity. Presently, the current sensitivity is insufficient since, in the NICU, it is crucial that no real alarms are missed. This will most likely be improved by including more subjects and data in the training of the MLAs, which makes pursuing this approach worthwhile.

Evolution of the Intensive Care Unit Telemedicine Value Proposition

Advances in clinical information sciences, telecommunication technologies, electronic health records, early warning systems, automated acuity assessment, and clinician communication support systems have allowed current-generation intensive care (ICU) telemedicine systems to address the inefficiencies of the failed advice-upon-request ICU telemedicine model. Value is related to the ability of health care systems to leverage ICU telemedicine resources to provide care. Local financial benefits of ICU telemedicine program implementation depend on changing behavior to better focus on activities that reduce the duration of critical illness and length of stay.

Developing safe devices for neonatal care

Currently, the majority of medical devices are designed for adults; some are then miniaturized for use in neonates. This process neglects population-specific testing that would ensure that the medical devices used for neonates are actually safe and effective for that group. Incorporating human-centered design principles and utilizing methods to evaluate devices that include simulation and clinical testing can improve the safety of devices used in caring for neonates. However, significant regulatory, financial, social and ethical barriers to development remain. In order to overcome these barriers and create a pipeline of safe and effective neonatal medical devices, specific incentives are required.

Smart pumps improve medication safety but increase alert burden in neonatal care

Background

Smart pumps have been widely adopted but there is limited evidence to understand and support their use in pediatric populations. Our objective was to assess whether smart pumps are effective at reducing medication errors in the neonatal population and determine whether they are a source of alert burden and alert fatigue in an intensive care environment.

Methods

Using smart pump records, over 370,000 infusion starts for continuously infused medications used in neonates and infants hospitalized in a level IV NICU from 2014 to 2016 were evaluated. Attempts to exceed preset soft and hard maximum limits, percent variance from those limits, and pump alert frequency, patterns and salience were evaluated.

Results

Smart pumps prevented 160 attempts to exceed the hard maximum limit for doses that were as high as 7–29 times the maximum dose and resulted in the reprogramming or cancellation of 2093 infusions after soft maximum alerts. While the overall alert burden from smart pumps for continuous infusions was not high, alerts clustered around specific patients and medications, and a small portion (17%) of infusions generated the majority of alerts. Soft maximum alerts were often overridden (79%), consistent with low alert salience.

Conclusions

Smart pumps have the ability to improve neonatal medication safety when compliance with dose error reducing software is high. Numerous attempts to administer high doses were intercepted by dosing alerts. Clustered alerts may generate a high alert burden and limit safety benefit by desensitizing providers to alerts. Future efforts should address ways to improve alert salience.

Dutch Neonatal Intensive Care Nurses' Perceptions of Pulse Oximeter Saturation Target Limits for Preterm Infants

PURPOSE

To conduct a national survey to assess practice, knowledge, barriers, and perceptions regarding oxygen saturation (SpO₂) target limits among Dutch neonatal intensive care unit (NICU) nurses.

DESIGN AND METHODS

Cross-sectional, web-based survey among 667 nurses from 9 level 3 Dutch NICUs. Part of the questions were based on a clinical scenario (28-weeks preterm infant, treated with CPAP, FiO₂ 0.4).

RESULTS

328 (53.6%) nurses responded to the survey. Of these, 281 (85.7%) reported to know the local policy of SpO₂ target limits, and 261 (79.6%) and 244 (74.4%) rightly identified the lower and upper limit, respectively. Six NICUs recently increased their lower SpO₂ limit and for 62.0% of their nurses this led to a significant alarm increase. For the majority of the respondents, the baby from the clinical scenario would spend <10% of the time outside the lower or upper SpO₂ limits. Automated oxygen control systems were considered a good idea by 59.2% of the respondents, but 53.9% considered allowing parents to participate in FiO₂ titration a bad or very bad idea_. CONCLUSIONS: The majority of the respondents identified their unit's policy-specified SpO₂ target limits and reported that the increase in SpO₂ target limits may have led to more alarms. Titration of FiO₂ is a part of care that respondents were reluctant to share with parents.

PRACTICE IMPLICATIONS

A potential increase in the number of SpO₂ alarms may lead to alarm fatigue. Although family-centered care philosophy is widely accepted across Dutch NICUs, there are still barriers to overcome.

The DIFFMASK score for predicting difficult facemask ventilation: a cohort study of 46,804 patients

Facemask ventilation is an essential part of airway management. Correctly predicting difficulties in facemask ventilation may reduce the risk of morbidity and mortality among patients at risk. We aimed to develop and evaluate a weighted risk score for predicting difficult facemask ventilation during anaesthesia. We analysed a cohort of 46,804 adult patients who were assessed pre-operatively airway for 13 predictors of difficult airway management and subsequently underwent facemask ventilation during general anaesthesia. We developed the Difficult Facemask (DIFFMASK) score in two consecutive steps: first, a multivariate regression analysis was performed; and second, the regression coefficients of the adjusted regression model were converted into a clinically applicable weighted point score. The predictive accuracy of the DIFFMASK score was evaluated by assessment of receiver operating characteristic curves. The prevalence of difficult facemask ventilation was 1.06% (95%CI 0.97-1.16). Following conversion of regression coefficients into 0, 1, 2 or 3 points, the cumulated DIFFMASK score ranged from 0 to 18 points and the area under the receiver operating characteristic curve was 0.82. The Youden index indicated a sum score ≥ 5 as an optimal cut-off value for prediction of difficult facemask ventilation giving a sensitivity of 85% and specificity of 59%. The DIFFMASK score indicated that a score of 6-10 points represents a population of patients who may require heightened attention when facemask ventilation is planned, compared with those patients who are obviously at a high- or low risk of difficulties. The DIFFMASK score may be useful in a clinical context but external, prospective validation is needed.

Evaluation of two SpO2 alarm strategies during automated FiO2 control in the NICU: a randomized crossover study

Background

Changes in oxygen saturation (SpO₂) exposure have been shown to have a marked impact on neonatal outcomes and therefore careful titration of inspired oxygen is essential. In routine use, however, the frequency of SpO₂ alarms not requiring intervention results in alarm fatigue and its corresponding risk. SpO₂ control systems that automate oxygen adjustments (Auto-FiO₂) have been shown to be safe and effective. We speculated that when using Auto-FiO₂, alarm settings could be refined to reduce unnecessary alarms, without compromising safety.

Methods

An unblinded randomized crossover study was conducted in a single NICU among infants routinely managed with Auto-FiO₂. During the first 6 days of respiratory support a tight and a loose alarm strategy were switched each 24 h. A balanced block randomization was used. The tight strategy set the alarms at the prescribed SpO₂ target range, with a 30-s delay. The loose strategy set the alarms 2 wider, with a 90-s delay. The effectiveness outcome was the frequency of SpO₂ alarms, and the safety outcomes were time at SpO₂ extremes (< 80, > 98%). We hypothesized that the loose strategy would result in a marked decrease in the frequency of SpO₂ alarms, and no increases at SpO₂ extremes with 20 subjects. Within subject differences between alarm strategies for the primary outcomes were evaluated with Wilcoxon signed-rank test.

Results

During a 13-month period 26 neonates were randomized. The analysis included 21 subjects with 49 days of both tight and loose intervention. The loose alarm strategy resulted in a reduction in the median rate of SpO₂ alarms from 5.2 to 1.6 per hour (p <  0.001, 95%-CI difference 1.6–3.7). The incidence of hypoxemia and hyperoxemia were very low (less than 0.1%-time) with no difference associated with the alarm strategy (95%-CI difference less than 0.0–0.2%).

Conclusions

In this group of infants we found a marked advantage of the looser alarm strategy. We conclude that the paradigms of alarm strategies used for manual titration of oxygen need to be reconsidered when using Auto-FiO₂. We speculate that with optimal settings false positive SpO₂ alarms can be minimized, with better vigilance of clinically relevant alarms.

Trial registration

Retrospectively registered 15 May 2018 at ISRCTN (49239883).

Electronic supplementary material

The online version of this article (10.1186/s12887-019-1496-5) contains supplementary material, which is available to authorized users.

The Connected Intensive Care Unit Patient: Exploratory Analyses and Cohort Discovery From a Critical Care Telemedicine Database

BACKGROUND

Many intensive care units (ICUs) utilize telemedicine in response to an expanding critical care patient population, off-hours coverage, and intensivist shortages, particularly in rural facilities. Advances in digital health technologies, among other reasons, have led to the integration of active, well-networked critical care telemedicine (tele-ICU) systems across the United States, which in turn, provide the ability to generate large-scale remote monitoring data from critically ill patients.

OBJECTIVE

The objective of this study was to explore opportunities and challenges of utilizing multisite, multimodal data acquired through critical care telemedicine. Using a publicly available tele-ICU, or electronic ICU (eICU), database, we illustrated the quality and potential uses of remote monitoring data, including cohort discovery for secondary research.

METHODS

Exploratory analyses were performed on the eICU Collaborative Research Database that includes deidentified clinical data collected from adult patients admitted to ICUs between 2014 and 2015. Patient and ICU characteristics, top admission diagnoses, and predictions from clinical scoring systems were extracted and analyzed. Additionally, a case study on respiratory failure patients was conducted to demonstrate research prospects using tele-ICU data.

RESULTS

The eICU database spans more than 200 hospitals and over 139,000 ICU patients across the United States with wide-ranging clinical data and diagnoses. Although mixed medical-surgical ICU was the most common critical care setting, patients with cardiovascular conditions accounted for more than 20% of ICU stays, and those with neurological or respiratory illness accounted for nearly 15% of ICU unit stays. The case study on respiratory failure patients showed that cohort discovery using the eICU database can be highly specific, albeit potentially limiting in terms of data provenance and sparsity for certain types of clinical questions.

CONCLUSIONS

Large-scale remote monitoring data sources, such as the eICU database, have a strong potential to advance the role of critical care telemedicine by serving as a testbed for secondary research as well as for developing and testing tools, including predictive and prescriptive analytical solutions and decision support systems. The resulting tools will also inform coordination of care for critically ill patients, intensivist coverage, and the overall process of critical care telemedicine.

A call to alarms: Current state and future directions in the battle against alarm fatigue

Research demonstrates that the majority of alarms derived from continuous bedside monitoring devices are non-actionable. This avalanche of unreliable alerts causes clinicians to experience sensory overload when attempting to sort real from false alarms, causing desensitization and alarm fatigue, which in turn leads to adverse events when true instability is neither recognized nor attended to despite the alarm. The scope of the problem of alarm fatigue is broad, and its contributing mechanisms are numerous. Current and future approaches to defining and reacting to actionable and non-actionable alarms are being developed and investigated, but challenges in impacting alarm modalities, sensitivity and specificity, and clinical activity in order to reduce alarm fatigue and adverse events remain. A multi-faceted approach involving clinicians, computer scientists, industry, and regulatory agencies is needed to battle alarm fatigue.

Hemoglobin oxygen saturation targets in the neonatal intensive care unit: Is there a light at the end of the tunnel? 1

The optimal oxygenation target needed to prevent the extremes of hypoxia and oxygen toxicity in premature and sick newborns has been the subject of much research and debate. The advent of the pulse oximeter has allowed the continuous monitoring of oxyhemoglobin saturation and the delivery of oxygen with greater precision. Well-run, large clinical trials to determine the safest oxygen concentration have led to several revisions in guidelines for neonatal care. However, monitoring of oxyhemoglobin saturation has its limitations and does not provide a comprehensive assessment of tissue oxygenation. To identify optimal oxygen therapy, various other factors (partial pressure of arterial carbon dioxide, hemoglobin concentration, blood pH, and tissue metabolic demand) that influence perfusion and tissue oxygenation need to be considered.

Validation of the VitalPAC Early Warning Score at the Intermediate Care Unit

AIM

To assess the performance and clinical relevance of the Early Warning Scoring (EWS) system at the Intermediate Care Unit (IMCU).

METHODS

This cohort study used all the VitalPAC EWS (ViEWS) scores collected during each nursing shift from 2014 through 2016 at the mixed surgical IMCU of an academic teaching hospital. Clinical deterioration defined as transfer to the Intensive Care Unit (ICU) or mortality within 24 h was the primary outcome of interest.

RESULTS

A total of 9113 aggregated ViEWS scores were obtained from 2113 admissions. The incidence of the combined outcome was 272 (3.0%). The area under the curve of the ViEWS was 0.72 (CI: 0.69-0.75). Using a threshold value of six, the sensitivity was 68% with a positive predictive value of 5% and a number needed to trigger (e.g., false alarms) of 19%.

CONCLUSION

The ViEWS at the IMCU has a discriminative performance that is considerably lower than at the hospital ward. The number of false alarms is high, which may result in alarm fatigue. Therefore, use of the ViEWS in its current form at the IMCU should be reconsidered.

Epidemiology of patient monitoring alarms in the neonatal intensive care unit

OBJECTIVE

To characterize the rate of monitoring alarms by alarm priority, signal type, and developmental age in a Level-IIIB Neonatal Intensive Care Unit (NICU) population.

STUDY DESIGN

Retrospective analysis of 2,294,687 alarm messages from Philips monitors in a convenience sample of 917 NICU patients, covering 12,001 patient-days. We stratified alarm rates by alarm priority, signal type, postmenstrual age (PMA) and birth weight (BW), and reviewed and adjudicated over 21,000 critical alarms.

RESULTS

Of all alarms, 3.6% were critical alarms, 55.0% were advisory alarms, and 41.4% were device alerts. Over 60% of alarms related to oxygenation monitoring. The average alarm rate (±SEM) was 177.1 ± 4.9 [median: 135.9; IQR: 89.2-213.3] alarms/patient-day; the medians varied significantly with PMA and BW (p < 0.001) in U-shaped patterns, with higher rates at lower and higher PMA and BW. Based on waveform reviews, over 99% of critical arrhythmia alarms were deemed technically false.

CONCLUSIONS

The alarm burden in this NICU population is very significant; the average alarm rate significantly underrepresents alarm rates at low and high PMA and BW. Virtually all critical arrhythmia alarms were artifactual.