Sirs and Septic Shock Alert Evaluation

INTRODUCTION: Prompt recognition of sepsis is imperative for timely treatment and has led to the creation of the CERNER St. Johns Sepsis (SJS) Surveillance Agent Algorithm. Patient specific values are analyzed to determine if criteria for a Systemic Inflammatory Response Syndrome (SIRS) or Septic Shock Alert is met. The SJS Surveillance Agent Algorithm has a positive predictive value of 64%. The study site modified the alert criteria in the acute care areas and the emergency department to reduce alert fatigue. The purpose of this evaluation was to assess whether the modified alert criteria accurately identifies patients with possible sepsis. METHOD(S): This is a single center, retrospective, cohort evaluation. A Cerner Sepsis Audit report of all SIRS and Septic Shock Alert patients admitted between July 1 and July 14, 2021 was used for analysis. Patients were screened at random and included once per admission, first occurrence only. Patients were excluded if they had a presumed or confirmed COVID-19 diagnosis during admission. The proportion of SIRS and Septic Shock Alerts that correlate to a sepsis diagnosis and the proportion of patients with a discharge diagnosis code of sepsis where no alert was generated were analyzed using descriptive statistics. RESULT(S): A total of 147 patients were screened for inclusion with 121 patients included in the final analysis. There were 105 patients who triggered a SIRS or Septic Shock Alert and 16 patients coded for sepsis with no alert generated. The modified SJS criteria resulted in a positive predictive value of 60% (63 sepsis diagnosis vs. 42 noninfectious diagnosis). A majority of alerts were generated by SIRS criteria versus Septic Shock criteria. The most common non-infectious diagnoses in patients who alerted without sepsis were hemorrhage, hypovolemia, and trauma. CONCLUSION(S): Modification of the SJS algorithm occurred in an effort to decrease alert fatigue and was found to be comparable in positive predictive value to the unmodified algorithm.

VENTILATOR ALARM TRENDS IN A MEDICAL ICU

SESSION TITLE: Actionable Improvements in Safety and Quality SESSION TYPE: Rapid Fire Original Inv PRESENTED ON: 10/17/2022 12:15 pm - 1:15 pm PURPOSE: Ventilator alarms are an audible and visual safeguard within a system which alerts clinicians to potentially critical changes within the patient or ventilator unit. They are a crucial aspect of patient care;however, not every alarm that is generated by the ventilator will provide actionable information. Unfortunately, this can contribute significantly to the overall alarm burden in the intensive care unit. This has been especially true with the marked increase in ventilator use during the COVID-19 pandemic. The individual impact of each alarm can easily become dampened due to the sheer quantity of alarms, ventilator-related and others. Excessive alarming may lead to cognitive overload and alarm fatigue for providers, and eventually, adversely impact patient outcomes. This potentially can lead to missed life-sustaining interventions and medical errors. METHODS: As part of a quality improvement initiative, we evaluated ventilator alarms through the month of October 2021 in the medical intensive care unit within Bellevue Hospital Center in New York City. Respiratory therapists recorded ventilator parameters and extracted alarm data daily from every ventilator within the medical intensive care unit. Ventilator logs were exported from each individual Servo-U ventilator unit in use onto a USB flash drive and the captured data was uploaded to a secure network for review. For each ventilator, data regarding specific alarm type and priority as defined by the manufacturer, as well as time, frequency, and duration was obtained for review. RESULTS: From October 4, 2021, to October 31, 2021, a total of 30,230 ventilator alarms were initiated over 672 hours in the MICU. This provided an approximate mean of 45 alarms per ventilator hour. Data was collected daily from all MICU ventilators in use which averaged about 12 ventilators per day (between 6-16). The top four alarms as defined by the ventilator were “airway pressure high,” “respiratory rate high,” “PEEP [positive end expiratory pressure] low,” and “expiratory minute volume low.” 18,451 alarms over the month were “airway pressure high.” 3,982 alarms were defined as “respiratory rate high.” 2,220 alarms were “PEEP low” and 2,041 alarms were “expiratory minute volume low.” CONCLUSIONS: Ventilator alarms, both nuisance and actionable alarms, contribute significantly to the alarm burden in the medical intensive care unit. Dedicated research is necessary to ensure safer alarm practices. CLINICAL IMPLICATIONS: Evaluating baseline alarm data allows for assessments as well as analyses of trends and patterns that are contributing to the excessive noise within the intensive care units. This gives hospitals an opportunity to provide targeted multidisciplinary educational initiatives and create standardized protocols to enhance the quality and safety surrounding ventilator alarms within intensive care units. DISCLOSURES: No relevant relationships by Kerry Hena No relevant relationships by Charmel Rogers no disclosure on file for Amit Uppal;No relevant relationships by Tatiana Weinstein

PUBLIC VIEWS DURING THE CORONAVIRUS PANDEMIC: A UK BASED MIXED METHOD STUDY

Introduction: The coronavirus pandemic presents the greatest challenge to public health in living memory. To slow the spread of the virus the UK initiated periods of strict social distancing, or lockdown. The ongoing social and psychological impacts of the pandemic and lockdowns are still under investigation. We aimed to explore longitudinally the attitudes and behaviors of members of the UK public from the start of UK lockdowns in March, 2020. We focused on mental health, adherence to health behaviours and government regulations, perceptions of vaccinations, and impact on Black, Asian, Minority Ethnic (BAME) participants. Method: Focus groups (2-8 people, 60 min) and surveys were conducted with 57 UK residents from March 23, 2020 to the present at 5 different timepoints that captured lockdowns and firebreaks (93% retention). Participants were 51% Female, mean age 37.1 (Range: 20-60), 72% White, 5% Mixed or Multiple ethnic groups, 16% Asian or Asian British, and 7% Black, African, Caribbean or Black British. Surveys included the Patient Health Questionnaire - Somatic, Anxiety, and Depressive Symptoms (PHQ-SADS), the Capabilities, Opportunities, Motivations and Behaviours questionnaire (COM-B), and coronavirus specific questions such as vaccination intention. Qualitative results: The central theme was that of loss;'practical losses' e.g. income and 'psychological losses' e.g. motivation. Loss improved, but uncertainty and anticipatory anxiety continued across timepoints. Reported mental health issues improved over Summer 2020 and worsened in Nov 2020. Alert fatigue and learned helplessness emerged as the main themes at that time and marginalization by BAME participants. Behavioural adherence and vaccination uptake focused around perception of risk and community vs individual responsibility. Quantitative results: Data will be analysed following the current wave of data collection (Nov-Dec 2021) and will presented in March, 2022. Conclusion: Mental health fluctuated with the ability to socially connect with others outside of the household. Feelings of loss improved over time. Alert fatigue and general mistrust in government increased as did learned helplessness resulting in a loss of motivation. Results have had a significant policy and media impact in the UK and resulted in several publications to date.

ICU Clinician Perspectives on Machine Learning and the Implementation of a Mechanical Ventilation Prediction Tool: A Single Center Survey Study

Rationale Although there is considerable interest in machine learning (ML) algorithms to improve patient care, implementation of these algorithms into practice has been limited. Our team developed and validated a deep learning algorithm to predict respiratory failure requiring mechanical ventilation in patients in the intensive care unit (ICU), including those with COVID-19. To help optimize implementation of this tool, we developed and disseminated a survey assessing ICU physician perspectives on the acceptability and feasibility of this tool at our institution. Methods We distributed an 8-item survey to 99 critical care trainees and faculty at our institution via email. The survey consisted of 6 multiple choice and 2 free response questions, with an ordinal scale of 1-5 used in perception-based questions. The survey was designed in accordance with international recommendations for web-based surveys. Our survey was reviewed for completeness by a team of critical care, machine learning, and implementation science experts. Data were collected over a 2- week period in May of 2021. This survey was anonymous and exempt from IRB review. Results Fifty-three critical care physicians (53.5% of providers contacted) started the survey, and of these, 88.7% (47/53) completed the survey. Fifty-nine percent (n=31) of respondents were attendings, 36% (n=19) fellows, and 3.7% (n=2) residents. Baseline knowledge of ML was low (mean= 2.40/5), with only 7.5% (n=4) of respondents rating their knowledge as a 4 or 5. Fifteen percent (n=8) had knowingly used an ML-based tool in their clinical practice. Confidence in predicting the need for mechanical ventilation due to COVID-19 (mean=3.57/5) was slightly lower than for respiratory failure due to all other causes (mean=3.89/5). Overall willingness to utilize an ML-based algorithm was favorable (mean=3.32/5). Factors most likely to increase likelihood of utilization were “high quality evidence that it outperformed trained clinicians” (mean=4.28/5), “transparency of the data utilized” (mean= 4.13/5), and “limited workflow interruption” (mean=4.09/5). Shared concerns from participants included “alarm fatigue” and “workflow interruption.” Conclusion The results suggest that ICU physicians have had limited exposure to ML-based tools, but feel such a tool would be beneficial in the context of predicting need for mechanical ventilation in ICU patients and those with COVID-19. Evidence of the tool's efficacy and data transparency were high priorities for respondents, and there was concern over workflow interruptions. This survey provided a baseline assessment of physician acceptance of a novel ML-based tool, which will be crucial in optimizing its implementation into clinical practice at our institution.

Promoting ß-lactam utilization through suppression of electronic medical record cross-allergy alerts.

PURPOSE: Current literature surrounding management of patients with reported ß-lactam allergies focuses on allergy delabeling. Standard clinical decision support tools have not been optimized to be compatible with the currently accepted cross-reaction rate of 1% to 2%. This potentially promotes use of non-ß-lactam antibiotics, which are often not first-line therapy and may carry increased risks. The impact of electronic medical record (EMR) clinical decision support tool optimization on utilization of ß-lactam antibiotics in ß-lactam-allergic patients was evaluated. METHODS: A retrospective pre-post ß-lactam cross-allergy EMR alert suppression quality improvement intervention cohort study of ß-lactam-allergic adult inpatients prescribed antibiotics was conducted. Preintervention baseline data were collected for an initial cohort admitted during September 2018. The intervention, in which clinical decision support rules were updated to display ß-lactam cross-sensitivity allergy alerts only for ß-lactam-allergic patients with documentation of organization-defined high-severity reactions of anaphylaxis, hives, and shortness of breath, was implemented August 20, 2019. The postintervention cohort included patients admitted during September 2019. RESULTS: A 91% increase in the percentage of ß-lactam-allergic patients who received a ß-lactam agent at any time during their admission was noted after the intervention (26.6% vs 51%, P < 0.001). Statistically significant decreases in prescribing of alternative antibiotic classes were seen for fluoroquinolones (decrease from 45.3% to 26%, P < 0.001), aminoglycosides (decrease from 9.4% to 2.9%, P = 0.002), and aztreonam (decrease from 30% to 16.7%, P < 0.001). CONCLUSION: EMR ß-lactam cross-allergy alert optimization consistent with current literature significantly improved the utilization of alternative ß-lactam subclasses, mostly through ß-lactam prescribing as initial therapy in ß-lactam-allergic patients.

Alerts in Clinical Decision Support Systems (CDSS): A Bibliometric Review and Content Analysis.

A clinical decision support system (CDSS) informs or generates medical recommendations for healthcare practitioners. An alert is the most common way for a CDSS to interact with practitioners. Research about alerts in CDSS has proliferated over the past ten years. The research trend is ongoing with new emerging terms and focus. Bibliometric analysis is ideal for researchers to understand the research trend and future directions. Influential articles, institutes, countries, authors, and commonly used keywords were analyzed to grasp a comprehensive view on our topic, alerts in CDSS. Articles published between 2011 and 2021 were extracted from the Web of Science database. There were 728 articles included for bibliometric analysis, among which 24 papers were selected for content analysis. Our analysis shows that the research direction has shifted from patient safety to system utility, implying the importance of alert usability to be clinically impactful. Finally, we conclude with future research directions such as the optimization of alert mechanisms and comprehensiveness to enhance alert appropriateness and to reduce alert fatigue.

A cost-effective alertness-rating tool to enable situational awareness among on-duty static security guards in Covid-19 pandemic.

The workload of the static security guards has doubled due to the Covid-19 outbreak. In addition to their regular duties, they undertake some additional tasks to evaluate each individual's body temperature and welcome them with a hand sanitizer. In this scenario, their situational awareness is hugely desirable to perform these activities for the entire campus's safety. This situational awareness of guards means their ability to observe, inspect, and make the right decisions. However, due to their fatigue and other secondary activities, such as cell phone use, they cannot perform their duties correctly. In this context, this paper presents a method for sending random alarms in real-time to the on-duty guards, who are executing their work at the campus gates, remotely monitoring the alertness throughout the day from the head security office. For alertness detection, the system uses a simple client-server model. The system is designed using NodeMCU Wi-Fi modules. The algorithm of the Client, server, and repeater has been developed. The prototype has been tested by placing it on the working individuals' desk inside the departmental lab inside the campus. The system records the response time of the working individuals. These data are further used to calculate their percentage of alertness. In addition, an alertness-rating/scoring method has been developed to improve their work performance. This system can be an economical solution to enable the awareness of on-duty guards.

A Closer Look at the "Right" Format for Clinical Decision Support: Methods for Evaluating a Storyboard BestPractice Advisory.

(1) Background: The five rights of clinical decision support (CDS) are a well-known framework for planning the nuances of CDS, but recent advancements have given us more options to modify the format of the alert. One-size-fits-all assessments fail to capture the nuance of different BestPractice Advisory (BPA) formats. To demonstrate a tailored evaluation methodology, we assessed a BPA after implementation of Storyboard for changes in alert fatigue, behavior influence, and task completion; (2) Methods: Data from 19 weeks before and after implementation were used to evaluate differences in each domain. Individual clinics were evaluated for task completion and compared for changes pre- and post-redesign; (3) Results: The change in format was correlated with an increase in alert fatigue, a decrease in erroneous free text answers, and worsened task completion at a system level. At a local level, however, 14% of clinics had improved task completion; (4) Conclusions: While the change in BPA format was correlated with decreased performance, the changes may have been driven primarily by the COVID-19 pandemic. The framework and metrics proposed can be used in future studies to assess the impact of new CDS formats. Although the changes in this study seemed undesirable in aggregate, some positive changes were observed at the level of individual clinics. Personalized implementations of CDS tools based on local need should be considered.