Prospective, multi-site study of patient outcomes after implementation of the TREWS machine learning-based early warning system for sepsis.

Early recognition and treatment of sepsis are linked to improved patient outcomes. Machine learning-based early warning systems may reduce the time to recognition, but few systems have undergone clinical evaluation. In this prospective, multi-site cohort study, we examined the association between patient outcomes and provider interaction with a deployed sepsis alert system called the Targeted Real-time Early Warning System (TREWS). During the study, 590,736 patients were monitored by TREWS across five hospitals. We focused our analysis on 6,877 patients with sepsis who were identified by the alert before initiation of antibiotic therapy. Adjusting for patient presentation and severity, patients in this group whose alert was confirmed by a provider within 3 h of the alert had a reduced in-hospital mortality rate (3.3%, confidence interval (CI) 1.7, 5.1%, adjusted absolute reduction, and 18.7%, CI 9.4, 27.0%, adjusted relative reduction), organ failure and length of stay compared with patients whose alert was not confirmed by a provider within 3 h. Improvements in mortality rate (4.5%, CI 0.8, 8.3%, adjusted absolute reduction) and organ failure were larger among those patients who were additionally flagged as high risk. Our findings indicate that early warning systems have the potential to identify sepsis patients early and improve patient outcomes and that sepsis patients who would benefit the most from early treatment can be identified and prioritized at the time of the alert.

Comparison of Automated Activity Recognition to Provider Observations of Patient Mobility in the ICU.

OBJECTIVES: To compare noninvasive mobility sensor patient motion signature to direct observations by physicians and nurses. DESIGN: Prospective, observational study. SETTING: Academic hospital surgical ICU. PATIENTS AND MEASUREMENTS: A total of 2,426 1-minute clips from six ICU patients (development dataset) and 4,824 1-minute clips from five patients (test dataset). INTERVENTIONS: None. MAIN RESULTS: Noninvasive mobility sensor achieved a minute-level accuracy of 94.2% (2,138/2,272) and an hour-level accuracy of 81.4% (70/86). CONCLUSIONS: The automated noninvasive mobility sensor system represents a significant departure from current manual measurement and reporting used in clinical care, lowering the burden of measurement and documentation on caregivers.

A quality improvement project to reduce door-to-electrocardiogram time: A multicenter study.

OBJECTIVE: To improve compliance with a target door-to-electrocardiogram (EKG) time of 10 minutes or less in patients presenting with symptoms concerning for acute coronary syndrome. METHODS: A pre-post study was performed between January 2014 and May 2016 at five emergency departments (EDs) in Saudi Arabia. Patients who presented to ED with symptoms concerning for acute coronary syndrome were included in the study. The primary outcome of interest was whether EKG was completed within 10 minutes after the patient arrival to ED. Quality improvement interventions consisted of human resources adjustments, education, technological improvements, and improved interdepartmental collaboration. Multivariate analysis was used to model the percentage of EKGs that were completed within the targeted time. RESULTS: During the study period, 11,518 patients received EKGs. Prior to the intervention, compliance with a door-to-EKG time of 10 minutes or less was found to be 62.6%. Post intervention, compliance improved to 87.7%. On multivariate analysis, male patients were significantly more likely to receive EKG within 10 minutes than female patients (odds ratio = 1.231, 95% confidence interval = 1.113-1.361; p < 0.001). CONCLUSION: A quality improvement project can successfully increase the percentage of patients receiving EKG within 10 minutes of presentation to ED. Further research is required to demonstrate the clinical significance of improved door-to-EKG times.

Gaps in the Substance Use Disorder Treatment Referral Process: Provider Perceptions.

OBJECTIVES: The demand for substance use disorder treatment is increasing, fueled by the opioid epidemic and the Affordable Care Act mandate to treat substance use disorders. The increased demand for treatment, however, is not being met by a corresponding increase in access to or availability of treatment. This report focuses specifically on the treatment referral process, which we have identified as 1 of the key barriers to timely and effective treatment. Difficulties in referral to substance use disorder treatment are examined through the lens of providers who make referrals (ie, referral source) and individuals who work in substance use disorder facilities (ie, referral recipient). METHODS: Administrative officials, emergency department physicians, addiction physicians, government officials, providers, insurance officials, and mental health advocates (n = 59) were interviewed on the referral process protocol, challenges for providers and others making referrals, and issues with substance use treatment facility intake procedures. RESULTS: Several main themes were identified as barriers in the process: difficulties in determining patient eligibility, lack of transparency regarding treatment capacity, referral source knowledge/understanding of options, and issues with communication between referral source and recipient. We then proposed several solutions to address specific barriers. CONCLUSIONS: Current gaps in the referral process cause delays to care. Improving systems would involve addressing these themes and expanding the use of appropriate treatments for the many patients in need.

Two-State Collaborative Study of a Multifaceted Intervention to Decrease Ventilator-Associated Events.

OBJECTIVES: Ventilator-associated events are associated with increased mortality, prolonged mechanical ventilation, and longer ICU stay. Given strong national interest in improving ventilated patient care, the National Institute of Health and Agency for Healthcare Research and Quality funded a two-state collaborative to reduce ventilator-associated events. We describe the collaborative's impact on ventilator-associated event rates in 56 ICUs. DESIGN: Longitudinal quasi-experimental study. SETTING: Fifty-six ICUs at 38 hospitals in Maryland and Pennsylvania from October 2012 to March 2015. INTERVENTIONS: We organized a multifaceted intervention to improve adherence with evidence-based practices, unit teamwork, and safety culture. Evidence-based interventions promoted by the collaborative included head-of-bed elevation, use of subglottic secretion drainage endotracheal tubes, oral care, chlorhexidine mouth care, and daily spontaneous awakening and breathing trials. Each unit established a multidisciplinary quality improvement team. We coached teams to establish comprehensive unit-based safety programs through monthly teleconferences. Data were collected on rounds using a common tool and entered into a Web-based portal. MEASUREMENTS AND RESULTS: ICUs reported 69,417 ventilated patient-days of intervention compliance observations and 1,022 unit-months of ventilator-associated event data. Compliance with all evidence-based interventions improved over the course of the collaborative. The quarterly mean ventilator-associated event rate significantly decreased from 7.34 to 4.58 cases per 1,000 ventilator-days after 24 months of implementation (p = 0.007). During the same time period, infection-related ventilator-associated complication and possible and probable ventilator-associated pneumonia rates decreased from 3.15 to 1.56 and 1.41 to 0.31 cases per 1,000 ventilator-days (p = 0.018, p = 0.012), respectively. CONCLUSIONS: A multifaceted intervention was associated with improved compliance with evidence-based interventions and decreases in ventilator-associated event, infection-related ventilator-associated complication, and probable ventilator-associated pneumonia. Our study is the largest to date affirming that best practices can prevent ventilator-associated events.

Measuring Patient Mobility in the ICU Using a Novel Noninvasive Sensor.

OBJECTIVES: To develop and validate a noninvasive mobility sensor to automatically and continuously detect and measure patient mobility in the ICU. DESIGN: Prospective, observational study. SETTING: Surgical ICU at an academic hospital. PATIENTS: Three hundred sixty-two hours of sensor color and depth image data were recorded and curated into 109 segments, each containing 1,000 images, from eight patients. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: Three Microsoft Kinect sensors (Microsoft, Beijing, China) were deployed in one ICU room to collect continuous patient mobility data. We developed software that automatically analyzes the sensor data to measure mobility and assign the highest level within a time period. To characterize the highest mobility level, a validated 11-point mobility scale was collapsed into four categories: nothing in bed, in-bed activity, out-of-bed activity, and walking. Of the 109 sensor segments, the noninvasive mobility sensor was developed using 26 of these from three ICU patients and validated on 83 remaining segments from five different patients. Three physicians annotated each segment for the highest mobility level. The weighted Kappa (κ) statistic for agreement between automated noninvasive mobility sensor output versus manual physician annotation was 0.86 (95% CI, 0.72-1.00). Disagreement primarily occurred in the "nothing in bed" versus "in-bed activity" categories because "the sensor assessed movement continuously," which was significantly more sensitive to motion than physician annotations using a discrete manual scale. CONCLUSIONS: Noninvasive mobility sensor is a novel and feasible method for automating evaluation of ICU patient mobility.

A systematic approach for developing a ventilator-associated pneumonia prevention bundle.

BACKGROUND: Ventilator-associated pneumonia (VAP) is among the most common type of health care-associated infection in the intensive care unit and is associated with significant morbidity and mortality. Existing VAP prevention intervention bundles vary widely on the interventions included and in the approaches used to develop these bundles. The objective of this study was to develop a new VAP prevention bundle using a systematic approach that elicits clinician perceptions on which interventions are most important and feasible to implement. METHODS: We identified potential interventions to include through a review of current guidelines and literature. We implemented a 2-step modified Delphi method to gain consensus on the final list of interventions. An interdisciplinary group of clinical experts participated in the Delphi process, which was guided by a technical expert panel. RESULTS: We identified 65 possible interventions. Through the Delphi method, we narrowed that list to 19 interventions that included 5 process and 14 structural measures. CONCLUSIONS: We described a structured approach for developing a new VAP prevention bundle. Obtaining clinician input on what interventions to include increases the likelihood that providers will adhere to the bundle.

Process Monitoring in the Intensive Care Unit: Assessing Patient Mobility Through Activity Analysis with a Non-Invasive Mobility Sensor.

Throughout a patient's stay in the Intensive Care Unit (ICU), accurate measurement of patient mobility, as part of routine care, is helpful in understanding the harmful effects of bedrest [1]. However, mobility is typically measured through observation by a trained and dedicated observer, which is extremely limiting. In this work, we present a video-based automated mobility measurement system called NIMS: Non-Invasive Mobility Sensor . Our main contributions are: (1) a novel multi-person tracking methodology designed for complex environments with occlusion and pose variations, and (2) an application of human-activity attributes in a clinical setting. We demonstrate NIMS on data collected from an active patient room in an adult ICU and show a high inter-rater reliability using a weighted Kappa statistic of 0.86 for automatic prediction of the highest level of patient mobility as compared to clinical experts.

An official American Thoracic Society/American Association of Critical-Care Nurses/American College of Chest Physicians/Society of Critical Care Medicine policy statement: the Choosing Wisely® Top 5 list in Critical Care Medicine.

RATIONALE: The high costs of health care in the United States and other developed nations are attributable, in part, to overuse of tests, treatments, and procedures that provide little to no benefit for patients. To improve the quality of care while also combating this problem of cost, the American Board of Internal Medicine Foundation developed the Choosing Wisely Campaign, tasking professional societies to develop lists of the top five medical services that patients and physicians should question. OBJECTIVES: To present the Critical Care Societies Collaborative's Top 5 list in Critical Care Medicine and describe its development. METHODS: Each professional society in the Collaborative nominated members to the Choosing Wisely task force, which established explicit criteria for evaluating candidate items, generated lists of items, performed literature reviews on each, and sought external input from content experts. Task force members narrowed the list to the Top 5 items using a standardized scoring system based on each item's likely overall impact and merits on the five explicit criteria. MEASUREMENTS AND MAIN RESULTS: From an initial list of 58 unique recommendations, the task force proposed a Top 5 list that was ultimately endorsed by each Society within the Collaborative. The five recommendations are: (1) do not order diagnostic tests at regular intervals (such as every day), but rather in response to specific clinical questions; (2) do not transfuse red blood cells in hemodynamically stable, nonbleeding ICU patients with an Hb concentration greater than 7 g/dl; (3) do not use parenteral nutrition in adequately nourished critically ill patients within the first 7 days of an ICU stay; (4) do not deeply sedate mechanically ventilated patients without a specific indication and without daily attempts to lighten sedation; and (5) do not continue life support for patients at high risk for death or severely impaired functional recovery without offering patients and their families the alternative of care focused entirely on comfort. CONCLUSIONS: These five recommendations provide a starting point for clinicians and patients to make decisions leading to higher-quality, lower-cost care. Future work is needed to promote adherence to these recommendations and to develop additional ways for intensive care clinicians to take leadership in reining in health-care costs.

An evaluation of ventilator-associated pneumonia process measure sampling strategies in a surgical ICU.

Ventilator-associated pneumonia (VAP) is common, lethal, and expensive. Little is known about optimal strategies to evaluate process measures for VAP prevention. The authors conducted a prospective study of different sampling strategies for evaluating head of bed (HOB) elevation and oral care. There was no significant difference between morning and evening shift HOB elevation compliance rates (P = .47). If oral care was performed at least once during a 12-hour shift, there was an 87% probability that it also was performed at least twice. If oral care was performed at least twice during a 12-hour shift, then there was a 93% probability that chlorhexidine oral care was performed at least once. The results of this study suggest that sampling HOB elevation twice as compared with once daily is unlikely to change the estimate of performance, oral care need not be frequently sampled, and high oral care compliance may predict chlorhexidine oral care compliance.

National study on the distribution, causes, and consequences of voluntarily reported medication errors between the ICU and non-ICU settings.

OBJECTIVE: To compare the distribution, causes, and consequences of medication errors in the ICU with those in non-ICU settings. DESIGN: : A cross-sectional study of all hospital ICU and non-ICU medication errors reported to the MEDMARX system between 1999 and 2005. Adjusted odds ratios are presented. SETTING: Hospitals participating in the MEDMARX reporting system. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: MEDMARX is an anonymous, self-reported, confidential, deidentified, internet-accessible medication error reporting program that allows hospitals to report, track, and share medication error data. There were 839,553 errors reported from 537 hospitals. ICUs accounted for 55,767 (6.6%) errors, of which 2,045 (3.7%) were considered harmful. Non-ICUs accounted for 783,800 (93.4%) errors, of which 14,471 (1.9%) were harmful. Errors most often originated in the administration phase (ICU 44% vs. non-ICU 33%; odds ratio 1.63 [1.43-1.86]). The most common error type was omission (ICU 26% vs. non-ICU 28%; odds ratio 1.00 [0.91-1.10]). Among harmful errors, dispensing devices (ICU 14% vs. non-ICU 7.1%; odds ratio 2.09 [1.69-2.59]) and calculation mistakes (ICU 9.8% vs. non-ICU 5.3%; odds ratio 1.82 [1.48-2.24]) were more commonly identified to be the cause in the ICU compared to the non-ICU setting. ICU errors were more likely to be associated with any harm (odds ratio 1.89 [1.62-2.17]), permanent harm (odds ratio 2.45 [1.17-5.13]), harm requiring life-sustaining intervention (odds ratio 2.91 [1.86-4.56]), or death (odds ratio 2.48 [1.18-5.19]). When an error did occur, patients and their caregivers were rarely informed (ICU 1.5% vs. non-ICU 2.1%; odds ratio 0.63 [0.48-0.84]) by the time of reporting. CONCLUSIONS: More harmful errors are reported in ICU than non-ICU settings. Medication errors occur frequently in the administration phase in the ICU. When errors occur, patients and their caregivers are rarely informed. Consideration should be given to developing additional safeguards against ICU errors, particularly during drug administration, and eliminating barriers to error disclosures.

The correlation between aerobic fitness and motion sickness susceptibility.

Susceptibility to motion sickness has been linked to aerobic fitness in several studies, however, these studies have not elucidated the underlying physiological mechanism by which increased aerobic fitness is related to a decreased ability to tolerate motion sickness stimuli. This pilot study provides further evidence of a relationship between aerobic fitness and motion sickness susceptibility. It also suggests that aerobic capacity is more specifically linked to signs and symptoms of vasomotor origin including stomach discomfort, nausea and/or vomiting, headache, and diaphoresis. By independently correlating vasomotor susceptibility and neurogenic susceptibility to maximum oxygen uptake, we find that vasomotor symptoms in particular are significantly increased in aerobically fit individuals. Larger studies should be conducted to confirm this relationship.