An Interdepartmental Care Model to Expedite Admission from the Emergency Department to the Medical ICU

Development of a machine learning-based clinical decision support system to predict clinical deterioration in patients visiting the emergency department

This study aimed to develop a machine learning-based clinical decision support system for emergency departments based on the decision-making framework of physicians. We extracted 27 fixed and 93 observation features using data on vital signs, mental status, laboratory results, and electrocardiograms during emergency department stay. Outcomes included intubation, admission to the intensive care unit, inotrope or vasopressor administration, and in-hospital cardiac arrest. eXtreme gradient boosting algorithm was used to learn and predict each outcome. Specificity, sensitivity, precision, F1 score, area under the receiver operating characteristic curve (AUROC), and area under the precision-recall curve were assessed. We analyzed 303,345 patients with 4,787,121 input data, resampled into 24,148,958 1 h-units. The models displayed a discriminative ability to predict outcomes (AUROC > 0.9), and the model with lagging 6 and leading 0 displayed the highest value. The AUROC curve of in-hospital cardiac arrest had the smallest change, with increased lagging for all outcomes. With inotropic use, intubation, and intensive care unit admission, the range of AUROC curve change with the leading 6 was the highest according to different amounts of previous information (lagging). In this study, a human-centered approach to emulate the clinical decision-making process of emergency physicians has been adopted to enhance the use of the system. Machine learning-based clinical decision support systems customized according to clinical situations can help improve the quality of care.

Implementation of a medical intensive care team in the emergency department of a tertiary medical center in the USA

OBJECTIVE

Critically ill patients boarding in the ED have higher mortality rates. Several strategies have been implemented to deliver care to boarding patients. Our institution opted for a strategy consisting on deploying an Intensive Care team in the ED. This article reports outcomes before-and-after implementation of that team.

METHODS

On November 2020, a Medical Intensive Care Team was deployed in the ED. The team performed consultations for ICU patients boarding in the ED. A retrospective analysis of critically ill patients arriving to the ED before-and-after team implementation was performed. Outcome data were reviewed. Direct hospitalization costs per patient, and direct costs per department were assessed. Wilcoxon rank sum and Chisq-test were utilized to compare differences pre- and post-implementation. Multivariate analyses to model outcomes toward pre- and post-implementation and other variables were performed.

RESULTS

1,828 and 3,272 patients were included in the pre- and post-intervention groups. ICU LOS (days) pre- and post-intervention were 3 (1,6) and 3 (1,6), respectively (p = 0.41). ICU readmission rates were 6.7% pre-intervention and 7.4% post-intervention (p = 0.37). Total direct costs were US$ 19,928 (11,006, 37,815) and US$ 15,795 (9016, 28,993), respectively (p < 0.01). Multivariate analysis showed no association between team deployment and ICU LOS or readmission. However, there was association between its implementation and hospitalization cost reduction per patient of US$ 7,171.

CONCLUSION

The implementation of a Medical Intensive Care team in the ED is not associated with a reduction of ICU LOS or ICU readmission. Nevertheless, its implementation is associated with a reduction of hospitalization costs.

Prediction of hospitalization using artificial intelligence for urgent patients in the emergency department

Timely assessment to accurately prioritize patients is crucial for emergency department (ED) management. Urgent (i.e., level-3, on a 5-level emergency severity index system) patients have become a challenge since under-triage and over-triage often occur. This study was aimed to develop a computational model by artificial intelligence (AI) methodologies to accurately predict urgent patient outcomes using data that are readily available in most ED triage systems. We retrospectively collected data from the ED of a tertiary teaching hospital between January 1, 2015 and December 31, 2019. Eleven variables were used for data analysis and prediction model building, including 1 response, 2 demographic, and 8 clinical variables. A model to predict hospital admission was developed using neural networks and machine learning methodologies. A total of 282,971 samples of urgent (level-3) visits were included in the analysis. Our model achieved a validation area under the curve (AUC) of 0.8004 (95% CI 0.7963–0.8045). The optimal cutoff value identified by Youden's index for determining hospital admission was 0.5517. Using this cutoff value, the sensitivity was 0.6721 (95% CI 0.6624–0.6818), and the specificity was 0.7814 (95% CI 0.7777–0.7851), with a positive predictive value of 0.3660 (95% CI 0.3586–0.3733) and a negative predictive value of 0.9270 (95% CI 0.9244–0.9295). Subgroup analysis revealed that this model performed better in the nontraumatic adult subgroup and achieved a validation AUC of 0.8166 (95% CI 0.8199–0.8212). Our AI model accurately assessed the need for hospitalization for urgent patients, which constituted nearly 70% of ED visits. This model demonstrates the potential for streamlining ED operations using a very limited number of variables that are readily available in most ED triage systems. Subgroup analysis is an important topic for future investigation.

Challenges and potential improvements in hospital patient flow: the contribution of frontline, top and middle management professionals

PURPOSE

This study aims to describe and understand the contributions of frontline, middle and top management healthcare professionals in detecting areas of potential improvement in hospital patient flow and proposing solutions.

DESIGN/METHODOLOGY/APPROACH

This is a qualitative interview study. Semistructured interviews were conducted with 22 professionals in the orthopedic department of a 250-bed academic teaching hospital. Data were analyzed through a thematic framework analytical approach by using an a priori framework. The Consolidated Criteria for Reporting Qualitative (COREQ) checklist for qualitative studies was followed.

FINDINGS

When dealing with a hospital-wide process, the involvement of all professionals, including nonhealth professionals, can reveal priority areas for improvement and for services integration. The improvements identified by the professionals largely focus on covering major gaps detected in the technical and administrative quality.

RESEARCH LIMITATIONS/IMPLICATIONS

This study focused on the professional viewpoint and the connections between services and further studies should explore the role of patient involvement. The study design could limit the generalizability of findings.

PRACTICAL IMPLICATIONS

Improving high-quality, efficient hospital patient flow cannot be accomplished without learning the perspective of the healthcare professionals on the process of service delivery.

ORIGINALITY/VALUE

Few qualitative studies explore professionals' perspectives on patient needs in hospital flow management. This study provides insights into what produces value for the patient within a complex process by analyzing the contribution of professionals from their particular role in the organization.

XGBoost Algorithm Prediction of Critical Care Outcome for Adult Patients Presenting to Emergency Department Using Initial Triage Information

Background

The emergency department (ED) triage system to classify and prioritize patients from high risk to less urgent continues to be a challenge.

Objective

This study, comprising 80,433 patients, aims to develop a machine learning algorithm prediction model of critical care outcomes for adult patients using information collected during ED triage and compare the performance with that of the baseline model using the Korean Triage and Acuity Scale (KTAS).

Methods

To predict the need for critical care, we used 13 predictors from triage information: age, gender, mode of ED arrival, the time interval between onset and ED arrival, reason of ED visit, chief complaints, systolic blood pressure, diastolic blood pressure, pulse rate, respiratory rate, body temperature, oxygen saturation, and level of consciousness. The baseline model with KTAS was developed using logistic regression, and the machine learning model with 13 variables was generated using extreme gradient boosting (XGB) and deep neural network (DNN) algorithms. The discrimination was measured by the area under the receiver operating characteristic (AUROC) curve. The ability of calibration with Hosmer–Lemeshow test and reclassification with net reclassification index were evaluated. The calibration plot and partial dependence plot were used in the analysis.

Results

The AUROC of the model with the full set of variables (0.833-0.861) was better than that of the baseline model (0.796). The XGB model of AUROC 0.861 (95% CI 0.848-0.874) showed a higher discriminative performance than the DNN model of 0.833 (95% CI 0.819-0.848). The XGB and DNN models proved better reclassification than the baseline model with a positive net reclassification index. The XGB models were well-calibrated (Hosmer-Lemeshow test; P>.05); however, the DNN showed poor calibration power (Hosmer-Lemeshow test; P<.001). We further interpreted the nonlinear association between variables and critical care prediction.

Conclusions

Our study demonstrated that the performance of the XGB model using initial information at ED triage for predicting patients in need of critical care outperformed the conventional model with KTAS.

Boarding of critically Ill patients in the emergency department

OBJECTIVES

Emergency department boarding is the practice of caring for admitted patients in the emergency department after hospital admission, and boarding has been a growing problem in the United States. Boarding of the critically ill has achieved specific attention because of its association with poor clinical outcomes. Accordingly, the Society of Critical Care Medicine and the American College of Emergency Physicians convened a Task Force to understand the implications of emergency department boarding of the critically ill. The objective of this article is to review the U.S. literature on (1) the frequency of emergency department boarding among the critically ill, (2) the outcomes associated with critical care patient boarding, and (3) local strategies developed to mitigate the impact of emergency department critical care boarding on patient outcomes.

DATA SOURCES AND STUDY SELECTION

Review article.

DATA EXTRACTION AND DATA SYNTHESIS

Emergency department-based boarding of the critically ill patient is common, but no nationally representative frequency estimates has been reported. Boarding literature is limited by variation in the definitions used for boarding and variation in the facilities studied (boarding ranges from 2% to 88% of ICU admissions). Prolonged boarding in the emergency department has been associated with longer duration of mechanical ventilation, longer ICU and hospital length of stay, and higher mortality. Health systems have developed multiple mitigation strategies to address emergency department boarding of critically ill patients, including emergency department-based interventions, hospital-based interventions, and emergency department-based resuscitation care units.

CONCLUSIONS

Emergency department boarding of critically ill patients was common and was associated with worse clinical outcomes. Health systems have generated a number of strategies to mitigate these effects. A definition for emergency department boarding is proposed. Future work should establish formal criteria for analysis and benchmarking of emergency department-based boarding overall, with subsequent efforts focused on developing and reporting innovative strategies that improve clinical outcomes of critically ill patients boarded in the emergency department.

Nurse Practitioners and Physician Assistants in Acute and Critical Care: A Concise Review of the Literature and Data 2008-2018

OBJECTIVES

To provide a concise review of the literature and data pertaining to the use of nurse practitioners and physician assistants, collectively called advanced practice providers, in ICU and acute care settings.

DATA SOURCES

Detailed search strategy using the databases PubMed, Ovid MEDLINE, and the Cumulative Index of Nursing and Allied Health Literature for the time period from January 2008 to December 2018.

STUDY SELECTION

Studies addressing nurse practitioner, physician assistant, or advanced practice provider care in the ICU or acute care setting.

DATA EXTRACTION

Relevant studies were reviewed, and the following aspects of each study were identified, abstracted, and analyzed: study population, study design, study aims, methods, results, and relevant implications for critical care practice.

DATA SYNTHESIS

Five systematic reviews, four literature reviews, and 44 individual studies were identified, reviewed, and critiqued. Of the research studies, the majority were retrospective with others being observational, quasi-experimental, or quality improvement, along with two randomized control trials. Overall, the studies assessed a variety of effects of advanced practice provider care, including on length of stay, mortality, and quality-related metrics, with a majority demonstrating similar or improved patient care outcomes.

CONCLUSIONS

Over the past 10 years, the number of studies assessing the impact of advanced practice providers in acute and critical care settings continue to increase. Collectively, these studies identify the value of advanced practice providers in patient care management, continuity of care, improved quality and safety metrics, patient and staff satisfaction, and on new areas of focus including enhanced educational experience of residents and fellows.

Moving patients from emergency department to medical intensive care unit: Tracing barriers and root contributors

BACKGROUND

Patient transfers involve the physical movement of patients, along with the transfer of their care-related information, responsibility, and control between sending and receiving clinicians. Patient transfers between critical care units are complex and vulnerable to bottlenecks.

OBJECTIVE

To examine the patient transfer process from emergency department (ED) to medical intensive care unit (MICU).

MATERIALS AND METHOD

A qualitative study on transfers from ED to MICU was conducted at two academic hospitals. Using a process-based methodological approach supported by shadowing of patient transfers and clinician interviews, we examined the process-based similarities and differences in barriers and strategies used across hospitals.

RESULTS

Phases underlying ED-MICU transfer process included: pre-transfer phase involving ED care coordination and MICU transfer decision-making; transfer phase involving ED-MICU resident handoff, and post-transfer phase involving MICU care planning and management.

DISCUSSION AND CONCLUSION

Transfer of information, responsibility and control between sending and receiving clinicians is key to effective management of interdependencies between the pre-transfer, transfer and post-transfer phases underlying the patient transfer process. Evidence-based strategies to address challenges related to transfer of information, responsibility and control include the use of videophones and communication checklists, the allocation of a crash bed, engagement of sending, receiving and consulting teams in the physical movement of patients, and in-hospital transfer protocols.

Effectiveness of collaboration between emergency department and intensive care unit teams on mortality rates of patients presenting with critical illness: a quantitative systematic review protocol

REVIEW OBJECTIVE

The objective of this review is to identify the effectiveness of collaboration between emergency department (ED) and intensive care unit teams on mortality rates of critically ill adult patients in the ED.

Emergency Department Length of Stay for Critical Care Admissions. A Population-based Study

RATIONALE

Hospital emergency department (ED) strain is common in North America. Excessive strain may result in prolonged ED length of stay and may lead to worse outcomes for patients admitted to intensive care units (ICUs).

OBJECTIVES

To describe patient, ED, and hospital characteristics associated with prolonged ED length of stay for adult patients admitted from EDs to ICUs.

METHODS

We conducted a population-based cohort study in the Province of Ontario, Canada, including patients admitted to an adult ICU from an ED and excluding only interhospital transfers and scheduled visits. Using regression modeling, we examined associations between patient- and hospital-level characteristics and two ED performance measures: length of stay in the ED of more than 6 hours and 90-day mortality.

MEASUREMENTS AND MAIN RESULTS

From April 2007 to March 2012, 261,274 adults presented to 118 EDs in Ontario, generating 314,836 ICU admissions. This activity represented 4.1% of all adult ED visits (incidence, 1,374 ICU admissions/100,000 ED visits). Median (interquartile range) ED length of stay was 7 (4-13) hours. Less than half (41.4%; 95% confidence interval [CI], 41.2-41.5) of these patients had an ED length of stay of 6 hours or less, whereas 10.5% (95% CI, 10.4-10.6) stayed 24 hours or longer. Hospital characteristics associated with ED length of stay more than 6 hours included shift-level ED crowding (mean length of stay of patients of similar acuity registering during same 8 h epoch) (odds ratio [OR], 1.19/h; 95% CI, 1.19-1.19), ED annual visit volume (OR, 1.01/1,000 patients; 95% CI, 1.01-1.01), time of ED presentation (00:00-07:59) (OR, 1.41; 95% CI, 1.38-1.45), and ICU functioning at greater than 20% above the average annual census (OR, 1.10; 95% CI, 1.08-1.12). ED length of stay more than 6 hours was not associated with 90-day mortality after adjustment for selected confounders (OR, 0.99; 95% CI, 0.97-1.02).

CONCLUSIONS

In this population-based study, less than half of adult ED patients were admitted to an ICU 6 hours or less after arrival to an ED, an internationally recognized performance indicator for ED care quality. ED and ICU strain generated by time-varying demand on capacity was an important determinant of ED length of stay. However, prolonged length of stay in an ED did not measurably reduce 90-day mortality.

Frequency of and factors associated with emergency department intracranial pressure monitor placement in severe paediatric traumatic brain injury

OBJECTIVE

To examine the frequency of and factors associated with emergency department (ED) intracranial pressure (ICP) monitor placement in severe paediatric traumatic brain injury (TBI).

METHODS

Retrospective, multicentre cohort study of children <18 years admitted to the ED with severe TBI and intubated for >48 hours from 2007 to 2011.

RESULTS

Two hundred and twenty-four children had severe TBI and 75% underwent either ED, operating room (OR) or paediatric intensive care unit (PICU) ICP monitor placement. Four out of five centres placed ICP monitors in the ED, mostly (83%) fibreoptic. Nearly 40% of the patients who received ICP monitors get it placed in the ED (29% overall). Factors associated with ED ICP monitor placement were as follows: age 13 to <18 year olds compared to infants (aRR 2.02; 95% CI 1.37, 2.98), longer ED length of stay (LOS) (aRR 1.15; 95% CI 1.08, 1.21), trauma centre designation paediatric only I/II compared to adult/paediatric I/II (aRR 1.71; 95% CI 1.48, 1.98) and higher mean paediatric TBI patient volume (aRR 1.88;95% CI 1.68, 2.11). Adjusted for centre, higher bedside ED staff was associated with longer ED LOS (aRR 2.10; 95% CI 1.06, 4.14).

CONCLUSION

ICP monitors are frequently placed in the ED at paediatric trauma centres caring for children with severe TBI. Both patient and organizational level factors are associated with ED ICP monitor placement.