Abnormal vital signs are strong predictors for intensive care unit admission and in-hospital mortality in adults triaged in the emergency department - a prospective cohort study

Patient mortality and the neglect of vital signs' assessment: An audit of a national coronial database

BACKGROUND

Vital signs assessment is critical for patient surveillance and safety. Research has found, however, that this assessment is often neglected in clinical practice. The reasons for this are unclear as few studies have explored this issue. Those studies that have are small, single site studies and found that culture and poor understanding are contributing factors.

AIM

The aim was to explore the link between the clinical neglect of vital signs assessment and patient mortality and provide a better understanding of factors influencing vital signs assessment in the context of acute patient care. Coroners' reports represent an untapped source of information regarding shortfalls in vital signs assessment. Using a framework analysis, an audit was conducted of the Australian National Coronial Information System for cases where vital signs' assessment was mentioned in coronial reports.

RESULTS

Fifty-eight cases met the eligibility criteria, with deceased patients aged from 7 days to 93 years. Key themes related to absence of reassessment of vital signs, inappropriate delegation, passing responsibility to another staff member and not following policy.

CONCLUSIONS

The findings reflect a combination of individual and institutional failings and suggest that vital signs assessment was not considered a priority aspect of care.

RELEVANCE TO CLINICAL PRACTICE

Vital signs assessment must be considered an essential aspect of clinical care in all patients. This important aspect of care should be emphasized across all domains of patient care.

Predictability of adult patient medical emergency condition from triage vital signs and comorbidities: a single-center, observational study

BACKGROUND

Vital signs and comorbid diseases are the first information evaluated in patients admitted to the emergency department (ED). In most EDs, triage of patients takes place with vital signs and admission complaints only. Comorbidities are generally underestimated when determining the patient's status at the triage area. This study aims to assess the relationship between initial vital signs, comorbid diseases, and medical emergency conditions (MEC) in patients admitted to the ED.

METHODS

This prospective study was designed as a single-center observational study, including patients admitted to a tertiary ED between 16.06.2022 and 09.09.2022. Patients younger than 18, readmitted to the ED within 24 h, or absence of vital signs due to cardiac arrest were excluded from the study. Vital signs and comorbid diseases of all patients were recorded. The mortality within 24 h, the need for intensive care unit admission, emergency surgery, and life-saving procedures were considered "medical emergency conditions". The role of vital signs and comorbid diseases in predicting emergencies was analyzed by binary logistic regression.

RESULTS

A total of 10,022 patients were included in the study; 5056 (50.4%) were female, and 4966 (49.6%) were male. Six hundred four patients presented with an MEC. All vital signs -except diastolic hypertension and tachycardia- and comorbidities were found statistically significant. Hypoxia (Odd's Ratio [OR]: 1.73), diastolic hypotension (OR: 3.71), tachypnea (OR: 8.09), and tachycardia (OR: 1.61) were associated with MECs. Hemiplegia (OR: 5.7), leukemia (OR: 4.23), and moderate-severe liver disease (OR: 2.99) were the most associated comorbidities with MECs. In our study, an MEC was detected in 3.6% (186 patients) of the patients with no abnormal vital signs and without any comorbidities.

CONCLUSION

Among the vital signs, hypoxia, diastolic hypotension, tachypnea, and tachycardia should be considered indicators of an MEC. Hemiplegia, leukemia, and moderate-severe liver disease are the most relevant comorbidities that may accompany the MECs.

Predicting severe outcomes in pediatric trauma patients: Shock index pediatric age-adjusted vs. age-adjusted tachycardia

INTRODUCTION

When an injured patient arrives in the Emergency Department (ED), timely and appropriate care is crucial. Shock Index Pediatric Age-Adjusted (SIPA) has been shown to accurately identify pediatric patients in need of emergency interventions. However, no study has evaluated SIPA against age-adjusted tachycardia (AT). This study aims to compare SIPA with AT in predicting outcomes such as mortality, severe injury, and the need for emergent intervention in pediatric trauma patients.

MATERIAL AND METHODS

This is a retrospective cross-sectional analysis of patient data abstracted from the Trauma Quality Improvement Program Participant Use Files (TQIP PUFs) for years 2013-2020. Patients aged 4-16 with blunt mechanism of injury and injury severity score (ISS) > 15 were included. 36,517 children met this criteria. Sensitivity, specificity, overtriage, and undertriage rates were calculated to compare the effectiveness of AT and elevated SIPA as predictors of severe injuries and need for emergent intervention. Emergent interventions included craniotomy, endotracheal intubation, thoracotomy, laparotomy, or chest tube placement within 24 h of arrival.

RESULTS

AT classified 59% of patients as "high risk," while elevated SIPA identified 26%. Compared to AT patients, a greater proportion of patients with elevated SIPA required a blood transfusion within 24 h (22% vs. 12%, respectively; p < 0.001). In-hospital mortality was higher for the elevated SIPA group than AT (10% vs. 5%, respectively; p < 0.001) as well as the need for emergent operative interventions (43% vs. 32% respectively; p < 0.001). Grade 3 or higher liver/spleen lacerations requiring blood transfusion were also more common among elevated SIPA patients than AT patients (8% vs. 4%, respectively; p < 0.001). AT demonstrated greater sensitivity but lower specificity compared to SIPA across all outcomes. AT showed improved overtriage and undertriage rates compared to SIPA, but this is attributed to identifying a large proportion of the sample as "high risk."

CONCLUSIONS

AT outperforms SIPA in sensitivity for mortality, injury severity and emergent interventions in pediatric trauma patients while the specificity of SIPA is high across these outcomes.

Risk factors predicting the need for intensive care unit admission within forty-eight hours of emergency department presentation: A case-control study

BACKGROUND

Patients admitted from the emergency department to the wards, who progress to a critically unwell state, may require expeditious admission to the intensive care unit. It can be argued that earlier recognition of such patients, to facilitate prompt transfer to intensive care, could be linked to more favourable clinical outcomes. Nevertheless, this can be clinically challenging, and there are currently no established evidence-based methods for predicting the need for intensive care in the future.

OBJECTIVES

We aimed to analyse the emergency department data to describe the characteristics of patients who required an intensive care admission within 48 h of presentation. Secondly, we planned to test the feasibility of using this data to identify the associated risk factors for developing a predictive model.

METHODS

We designed a retrospective case-control study. Cases were patients admitted to intensive care within 48 h of their emergency department presentation. Controls were patients who did not need an intensive care admission. Groups were matched based on age, gender, admission calendar month, and diagnosis. To identify the associated variables, we used a conditional logistic regression model.

RESULTS

Compared to controls, cases were more likely to be obese, and smokers and had a higher prevalence of cardiovascular (39 [35.1%] vs 20 [18%], p = 0.004) and respiratory diagnoses (45 [40.5%] vs 25 [22.5%], p = 0.004). They received more medical emergency team reviews (53 [47.8%] vs 24 [21.6%], p < 0.001), and more patients had an acute resuscitation plan (31 [27.9%] vs 15 [13.5%], p = 0.008). The predictive model showed that having acute resuscitation plans, cardiovascular and respiratory diagnoses, and receiving medical emergency team reviews were strongly associated with having an intensive care admission within 48 h of presentation.

CONCLUSIONS

Our study used emergency department data to provide a detailed description of patients who had an intensive care unit admission within 48 h of their presentation. It demonstrated the feasibility of using such data to identify the associated risk factors to develop a predictive model.

An Inertial-Based Wearable System for Monitoring Vital Signs during Sleep

This study explores the feasibility of a wearable system to monitor vital signs during sleep. The system incorporates five inertial measurement units (IMUs) located on the waist, the arms, and the legs. To evaluate the performance of a novel framework, twenty-three participants underwent a sleep study, and vital signs, including respiratory rate (RR) and heart rate (HR), were monitored via polysomnography (PSG). The dataset comprises individuals with varying severity of sleep-disordered breathing (SDB). Using a single IMU sensor positioned at the waist, strong correlations of more than 0.95 with the PSG-derived vital signs were obtained. Low inter-participant mean absolute errors of about 0.66 breaths/min and 1.32 beats/min were achieved, for RR and HR, respectively. The percentage of data available for analysis, representing the time coverage, was 98.3% for RR estimation and 78.3% for HR estimation. Nevertheless, the fusion of data from IMUs positioned at the arms and legs enhanced the inter-participant time coverage of HR estimation by over 15%. These findings imply that the proposed methodology can be used for vital sign monitoring during sleep, paving the way for a comprehensive understanding of sleep quality in individuals with SDB.

Drinking from the Holy Grail-Does a Perfect Triage System Exist? And Where to Look for It?

The Emergency Department (ED) is a facility meant to treat patients in need of medical assistance. The choice of triage system hugely impactsed the organization of any given ED and it is important to analyze them for their effectiveness. The goal of this review is to briefly describe selected triage systems in an attempt to find the perfect one. Papers published in PubMed from 1990 to 2022 were reviewed. The following terms were used for comparison: "ED" and "triage system". The papers contained data on the design and function of the triage system, its validation, and its performance. After studies comparing the distinct means of patient selection were reviewed, they were meant to be classified as either flawed or non-ideal. The validity of all the comparable segregation systems was similar. A possible solution would be to search for a new, measurable parameter for a more accurate risk estimation, which could be a game changer in terms of triage assessment. The dynamic development of artificial intelligence (AI) technologies has recently been observed. The authors of this study believe that the future segregation system should be a combination of the experience and intuition of trained healthcare professionals and modern technology (artificial intelligence).

Utility of non-invasive monitoring of exhaled carbon dioxide and perfusion index in adult patients in the emergency department

BACKGROUND

Several noninvasive solutions are available for the assessment of patients at risk of deterioration. Capnography, in the form of end-tidal exhaled CO2 (ETCO2) and perfusion index (PI), could provide relevant information about patient prognosis. The aim of the present project was to determine the association of ETCO2 and PI with mortality of patients admitted to the emergency department (ED).

METHODS

Multicenter, prospective, cohort study of adult patients with acute disease who needed continuous monitoring in the ED. The study included two tertiary hospitals in Spain between October 2022 and June 2023. The primary outcome of the study was in-hospital mortality (all-cause). Demographics, vital signs, ETCO2 and PI were collected.

RESULTS

A total of 687 patients were included in the study. The in-hospital mortality rate was 6.8%. The median age was 79 years (IQR: 69-86), and 63.3% were males. The median ETCO2 value was 30 mmHg (26-35) in survivors and 23 mmHg (16-30) in nonsurvivors (p = 0.001). For the PI, the medians were 4.7% (2.8-8.1) for survivors and 2.5% (0.98-4-4) for nonsurvivors (p < 0.001). The model that presented the best AUC was age (odds ratio (OR): 1.02 (1.00-1.05)), the respiratory rate (OR: 1.06 (1.02-1.11)), and the PI (OR: 0.83 (0.75-0.91)), with a result of 0.840 (95% CI: 0.795-0.886); the model with the respiratory rate (OR: 1.05 (1.01-1.10)), the PI (OR: 0.84 (0.76-0.93)), and the ETCO2 (no statistically significant OR), with an AUC of 0.838 (95% CI: 0.787-0.889).

CONCLUSIONS

The present study showed that the PI and respiratory rate are independently associated with in-hospital mortality. Both the PI and ETCO2 are predictive parameters with improved prognostic performance compared with that of standard vital signs.

Time to death and its predictors among adult patients on mechanical ventilation admitted to intensive care units in West Amhara comprehensive specialized hospitals, Ethiopia: a retrospective follow-up study

INTRODUCTION

Mechanical ventilation is the most common intervention for patients with respiratory failure in the intensive care unit. There is limited data from African countries, including Ethiopia on time to death and its predictors among patients on mechanical ventilators. Therefore, this study aimed to assess time to death and its predictors among adult patients on mechanical ventilation admitted in comprehensive specialized hospitals in West Amhara, Ethiopia.

METHODS

An institutional-based retrospective follow-up study was conducted from January 1, 2020, to December 31, 2022. A simple random sampling was used to select a total of 391 patients' charts. Data were collected using data the extraction tool, entered into Epi-data version 4.6.0, and exported to STATA version 14 for analysis. Kaplan-Meier failure curve and the log-rank test were fitted to explore the survival difference among groups. The Cox regression model was fitted, and variables with a p-value < 0.25 in the bivariable Cox regression were candidates for the multivariable analysis. In the multivariable Cox proportional hazard regression, an adjusted hazard ratio with 95% confidence intervals were reported to declare the strength of association between mortality and predictors when a p value is < 0.05.

RESULTS

A total of 391 mechanically ventilated patients were followed for 4098 days at risk. The overall mortality of patients on mechanical ventilation admitted to the intensive care units was 62.2%, with a median time to death of 16 days (95% CI: 11, 22). Those patients who underwent tracheostomy procedure (AHR = 0.40, 95% CI: 0.20, 0.80), received cardio-pulmonary resuscitation (AHR = 8.78, 95% CI: 5.38, 14.35), being hypotensive (AHR = 2.96, 95% CI: 1.11, 7.87), and had a respiratory rate less than 12 (AHR = 2.74, 95% CI: 1.48, 5.07) were statistically significant predictors of time to death among mechanically ventilated patients.

CONCLUSION

The mortality rate of patients on mechanical ventilation was found to be high and the time to death was short. Being cardiopulmonary resuscitated, hypotensive, and had lower respiratory rate were significant predictors of time to death, whereas patients who underwent tracheostomy was negatively associated with time to death. Tracheostomy is needed for patients who received longer mechanical ventilation, and healthcare providers should give a special attention for patients who are cardiopulmonary resuscitated, hypotensive, and have lower respiratory rate.

Developing a consensus-based definition of out-of-hospital clinical deterioration: A Delphi study

BACKGROUND

Clinical deterioration is a time-critical medical emergency requiring rapid recognition and intervention. Deteriorating patients are seen across various healthcare settings, including the out-of-hospital (OOH) environment. OOH care is an evolving area of medicine where decisions are made regarding priority and timing of clinical interventions, ongoing management, and transport to appropriate care. To date, the literature lacks a standardised definition of OOH clinical deterioration.

OBJECTIVE

The objective of this study was to create a consensus-based definition of OOH clinical deterioration informed by emergency medicine health professionals.

METHODS

A Delphi study consisting three rounds was conducted electronically between June 2020 and January 2021. The expert panel consisted of 30 clinicians, including emergency physicians and paramedics.

RESULTS

A consensus-based definition of OOH clinical deterioration was identified as changes from a patient's baseline physiological status resulting in their condition worsening. These changes primarily take the form of measurable vital signs and assessable symptoms but should be evaluated in conjunction with the history of events and pertinent risk factors. Clinicians should be suspicious that a patient could deteriorate when changes occur in one or more of the following vital signs: respiratory rate, heart rate, blood pressure, Glasgow Coma Scale, oxygen saturation, electrocardiogram, and skin colour. Almost all participants (92%) indicated an early warning system would be helpful to assist timely recognition of deteriorating patients.

CONCLUSION

The creation of a consensus-based definition of OOH clinical deterioration can serve as a starting point for the development and validation of OOH-specific early warning systems. Moreover, a standardised definition allows meaningful comparisons to be made across health services and ensures consistency in future research. This study has shown recognition of OOH clinical deterioration to be a complex issue requiring further research. Improving our understanding of key factors contributing to deterioration can assist timely recognition and intervention, potentially reducing unnecessary morbidity and mortality.

Improved interpretable machine learning emergency department triage tool addressing class imbalance

Objective

The Score for Emergency Risk Prediction (SERP) is a novel mortality risk prediction score which leverages machine learning in supporting triage decisions. In its derivation study, SERP-2d, SERP-7d and SERP-30d demonstrated good predictive performance for 2-day, 7-day and 30-day mortality. However, the dataset used had significant class imbalance. This study aimed to determine if addressing class imbalance can improve SERP's performance, ultimately improving triage accuracy.

Methods

The Singapore General Hospital (SGH) emergency department (ED) dataset was used, which contains 1,833,908 ED records between 2008 and 2020. Records between 2008 and 2017 were randomly split into a training set (80%) and validation set (20%). The 2019 and 2020 records were used as test sets. To address class imbalance, we used random oversampling and random undersampling in the AutoScore-Imbalance framework to develop SERP+-2d, SERP+-7d, and SERP+-30d scores. The performance of SERP+, SERP, and the commonly used triage risk scores was compared.

Results

The developed SERP+ scores had five to six variables. The AUC of SERP+ scores (0.874 to 0.905) was higher than that of the corresponding SERP scores (0.859 to 0.894) on both test sets. This superior performance was statistically significant for SERP+-7d (2019: Z = -5.843, p < 0.001, 2020: Z = -4.548, p < 0.001) and SERP+-30d (2019: Z = -3.063, p = 0.002, 2020: Z = -3.256, p = 0.001). SERP+ outperformed SERP marginally on sensitivity, specificity, balanced accuracy, and positive predictive value measures. Negative predictive value was the same for SERP+ and SERP. Additionally, SERP+ showed better performance compared to the commonly used triage risk scores.

Conclusions

Accounting for class imbalance during training improved score performance for SERP+. Better stratification of even a small number of patients can be meaningful in the context of the ED triage. Our findings reiterate the potential of machine learning-based scores like SERP+ in supporting accurate, data-driven triage decisions at the ED.

Impact of an emergency department rapid response system on inpatient clinical deterioration: A controlled pre-post study

AIM

To determine the impact implementation of Emergency Department Clinical Emergency Response System (EDCERS) on inpatient deterioration events and identify contributing causal factors.

METHODS

EDCERS was implemented in an Australian regional hospital, integrating a single parameter track and trigger criteria for escalation of care, and emergency, specialty and critical care clinician response to patient deterioration. In this controlled pre-post study, electronic medical records of patients who experienced a deterioration event (rapid response call, cardiac arrest or unplanned intensive care admission) on the ward within 72 h of admission from the emergency department (ED) were reviewed. Causal factors contributing to the deteriorating event were assessed using a validated human factors framework.

RESULTS

Implementation of EDCERS reduced the number of inpatient deterioration events within 72 h of emergency admission with failure or delayed response to ED patient deterioration as a causal factor. There was no change in the overall rate of inpatient deterioration events.

CONCLUSION

This study supports wider implementation of rapid response systems in the ED to improve management of deteriorating patients. Tailored implementation strategies should be used to achieve successful and sustainable uptake of ED rapid response systems and improve outcomes in deteriorating patients.

Clinical support system for triage based on federated learning for the Korea triage and acuity scale

Background and aims

This study developed a clinical support system based on federated learning to predict the need for a revised Korea Triage Acuity Scale (KTAS) to facilitate triage.

Methods

This was a retrospective study that used data from 11,952,887 patients in the Korean National Emergency Department Information System (NEDIS) from 2016 to 2018 for model development. Separate cohorts were created based on the emergency medical center level in the NEDIS: regional emergency medical center (REMC), local emergency medical center (LEMC), and local emergency medical institution (LEMI). External and temporal validation used data from emergency department (ED) of the study site from 2019 to 2021. Patient features obtained during the triage process and the initial KTAS scores were used to develop the prediction model. Federated learning was used to rectify the disparity in data quality between EDs. The patient's demographic information, vital signs in triage, mental status, arrival information, and initial KTAS were included in the input feature.

Results

3,626,154 patients' visits were included in the regional emergency medical center cohort; 8,278,081 patients' visits were included in the local emergency medical center cohort; and 48,652 patients' visits were included in the local emergency medical institution cohort. The study site cohort, which is used for external and temporal validation, included 135,780 patients visits. Among the patients in the REMC and study site cohorts, KTAS level 3 patients accounted for the highest proportion at 42.4% and 45.1%, respectively, whereas in the LEMC and LEMI cohorts, KTAS level 4 patients accounted for the highest proportion. The area under the receiver operating characteristic curve for the prediction model was 0.786, 0.750, and 0.770 in the external and temporal validation. Patients with revised KTAS scores had a higher admission rate and ED mortality rate than those with unaltered KTAS scores.

Conclusions

This novel system might accurately predict the likelihood of KTAS acuity revision and support clinician-based triage.

Using the Field Artificial Intelligence Triage (FAIT) tool to predict hospital critical care resource utilization in patients with truncal gunshot wounds

BACKGROUND

Tiered trauma triage systems have resulted in a significant mortality reduction, but models have remained unchanged. The aim of this study was to develop and test an artificial intelligence algorithm to predict critical care resource utilization.

METHODS

We queried the ACS-TQIP 2017-18 database for truncal gunshot wounds(GSW). An information-aware deep neural network (DNN-IAD) model was trained to predict ICU admission and need for mechanical ventilation (MV). Input variables included demographics, comorbidities, vital signs, and external injuries. The model's performance was assessed using the area under receiver operating characteristic curve (AUROC) and the area under the precision-recall curve (AUPRC).

RESULTS

For the ICU admission analysis, we included 39,916 patients. For the MV need analysis, 39,591 patients were included. Median (IQR) age was 27 (22,36). AUROC and AUPRC for predicting ICU need were 84.8 ± 0.5 and 75.4 ± 0.5, and the AUROC and AUPRC for MV need were 86.8 ± 0.5 and 72.5 ± 0.6.

CONCLUSIONS

Our model predicts hospital utilization outcomes in patients with truncal GSW with high accuracy, allowing early resource mobilization and rapid triage decisions in hospitals with capacity issues and austere environments.

Is It Necessary to Wake Patients for Overnight Vital Signs Following Total Joint Arthroplasty?

Benefits of sleep are well-established in postoperative recovery; however, patients undergoing total joint arthroplasty (TJA) often experience poor sleep during hospitalization. While multifactorial, among the major reasons are the frequent and ritualized overnight vital sign checks. In the absence of data in support of or against this practice, we asked whether it remains necessary. We retrospectively analyzed a cohort of 419 primary TJA patients. Demographics, comorbidities, operative, and vital sign data were collected through postoperative Day 3. Correlation between daytime (6:00 a.m. to 10:00 p.m.) and nighttime (10:01 p.m. to 5:59 a.m.) vitals was examined. The vast majority of nighttime vitals fell within normal ranges, including O2 saturation (O2; 99.4%), temperature (TEMP; 97.8%), heart rate (HR; 87.5%), systolic blood pressure (SBP; 85.8%), and diastolic blood pressure (DBP; 84.4%). Predictors of abnormal nighttime vitals included American Society of Anesthesiologists (ASA) score (abnormal SBP; odds ratio [OR] 1.64, p = .045), obesity (abnormal DBP; OR: 0.37, p = .011), and smoking status (elevated temperature; OR: 2.79, p = .042). Estimated blood loss was predictive of an abnormal nighttime TEMP (OR: 1.002; p < .001). Postoperatively, there were several correlations between abnormal daytime and nighttime vitals, including SBP (OR: 6.23, p < .001), DBP (OR: 4.31, p < .001), and HR (OR: 10.35; p < .001). Of the 419 patients, only 9 (2.1%) received any intervention based on abnormal nighttime vitals. Each exhibited daytime vital sign abnormalities prior to the abnormal nighttime readings. Patients with abnormal nighttime vitals can be predicted on the basis of medical comorbidities and abnormal daytime vitals. These findings suggest that healthy post-TJA patients with normal daytime vitals may not need to be routinely woken at night.

Predicting patient decompensation from continuous physiologic monitoring in the emergency department

Anticipation of clinical decompensation is essential for effective emergency and critical care. In this study, we develop a multimodal machine learning approach to predict the onset of new vital sign abnormalities (tachycardia, hypotension, hypoxia) in ED patients with normal initial vital signs. Our method combines standard triage data (vital signs, demographics, chief complaint) with features derived from a brief period of continuous physiologic monitoring, extracted via both conventional signal processing and transformer-based deep learning on ECG and PPG waveforms. We study 19,847 adult ED visits, divided into training (75%), validation (12.5%), and a chronologically sequential held-out test set (12.5%). The best-performing models use a combination of engineered and transformer-derived features, predicting in a 90-minute window new tachycardia with AUROC of 0.836 (95% CI, 0.800-0.870), new hypotension with AUROC 0.802 (95% CI, 0.747-0.856), and new hypoxia with AUROC 0.713 (95% CI, 0.680-0.745), in all cases significantly outperforming models using only standard triage data. Salient features include vital sign trends, PPG perfusion index, and ECG waveforms. This approach could improve the triage of apparently stable patients and be applied continuously for the prediction of near-term clinical deterioration.

Development and Validation of a Red Flag Prediction Model for Admission of COVID-19 Patients to the Intensive Care Unit

We aimed to develop and validate a model for the criteria for admission of COVID-19 patients to the intensive care unit (ICU). A Delphi design study was conducted. The content validity index (CVI) was used to determine the degree of agreement among the experts to validate the content of the admission criteria tool. Eleven experts determined the validity. The evaluation was conducted using a 4-point rating scale. The accepted CVI value was 0.50 and more. The model was validated with 31 items in the 5 dimensions, with the item-CVI of 1, a face validity index of 1, and a scale-level content validity index (S-CVI) value of 1. We have developed and validated a red flag prediction model for ICU admission of COVID-19 patients. The accurate implementation of this model could improve the outcomes of those patients and possibly decrease mortality.

Factors associated with unfavorable outcomes in patients with acute abdominal pain visiting the emergency department

BACKGROUND

Unfavorable outcomes occur in patients with acute abdominal pain who visit the emergency department (ED). We aimed to determine the factors associated with unfavorable outcomes in patients with acute abdominal pain visiting the ED.

METHODS

This retrospective cohort study was conducted from July 1, 2015 to June 30, 2016. The inclusion criterion was patients aged older than 18 years who presented to the ED with acute abdominal pain. Significant factors associated with unfavorable outcomes were examined using univariate and multivariate logistic regression analyses.

RESULTS

A total of 951 patients were included in the study. Multivariate logistic regression analysis showed that the ED length of stay (EDLOS) > 4 h (adjusted odds ratio (AOR) 2.62, 95% confidence interval [CI]: 1.33-5.14; p = 0.005), diastolic blood pressure (DBP) < 80 mmHg (AOR 3.31, 95% CI: 1.71-6.4; p ≤ 0.001), respiratory rate ≥ 24 breaths/min (AOR 2.03, 95% CI: 1.07-3.86; p ≤ 0.031), right lower quadrant (RLQ) tenderness (AOR 3.72, 95% CI: 1.89-7.32; p ≤ 0.001), abdominal distension (AOR 2.91, 95% CI: 1.29-6.57; p = 0.010), hypoactive bowel sounds (AOR 2.89, 95% CI: 1.09-7.67; p = 0.033), presence of specific abdominal signs (AOR 2.07, 95% CI: 1.1-3.88; p = 0.024), white blood cell count ≥ 12,000 cells/mm³ (AOR 2.37, 95% CI: 1.22-4.6; p = 0.011), and absolute neutrophil count (ANC) > 75% (AOR 2.83, 95% CI: 1.39-5.75; p = 0.004) were revealed as significant factors associated with unfavorable outcomes.

CONCLUSIONS

The present study revealed that the significant clinical signs associated with the occurrence of unfavorable outcomes were DBP < 80 mmHg, tachypnea (≥ 24 breaths/min), RLQ tenderness, abdominal distension, hypoactive bowel sounds, and presence of specific abdominal signs. Moreover, the associated laboratory results identified in this study were leukocytosis and ANC > 75%. Additionally, patients with abdominal pain visiting the ED who had an EDLOS longer than 4 h were associated with unfavorable outcomes.

The magnitude of mortality and its determinants in Ethiopian adult intensive care units: A systematic review and meta-analysis

Introduction

Despite mortality in intensive care units being a global burden, it is higher in low-resource countries, including Ethiopia. A sufficient number of evidence is not yet established regarding mortality in the intensive care unit and its determinants. This study intended to determine the prevalence of ICU mortality and its determinants in Ethiopia.

Methods

PubMed, Google Scholar, The Cochrane Library, HINARI, and African Journals Online (AJOL) databases were systematically explored for potentially eligible studies on mortality prevalence and determinants reported by studies done in Ethiopia. Using a Microsoft Excel spreadsheet, two reviewers independently screen, select, review, and extract data for further analysis using STATA/MP version 17. A meta-analysis using a random-effects model was performed to calculate the pooled prevalence and odds ratio with a 95% confidence interval. In addition, using study region and sample size, subgroup analysis was also performed.

Results

9799 potential articles were found after removing duplicates and screening for eligibility, 14 were reviewed. Ethiopia's pooled national prevalence of adult intensive care unit mortality was 39.70% (95% CI: 33.66, 45.74). Mechanical ventilation, length of staying more than two weeks, GCS below 9, and acute respiratory distress syndrome were major predictors of mortality in intensive care units of Ethiopia.

Conclusion

Mortality in adult ICU is high in Ethiopia. We strongly recommend that all health care professionals and other stakeholders should act to decrease the high mortality among critically ill patients in Ethiopia.

Reducing Crowding in Emergency Departments With Early Prediction of Hospital Admission of Adult Patients Using Biomarkers Collected at Triage: Retrospective Cohort Study

BACKGROUND

Emergency department crowding continues to threaten patient safety and cause poor patient outcomes. Prior models designed to predict hospital admission have had biases. Predictive models that successfully estimate the probability of patient hospital admission would be useful in reducing or preventing emergency department "boarding" and hospital "exit block" and would reduce emergency department crowding by initiating earlier hospital admission and avoiding protracted bed procurement processes.

OBJECTIVE

To develop a model to predict imminent adult patient hospital admission from the emergency department early in the patient visit by utilizing existing clinical descriptors (ie, patient biomarkers) that are routinely collected at triage and captured in the hospital's electronic medical records. Biomarkers are advantageous for modeling due to their early and routine collection at triage; instantaneous availability; standardized definition, measurement, and interpretation; and their freedom from the confines of patient histories (ie, they are not affected by inaccurate patient reports on medical history, unavailable reports, or delayed report retrieval).

METHODS

This retrospective cohort study evaluated 1 year of consecutive data events among adult patients admitted to the emergency department and developed an algorithm that predicted which patients would require imminent hospital admission. Eight predictor variables were evaluated for their roles in the outcome of the patient emergency department visit. Logistic regression was used to model the study data.

RESULTS

The 8-predictor model included the following biomarkers: age, systolic blood pressure, diastolic blood pressure, heart rate, respiration rate, temperature, gender, and acuity level. The model used these biomarkers to identify emergency department patients who required hospital admission. Our model performed well, with good agreement between observed and predicted admissions, indicating a well-fitting and well-calibrated model that showed good ability to discriminate between patients who would and would not be admitted.

CONCLUSIONS

This prediction model based on primary data identified emergency department patients with an increased risk of hospital admission. This actionable information can be used to improve patient care and hospital operations, especially by reducing emergency department crowding by looking ahead to predict which patients are likely to be admitted following triage, thereby providing needed information to initiate the complex admission and bed assignment processes much earlier in the care continuum.

Shedding light into the black box of out-of-hospital respiratory distress—A retrospective cohort analysis of discharge diagnoses, prehospital diagnostic accuracy, and predictors of mortality

Background

Although respiratory distress is one of the most common complaints of patients requiring emergency medical services (EMS), there is a lack of evidence on important aspects.

Objectives

Our study aims to determine the accuracy of EMS physician diagnostics in the out-of-hospital setting, identify examination findings that correlate with diagnoses, investigate hospital mortality, and identify mortality-associated predictors.

Methods

This retrospective observational study examined EMS encounters between December 2015 and May 2016 in the city of Aachen, Germany, in which an EMS physician was present at the scene. Adult patients were included if the EMS physician initially detected dyspnea, low oxygen saturation, or pathological auscultation findings at the scene (n = 719). The analyses were performed by linking out-of-hospital data to hospital records and using binary logistic regressions.

Results

The overall diagnostic accuracy was 69.9% (485/694). The highest diagnostic accuracies were observed in asthma (15/15; 100%), hypertensive crisis (28/33; 84.4%), and COPD exacerbation (114/138; 82.6%), lowest accuracies were observed in pneumonia (70/142; 49.3%), pulmonary embolism (8/18; 44.4%), and urinary tract infection (14/35; 40%). The overall hospital mortality rate was 13.8% (99/719). The highest hospital mortality rates were seen in pneumonia (44/142; 31%) and urinary tract infection (7/35; 20%). Identified risk factors for hospital mortality were metabolic acidosis in the initial blood gas analysis (odds ratio (OR) 11.84), the diagnosis of pneumonia (OR 3.22) reduced vigilance (OR 2.58), low oxygen saturation (OR 2.23), and increasing age (OR 1.03 by 1 year increase).

Conclusions

Our data highlight the diagnostic uncertainties and high mortality in out-of-hospital emergency patients presenting with respiratory distress. Pneumonia was the most common and most frequently misdiagnosed cause and showed highest hospital mortality. The identified predictors could contribute to an early detection of patients at risk.

Advanced Triage Protocol: The Role of an Automated Lactate Order in Expediting Rapid Identification of Patients at Risk of Sepsis in the Emergency Department

We undertook a process improvement initiative to expedite rapid identification of potential sepsis patients based on triage chief complaint, vital signs, and initial lactate level.

Multisite implementation of a workflow-integrated machine learning system to optimize COVID-19 hospital admission decisions

Demand has outstripped healthcare supply during the coronavirus disease 2019 (COVID-19) pandemic. Emergency departments (EDs) are tasked with distinguishing patients who require hospital resources from those who may be safely discharged to the community. The novelty and high variability of COVID-19 have made these determinations challenging. In this study, we developed, implemented and evaluated an electronic health record (EHR) embedded clinical decision support (CDS) system that leverages machine learning (ML) to estimate short-term risk for clinical deterioration in patients with or under investigation for COVID-19. The system translates model-generated risk for critical care needs within 24 h and inpatient care needs within 72 h into rapidly interpretable COVID-19 Deterioration Risk Levels made viewable within ED clinician workflow. ML models were derived in a retrospective cohort of 21,452 ED patients who visited one of five ED study sites and were prospectively validated in 15,670 ED visits that occurred before (n = 4322) or after (n = 11,348) CDS implementation; model performance and numerous patient-oriented outcomes including in-hospital mortality were measured across study periods. Incidence of critical care needs within 24 h and inpatient care needs within 72 h were 10.7% and 22.5%, respectively and were similar across study periods. ML model performance was excellent under all conditions, with AUC ranging from 0.85 to 0.91 for prediction of critical care needs and 0.80-0.90 for inpatient care needs. Total mortality was unchanged across study periods but was reduced among high-risk patients after CDS implementation.

Modified Early Warning Score vs Cardiac Arrest Risk Triage Score for Prediction of Cardiopulmonary Arrest: A Case-Control Study

Background

Delayed transfer to the intensive care unit (ICU) contributes to increased mortality. Clinical tools, developed to shorten this delay, are especially useful in hospitals where the ideal healthcare provider-to-patient ratio is not met. This study aimed to validate and compare the accuracy of the well-accepted modified early warning score (MEWS) and the newer cardiac arrest risk triage (CART) score in the Philippine setting.

Patients and methods

This case-control study involved 82 adult patients admitted to the Philippine Heart Center. Patients who had cardiopulmonary (CP) arrest at the wards and those transferred to the ICU were included. Vital signs and alert-verbal-pain-unresponsive (AVPU) scales were recorded from recruitment until 48 hours prior to CP arrest or ICU transfer. The MEWS and CART scores were computed at specific time points and compared using measures of validity.

Results

The highest accuracy was obtained by the CART score with a cut-off of ≥12 at 8 hours prior to CP arrest or ICU transfer, with a specificity of 80.43% and sensitivity of 66.67%. At this time point, the MEWS with a cut-off of ≥3 had a specificity of 78.26% but a lower sensitivity of 58.33%. The area under the curve (AUC) analysis revealed that these differences were not statistically significant.

Conclusion

We recommend an MEWS threshold of 3 and a CART score threshold of 12 to help identify patients at risk for clinical deterioration. The CART score had comparable accuracy to the MEWS, but the latter's computation may be easier.

How to cite this article

Tan ADA, Permejo CC, Torres MCD. Modified Early Warning Score vs Cardiac Arrest Risk Triage Score for Prediction of Cardiopulmonary Arrest: A Case-Control Study. Indian J Crit Care Med 2022;26(7):780-785.

Contactless Vital Signs Acquisition Using Video Photoplethysmography, Motion Analysis and Passive Infrared Thermography Devices During Emergency Department Walk-In Triage in Pandemic Conditions

BACKGROUND

Contactless vital signs (VS) measurement with video photoplethysmography (vPPG), motion analysis (MA), and passive infrared thermometry (pIR) has shown promise.

OBJECTIVES

To compare conventional (contact-based) and experimental contactless VS measurement approaches for emergency department (ED) walk-in triage in pandemic conditions.

METHODS

Patients' heart rates (HR), respiratory rates (RR), and temperatures were measured with cardiorespiratory monitor and vPPG, manual count and MA, and contact thermometers and pIR, respectively.

RESULTS

There were 475 walk-in ED patients studied (95% of eligible). Subjects were 35.2 ± 20.8 years old (range 4 days‒95 years); 52% female, 0.2% transgender; had Fitzpatrick skin type of 2.3 ± 1.4 (range 1‒6), Emergency Severity Index of 3.0 ± 0.6 (range 2‒5), and contact temperature of 36.83°C (range 35.89-39.4°C) (98.3°F [96.6‒103°F]). Pediatric HR and RR data were excluded from analysis due to research challenges associated with pandemic workflow. For a 30-s, unprimed "Triage" window in 377 adult patients, vPPG-MA acquired 377 (100%) HR measurements featuring a mean difference with cardiorespiratory monitor HR of 5.9 ± 12.8 beats/min (R = 0.6833) and 252 (66.8%) RR measurements featuring a mean difference with manual RR of -0.4 ± 2.6 beats/min (R = 0.8128). Subjects' Emergency Severity Index components based on conventional VS and contactless VS matched for 83.8% (HR) and 89.3% (RR). Filtering out vPPG-MA measurements with low algorithmic confidence reduced VS acquired while improving correlation with conventional measurements. The mean difference between contact and pIR temperatures was 0.83 ± 0.67°C (range -1.16-3.5°C) (1.5 ± 1.2°F [range -2.1-6.3°F]); pIR fever detection improved with post hoc adjustment for mean bias.

CONCLUSION

Contactless VS acquisition demonstrated good agreement with contact methods during adult walk-in ED patient triage in pandemic conditions; clinical applications will need further study.

Which model is superior in predicting ICU survival: artificial intelligence versus conventional approaches

Background

A disease severity classification system is widely used to predict the survival of patients admitted to the intensive care unit with different diagnoses. In the present study, conventional severity classification systems were compared with artificial intelligence predictive models (Artificial Neural Network and Decision Tree) in terms of the prediction of the survival rate of the patients admitted to the intensive care unit.

Methods

This retrospective cohort study was performed on the data of the patients admitted to the ICU of Ghaemshahr’s Razi Teaching Care Center from March 20th, 2017, to September 22nd, 2019. The required data for calculating conventional severity classification models (SOFA, SAPS II, APACHE II, and APACHE IV) were collected from the patients’ medical records. Subsequently, the score of each model was calculated. Artificial intelligence predictive models (Artificial Neural Network and Decision Tree) were developed in the next step. Lastly, the performance of each model in predicting the survival of the patients admitted to the intensive care unit was evaluated using the criteria of sensitivity, specificity, accuracy, F-measure, and area under the ROC curve. Also, each model was validated externally. The R program, version 4.1, was used to create the artificial intelligence models, and SPSS Statistics Software, version 21, was utilized to perform statistical analysis.

Results

The area under the ROC curve of SOFA, SAPS II, APACHE II, APACHE IV, multilayer perceptron artificial neural network, and CART decision tree were 76.0, 77.1, 80.3, 78.5, 84.1, and 80.0, respectively.

Conclusion

The results showed that although the APACHE II model had better results than other conventional models in predicting the survival rate of the patients admitted to the intensive care unit, the other conventional models provided acceptable results too. Moreover, the findings showed that the artificial neural network model had the best performance among all the studied models, indicating the discrimination power of this model in predicting patient survival compared to the other models.

Machine learning-based suggestion for critical interventions in the management of potentially severe conditioned patients in emergency department triage

Providing timely intervention to critically ill patients is a challenging task in emergency departments (ED). Our study aimed to predict early critical interventions (CrIs), which can be used as clinical recommendations. This retrospective observational study was conducted in the ED of a tertiary hospital located in a Korean metropolitan city. Patient who visited ED from January 1, 2016, to December 31, 2018, were included. Need of six CrIs were selected as prediction outcomes, namely, arterial line (A-line) insertion, oxygen therapy, high-flow nasal cannula (HFNC), intubation, Massive Transfusion Protocol (MTP), and inotropes and vasopressor. Extreme gradient boosting (XGBoost) prediction model was built by using only data available at the initial stage of ED. Overall, 137,883 patients were included in the study. The areas under the receiver operating characteristic curve for the prediction of A-line insertion was 0·913, oxygen therapy was 0.909, HFNC was 0.962, intubation was 0.945, MTP was 0.920, and inotropes or vasopressor administration was 0.899 in the XGBoost method. In addition, an increase in the need for CrIs was associated with worse ED outcomes. The CrIs model was integrated into the study site's electronic medical record and could be used to suggest early interventions for emergency physicians.

Prehospital Time Disparities for Rural Patients with Suspected STEMI

BACKGROUND

Rural patients with ST-elevation myocardial infarction (STEMI) may be less likely to receive prompt reperfusion therapy. This study's primary objective was to compare rural versus urban time intervals among a national cohort of prehospital patients with STEMI.

METHODS

The ESO Data Collaborative (Austin, TX), containing records from 1,366 emergency medical services agencies, was queried for adult 9-1-1 responses with suspected STEMI from 1/1/2018-12/31/2019. The scene address for each encounter was classified as either urban or rural using the 2010 US Census Urban Area Zip Code Tabulation Area relationship. The primary outcome was total EMS interval (9-1-1 call to hospital arrival); a key secondary outcome was the proportion of responses that had EMS intervals under 60 minutes. Generalized estimating equations were used to determine whether rural versus urban differences in interval outcomes occurred when adjusting for loaded mileage (distance from scene to hospital) and patient and clinical encounter characteristics.

RESULTS

Of 15,915,027 adult 9-1-1 transports, 23,655 records with suspected STEMI were included in the analysis. Most responses (91.6%, n = 21,661) occurred in urban settings. Median EMS interval was 37.6 minutes (IQR 30.0-48.0) in urban settings compared to 57.0 minutes (IQR 46.5-70.7) in rural settings (p < 0.01). Urban responses more frequently had EMS intervals <60 minutes (89.5%, n = 19,130), compared to rural responses (55.5%, n = 1,100, p < 0.01). After adjusting for loaded mileage, age, sex, race/ethnicity, abnormal vital signs, pain assessment, aspirin administration, and IV/IO attempt, rural location was associated with a 5.8 (95%CI 4.2-7.4) minute longer EMS interval than urban, and rural location was associated with a reduced chance of achieving EMS interval < 60 minutes (OR 0.40; 95%CI 0.33-0.49) as compared to urban location.

CONCLUSION

In this large national sample, rural location was associated with significantly longer EMS interval for patients with suspected STEMI, even after accounting for loaded mileage.

Are 5-level triage systems improved by using a symptom based approach?-a Danish cohort study

Background

Five-level triage systems are being utilized in Danish emergency departments with and without the use of presenting symptoms. The aim of this study was to validate and compare two 5-level triage systems used in Danish emergency departments: “Danish Emergency Process Triage” (DEPT) based on a combination of vital signs and presenting symptoms and a locally adapted version of DEPT (VITAL-TRIAGE) using vital signs only.

Methods

This was a retrospective cohort using data from five Danish emergency departments. All patients attending an emergency department during the period of 1 April 2012 until 31 December 2015 were included. Validity of the two triage systems was assessed by comparing urgency categories determined by each triage system with critical outcomes: admission to Intensive care unit (ICU) within 24 h, 2-day mortality, diagnosis of critical illness, surgery within 48 h, discharge within 4 h and length of hospital stay.

Results

We included 632,196 ED contacts. Sensitivity for 24-h ICU admission was 0.79 (95% confidence interval 0.78–0.80) for DEPT and 0.44 (0.41–0.47) for VITAL-TRIAGE. The sensitivity for 2-day mortality was 0.69 (0.67–0.70) for DEPT and 0.37 (0.34–0.41) for VITAL-TRIAGE. The sensitivity to detect diagnoses of critical illness was 0.48 (0.47–0.50) for DEPT and 0.09 (0.08–0.10) for VITAL-TRIAGE. The sensitivity for predicting surgery within 48 h was 0.30 (0.30–0.31) in DEPT and 0.04 (0.04–0.04) in VITAL-TRIAGE. Length of stay was longer in VITAL-TRIAGE than DEPT. The sensitivity of DEPT to predict patients discharged within 4 h was 0.91 (0.91–0.92) while VITAL-TRIAGE was higher at 0.99 (0.99–0.99). The odds ratio for 24-h ICU admission and 2-day mortality was increased in high-urgency categories of both triage systems compared to low-urgency categories.

Conclusions

High urgency categories in both triage systems are correlated with adverse outcomes. The inclusion of presenting symptoms in a modern 5-level triage system led to significantly higher sensitivity measures for the ability to predict outcomes related to patient urgency. DEPT achieves equal prognostic performance as other widespread 5-level triage systems.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13049-022-01016-2.

Measuring sustainable practice change of the sepsis guideline in one emergency department: A retrospective health care record audit

AIMS AND OBJECTIVES

To explore the longitudinal impact of the New South Wales Sepsis guideline on time to antibiotics, triage assessment and emergency management before and four years after guideline implementation.

BACKGROUND

Globally, sepsis continues to be a significant cause of mortality and morbidity within hospitals. To reduce avoidable adverse patient outcomes the corner stone has been to improve the early recognition and management of sepsis. The New South Wales government in Australia introduced sepsis guidelines into Emergency Departments. However, the longitudinal impact of the sepsis guideline, has never been conducted.

METHODS

A 12-month retrospective randomised health care record audit of adult patients with a sepsis diagnosis was conducted 12-months before and four years after implementation of the sepsis guideline.

RESULTS

This study demonstrated sustained improvement in allocation of urgent triage categories in the follow-up group (n = 43; 53.1%) and a reduction in the median time to antibiotics from 189 min to 102 min (p ≤ 0.001) after the implementation of the sepsis guideline.

CONCLUSION

The study has demonstrated the sepsis guideline has improved a sustained change in early assessment, recognition and management of patients presenting with sepsis in one tertiary referral Emergency Department.

The Association Between Abnormal Vital Signs and Mortality in the Emergency Department

Background

The emergency department (ED) receives patients from all over the world every day. Hence, using various triage scales to detect sick patients and the need for early admission are essential. Triage is a process used in the ED to prioritize patients requiring the most urgent care over those with minor injuries based on medical urgency and medical needs. These decisions may be based on patients’ chief complaints at the time of their ED visit and their vital signs. Vital signs, including blood pressure (BP), respiratory rate (RR), heart rate (HR), and body temperature, are necessary tools that are traditionally used in the ED during procedures such as triage and recognizing high-risk hospital inpatients. This study aimed to determine the relationship between abnormal vital signs and mortality in the ED.

Method and Material

This retrospective record review study was performed at the ED of King Abdulaziz University Hospital (KAUH). Altogether, 641 patients fulfilled our inclusion criteria. Data including patients’ demographics, vital signs, in-hospital mortality, triage level, and precipitating factors were collected.

Results

The mean age of the patients was 45.66 ± 18.43 years (69.3% females), and the majority of them had Canadian Triage and Acuity Scale (CTAS) level 3 (71.1%). The total number of in-hospital mortalities was 32 (5%). Lower systolic blood pressure (SBP) and diastolic blood pressure (DBP), high respiratory rates, and low oxygen saturation (O₂SAT) were significantly associated with high mortality rates.

Conclusion

Abnormal vital signs play a major role in determining patient prognosis and outcomes. Triage score systems should be adjusted and carefully studied in each center according to its population.

Preclinical evaluation of noncontact vital signs monitoring using real-time IR-UWB radar and factors affecting its accuracy

Recently, noncontact vital sign monitors have attracted attention because of issues related to the transmission of contagious diseases. We developed a real-time vital sign monitor using impulse-radio ultrawideband (IR-UWB) radar with embedded processors and software; we then evaluated its accuracy in measuring heart rate (HR) and respiratory rate (RR) and investigated the factors affecting the accuracy of the radar-based measurements. In 50 patients visiting a cardiology clinic, HR and RR were measured using IR-UWB radar simultaneously with electrocardiography and capnometry. All patients underwent HR and RR measurements in 2 postures—supine and sitting—for 2 min each. There was a high agreement between the RR measured using radar and capnometry (concordance correlation coefficient [CCC] 0.925 [0.919–0.926]; upper and lower limits of agreement [LOA], − 2.21 and 3.90 breaths/min). The HR measured using radar was also in close agreement with the value measured using electrocardiography (CCC 0.749 [0.738–0.760]; upper and lower LOA, − 12.78 and 15.04 beats/min). Linear mixed effect models showed that the sitting position and an HR < 70 bpm were associated with an increase in the absolute biases of the HR, whereas the sitting position and an RR < 18 breaths/min were associated with an increase in the absolute biases of the RR. The IR-UWB radar sensor with embedded processors and software can measure the RR and HR in real time with high precision. The sitting position and a low RR or HR were associated with the accuracy of RR and HR measurement, respectively, using IR-UWB radar.

Vital Signs Prediction for COVID-19 Patients in ICU

This study introduces machine learning predictive models to predict the future values of the monitored vital signs of COVID-19 ICU patients. The main vital sign predictors include heart rate, respiration rate, and oxygen saturation. We investigated the performances of the developed predictive models by considering different approaches. The first predictive model was developed by considering the following vital signs: heart rate, blood pressure (systolic, diastolic and mean arterial, pulse pressure), respiration rate, and oxygen saturation. Similar to the first approach, the second model was developed using the same vital signs, but it was trained and tested based on a leave-one-subject-out approach. The third predictive model was developed by considering three vital signs: heart rate (HR), respiration rate (RR), and oxygen saturation (SpO2). The fourth model was a leave-one-subject-out model for the three vital signs. Finally, the fifth predictive model was developed based on the same three vital signs, but with a five-minute observation rate, in contrast with the aforementioned four models, where the observation rate was hourly to bi-hourly. For the five models, the predicted measurements were those of the three upcoming observations (on average, three hours ahead). Based on the obtained results, we observed that by limiting the number of vital sign predictors (i.e., three vital signs), the prediction performance was still acceptable, with the average mean absolute percentage error (MAPE) being 12%,5%, and 21.4% for heart rate, oxygen saturation, and respiration rate, respectively. Moreover, increasing the observation rate could enhance the prediction performance to be, on average, 8%,4.8%, and 17.8% for heart rate, oxygen saturation, and respiration rate, respectively. It is envisioned that such models could be integrated with monitoring systems that could, using a limited number of vital signs, predict the health conditions of COVID-19 ICU patients in real-time.

Machine learning techniques for mortality prediction in emergency departments: a systematic review

OBJECTIVES

This systematic review aimed to assess the performance and clinical feasibility of machine learning (ML) algorithms in prediction of in-hospital mortality for medical patients using vital signs at emergency departments (EDs).

DESIGN

A systematic review was performed.

SETTING

The databases including Medline (PubMed), Scopus and Embase (Ovid) were searched between 2010 and 2021, to extract published articles in English, describing ML-based models utilising vital sign variables to predict in-hospital mortality for patients admitted at EDs. Critical appraisal and data extraction for systematic reviews of prediction modelling studies checklist was used for study planning and data extraction. The risk of bias for included papers was assessed using the prediction risk of bias assessment tool.

PARTICIPANTS

Admitted patients to the ED.

MAIN OUTCOME MEASURE

In-hospital mortality.

RESULTS

Fifteen articles were included in the final review. We found that eight models including logistic regression, decision tree, K-nearest neighbours, support vector machine, gradient boosting, random forest, artificial neural networks and deep neural networks have been applied in this domain. Most studies failed to report essential main analysis steps such as data preprocessing and handling missing values. Fourteen included studies had a high risk of bias in the statistical analysis part, which could lead to poor performance in practice. Although the main aim of all studies was developing a predictive model for mortality, nine articles did not provide a time horizon for the prediction.

CONCLUSION

This review provided an updated overview of the state-of-the-art and revealed research gaps; based on these, we provide eight recommendations for future studies to make the use of ML more feasible in practice. By following these recommendations, we expect to see more robust ML models applied in the future to help clinicians identify patient deterioration earlier.

Emergency department utilization and risk factors for mortality in older patients: an analysis of Korean National Emergency Department Information System data

Objective

With trends in population aging an increasing number of older patients are visiting the emergency department (ED). This study aimed to identify the characteristics of ED utilization and risk factors for in-hospital mortality in older patients who visited EDs.

Methods

This nationwide observational study used National Emergency Department Information System data collected during a 2-year period from January 2016 to December 2017. The characteristics of older patients aged 70 years or older were compared with those of younger patients aged 20 to 69 years. Risk factors associated with in-hospital mortality were analyzed by multivariable logistic regression.

Results

A total of 6,596,423 younger patients and 1,737,799 older patients were included. In the medical and nonmedical older patient groups, significantly higher proportions of patients were transferred from another hospital, utilized emergency medical services, had Korean Triage and Acuity Scale scores of 1 and 2, required hospitalization, and required intensive care unit admission in the older patient group than in the younger patient group. ED and post-hospitalization mortality rates increased with age; in particular, older medical patients aged 90 or older had an in-hospital mortality rate of 9%. Older age, male sex, transfer from another hospital, emergency medical service utilization, a high Korean Triage and Acuity Scale score, systolic blood pressure <100 mmHg, respiratory rate >20/min, heart rate >100/min, body temperature <36°C, and altered mental status were associated with in-hospital mortality.

Conclusion

Development of appropriate decision-making algorithms and treatment protocols for high risk older patients visiting the ED might facilitate appropriate allocation of medical resources to optimize outcomes.

Readmission following both cardiac and non-cardiac acute dyspnoea is associated with a striking risk of death

Aims

Readmission and mortality are the most common and often combined endpoints in acute heart failure (AHF) trials, but an association between these two outcomes is poorly investigated. The aim of this study was to determine whether unplanned readmission is associated with a greater subsequent risk of death in patients with acute dyspnoea due to cardiac and non‐cardiac causes.

Methods and results

Derivation cohort (1371 patients from the LEDA study) and validation cohort (1986 patients from the BASEL V study) included acute dyspnoea patients admitted to the emergency department. Cox regression analysis was used to determine the association of 6 month readmission and the risk of 1 year all‐cause mortality in AHF and non‐AHF patients and those readmitted due to cardiovascular and non‐cardiovascular causes. In the derivation cohort, 666 (49%) of patients were readmitted at 6 months and 282 (21%) died within 1 year. Six month readmission was associated with an increased 1 year mortality risk in both the derivation cohort [adjusted hazard ratio (aHR) 3.0 (95% confidence interval, CI 2.2–4.0), P < 0.001] and the validation cohort (aHR 1.8, 95% CI 1.4–2.2, P < 0.001). The significant association was similarly observed in AHF (aHR 3.2, 95% CI 2.1–4.9, P < 0.001) and other causes of acute dyspnoea (aHR 2.9, 95% CI 1.9–4.5, P < 0.001), and it did not depend on the aetiology [aHR 2.2, 95% CI 1.6–3.1 for cardiovascular readmissions; aHR 4.1, 95% CI 2.9–5.7 for non‐cardiovascular readmissions (P < 0.001 for both)] or timing of readmission.

Conclusion​s

Our study demonstrated a long‐lasting detrimental association between readmission and death in AHF and non‐AHF patients with acute dyspnoea. These patients should be considered ‘vulnerable patients’ that require personalized follow‐up for an extended period.

Systems for recognition and response to deteriorating emergency department patients: a scoping review

Background

Assessing and managing the risk of clinical deterioration is a cornerstone of emergency care, commencing at triage and continuing throughout the emergency department (ED) care. The aim of this scoping review was to assess the extent, range and nature of published research related to formal systems for recognising and responding to clinical deterioration in emergency department (ED) patients.

Materials and methods

We conducted a scoping review according to PRISMA-ScR guidelines. MEDLINE complete, CINAHL and Embase were searched on 07 April 2021 from their dates of inception. Human studies evaluating formal systems for recognising and responding to clinical deterioration occurring after triage that were published in English were included. Formal systems for recognising and responding to clinical deterioration were defined as: i) predefined patient assessment criteria for clinical deterioration (single trigger or aggregate score), and, or ii) a predefined, expected response should a patient fulfil the criteria for clinical deterioration. Studies of short stay units and observation wards; deterioration during the triage process; system or score development or validation; and systems requiring pathology test results were excluded. The following characteristics of each study were extracted: author(s), year, design, country, aims, population, system tested, outcomes examined, and major findings.

Results

After removal of duplicates, there were 2696 publications. Of these 33 studies representing 109,066 patients were included: all were observational studies. Twenty-two aggregate scoring systems were evaluated in 29 studies and three single trigger systems were evaluated in four studies. There were three major findings: i) few studies reported the use of systems for recognising and responding to clinical deterioration to improve care of patients whilst in the ED; ii) the systems for recognising clinical deterioration in ED patients were highly variable and iii) few studies reported on the ED response to patients identified as deteriorating.

Conclusion

There is a need to re-focus the research related to use of systems for recognition and response to deteriorating patients from predicting various post-ED events to their real-time use to improve patient safety during ED care.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13049-021-00882-6.

Some machine’s doin’ that for you* – elektronische Triagesysteme in der Notaufnahme

Hintergrund

In den letzten 25 Jahren haben sich Triagesysteme zur Dringlichkeitseinschätzung in den Notaufnahmen etabliert. Die bisherigen symptomorientierten Triagesysteme haben allerdings auch Schwächen. Inzwischen ermöglichen die Digitalisierung der Notaufnahmen und die Leistungsfähigkeit der aktuellen Computergeneration bereits zum Triagezeitpunkt einen algorithmenbasierten Datenvergleich und eine Risikostratifizierung für bestimmte klinische Endpunkte über die reine Triagestufe hinaus.

Ziel der Arbeit

Nach selektiver Literaturrecherche erfolgt eine Übersicht über elektronische Triagesysteme (ETS). Das Funktionsprinzip und die aktuellen Möglichkeiten der ETS werden dargestellt. Daneben werden Chancen und Schwierigkeiten einer Etablierung von ETS in deutschen Notaufnahmen betrachtet.

Ergebnisse

Es wurden wesentliche Prädiktorvariablen wie Alter und bestimmte Vitalparameter identifiziert, die bisher nicht standardisiert in die Triagestufen einfließen, aber mithilfe von Modelllernen (ML) in belastbare Vorhersagen für klinische Endpunkte wie stationäre Aufnahme oder Mortalität einfließen können. Die Güte der Ersteinschätzung durch ein ETS ist insgesamt hoch. Ein ETS kann das Triagepersonal evidenzbasiert bei der Disposition der Patienten unterstützen und Über- und Untertriage reduzieren. Es gibt einige Entwicklungen, die günstige Bedingungen für den Einsatz von ETS in deutschen ZNA schaffen. So erleichtern z. B. repräsentative Notaufnahmeregister die Erstellung von Referenzdatensätzen, die zum Aufbau computerbasierter Klassifikationsmodelle benötigt werden. Außerdem müssen individuelle Patientendaten schnell verfügbar sein.

Schlussfolgerung

ETS können zur Erhöhung der Patientensicherheit und zur besseren Ressourcennutzung beitragen. Bislang fehlen allerdings noch objektive Referenzstandards und Leitlinien zum maschinellen Lernen.

Elevated Heart Rate and Risk of Revisit With Admission in Pediatric Emergency Patients

OBJECTIVE

The aim of this study was to identify emergency department (ED) heart rate (HR) values that identify children at elevated risk of ED revisit with admission.

METHODS

We performed a retrospective cohort study of patients 0 to 18 years old discharged from a tertiary-care pediatric ED from January 2013 to December 2014. We created percentile curves for the last recorded HR for age using data from calendar year 2013 and used receiver operating characteristic (ROC) curves to characterize the performance of the percentiles for predicting ED revisit with admission within 72 hours. In a held-out validation data set (calendar year 2014 data), we evaluated test characteristics of last-recorded HR-for-age cut points identified as promising on the ROC curves, as well as those identifying the highest 5% and 1% of last recorded HRs for age.

RESULTS

We evaluated 183,433 eligible ED visits. Last recorded HR for age had poor discrimination for predicting revisit with admission (area under the curve, 0.61; 95% confidence interval, 0.58-0.63). No promising cut points were identified on the ROC curves. Cut points identifying the highest 5% and 1% of last recorded HRs for age showed low sensitivity (10.1% and 2.5%) with numbers needed to evaluate of 62 and 50, respectively, to potentially prevent 1 revisit with admission.

CONCLUSIONS

Last recorded ED HR discriminates poorly between children who are and are not at risk of revisit with admission in a pediatric ED. The use of single-parameter HR in isolation as an automated trigger for mandatory reevaluation prior to discharge may not improve revisit outcomes.

Machine Learning-Based Early Warning Systems for Clinical Deterioration: Systematic Scoping Review

Background

Timely identification of patients at a high risk of clinical deterioration is key to prioritizing care, allocating resources effectively, and preventing adverse outcomes. Vital signs–based, aggregate-weighted early warning systems are commonly used to predict the risk of outcomes related to cardiorespiratory instability and sepsis, which are strong predictors of poor outcomes and mortality. Machine learning models, which can incorporate trends and capture relationships among parameters that aggregate-weighted models cannot, have recently been showing promising results.

Objective

This study aimed to identify, summarize, and evaluate the available research, current state of utility, and challenges with machine learning–based early warning systems using vital signs to predict the risk of physiological deterioration in acutely ill patients, across acute and ambulatory care settings.

Methods

PubMed, CINAHL, Cochrane Library, Web of Science, Embase, and Google Scholar were searched for peer-reviewed, original studies with keywords related to “vital signs,” “clinical deterioration,” and “machine learning.” Included studies used patient vital signs along with demographics and described a machine learning model for predicting an outcome in acute and ambulatory care settings. Data were extracted following PRISMA, TRIPOD, and Cochrane Collaboration guidelines.

Results

We identified 24 peer-reviewed studies from 417 articles for inclusion; 23 studies were retrospective, while 1 was prospective in nature. Care settings included general wards, intensive care units, emergency departments, step-down units, medical assessment units, postanesthetic wards, and home care. Machine learning models including logistic regression, tree-based methods, kernel-based methods, and neural networks were most commonly used to predict the risk of deterioration. The area under the curve for models ranged from 0.57 to 0.97.

Conclusions

In studies that compared performance, reported results suggest that machine learning–based early warning systems can achieve greater accuracy than aggregate-weighted early warning systems but several areas for further research were identified. While these models have the potential to provide clinical decision support, there is a need for standardized outcome measures to allow for rigorous evaluation of performance across models. Further research needs to address the interpretability of model outputs by clinicians, clinical efficacy of these systems through prospective study design, and their potential impact in different clinical settings.

Variation of vital signs with potential to influence the performance of qSOFA scoring in the Ethiopian general population at different altitudes of residency: A multisite cross-sectional study

Introduction

The physiological range of different vital signs is dependent on various environmental and individual factors. There is a strong interdependent relationship between vital signs and health conditions. Deviations of the physiological range are commonly used for risk assessment in clinical scores, e.g. respiratory rate (RR) and systolic blood pressure (BP_sys) in patients with infections within the quick sequential organ failure assessment (qSOFA) score. A limited number of studies have evaluated the performance of such scores in resource-limited health care settings, showing inconsistent results with mostly poor discriminative power. Divergent standard values of vital parameters in different populations, e.g. could influence the accuracy of various clinical scores.

Methods

This multisite cross-sectional observational study was performed among Ethiopians residing at various altitudes in the cities of Asella (2400m above sea level (a.s.l.)), Adama (1600m a.s.l.), and Semara (400m a.s.l.). Volunteers from the local general population were asked to complete a brief questionnaire and have vital signs measured. Individuals reporting acute or chronic illness were excluded.

Results

A positive qSOFA score (i.e. ≥2), indicating severe illness in patients with infection, was common among the studied population (n = 612). The proportion of participants with a positive qSOFA score was significantly higher in Asella (28.1%; 55/196), compared with Adama, (8.3%; 19/230; p<0.001) and Semara (15.1%; 28/186; p = 0.005). Concerning the parameters comprised in qSOFA, the thresholds for RR (≥22/min) were reached in 60.7%, 34.8%, and 38.2%, and for BP_sys (≤100 mmHg) in 48.5%, 27.8%, and 36.0% in participants from Asella, Adama, and Semara, respectively.

Discussion

The high positivity rate of qSOFA score in the studied population without signs of acute infection may be explained by variations of the physiological range of different vital signs, possibly related to the altitude of residence. Adaptation of existing scores using local standard values could be helpful for reliable risk assessment.

Patterns of Admission and Clinical Outcomes Among Patients Admitted to Medical Intensive Care Unit of a Teaching and Referral Hospital, Northwest Ethiopia

Background

The intensive care unit (ICU) is a health care delivery service for patients who are in critical condition with potentially recoverable diseases. Patients can benefit from more detailed observation, monitoring and advanced treatment than other wards or department. The care is advancing but in resource-limited settings, it is lagging far behind and mortality is still higher due to various reasons. Therefore, we aimed to determine the admission patterns, clinical outcomes and associated factors among patients admitted medical intensive care unit (MICU).

Methods

A retrospective cross-sectional study was conducted based on a record review of logbook and charts of patients admitted from September, 2015 to April, 2019. Data were entered and analysed using SPSS version 20. Both bivariate and multivariate logistic regression analyses were used and a P-value < 0.05 was considered statistically significant.

Results

A total of 738 patients were admitted to medical intensive care unit (MICU) during September, 2015 - April, 2019. Five hundred and four patients (68%) of all intensive care unit (ICU) admissions had complete data. Out of the 504 patients, 268 (53.2%) patients were females. Cardiovascular disease 182(36.1%) was the commonest categorical admission diagnosis. The overall mortality rate was 38.7%. In the multivariate analysis, mortality was associated with need for mechanical ventilation (AOR = 5.87, 95% CI: 3.24 - 10.65) and abnormal mental status at admission (AOR = 2.8, 95% CI: 1.83-4.29). Patients who had stay less than four days in MICU were 5 times more likely to die than those who has stay longer time (AOR= 5.58, 95% CI: 3.58- 8.69).

Conclusions

The overall mortality was considerably high and cardiovascular diseases were the most common cause of admission in MICU. Need for mechanical ventilator, length of intensive care unit stay and mental status at admission were strongly associated with clinical outcome of patients admitted to medical intensive care unit.

Consensus on predictors of clinical deterioration in emergency departments: A Delphi process study

AIM

The study aim was to determine relevance and applicability of generic predictors of clinical deterioration in emergency departments based on consensus among clinicians.

METHODS

Thirty-three predictors of clinical deterioration identified from literature were assessed in a modified two-stage Delphi-process. Sixty-eight clinicians (physicians and nurses) participated in the first round and 48 in the second round; all treating hospitalized patients in Danish emergency departments, some with pre-hospital experience. The panel rated the predictors for relevance (relevant marker of clinical deterioration) and applicability (change in clinical presentation over time, generic in nature and possible to detect bedside). They rated their level of agreement on a 9-point Likert scale and were also invited to propose additional generic predictors between the rounds. New predictors suggested by more than one clinician were included in the second round along with non-consensus predictors from the first round. Final decisions of non-consensus predictors after second round were made by a research group and an impartial physician.

RESULTS

The Delphi-process resulted in 19 clinically relevant and applicable predictors based on vital signs and parameters (respiratory rate, saturation, dyspnoea, systolic blood pressure, pulse rate, abnormal electrocardiogram, altered mental state and temperature), biochemical tests (serum c-reactive protein, serum bicarbonate, serum lactate, serum pH, serum potassium, glucose, leucocyte counts and serum haemoglobin), objective clinical observations (skin conditions) and subjective clinical observations (pain reported as new or escalating, and relatives' concerns).

CONCLUSION

The Delphi-process led to consensus of 19 potential predictors of clinical deterioration widely accepted as relevant and applicable in emergency departments.

Prediction of Mortality Associated with Cardiac and Radiological Findings in Patients with Pulmonary Embolism

Background: In this study, we aimed to compare echocardiography, electrocardiography (ECG) abnormalities, Doppler ultrasonography (USG), and computed tomography pulmonary angiography (CTPA) results in predicting 3-month mortality in patients with acute pulmonary embolism (PE).

Methods: This retrospective cohort study included 124 patients (72 females, 52 males) with acute PE. Demographics, symptoms, clinical signs, comorbidities, history of surgery, arterial blood gas, liver-renal functions, complete blood count, echocardiography, ECG, Doppler USG, and CTPA results, as well as 3-month mortality were recorded.

Results: pH (z = –2.623; p <0.01), hemoglobin (z = –3.112; p <0.01), and oxygen saturation (z = –2.165; p <0. 01) were significantly higher in survivors. White blood cell (z = –2.703; p <0.01), blood urea nitrogen (z = –3.840; p <0.01), creatinine (z = –3.200; p <0.01), respiratory rate (z = –2.759; p <0.01), and heart rate (z = –2.313; p <0.01) were significantly higher in non-survivors. Nonspecific ST changes (AUC 0.52, 95% CI 0.43–0.61), p pulmonale (AUC 0.52, 95% CI 0.43–0.61), normal axis (AUC 0.61), right axis deviation (AUC 0.56), right ventricle strain pattern (AUC 0.59), and right pulmonary artery embolism (AUC 0.54) on CTPA showed the highest mortality prediction.

Conclusions: Nonspecific ST changes, p pulmonale, normal axis and right axis deviation in ECG, RV strain in echocardiography, and right pulmonary artery embolism on CTPA are associated with a higher mortality in patients with PE.

Risk factors for unplanned ICU admission after emergency department holding orders

STUDY HYPOTHESIS

Emergency department (ED) holding orders are used in an effort to streamline patient flow. Little research exists on the safety of this practice. Here, we report on prevalence and risk factors for upgrade of medical admissions to ICU for whom holding orders were written.

METHODS

Retrospective review of holding order admissions through our ED for years 2013-2018. Pregnancy, prisoner, pediatric, surgical, and ICU admissions were excluded, as were transfers from other hospitals. Risk factors of interest included vital signs, physiologic data, laboratory markers, sequential organ failure assessment (SOFA), Quick SOFA (qSOFA), modified early warning (MEWS) scores, and Charlson Comorbidity Index (CCI). Primary outcome was ICU transfer within 24 hours of admission. Analysis was completed using multivariable logistic regression.

RESULTS

Between 2013 and 2018, the ED had 203,374 visits. Approximately 20% (N = 54,915) were admitted, 23% of whom had holding orders (N = 12,680). A minority of those with a holding order were transferred to the ICU within 24 hours (N = 79; 0.62%). Those transferred to ICU had increased heart and respiratory rate, P/F ratio, and increased oxygen need. They also had higher MEWS, quick SOFA (qSOFA), and SOFA scores. Multivariable logistic regression demonstrated a significant association between ICU admission and FiO2 (odds ratio [OR] 1.47; 95% confidence interval [CI] 1.25-1.74), MEWS (OR 1.31; 95% CI 1.14-1.52), SOFA Score (OR 1.19; 95% CI 1.05-1.35), and gastrointestinal (OR 3.25; 95% CI: 1.50-7.03) or other combined diagnosis (OR 2.19; CI: 1.07-4.48) (P = 0.0017).

CONCLUSION

Holding orders are used for >20% of all admissions and <1% of those admissions required transfer to ICU within 24 hours.

Vital Signs Prediction and Early Warning Score Calculation Based on Continuous Monitoring of Hospitalised Patients Using Wearable Technology

In this prospective, interventional, international study, we investigate continuous monitoring of hospitalised patients' vital signs using wearable technology as a basis for real-time early warning scores (EWS) estimation and vital signs time-series prediction. The collected continuous monitored vital signs are heart rate, blood pressure, respiration rate, and oxygen saturation of a heterogeneous patient population hospitalised in cardiology, postsurgical, and dialysis wards. Two aspects are elaborated in this study. The first is the high-rate (every minute) estimation of the statistical values (e.g., minimum and mean) of the vital signs components of the EWS for one-minute segments in contrast with the conventional routine of 2 to 3 times per day. The second aspect explores the use of a hybrid machine learning algorithm of kNN-LS-SVM for predicting future values of monitored vital signs. It is demonstrated that a real-time implementation of EWS in clinical practice is possible. Furthermore, we showed a promising prediction performance of vital signs compared to the most recent state of the art of a boosted approach of LSTM. The reported mean absolute percentage errors of predicting one-hour averaged heart rate are 4.1, 4.5, and 5% for the upcoming one, two, and three hours respectively for cardiology patients. The obtained results in this study show the potential of using wearable technology to continuously monitor the vital signs of hospitalised patients as the real-time estimation of EWS in addition to a reliable prediction of the future values of these vital signs is presented. Ultimately, both approaches of high-rate EWS computation and vital signs time-series prediction is promising to provide efficient cost-utility, ease of mobility and portability, streaming analytics, and early warning for vital signs deterioration.

Level of vital and laboratory values on arrival, and increased risk of 7-day mortality among adult patients in the emergency department: a population-based cohort study

OBJECTIVES

The aim of the study was to provide evidence for, at which vital and laboratory values, increased risk of 7-day mortality in acute adult patients on arrival to an emergency department (ED).

DESIGN

A population-based cohort study.

SETTING

ED at Odense University Hospital, Denmark.

PARTICIPANTS

All patients ≥18 years with a first-time contact within the study period, 1 April 2012 to 31 March 2015.

PRIMARY AND SECONDARY OUTCOME MEASURES

Primary outcome was 7-day all-cause mortality.Variables were first recorded vital and laboratory values included in risk stratification scores; respiratory frequency, blood pressure, heart rate, Glasgow Coma Scale, temperature, saturation, creatinine, PaO₂, platelet count and bilirubin. The association between values and mortality was described using a restricted cubic spline. A predefined 7-day mortality of 2.5% was chosen as a relevant threshold.

RESULTS

We included 40 423 patients, 52.5% women, median age 57 (IQR 38-74) years and 7-day mortality 2.8%. Seven-day mortality of 2.5% had thresholds of respiratory frequency <12 and >18/min, systolic blood pressure <112 and >192 mm Hg, heart rate <54 and >102 beats/min, temperature <36.0°C and >39.8°C, saturation <97%, Glasgow Coma Scale score <15, creatinine <41 and >98 µmol/L for PaO₂ <9.9 and >12.3 kPa, platelet count <165 and >327×10⁹/L and bilirubin >12 µmol/L.

CONCLUSION

Vital values on arrival, outside the normal ranges for the measures, are indicative of increased risk of short-term mortality, and most of the value thresholds are included in the lowest urgency level in triage and risk stratification scoring systems.

Pre-hospital predictors of an adverse outcome among patients with dyspnoea as the main symptom assessed by pre-hospital emergency nurses - a retrospective observational study

Background

Dyspnoea is one of the most common reasons for patients contacting emergency medical services (EMS). Pre-hospital Emergency Nurses (PENs) are independently responsible for advanced care and to meet these patients individual needs. Patients with dyspnoea constitute a complex group, with multiple different final diagnoses and with a high risk of death. This study aimed to describe on-scene factors associated with an increased risk of a time-sensitive final diagnosis and the risk of death.

Methods

A retrospective observational study including patients aged ≥16 years, presenting mainly with dyspnoea was conducted. Patients were identified thorough an EMS database, and were assessed by PENs in the south-western part of Sweden during January to December 2017. Of 7260 missions (9% of all primary missions), 6354 were included. Among those, 4587 patients were randomly selected in conjunction with adjusting for unique patients with single occasions. Data were manually collected through both EMS- and hospital records and final diagnoses were determined through the final diagnoses verified in hospital records. Analysis was performed using multiple logistic regression and multiple imputations.

Results

Among all unique patients with dyspnoea as the main symptom, 13% had a time-sensitive final diagnosis. The three most frequent final time-sensitive diagnoses were cardiac diseases (4.1% of all diagnoses), infectious/inflammatory diseases (2.6%), and vascular diseases (2.4%). A history of hypertension, renal disease, symptoms of pain, abnormal respiratory rate, impaired consciousness, a pathologic ECG and a short delay until call for EMS were associated with an increased risk of a time-sensitive final diagnosis. Among patients with time-sensitive diagnoses, approximately 27% died within 30 days. Increasing age, a history of renal disease, cancer, low systolic blood pressures, impaired consciousness and abnormal body temperature were associated with an increased risk of death.

Conclusions

Among patients with dyspnoea as the main symptom, age, previous medical history, deviating vital signs, ECG pattern, symptoms of pain, and a short delay until call for EMS are important factors to consider in the prehospital assessment of the combined risk of either having a time-sensitive diagnosis or death.

Supplementary Information

Supplementary information accompanies this paper at 10.1186/s12873-020-00384-1.

Abnormal Vital Sign Recognition and Provider Notification in the Pediatric Emergency Department

INTRODUCTION

Vital signs measurements aid in the early identification of patients at risk of clinical deterioration and determining the severity of illness. Health care providers rely on registered nurses to document vital signs and communicate abnormalities. The purpose of this project was to improve the provider notification process regarding abnormal vital signs in a pediatric emergency department.

METHOD

A best practice advisory (BPA) was piloted by the advanced practice providers in the pediatric emergency department. To evaluate the effects of the BPA, a mixed-methods study was employed.

RESULTS

Implementation of the BPA improved the provider notification process and enhanced clinical decision making. The percentage of patients discharged home with abnormal respiratory rates (10.9% vs. 5.9%, p = .31), abnormal temperatures (15.6% vs. 7.5%, p = .14), and abnormal heart rates (25% vs. 11.9%, p = .11) improved.

DISCUSSION

Creation and implementation of the BPA improved the abnormal vital sign communication process to providers at this single institution.

Triage and Prognostication of Cancer Patients Admitted to the Intensive Care Unit

Cancer remains a leading cause of morbidity and mortality. Advances in cancer screening, early detection, targeted therapies, and supportive care have led to improvements in outcomes and quality of life. The rapid increase in novel cancer therapies can cause life-threatening adverse events. The need for intensive care unit (ICU) care is projected to increase. Until 2 decades ago, cancer diagnosis often precluded ICU admission. Recently, substantial cancer survival has been achieved; therefore, ICU denial is not recommended. ICU resources are limited and expensive; hence, appropriate utilization is needed. This review focuses on triage and prognosis in critically ill cancer patients requiring ICU admission.