Using the National Early Warning Score (NEWS) outside acute hospital settings: a qualitative study of staff experiences in the West of England

Paediatric family activation rapid response (FARR) in tertiary healthcare organisations: Protocol for an online, multi-lingual, application (app) intervention development study

INTRODUCTION

At least 85% of unplanned admissions to critical care wards for children and young people (CYP) are associated with clinical deterioration. CYP and their families play an integral role in the recognition of deterioration. The Paediatric Critical Care Outreach Team (PCCOT) supports the reduction of avoidable harm through earlier recognition and treatment of the deteriorating child, acting as a welcome conduit between the multiprofessional teams, helping ensure that CYP gets the right care, at the right time and in the right place. This positions PCCOT well to respond to families who call for help as part of family activation.

AIM

This protocol details the methods and process of developing a family activation rapid response online application.

METHODS

This is a single-centre, sequential, multiple methods study design. Firstly, a systematic review of the international literature on rapid response interventions in paediatric family activation was conducted. Findings from the review aimed to inform the content for next stages; interviews/ focus groups and experience-based co-design (EBCD) workshops.

PARTICIPANTS

parents / caregivers whose children have been discharged or admitted to an acute care hospital and healthcare professionals who care for paediatric patients (CYP). During interviews and workshops participants' opinion, views and input will be sort on designing a family activation rapid response online-app, detailing content, aesthetics, broad functionality and multi-lingual aspects. Further areas of discussions include; who will use the app, access, appropriate language and terminology for use. A suitable app development company will be identified and will be part of the stakeholders present at workshops. Data obtained will be used to develop a multi-lingual paediatric family activation rapid response web based application prototype.

ETHICS AND DISSEMINATION

Full ethical approval was received from the Wales Research Ethics Committee 2. Cardiff; REC reference: 22/WA/0174. The findings will be made available to all stakeholders.

Early warning scores and trigger recommendations must be used with care in older home nursing care patients: Results from an observational study

AIMS

To explore modified early warning scores (MEWSs) and deviating vital signs among older home nursing care patients to determine whether the MEWS trigger recommendations were adhered to in cases of where registered nurses (RNs) suspected acute functional decline.

DESIGN

Prospective observational study with a descriptive, explorative design.

METHODS

Participants were included from April 2018 to February 2019. Demographic, health-related and clinical data were collected over a 3-month period.

RESULTS

In all, 135 older patients participated. Median MEWS (n = 444) was 1 (interquartile range (IQR) 1-2). Frequently deviating vital signs were respiratory (88.8%) and heart rate (15.3%). Median habitual MEWS (n = 51) was 1 (IQR 0-1). Deviating vital signs were respiratory (72.5%) and heart rate (19.6%). A significant difference between habitual MEWS and MEWS recorded in cases of suspected functional decline was found (p = 0.002). MEWS' trigger recommendations were adhered to in 68.9% of all MEWS measurements.

Tracking the National Early Warning Score 2 from Prehospital Care to the Emergency Department: A Prospective, Ambulance-Based, Observational Study

Aim of the study: To assess the prognostic ability of the National Early Warning Score 2 (NEWS2) at three time points of care -at the emergency scene (NEWS2-1), just before starting the transfer by ambulance to the hospital (NEWS2- 2), and at the hospital triage box (NEWS2-3)- to estimate in-hospital mortality after two days since the index event.Methods: Prospective, multicenter, ambulance-based, cohort ongoing study in adults (>18 years) consecutively attended by advanced life support (ALS) and evacuated with high-priority to the emergency departments (ED) between October 2018 and May 2021. Vital sign measures were used to calculate the NEWS2 score at each time point, then this score was entered in a logistic regression model as the single predictor. Two outcomes were considered: first, all-cause mortality of the patients within 2 days of presentation to EMS, and second, unplanned ICU admission. The calibration and scores comparison was performed by representing the predicted vs the observed risk curves according to NEWS score value.Results: 4943 patients were enrolled. Median age was 69 years (interquartile range 53- 81). The NEWS2-3 presented the better performance for all-cause two-day in-hospital mortality with an AUC of 0.941 (95% CI: 0.917-0.964), showing statistical differences with both the NEWS2-1 (0.872 (95% CI: 0.833-0.911); p < 0.003) and with the NEWS2- 2 (0.895 (95% CI: 0.866-0.925; p < 0.05). The calibration and scores comparison results showed that the NEWS2-3 was the best predictive score followed by the NEWS2-2 and the NEWS2-1, respectively.Conclusions: The NEWS2 has an excellent predictive performance. The score showed a very consistent response over time with the difference between "at the emergency scene" and "pre-evacuation" presenting the sharpest change with decreased threshold values, thus displaying a drop in the risk of acute clinical impairment.

NEWS2 in out-of-hospital settings, the ambulance and the emergency department

As more healthcare is provided in non-hospital settings, it is essential to support clinicians in recognising early signs of clinical deterioration to enable prompt intervention and treatment. There are intuitive reasons why the use of the National Early Warning Score 2 (NEWS2) in out-of-hospital settings may enhance the community response to acute illness by using a common language across healthcare. An additional advantage of the use of NEWS2 in community settings is that it is not disease specific and requires no expensive technology or great expertise to take a full set of observations that can be an indicator of clinical acuity. However, concerns have been expressed as NEWS2 was developed in acute hospital settings that it may not be applicable in community settings; this review shares some of the practical ways that NEWS2 can support clinical practice along with the emerging published evidence.

Improving sepsis recognition through use of the Sepsis Trust's community screening tool

Sepsis is associated with high levels of morbidity and mortality. All healthcare professionals have a responsibility to ensure they have sufficient knowledge to effectively screen patients for signs and symptoms of sepsis. In the community setting, screening for sepsis can be challenging, due to the complexity within the patient population and difficulties associated with observation for changes in the patient's condition. The Sepsis Trust community nursing sepsis screening tool provides decision-making support to community healthcare professionals, enabling them to make a rapid assessment for risk factors for sepsis, ensuring a proportionate, consistent and appropriate response. Through implementation of a decision-support tool within the clinical setting, it is likely that patients at risk of sepsis will be identified earlier, and patients will be escalated in a more consistent manner. This process of improving consistency in practice can improve patient outcomes, including mortality, morbidity and overall patient experience.

A new tool to measure acuity in the community: a case study

The provision of acute healthcare within patients own home (i.e. hospital in the home) is an important method of providing individualised patient-centred care that reduces the need for acute hospital admissions and enables early hospital discharge for appropriate patient groups. The Hospital in the Home (HitH) model of care ensures that this approach maximises patient safety and limits potential risk for patients. As HitH services have seen record numbers of patient referrals in the past 2 years, there is now a greater need to measure and understand the acuity and dependency levels of the caseload. Through an expert clinician development process at one NHS trust, aspects of procedural complexity, interdisciplinary working, risk stratification and comorbidities were used to quantify acuity and dependency. This paper uses a case study approach to present a new method of measuring this important concept.

National Early Warning Scores and COVID-19 deaths in care homes: an ecological time-series study

OBJECTIVES

To investigate whether National Early Warning Scores (NEWS/NEWS2) could contribute to COVID-19 surveillance in care homes.

SETTING

460 care home units using the same software package to collect data on residents, from 46 local authority areas in England.

PARTICIPANTS

6464 care home residents with at least one NEWS recording.

EXPOSURE MEASURE

29 656 anonymised person-level NEWS from 29 December 2019 to 20 May 2020 with component physiological measures: systolic blood pressure, respiratory rate, pulse rate, temperature and oxygen saturation. Baseline values for each measure calculated using 80th and 20th centile scores before March 2020.

OUTCOME MEASURE

Cross-correlation comparison of time series with Office for National Statistics weekly reported registered deaths of care home residents where COVID-19 was the underlying cause of death, and all other deaths (excluding COVID-19) up to 10 May 2020.

RESULTS

Deaths due to COVID-19 were registered from 23 March 2020 in the local authority areas represented in the study. Between 23 March 2020 and 10 May 2020, there were 5753 deaths (1532 involving COVID-19 and 4221 other causes). We observed a rise in the proportion of above-baseline NEWS beginning 16 March 2020, followed 2 weeks later by an increase in registered deaths (cross-correlation of r=0.82, p<0.05 for a 2 week lag) in corresponding local authorities. The proportion of above-baseline oxygen saturation, respiratory rate and temperature measurements also increased approximately 2 weeks before peaks in deaths.

CONCLUSIONS

NEWS could contribute to COVID-19 disease surveillance in care homes during the pandemic. Oxygen saturation, respiratory rate and temperature could be prioritised as they appear to signal rise in mortality almost as well as NEWS. This study reinforces the need to collate data from care homes, to monitor and protect residents' health. Further work using individual level outcome data is needed to evaluate the role of NEWS in the early detection of resident illness.

Use of the National Early Warning Score in community nursing: a scoping review

People in the UK are living longer and with multi-morbidities, increasing the size, complexity and acuity of Community Nursing caseloads. Nurses visiting infrequently and inconsistently on a task-focused basis need an objective method by which to identify / quantify physical deterioration for early treatment avoiding crisis and hospital admission. The National Early Warning Score (NEWS), is the most recognised tool for identification of deterioration in acute settings but is not validated for community use. Using published frameworks for scoping review and evaluation, this study aims to explore the current evidence for use of NEWS in community settings. Although there is work to be done, particularly in terms of frequency of scoring and response, this study identifies benefits in communication and prioritisation of care as well as sensitivity, particularly in predicting poor outcomes. The identified barriers to use include integration into practice and perceived dissonance with clinical judgement.

Experiences of a National Early Warning Score (NEWS) intervention in care homes during the COVID-19 pandemic: a qualitative interview study

BACKGROUND

The COVID-19 pandemic has taken a heavy toll on the care home sector, with residents accounting for up to half of all deaths in Europe. The response to acute illness in care homes plays a particularly important role in the care of residents during a pandemic. Digital recording of a National Early Warning Score (NEWS), which involves the measurement of physical observations, started in care homes in one area of England in 2016. Implementation of a NEWS intervention (including equipment, training and support) was accelerated early in the pandemic, despite limited evidence for its use in the care home setting.

OBJECTIVES

To understand how a NEWS intervention has been used in care homes in one area of North-East England during the COVID-19 pandemic, and how it has influenced resident care, from the perspective of stakeholders involved in care delivery and commissioning.

METHODS

A qualitative interview study with care home (n=10) and National Health Service (n=7) staff. Data were analysed using thematic analysis.

RESULTS

Use of the NEWS intervention in care homes in this area accelerated during the COVID-19 pandemic. Stakeholders felt that NEWS, and its associated education and support package, improved the response of care homes and healthcare professionals to deterioration in residents' health during the pandemic. Healthcare professionals valued the ability to remotely monitor resident observations, which facilitated triage and treatment decisions. Care home staff felt empowered by NEWS, providing a common clinical language to communicate concerns with external services, acting as an adjunct to staff intuition of resident deterioration.

CONCLUSIONS

The NEWS intervention formed an important part of the care home response to COVID-19 in the study area. Positive staff perceptions now need to be supplemented with data on the impact on resident health and well-being, workload, and service utilisation, during the pandemic and beyond.

National early warning score on admission as risk factor for invasive mechanical ventilation in COVID-19 patients: A STROBE-compliant study

The coronavirus disease (COVID-19) has become a global pandemic. Invasive mechanical ventilation is recommended for the management of patients with COVID-19 who have severe respiratory symptoms. However, various complications can develop after its use. The efficient and appropriate management of patients requires the identification of factors associated with an aggravation of COVID-19 respiratory symptoms to a degree where invasive mechanical ventilation becomes necessary, thereby enabling clinicians to prevent such ventilation. This retrospective study included 138 inpatients with COVID-19 at a tertiary hospital. We evaluated the differences in the demographic and clinical data between 27 patients who required invasive mechanical ventilation and 111 patients who did not. Multivariate logistic regression analysis indicated that the duration of fever, national early warning score (NEWS), and lactate dehydrogenase (LDH) levels on admission were significantly associated with invasive mechanical ventilation in this cohort. The optimal cut-off values were: fever duration ≥1 day (sensitivity 100.0%, specificity 54.95%), NEWS ≥7 (sensitivity 72.73%, specificity 92.52%), and LDH >810 mg/dL (sensitivity 56.0%, specificity 90.29%). These findings can assist in the early identification of patients who will require invasive mechanical ventilation. Further studies in larger patient populations are recommended to validate our findings.

Factors associated with potentially missed acute deterioration in primary care: cohort study of UK general practices

Background

In the UK, while most primary care contacts are uncomplicated, safety incidents do occur and result in patient harm, for example, failure to recognise a patient’s deterioration in health.

Aim

To determine the patient and healthcare factors associated with potentially missed acute deterioration in health.

Design and setting

Cohort of patients registered with English Clinical Practice Research Datalink general practices between 1 April 2014 and 31 December 2017 with linked hospital data.

Method

A potentially missed acute deterioration was defined as a patient having a self-referred admission to hospital having been seen in primary care by a GP in the 3 days beforehand. All diagnoses and subsets of commonly-reported missed conditions were analysed..

Results

A total of 116 097 patients contacted a GP 3 days before an emergency admission. Patients with sepsis (adjusted odds ratio [aOR] 1.09, 95% confidence interval [CI] = 1.01 to 1.18) or urinary tract infections (aOR 1.09, 95% CI = 1.04 to 1.14) were more likely to self-refer. The duration of GP appointments was associated with self-referral. On average, a 5-minute increase in appointment time resulted in a 10% decrease in the odds of self-referred admissions (aOR 0.90, 95% CI = 0.89 to 0.91). Patients having a telephone consultation (compared with face-to-face consultation) (aOR 1.14, 95% CI = 1.11 to 1.18) previous health service use, and presence of comorbidities were also associated with self-referred admission.

Conclusion

Differentiating acute deterioration from self-limiting conditions can be difficult for clinicians, particularly in patients with sepsis, urinary tract infections, or long-term conditions. The findings of this study support the call for longer GP consultations and caution against reliance on telephone consultations in primary care; however, more research is needed to understand the underlying mechanisms.

The Modified National Early Warning Score (m-NEWS) for COVID-19-Infected Patient Evaluation: a Proof-of-Concept

The second wave of Sars CoV 2 pandemic in Italy still represents an important concern for the Italian health system (IHS). Despite the experience gained during the first phase of the pandemic in January 2020, COVID-19 patients are still arising, putting on a strain resources of local authorities and emergency services. The aim of this research project is to analyze the feasibility of using the modified National Early Warning Score (m-NEWS) as a way to rapidly identify COVID-19-infected patient with high risk of clinical deterioration, helping the clinical pre-evaluation in a moment of overwhelming request for the Italian out-of-hospital emergency system (Perlini et al., Intern Emerg Med 15(5):825–833, 2020) as during the initial coronavirus outbreak.

Implementation of the National Early Warning Score in UK care homes: a qualitative evaluation

BACKGROUND

The National Early Warning Score (NEWS) is a tool for identifying and responding to acute illness. When used in care homes, staff measure residents' vital signs and record them on a tablet computer, which calculates a NEWS to share with health services. This article outlines an evaluation of NEWS implementation in care homes across one clinical commissioning group area in northern England.

AIM

To identify challenges to implementation of NEWS in care homes.

DESIGN AND SETTING

Qualitative analysis of interviews conducted with 15 staff members from six care homes, five health professionals, and one clinical commissioning group employee.

METHOD

Interviews were intended to capture people's attitudes and experiences of using the intervention. Following an inductive thematic analysis, data were considered deductively against normalisation process theory constructs to identify the challenges and successes of implementing NEWS in care homes.

RESULTS

Care home staff and other stakeholders acknowledged that NEWS could enhance the response to acute illness, improve communication with the NHS, and increase the confidence of care home staff. However, the implementation did not account for the complexity of either the intervention or the care home setting. Challenges to engagement included competing priorities, insufficient training, and shortcomings in communication.

CONCLUSION

This evaluation highlights the need to involve care home staff and the primary care services that support them when developing and implementing interventions in care homes. The appropriateness and value of NEWS in non-acute settings requires ongoing monitoring.

The prognostic value of national early warning scores (NEWS) during transfer of care from community settings to hospital: a retrospective service evaluation

Background

The National Early Warning Score (NEWS) calculated from physiological observations provides a simple away to identify and respond to the deteriorating patient. There is increasing interest in the application of NEWS to facilitate referrals from the community.

Aim

To establish whether elevated NEWS are associated with adverse outcomes at 5 and 30 days when obtained in a community setting at the time of transfer to an acute setting.

Design & setting

A retrospective service evaluation was undertaken using a database of emergency admissions to secondary care from two NHS district general hospitals within the South of England between January 2018 and April 2019.

Method

The performance of NEWS recorded in a community setting to predict death or critical care admission at 5 and 30 days was calculated using established thresholds.

Results

2786 referrals from primary care were analysed. The 5 day and 30 day mortality was 2.2% (1.7 to 2.8) and 7.1% (6.2 to 8.1). The prevalence of the composite outcome was 3.4% (2.8 to 4.2) at 5 days and 8.5% (7.5 to 9.6) at 30 days. The risk of adverse outcomes increased incrementally with increasing NEWS. When calculated at the point of referral from primary care the positive predictive value of death at 5 and 30 days was 15% (95% confidence intervals [CI] = 12 to 19) and 23% (95% CI = 17 to 30) in the high-risk NEWS group.

Conclusion

Elevated NEWS obtained in the community during the process of emergency admission are associated with adverse outcomes. Communicating NEWS may allow downstream care to be better calibrated to risk.

Efficacy of prehospital National Early Warning Score to predict outpatient disposition at an emergency department of a Japanese tertiary hospital: a retrospective study

OBJECTIVES

The National Early Warning Score (NEWS) was originally developed to assess hospitalised patients in the UK. We examined whether the NEWS could be applied to patients transported by ambulance in Japan.

DESIGN

This retrospective study assessed patients and calculated the NEWS from paramedic records. Emergency department (ED) disposition data were categorised into the following groups: discharged from the ED, admitted to the ward, admitted to the intensive care unit (ICU) or died in the ED. The predictive performance of NEWS for patient disposition was assessed using receiver operating characteristic curve analysis. Patient dispositions were compared among NEWS-based categories after adjusting for age, sex and presence of traumatic injury.

SETTING

A tertiary hospital in Japan.

PARTICIPANTS

Overall, 2847 patients transported by ambulance between April 2017 and March 2018 were included.

RESULTS

The mean (±SD) NEWS differed significantly among patients discharged from the ED (n=1330, 3.7±2.9), admitted to the ward (n=1263, 60.3±3.8), admitted to the ICU (n=232, 9.4±4.0) and died in the ED (n=22, 110.7±2.9) (p<0.001). The prehospital NEWS C-statistics (95% CI) for admission to the ward, admission to the ICU or death in the ED; admission to the ICU or death in the ED; and death in the ED were 0.73 (0.72-0.75), 0.81 (0.78-0.83) and 0.90 (0.87-0.93), respectively. After adjusting for age, sex and trauma, the OR (95% CI) of admission to the ICU or death in the ED for the high-risk (NEWS ≥7) and medium-risk (NEWS 5-6) categories was 13.8 (8.9-21.6) and 4.2 (2.5-7.1), respectively.

CONCLUSION

The findings from this Japanese tertiary hospital setting showed that prehospital NEWS could be used to identify patients at a risk of adverse outcomes. NEWS stratification was strongly correlated with patient disposition.

Association between National Early Warning Scores in primary care and clinical outcomes: an observational study in UK primary and secondary care

Background

NHS England has mandated use of the National Early Warning Score (NEWS), more recently NEWS2, in acute settings, and suggested its use in primary care. However, there is reluctance from GPs to adopt NEWS/NEWS2.

Aim

To assess whether NEWS calculated at the point of GP referral into hospital is associated with outcomes in secondary care.

Design and setting

An observational study using routinely collected data from primary and secondary care.

Method

NEWS values were prospectively collected for 13 047 GP referrals into acute care between July 2017 and December 2018. NEWS values were examined and multivariate linear and logistic regression used to assess associations with process measures and clinical outcomes.

Results

Higher NEWS values were associated with faster conveyance for patients travelling by ambulance, for example, median 94 minutes (interquartile range [IQR] 69–139) for NEWS ≥7; median 132 minutes, (IQR 84–236) for NEWS = 0 to 2); faster time from hospital arrival to medical review (54 minutes [IQR 25–114] for NEWS ≥7; 78 minutes [IQR 34–158] for NEWS = 0 to 2); as well as increased length of stay (5 days [IQR 2–11] versus 1 day [IQR 0–5]); intensive care unit admissions (2.0% versus 0.5%); sepsis diagnosis (11.7% versus 2.5%); and mortality, for example, 30-day mortality 12.0% versus 4.1% for NEWS ≥7 versus NEWS = 0 to 2, respectively. On average, for patients referred without a NEWS value (NEWS = NR), most clinical outcomes were comparable with patients with NEWS = 3 to 4, but ambulance conveyance time and time to medical review were comparable with patients with NEWS = 0 to 2.

Conclusion

This study has demonstrated that higher NEWS values calculated at GP referral into hospital are associated with a faster medical review and poorer clinical outcomes.

Implementation of the National Early Warning Score in patients with suspicion of sepsis: evaluation of a system-wide quality improvement project

Background

The National Early Warning Score (NEWS) was introduced to standardise early warning scores (EWS) in England. It has been recommended that NEWS should be used in pre-hospital care but there is no published evidence that this improves outcomes. In 2015, the West of England Academic Health Science Network region standardised to NEWS across all healthcare settings. Calculation of NEWS was recommended for acutely unwell patients at referral into secondary care.

Aim

To evaluate whether implementation of NEWS across a healthcare system affects outcomes, specifically addressing the effect on mortality in patients with suspicion of sepsis (SOS).

Design and setting

A quality improvement project undertaken across the West of England from March 2015 to March 2019, with the aim of standardising to NEWS in secondary care and introducing NEWS into community and primary care.

Method

Data from the national dashboard for SOS for the West of England were examined over time and compared to the rest of England. Quality improvement methodology and statistical process control charts were used to measure improvement.

Results

There was a reduction in mortality in the SOS cohort in the West of England, which was not seen in the rest of England over the time period of the project. Admissions did not increase. By March 2019, the West of England had the lowest mortality in the SOS cohort in England.

Conclusion

To the authors’ knowledge, this is the first study demonstrating that use of NEWS in pre-hospital care is associated with improved outcomes in patients with SOS.

Early warning scores for detecting deterioration in adult hospital patients: systematic review and critical appraisal of methodology

OBJECTIVE

To provide an overview and critical appraisal of early warning scores for adult hospital patients.

DESIGN

Systematic review.

DATA SOURCES

Medline, CINAHL, PsycInfo, and Embase until June 2019.

ELIGIBILITY CRITERIA FOR STUDY SELECTION

Studies describing the development or external validation of an early warning score for adult hospital inpatients.

RESULTS

13 171 references were screened and 95 articles were included in the review. 11 studies were development only, 23 were development and external validation, and 61 were external validation only. Most early warning scores were developed for use in the United States (n=13/34, 38%) and the United Kingdom (n=10/34, 29%). Death was the most frequent prediction outcome for development studies (n=10/23, 44%) and validation studies (n=66/84, 79%), with different time horizons (the most frequent was 24 hours). The most common predictors were respiratory rate (n=30/34, 88%), heart rate (n=28/34, 83%), oxygen saturation, temperature, and systolic blood pressure (all n=24/34, 71%). Age (n=13/34, 38%) and sex (n=3/34, 9%) were less frequently included. Key details of the analysis populations were often not reported in development studies (n=12/29, 41%) or validation studies (n=33/84, 39%). Small sample sizes and insufficient numbers of event patients were common in model development and external validation studies. Missing data were often discarded, with just one study using multiple imputation. Only nine of the early warning scores that were developed were presented in sufficient detail to allow individualised risk prediction. Internal validation was carried out in 19 studies, but recommended approaches such as bootstrapping or cross validation were rarely used (n=4/19, 22%). Model performance was frequently assessed using discrimination (development n=18/22, 82%; validation n=69/84, 82%), while calibration was seldom assessed (validation n=13/84, 15%). All included studies were rated at high risk of bias.

CONCLUSIONS

Early warning scores are widely used prediction models that are often mandated in daily clinical practice to identify early clinical deterioration in hospital patients. However, many early warning scores in clinical use were found to have methodological weaknesses. Early warning scores might not perform as well as expected and therefore they could have a detrimental effect on patient care. Future work should focus on following recommended approaches for developing and evaluating early warning scores, and investigating the impact and safety of using these scores in clinical practice.

SYSTEMATIC REVIEW REGISTRATION

PROSPERO CRD42017053324.

Prehospital Point-Of-Care Lactate Increases the Prognostic Accuracy of National Early Warning Score 2 for Early Risk Stratification of Mortality: Results of a Multicenter, Observational Study

The objective of this study was to assess whether the use of prehospital lactate (pLA) can increase the prognostic accuracy of the National Early Warning Score 2 (NEWS2) to detect the risk of death within 48 h. A prospective, multicenter study in adults treated consecutively by the emergency medical services (EMS) included six advanced life support (ALS) services and five hospitals. Patients were assigned to one of four groups according to their risk of mortality (low, low-medium, medium, and high), as determined by the NEWS2 score. For each group, the validity of pLA in our cohort was assessed by the area under the curve (AUC) of the receiver operating characteristic (ROC) curve. In this study, 3081 participants with a median age of 69 years (Interquartile range (IQR): 54-81) were included. The two-day mortality was 4.4% (137 cases). The scale derived from the implementation of the pLA improved the capacity of the NEWS2 to discriminate low risk of mortality, with an AUC of 0.910 (95% CI: 0.87-0.94; p < 0.001). The risk stratification provided by the NEWS2 can be improved by incorporating pLA measurement to more accurately predict the risk of mortality in patients with low risk.

A validation of machine learning-based risk scores in the prehospital setting

BACKGROUND

The triage of patients in prehospital care is a difficult task, and improved risk assessment tools are needed both at the dispatch center and on the ambulance to differentiate between low- and high-risk patients. This study validates a machine learning-based approach to generating risk scores based on hospital outcomes using routinely collected prehospital data.

METHODS

Dispatch, ambulance, and hospital data were collected in one Swedish region from 2016-2017. Dispatch center and ambulance records were used to develop gradient boosting models predicting hospital admission, critical care (defined as admission to an intensive care unit or in-hospital mortality), and two-day mortality. Composite risk scores were generated based on the models and compared to National Early Warning Scores (NEWS) and actual dispatched priorities in a prospectively gathered dataset from 2018.

RESULTS

A total of 38203 patients were included from 2016-2018. Concordance indexes (or areas under the receiver operating characteristics curve) for dispatched priorities ranged from 0.51-0.66, while those for NEWS ranged from 0.66-0.85. Concordance ranged from 0.70-0.79 for risk scores based only on dispatch data, and 0.79-0.89 for risk scores including ambulance data. Dispatch data-based risk scores consistently outperformed dispatched priorities in predicting hospital outcomes, while models including ambulance data also consistently outperformed NEWS. Model performance in the prospective test dataset was similar to that found using cross-validation, and calibration was comparable to that of NEWS.

CONCLUSIONS

Machine learning-based risk scores outperformed a widely-used rule-based triage algorithm and human prioritization decisions in predicting hospital outcomes. Performance was robust in a prospectively gathered dataset, and scores demonstrated adequate calibration. Future research should explore the robustness of these methods when applied to other settings, establish appropriate outcome measures for use in determining the need for prehospital care, and investigate the clinical impact of interventions based on these methods.

Distributions of the National Early Warning Score (NEWS) across a healthcare system following a large-scale roll-out

Background

Early warning scores (EWS) were developed in acute hospital settings to improve recognition and response to patient deterioration. In 2012, the UK Royal College of Physicians developed the National Early Warning Score (NEWS) to standardise EWS across the NHS. Its use was also recommended outside acute hospital settings; however, there is limited information about NEWS in these settings. From March 2015, NEWS was implemented across the healthcare system in the West of England, with the aim that NEWS would be calculated for all patients prior to referral into acute care.

Aim

To describe the distribution and use of NEWS in out-of-hospital settings for patients with acute illness or long-term conditions, following system wide implementation.

Method

Anonymised data were obtained from 115 030 emergency department (ED) attendances, 1 137 734 ambulance electronic records, 31 063 community attendances and 15 160 general practitioner (GP) referrals into secondary care, in the West of England. Descriptive statistics are presented.

Results

Most attendance records had NEWS=0–2: 80% in ED, 67% of ambulance attendances and 72% in the community. In contrast, only 8%, 18% and 11% of attendances had NEWS ≥5 (the trigger for escalation of care in-hospital), respectively. Referrals by a GP had higher NEWS on average (46% NEWS=0–2 and 30% NEWS ≥5). By April 2016, the use of NEWS was reasonably stable in ED, ambulance and community populations, and still increasing for GP referrals.

Conclusions

NEWS ≥5 occurred in less than 20% of ED, ambulance and community populations studied and 30% of GP referrals. This suggests that in most out-of-hospital settings studied, high scores are reasonably uncommon.