Early Warning Scoring System Research Articles

Clinical features of coronavirus disease 2019 (COVID-19) in a cohort of patients with disability due to spinal cord injury.

Study designCohort study of patients with spinal cord injury (SCI).ObjectivesTo describe the clinical and analytical features of a coronavirus disease 2019 (Covid-19) infected cohort with SCI to enable accurate diagnosis and to outline prevention measures.SettingThis study was conducted at the National Hospital for Paraplegics (Toledo, Spain).MethodsA cohort analysis of seven patients with SCI infected by Covid-19 was performed. Diagnosis was confirmed with reverse transcriptase polymerase chain reaction (RT-PCR) of nasal exudate or sputum samples. Clinical, analytical, and radiographic findings were registered.ResultsRT-PCR detected COVID-19 infection in all patients, affecting males and people with a cervical level of injury more often (five out of seven). The average delay for diagnostic confirmation was 4 days (interquartile range, 1–10). Fever was the most frequent symptom (six out of seven). The second most common symptom was asthenia (four out of seven), followed by dyspnea, cough, and expectoration (three out of seven for each symptom). The Modified Early Warning System score for Covid-19 severity rating was classified as severe in five out of seven cases. All but one patient showed radiological alterations evident in chest X-rays at the time of diagnosis. All patients recovered gradually.ConclusionOur patients with SCI and Covid-19 infection exhibited fewer symptoms than the general population. Furthermore, they presented similar or greater clinical severity. The clinical evolution was not as pronounced as had been expected. This study recommends close supervision of the SCI population to detect early compatible signs and symptoms of Covid-19 infection.

Analysis of Implementation of EWSS (Early Warning Score Systems) Against AvLos (Average Length of Stay) and the Trust of Patients in Inpatient Installation at Jombang General Hospital

Hospitals are required to always improve the quality of service provided to patients. These challenges have forced the hospital to develop its ability to manifest in various aspects of health care quality responsible. One of them by applying the assessment and early detection in patients kegawatan as well as the critical state of activation becomes very important. Quick and proper response to a nurse against the worsening conditions of patients giving a great impact to the quality of the quality of service provided. The purpose of this research is to analyze the implementation of Early Warning systems (EWSS) Score against AvLOS and trust patients in Inpatient installation at Jombang General Hospitals. The research design was analytic observational with a quantitative approach. Research variables i.e. implementation of EWSS as independent variables. AvLos and trust patients as the dependent variable. The population of this entire research nurses in Inpatient installation at Jombang General Hospitals as much as 135 nurses, patients and families of patients who are being treated in Inpatient installation at Jombang General Hospitals Jombang. Samples taken with the cluster random sampling technique as much as 101 respondents. Data is collected with instruments ceklist and processed in coding, editing, tabulating and scoring as well as tested with logistics regression test. Logistic regression results indicate that partially and simultaneously show that the value of p values < 0.05 so that there were the implementation of Early Warning systems (EWSS) Score against AvLOS and trust of the patient, and the simultaneous influence of 83.2%. The existence of implementation of EWSS in patients with good then early detection and response officers can be done in a proper and effective against the condition and the healing of patients and can shorten the day care patients, so that it can affect the confidence and trust family and patient in receiving health services in the hospital

Development and validation of early warning score system: A systematic literature review.

This review aims to: 1) evaluate the quality of model reporting, 2) provide an overview of methodology for developing and validating Early Warning Score Systems (EWSs) for adult patients in acute care settings, and 3) highlight the strengths and limitations of the methodologies, as well as identify future directions for EWS derivation and validation studies. A systematic search was conducted in PubMed, Cochrane Library, and CINAHL. Only peer reviewed articles and clinical guidelines regarding developing and validating EWSs for adult patients in acute care settings were included. 615 articles were extracted and reviewed by five of the authors. Selected studies were evaluated based on the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) checklist. The studies were analyzed according to their study design, predictor selection, outcome measurement, methodology of modeling, and validation strategy. A total of 29 articles were included in the final analysis. Twenty-six articles reported on the development and validation of a new EWS, while three reported on validation and model modification. Only eight studies met more than 75% of the items in the TRIPOD checklist. Three major techniques were utilized among the studies to inform their predictive algorithms: 1) clinical-consensus models (n=6), 2) regression models (n=15), and 3) tree models (n=5). The number of predictors included in the EWSs varied from 3 to 72 with a median of seven. Twenty-eight models included vital signs, while 11 included lab data. Pulse oximetry, mental status, and other variables extracted from electronic health records (EHRs) were among other frequently used predictors. In-hospital mortality, unplanned transfer to the intensive care unit (ICU), and cardiac arrest were commonly used clinical outcomes. Twenty-eight studies conducted a form of model validation either within the study or against other widely-used EWSs. Only three studies validated their model using an external database separate from the derived database. This literature review demonstrates that the characteristics of the cohort, predictors, and outcome selection, as well as the metrics for model validation, vary greatly across EWS studies. There is no consensus on the optimal strategy for developing such algorithms since data-driven models with acceptable predictive accuracy are often site-specific. A standardized checklist for clinical prediction model reporting exists, but few studies have included reporting aligned with it in their publications. Data-driven models are subjected to biases in the use of EHR data, thus it is particularly important to provide detailed study protocols and acknowledge, leverage, or reduce potential biases of the data used for EWS development to improve transparency and generalizability.

Anticipating Pediatric Patient Transfers From Intermediate to Intensive Care.

To explore characteristics of patients who were admitted to the intermediate care (IC) unit at a tertiary academic institution. In particular, we sought to compare the characteristics of IC patients who were transferred with the characteristics of those who were not transferred to PICU care and evaluate predictors of patient transfer. Data were collected on all admitted IC patients between July 2016 and June 2018. Patients whose index IC admission was from the PICU were excluded. Data collected included demographics and physiologic characteristics: heart rate, respiratory rate, temperature, oxygen therapy, as well as Bedside Pediatric Early Warning System (BPEWS) score. In this time period, 427 eligible patient visits occurred, with 66 patients (15.46%) being transferred to the PICU. Patients were commonly transferred early in their IC course (1.41 days into admission [0.66-3.87]); transferred patients had higher median admission BPEWS scores (7 [4.25-9] vs 5 [3-7]; P < .01). In the univariate analysis, no individual physiologic characteristic was predictive for transfer. In the multivariate analysis, BPEWS (P < .001) and need for any form of respiratory support (P = .04) were significant predictive factors for transfer (R 2 = 0.56). The need for close monitoring of physiologic parameters remains paramount, especially in the first 48 hours of admission, in predicting the need for transfer from the IC to PICU. The need for any form of respiratory support is predictive of transfer. Situational awareness and assessment including BPEWS score is of critical importance.

How comorbidities impact Early Warning Score as a predictor of 7-day mortality.

Early Warning Score systems are used to monitor patients at risk of deterioration. How comorbidities impact Early Warning Score's ability to predict short-term mortality in the emergency department is not fully elucidated. The aim of the study was to investigate how comorbidities impact Early Warning Score as predictor of 7-day mortality. This is an observational cohort study of adult emergency department patients attending one of the five emergency departments in Central Region Denmark from 1 March 2015 to 31 May 2015. Charlson Comorbidity Index was used as a measure of comorbidities. Logistic regression was used to calculate the odds ratio for 7-day mortality. Patients were compared in three groups: Charlson Comorbidity Index: 0, 1-2, 3+. A total of 30 060 adult patients attended one of the five emergency departments. Nineteen thousand one hundred twenty-three patients were included. Charlson Comorbidity Index 3+ patients presenting with Early Warning Score 0, 1-2 or 3-4 had significantly higher odds ratio of 7-day mortality compared to Charlson Comorbidity Index 0 patients with equal Early Warning Score. For patients with Early Warning Score 5+, Charlson Comorbidity Index -status had no significant impact on 7-day mortality after adjusting for age. In patients presenting with lower acuity (Early Warning Score 0-4) Charlson Comorbidity Index has a significant impact on 7-day mortality regardless of Early Warning Score. Including Charlson Comorbidity Index status in Early Warning Score or adjusting for Charlson Comorbidity Index -status could increase the predictive value of Early Warning Score in predicting 7-day mortality.

Single blood pressure chart for children up to 13 years to improve the recognition of hypertension based on existing normative data

ObjectiveTo produce a single ‘growth-chart-style’ blood pressure (BP) chart with clear diagnostic thresholds to assist paediatricians to make prompt and accurate diagnoses of hypertension.DesignThe well-established but complex published data on...

Sepsis and Early Warning Score Systems

Sepsis is a significant cause of morbidity and mortality worldwide. Early diagnosis and management of sepsis is critical to improving patient prognoses. Surviving sepsis campaign guidelines issued in 2016 encourage health institutions to establish a screening system to identify patients who are at risk of sepsis. In 2012, the Royal College of Physicians in the UK began to advocate replacing local and regional scoring systems with the National Early Warning Score (NEWS), which is optimized for the identification of sepsis. Although many hospitals continue to use other scoring systems, all healthcare organizations are being encouraged to adopt a standardized scoring system to better promote patient safety by facilitating rapid diagnoses and screenings and thus, subsequently, improving decision-making by clinical staffs. NEWS plays a very important role in the treatment of sepsis patients. Although research findings related to this scoring system differ somewhat, they provide an important reference for clinical nursing staffs. Intelligent systems are not comprehensive in terms of their capabilities. However, combining human intelligence with system features and further optimizing the system should contribute significantly to the reduction of mortality risk in patients with sepsis.

The critically ill mother: Recognition and management (who, where and how?)

There is an ongoing debate about the management of the critically ill mother, notably with regards to who should manage this group of patients (the intensivist, the obstetric anaesthetist, or the obstetrician?) and where is the ideal place to manage them (labour ward, obstetric high dependency unit or the intensive care unit?). To make the most appropriate choice, an understanding of how to recognise maternal critical illness is paramount. Using the modified early obstetric warning system score (MEOWS) for obstetric patients is a useful tool 1. MEOWS looks at additional parameters to the standard early warning systems parameters with modified triggers to suit the altered physiology in the pregnant patient. Other predictors like APACHE and SOFA scores may also be used to predict maternal mortality 2. Data from several national audit and surveillance programs such as MBRRACE-UK (Mothers and Babies: Reducing Risk Through Audits and Confidential Enquiries across the UK) 3, UKOSS (The UK Obstetric Surveillance System), and ICNARC (Intensive Care National Audit & Research Centre) are used to aid the understanding of why mothers die in childbirth and up to six weeks postpartum and which critically ill mothers are admitted to the intensive care unit and the reason for their admission 4. Audit reports show that a significant number of deaths reported in the maternal mortality reports are associated with suboptimal care. There is a great need for an evidence-based triage system for the critically ill obstetric patient in order to help clinicians direct them to the appropriate level of care and avoid situations of suboptimal care. Regionalizing maternal critical care may help develop this triage system by increasing the exposure to such patients. Deciding on who should manage these patients will depend on the level of training and expertise of the team members involved in the management on how to detect an acutely deteriorating mother. The team members should include obstetricians, anaesthetists, intensivists, intensive care nurses and midwives. The training can be achieved using different educational approaches that are competency-based to improve the knowledge and skills in detecting signs of deterioration in order to take the appropriate actions. Multidisciplinary teams should train together using simulation-based learning focusing on human factors and communication skills 5. Deciding on where these patients should be managed will depend on the level of organ support and monitoring available as well as the access to support services such as obstetric and neonatal services, regardless of what the terminology of that location is. The different models of delivering care to the critically ill obstetric patient with the different requirements for these areas are highlighted in Table 1. Taking all the previous factors into consideration will help find the answer to the WHO, WHERE and HOW question.

Early Intervention Using the National Early Warning Scoring System for Hematological Mallignancy and HSCT Patients

Topic Significance & Study Purpose/Background/Rationale It was identified that the systemic inflammatory response syndrome (SIRS) criteria were overly sensitive in detecting clinical deterioration the malignant hematology and cellular therapy (HMCT) population. This may create inconsistency in the activation of rapid response team (RRT) with patient decline. Objectives The aim of this project is to evaluate the implementation and use of the National Early Warning Scoring (NEWS) system in HMCT patients. The registered nurse calculates the NEWS score from the vital signs, assessment, and implements actions which may include activation of the RRT and assessment of patient for transfer to intensive care unit (ICU). Methods, Intervention, & Analysis Retrospective data collection from 2016 - 2017 was used for this project. Findings & Interpretation A statically significant decrease in the mean time between patients meeting a NEWS score of 5 or greater and activation of RRT was noted in the post-implementation group. An increase in frequency of escalation of care to the ICU for patients with multiple RRT activations during admission was statistically significant (U=296, p=0.014, r=0.31). Use of the NEWS tool has demonstrated success in identifying patients who are experiencing clinical deterioration and improved response time to initiation of additional evaluation and treatments. Discussion & Implications Use of the NEWS scoring tool results in early and consistent intervention with clinically deteriorating patients. The appropriate escalation of care to ICU setting and timely intervention with declining patients to prevent unnecessary ICU transfer is now expected in these highly vulnerable patients.

Analysis of the effect of improved early warning score on the theory and practice interactive infiltration training model for surgical internship nurses

Objective To study the application value of improved early warning score in the practice of theory and practice interactive infiltration training mode for neurosurgery interns. Methods A total of 84 neurosurgery interns were selected as study samples and randomly divided into control group and intervention group by random double blind method, each group had 42 interns. The control group adopted the interactive infiltration model of theory and practice. The Intervention group adopted the interactive infiltration training mode of theory and practice under the improved early warning scoring system design. Statistics and comparison of the performance of the two groups of trainee nurses, the evaluation of teaching teachers and patients, the self-evaluation of trainee nurses, and the occurrence of nursing errors during the internship. Results The related examination results between the two groups showed significance (t value was 7.182,5.462,5.530, P<0.01). The evaluation for nursing students by teachers and patients also showed significant difference (t value was 6.989-8.790, P<0.01). The incidence of error event in the intervention group was 9.52% (4/42), lower than that in the control group [30.95% (13/42)]. There was statistical difference between two groups (χ2 value was 14.227, P<0.01). Conclusions The application of the improved early warning score in the theory and practice interactive infiltration training mode of neurosurgery interns can improve the satisfaction of teachers and patients to interns, enhance the self-satisfaction of interns and reduce the incidence of nursing errors of interns. Key words: Improved early warning score; Intensive care unit; Internship nurse; Theory and practice; Interactive infiltration

Development of a preoperative Early Warning Scoring System to identify highly suspect COVID-19 patients.

Background and Aims:The coronavirus disease 2019 (COVID-19) is spreading at an unprecedented speed. Lack of resources to test every patient scheduled for surgery and false negative test results contribute to considerable stress to anesthesiologists, along with health risks to both caregivers and other patients. The study aimed to develop an early warning screening tool to rapidly detect 'highly suspect' among the patients scheduled for surgery.Methods:Review of literature was conducted using terms 'coronavirus' OR 'nCoV 2019' OR 'SARS-CoV-2' OR 'COVID-19' AND 'clinical characteristics' in PUBMED and MedRxiv. Suitable articles were analysed for symptoms and investigations commonly found in COVID-19 patients. Additionally, COVID-19 patient's symptomatology and investigation profiles were obtained through a survey from 20 COVID-19 facilities in India. Based on literature evidence and the survey information, an Early Warning Scoring System was developed.Results:Literature search yielded 3737 publications, of which 195 were considered relevant. Of these 195 studies, those already included in the meta-analyses were not considered for independent assessment. Based on the combined data from meta-analyses and survey, risk factors of COVID-19 disease identified were as follows: history of exposure, fever, cough, myalgias, lymphocytopaenia, elevated C-reactive protein (CRP)/lactate dehydrogenase (LDH) and radiographic infiltrates.Conclusion:Development of this Early Warning Scoring System for preoperative screening of patients may help in identifying 'highly suspect' COVID-19 patients, alerting the physician and other healthcare workers on the need for adequate personal protection and also to implement necessary measures to prevent cross infection and contamination during the perioperative period.

Is age-adjusted Modified Early Warning Score upon admission a relevant prognostic tool for final outcome?

Introduction. Early warning scoring systems are important for timely identification of the critically ill, but are they a relevant prognostic tool? Our objective was to test if Modified Early Warning Score (MEWS), lactate, and base excess (BE) have any prognostic value in high dependency unit patients. Methods. This was a prospective observational study that included 364 patients treated at a respiratory high dependency unit. The values of MEWS, lactate, and BE at admission were recorded with patients? age, sex, and comorbidities. Negative outcome was defined as death or transfer to the intensive care unit. Independent predictors of negative outcome were identified with the use of multivariable logistic regression. Results. Of 369 patients, 203 (55%) were male. Mean age was 62 ? 16. There were 138 (37.4%) patients with negative outcome: 27.37% died, while 10.03% patients required intensive care unit transfer. The median length of hospital stay was 13 days (IQR 7?15). Patients with negative outcome had a significantly higher MEWS (3.68 ? 1.965 vs. 4.57 ? 2.33, p &lt; 0.001), lower BE (-0.139 ? 7.48 vs. -3.751 ? 6.159, p &lt; 0.001), and a higher lactate (2.299 ? 2.350 vs. 3.498 ? 3.578, p &lt; 0.001). MEWS ? 4 (OR 1.90, CI 1.082?3.340, p = 0.026) was the only independent predictor of mortality. Area under the curve (AUC) for MEWS with regard to in-hospital mortality prediction was 0.633 (95% CI 0.569?0.697). When age was added to MEWS, the AUC was 0.76 (95% CI 0.707?0.814). Conclusion. Our findings support the prognostic value of MEWS for final outcome of patients admitted to the high dependency unit.

The Vitals Risk Index-Retrospective Performance Analysis of an Automated and Objective Pediatric Early Warning System.

Pediatric in-hospital cardiac arrests and emergent transfers to the pediatric intensive care unit (ICU) represent a serious patient safety concern with associated increased morbidity and mortality. Some institutions have turned to the electronic health record and predictive analytics in search of earlier and more accurate detection of patients at risk for decompensation. Objective electronic health record data from 2011 to 2017 was utilized to develop an automated early warning system score aimed at identifying hospitalized children at risk of clinical deterioration. Five vital sign measurements and supplemental oxygen requirement data were used to build the Vitals Risk Index (VRI) model, using multivariate logistic regression. We compared the VRI to the hospital's existing early warning system, an adaptation of Monaghan's Pediatric Early Warning Score system (PEWS). The patient population included hospitalized children 18 years of age and younger while being cared for outside of the ICU. This dataset included 158 case hospitalizations (102 emergent transfers to the ICU and 56 "code blue" events) and 135,597 control hospitalizations. When identifying deteriorating patients 2 hours before an event, there was no significant difference between Pediatric Early Warning Score and VRI's areas under the receiver operating characteristic curve at false-positive rates ≤ 10% (pAUC10 of 0.065 and 0.064, respectively; P = 0.74), a threshold chosen to compare the 2 approaches under clinically tolerable false-positive rates. The VRI represents an objective, simple, and automated predictive analytics tool for identifying hospitalized pediatric patients at risk of deteriorating outside of the ICU setting.

Impact of using data from electronic protocols in nursing performance management: A qualitative interview study.

AimTo explore the impact of using electronic data in performance management to improve nursing compliance with a protocol.BackgroundElectronic data are increasingly used to monitor protocol compliance but little is known about the impact on nurses’ practice in hospital wards.MethodSeventeen acute hospital nursing staff participated in semi‐structured interviews about compliance with an early warning score (EWS) protocol delivered by a bedside electronic handheld device.ResultsBefore electronic EWS data was used to monitor compliance, staff combined protocol‐led actions with clinical judgement. However, some observations were missed to reduce noise and disruption at night. After compliance monitoring was introduced, observations were sometimes covertly omitted using a loophole. Interviewees described a loss of autonomy but acknowledged the EWS system sometimes flagged unexpected patient deterioration.ConclusionsIntroducing automated electronic systems to support nursing tasks can decrease nursing burden but remove the ability to record legitimate reasons for missing observations. This can result in covert resistance that could reduce patient safety.Implications for nursing managementProviding the ability to log legitimate reasons for missing observations would allow nurses to balance professional judgement with the use of electronic data in performance management of protocol compliance.

Four early warning scores predict mortality in emergency surgical patients at University Teaching Hospital, Lusaka: a prospective observational study.

The value of early warning scoring systems has been established in high-income countries. There is little evidence for their use in low-resource settings. We aimed to compare existing early warning scores to predict 30-day mortality. University Teaching Hospital is a tertiary center in Lusaka, Zambia. Adult surgical patients, excluding obstetrics, admitted for > 24 hr were included in this prospective observational study. On days 1 to 3 of admission, we collected data on patient demographics, heart rate, blood pressure, oxygen saturation, oxygen administration, temperature, consciousness level, and mobility. Two-, three-, and 30-day mortality were recorded with their associated variables analyzed using area under receiver operating curves (AUROC) for the National Early Warning Score (NEWS); the Modified Early Warning Score (MEWS); a modified Hypotension, Oxygen Saturation, Temperature, ECG, Loss of Independence (mHOTEL) score; and the Tachypnea, Oxygen saturation, Temperature, Alertness, Loss of Independence (TOTAL) score. Data were available for 254 patients from March 2017 to July 2017. Eighteen (7.5%) patients died at 30 days. The four early warning scores were found to be predictive of 30-day mortality: MEWS (AUROC, 0.76; 95% confidence interval [CI], 0.63 to 0.88; P < 0.001), NEWS (AUROC 0.805; 95% CI, 0.688 to 0.92; P < 0.001), mHOTEL (AUROC 0.759; 95% CI, 0.63 to 0.89, P < 0.001), and TOTAL (AUROC 0.782; 95% CI, 0.66 to 0.90; P < 0.001). We validated four scoring systems in predicting mortality in a Zambian surgical population. Further work is required to assess if implementation of these scoring systems can improve outcomes.

Monitoring of High- and Intermediate-Risk Surgical Patients.

Monitoring of High- and Intermediate-Risk Surgical Patients.

Deep Interpretable Early Warning System for the Detection of Clinical Deterioration.

Assessment of physiological instability preceding adverse events on hospital wards has been previously investigated through clinical early warning score systems. Early warning scores are simple to use yet they consider data as independent and identically distributed random variables. Deep learning applications are able to learn from sequential data, however they lack interpretability and are thus difficult to deploy in clinical settings. We propose the 'Deep Early Warning System' (DEWS), an interpretable end-to-end deep learning model that interpolates temporal data and predicts the probability of an adverse event, defined as the composite outcome of cardiac arrest, mortality or unplanned ICU admission. The model was developed and validated using routinely collected vital signs of patients admitted to the the Oxford University Hospitals between 21st March 2014 and 31st March 2018. We extracted 45 314 vital-sign measurements as a balanced training set and 359 481 vital-sign measurements as an imbalanced testing set to mimic a real-life setting of emergency admissions. DEWS achieved superior accuracy than the state-of-the-art that is currently implemented in clinical settings, the National Early Warning Score, in terms of the overall area under the receiver operating characteristic curve (AUROC) (0.880 vs. 0.866) and when evaluated independently for each of the three outcomes. Our attention-based architecture was able to recognize 'historical' trends in the data that are most correlated with the predicted probability. With high sensitivity, improved clinical utility and increased interpretability, our model can be easily deployed in clinical settings to supplement existing EWS systems.

Comparative prognostic accuracy of sepsis scores for hospital mortality in adults with suspected infection in non-ICU and ICU at an academic public hospital.

BackgroundSepsis is a global healthcare challenge and reliable tools are needed to identify patients and stratify their risk. Here we compare the prognostic accuracy of the sepsis-related organ failure assessment (SOFA), quick SOFA (qSOFA), systemic inflammatory response syndrome (SIRS), and national early warning system (NEWS) scores for hospital mortality and other outcomes amongst patients with suspected infection at an academic public hospital.Measurements and main results10,981 adult patients with suspected infection hospitalized at a U.S. academic public hospital between 2011–2017 were retrospectively identified. Primary exposures were the maximum SIRS, qSOFA, SOFA, and NEWS scores upon inclusion. Comparative prognostic accuracy for the primary outcome of hospital mortality was assessed using the area under the receiver operating characteristic curve (AUROC). Secondary outcomes included mortality in ICU versus non-ICU settings, ICU transfer, ICU length of stay (LOS) >3 days, and hospital LOS >7 days. Adjusted analyses were performed using a model of baseline risk for hospital mortality. 774 patients (7.1%) died in hospital. Discrimination for hospital mortality was highest for SOFA (AUROC 0.90 [95% CI, 0.89–0.91]), followed by NEWS (AUROC 0.85 [95% CI, 0.84–0.86]), qSOFA (AUROC 0.84 [95% CI, 0.83–0.85]), and SIRS (AUROC 0.79 [95% CI, 0.78–0.81]; p<0.001 for all comparisons). NEWS (AUROC 0.94 [95% CI, 0.93–0.95]) outperformed other scores in predicting ICU transfer (qSOFA AUROC 0.89 [95% CI, 0.87–0.91]; SOFA AUROC, 0.84 [95% CI, 0.82–0.87]; SIRS AUROC 0.81 [95% CI, 0.79–0.83]; p<0.001 for all comparisons). NEWS (AUROC 0.86 [95% CI, 0.85–0.86]) was also superior to other scores in predicting ICU LOS >3 days (SOFA AUROC 0.84 [95% CI, 0.83–0.85; qSOFA AUROC, 0.83 [95% CI, 0.83–0.84]; SIRS AUROC, 0.75 [95% CI, 0.74–0.76]; p<0.002 for all comparisons).ConclusionsMultivariate prediction scores, such as SOFA and NEWS, had greater prognostic accuracy than qSOFA or SIRS for hospital mortality, ICU transfer, and ICU length of stay. Complex sepsis scores may offer enhanced prognostic performance as compared to simple sepsis scores in inpatient hospital settings where more complex scores can be readily calculated.

Current status and analysis of knowledge-attitude-practice on modified early warning score system in Intensive Care Unit nurses

Objective To investigate the knowledge-attitude-practice level of the Intensive Care Unit (ICU) nurses on the Modified Early Warning Score (MEWS) system, and analyze its influencing factors, so as to lay a foundation for the establishment of related training program later. Methods From October to November 2018, by convenience sampling, ICU nurses in General Hospital of Ningxia Medical University were selected as objects of the study. Self-designed ICU Nurses' Knowledge-Attitude-Behavior on System Questionnaire was used to investigate the nurses by means of Wenjuanxing online. The influencing factors were analyzed by single factor analysis and multiple linear regression analysis. Results Totally 92 valid questionnaires were retrieved. The ICU nurses got the score of (68.42±22.09) in the knowledge of MEWS, and (52.29±19.75) in the of MEWS , and (56.64±18.99) in the of MEWS; multiple linear regression analysis results indicated that working length, whether or not had contacted before, and educational background were the influencing factors of the practice of (P<0.05) . Conclusions The knowledge, attitude and practice of ICU nurses in Ningxia are generally at the medium and low levels, among which is still acceptable, while attitude and practice are relatively poor. It suggests that managers should focus on attitudes, guide ICU nurses to recognize and actively apply them to assess patients' condition, and actively explore early warning management mode suitable for ICU critical patients. Key words: Intensive Care Unit; Nurses; Modified early warning score system; Knowledge; Attitude; Practice

Confidence-Enhanced Early Warning Score Based on Fuzzy Logic

Cardiovascular diseases are one of the world’s major causes of loss of life. The vital signs of a patient can indicate this up to 24 hours before such an incident happens. Healthcare professionals use Early Warning Score (EWS) as a common tool in healthcare facilities to indicate the health status of a patient. However, the chance of survival of an outpatient could be increased if a mobile EWS system would monitor them during their daily activities to be able to alert in case of danger. Because of limited healthcare professional supervision of this health condition assessment, a mobile EWS system needs to have an acceptable level of reliability - even if errors occur in the monitoring setup such as noisy signals and detached sensors. In earlier works, a data reliability validation technique has been presented that gives information about the trustfulness of the calculated EWS. In this paper, we propose an EWS system enhanced with the self-aware property confidence, which is based on fuzzy logic. In our experiments, we demonstrate that - under adverse monitoring circumstances (such as noisy signals, detached sensors, and non-nominal monitoring conditions) - our proposed Self-Aware Early Warning Score (SA-EWS) system provides a more reliable EWS than an EWS system without self-aware properties.