Detecting Deteriorating Patients in the Hospital: Development and Validation of a Novel Scoring System.

Rationale: Late recognition of patient deterioration in hospital is associated with worse outcomes, including higher mortality. Despite the widespread introduction of early warning score (EWS) systems and electronic health records, deterioration still goes unrecognized. Objectives: To develop and externally validate a Hospital- wide Alerting via Electronic Noticeboard (HAVEN) system to identify hospitalized patients at risk of reversible deterioration. Methods: This was a retrospective cohort study of patients 16 years of age or above admitted to four UK hospitals. The primary outcome was cardiac arrest or unplanned admission to the ICU. We used patient data (vital signs, laboratory tests, comorbidities, and frailty) from one hospital to train a machine-learning model (gradient boosting trees). We internally and externally validated the model and compared its performance with existing scoring systems (including the National EWS, laboratory-based acute physiology score, and electronic cardiac arrest risk triage score). Measurements and Main Results: We developed the HAVEN model using 230,415 patient admissions to a single hospital. We validated HAVEN on 266,295 admissions to four hospitals. HAVEN showed substantially higher discrimination (c-statistic, 0.901 [95% confidence interval, 0.898-0.903]) for the primary outcome within 24 hours of each measurement than other published scoring systems (which range from 0.700 [0.696-0.704] to 0.863 [0.860-0.865]). With a precision of 10%, HAVEN was able to identify 42% of cardiac arrests or unplanned ICU admissions with a lead time of up to 48 hours in advance, compared with 22% by the next best system. Conclusions: The HAVEN machine-learning algorithm for early identification of in-hospital deterioration significantly outperforms other published scores such as the National EWS.

Smoothing Effect in Vital Sign Recordings: Fact or Fiction? A Retrospective Cohort Analysis of Manual and Continuous Vital Sign Measurements to Assess Data Smoothing in Postoperative Care.

BACKGROUND: Data smoothing of vital signs has been reported in the anesthesia literature, suggesting that clinical staff are biased toward measurements of normal physiology. However, these findings may be partially explained by clinicians interpolating spurious values from noisy signals and by the undersampling of physiological changes by infrequent manual observations. We explored the phenomenon of data smoothing using a method robust to these effects in a large postoperative dataset including respiratory rate, heart rate, and oxygen saturation (SpO2). We also assessed whether the presence of the vital sign taker creates an arousal effect. METHODS: Study data came from a UK upper gastrointestinal postoperative ward (May 2009 to December 2013). We compared manually recorded vital sign data with contemporaneous continuous data recorded from monitoring equipment. We proposed that data smoothing increases differences between vital sign sources as vital sign abnormality increases. The primary assessment method was a mixed-effects model relating continuous-manual differences to vital sign values, adjusting for repeated measurements. We tested the regression slope significance and predicted the continuous-manual difference at clinically important vital sign values. We calculated limits of agreement (LoA) between vital sign sources using the Bland-Altman method, adjusting for repeated measures. Similarly, we assessed whether the vital sign taker affected vital signs, comparing continuous data before and during manual recording. RESULTS: From 407 study patients, 271 had contemporaneous continuous and manual recordings, allowing 3740 respiratory rate, 3844 heart rate, and 3896 SpO2 paired measurements for analysis. For the model relating continuous-manual differences to continuous-manual average vital sign values, the regression slope (95% confidence interval) was 0.04 (-0.01 to 0.10; P = .11) for respiratory rate, 0.04 (-0.01 to 0.09; P = .11) for heart rate, and 0.10 (0.07-0.14; P < .001) for SpO2. For SpO2 measurements of 91%, the model predicted a continuous-manual difference (95% confidence interval) of -0.88% (-1.17% to -0.60%). The bias (LoA) between measurement sources was -0.74 (-7.80 to 6.32) breaths/min for respiratory rate, -1.13 (-17.4 to 15.1) beats/min for heart rate, and -0.25% (-3.35% to 2.84%) for SpO2. The bias (LoA) between continuous data before and during manual observation was -0.57 (-5.63 to 4.48) breaths/min for respiratory rate, -0.71 (-10.2 to 8.73) beats/min for heart rate, and -0.07% (-2.67% to 2.54%) for SpO2. CONCLUSIONS: We found no evidence of data smoothing for heart rate and respiratory rate measurements. Although an effect exists for SpO2 measurements, it was not clinically significant. The wide LoAs between continuous and manually recorded vital signs would commonly result in different early warning scores, impacting clinical care. There was no evidence of an arousal effect caused by the vital sign taker.

Outcome Prediction for Patients with Traumatic Brain Injury with Dynamic Features from Intracranial Pressure and Arterial Blood Pressure Signals: A Gaussian Process Approach.

Previous work has been demonstrated that tracking features describing the dynamic and time-varying patterns in brain monitoring signals provide additional predictive information beyond that derived from static features based on snapshot measurements. To achieve more accurate predictions of outcomes of patients with traumatic brain injury (TBI), we proposed a statistical framework to extract dynamic features from brain monitoring signals based on the framework of Gaussian processes (GPs). GPs provide an explicit probabilistic, nonparametric Bayesian approach to metric regression problems. This not only provides probabilistic predictions, but also gives the ability to cope with missing data and infer model parameters such as those that control the function's shape, noise level and dynamics of the signal. Through experimental evaluation, we have demonstrated that dynamic features extracted from GPs provide additional predictive information in addition to the features based on the pressure reactivity index (PRx). Significant improvements in patient outcome prediction were achieved by combining GP-based and PRx-based dynamic features. In particular, compared with the a baseline PRx-based model, the combined model achieved over 30 % improvement in prediction accuracy and sensitivity and over 20 % improvement in specificity and the area under the receiver operating characteristic curve.

The association between the neutrophil-to-lymphocyte ratio and mortality in critical illness: an observational cohort study.

INTRODUCTION: The neutrophil-to-lymphocyte ratio (NLR) is a biological marker that has been shown to be associated with outcomes in patients with a number of different malignancies. The objective of this study was to assess the relationship between NLR and mortality in a population of adult critically ill patients. METHODS: We performed an observational cohort study of unselected intensive care unit (ICU) patients based on records in a large clinical database. We computed individual patient NLR and categorized patients by quartile of this ratio. The association of NLR quartiles and 28-day mortality was assessed using multivariable logistic regression. Secondary outcomes included mortality in the ICU, in-hospital mortality and 1-year mortality. An a priori subgroup analysis of patients with versus without sepsis was performed to assess any differences in the relationship between the NLR and outcomes in these cohorts. RESULTS: A total of 5,056 patients were included. Their 28-day mortality rate was 19%. The median age of the cohort was 65 years, and 47% were female. The median NLR for the entire cohort was 8.9 (interquartile range, 4.99 to 16.21). Following multivariable adjustments, there was a stepwise increase in mortality with increasing quartiles of NLR (first quartile: reference category; second quartile odds ratio (OR) = 1.32; 95% confidence interval (CI), 1.03 to 1.71; third quartile OR = 1.43; 95% CI, 1.12 to 1.83; 4th quartile OR = 1.71; 95% CI, 1.35 to 2.16). A similar stepwise relationship was identified in the subgroup of patients who presented without sepsis. The NLR was not associated with 28-day mortality in patients with sepsis. Increasing quartile of NLR was statistically significantly associated with secondary outcome. CONCLUSION: The NLR is associated with outcomes in unselected critically ill patients. In patients with sepsis, there was no statistically significant relationship between NLR and mortality. Further investigation is required to increase understanding of the pathophysiology of this relationship and to validate these findings with data collected prospectively.

COVID-19 vaccination and major cardiovascular and haematological adverse events in Abu Dhabi: retrospective cohort study.

The widespread administration of COVID-19 vaccines has prompted a need to understand their safety profile. This investigation focuses on the safety of inactivated and mRNA-based COVID-19 vaccines, particularly concerning potential cardiovascular and haematological adverse events. A retrospective cohort study was conducted for 1.3 million individuals residing in Abu Dhabi, United Arab Emirates, who received 1.8 million doses of the inactivated BBIBP CorV (by SinoPharm) and mRNA-based BNT162b2 (Pfizer-BioNTech) vaccines between June 1, 2021, and June 30, 2022. The study's primary outcome was to assess the occurrence of selected cardiovascular and haematological events leading to hospitalization or emergency room visits within 21 days post-vaccination. Results showed no significant increase in the incidence rates of these events compared to the subsequent 22 to 42 days following vaccination. Analysis revealed no elevated risk for adverse outcomes following first (IRR 1·03; 95% CI 0·82-1·31), second (IRR 0·92; 95% CI 0·72-1·16) and third (IRR 0·82; 95% CI 0·66-1·00) doses of either vaccine. This study found no substantial link between receiving either mRNA and inactivated COVID-19 vaccines and a higher likelihood of cardiovascular or haematological events within 21 days after vaccination.

Development of an enhanced scoring system to predict ICU readmission or in-hospital death within 24 hours using routine patient data from two NHS Foundation Trusts.

RATIONALE: Intensive care units (ICUs) admit the most severely ill patients. Once these patients are discharged from the ICU to a step-down ward, they continue to have their vital signs monitored by nursing staff, with Early Warning Score (EWS) systems being used to identify those at risk of deterioration. OBJECTIVES: We report the development and validation of an enhanced continuous scoring system for predicting adverse events, which combines vital signs measured routinely on acute care wards (as used by most EWS systems) with a risk score of a future adverse event calculated on discharge from the ICU. DESIGN: A modified Delphi process identified candidate variables commonly available in electronic records as the basis for a 'static' score of the patient's condition immediately after discharge from the ICU. L1-regularised logistic regression was used to estimate the in-hospital risk of future adverse event. We then constructed a model of physiological normality using vital sign data from the day of hospital discharge. This is combined with the static score and used continuously to quantify and update the patient's risk of deterioration throughout their hospital stay. SETTING: Data from two National Health Service Foundation Trusts (UK) were used to develop and (externally) validate the model. PARTICIPANTS: A total of 12 394 vital sign measurements were acquired from 273 patients after ICU discharge for the development set, and 4831 from 136 patients in the validation cohort. RESULTS: Outcome validation of our model yielded an area under the receiver operating characteristic curve of 0.724 for predicting ICU readmission or in-hospital death within 24 hours. It showed an improved performance with respect to other competitive risk scoring systems, including the National EWS (0.653). CONCLUSIONS: We showed that a scoring system incorporating data from a patient's stay in the ICU has better performance than commonly used EWS systems based on vital signs alone. TRIAL REGISTRATION NUMBER: ISRCTN32008295.

Localization of the hand motor area by arterial spin labeling and blood oxygen level-dependent functional magnetic resonance imaging.

The new clinically available arterial spin labeling (ASL) perfusion imaging sequences present some advantages relatively to the commonly used blood oxygen level-dependent (BOLD) method for functional brain studies using magnetic resonance imaging (MRI). In particular, regional cerebral blood flow (CBF) changes are thought to be more directly related with neuronal activation. In this study, we aimed to investigate the accuracy of the functional localization of the hand motor area obtained by simultaneous CBF and BOLD contrasts provided by ASL functional MRI (fMRI) and compare it with a standard BOLD fMRI protocol. For this purpose, we measured the distance between the center of gravity of the activation clusters obtained with each contrast (CBF, BOLD(ASL), and Standard BOLD) and 11 positions defined on a well-established anatomical landmark of the hand motor area (the omega in the axial plane of the precentral gyrus). We found that CBF measurements were significantly closer to the anatomical landmark than the ones obtained using either simultaneous BOLD(ASL) or standard BOLD contrasts. Moreover, we also observed reduced intersubject variability of the functional localization, as well as percent signal change, for CBF relative to both BOLD contrast measurements. In conclusion, our results add further evidence in support to the notion that CBF provides a more accurate localization of motor activation than BOLD contrast, indicating that ASL may be an appropriate technique for clinical fMRI studies.

A Real-Time Wearable System for Monitoring Vital Signs of COVID-19 Patients in a Hospital Setting.

The challenges presented by the Coronavirus disease 2019 (COVID-19) pandemic to the National Health Service (NHS) in the United Kingdom (UK) led to a rapid adaptation of infection disease protocols in-hospital. In this paper we report on the optimisation of our wearable ambulatory monitoring system (AMS) to monitor COVID-19 patients on isolation wards. A wearable chest patch (VitalPatch®, VitalConnect, United States of America, USA) and finger-worn pulse oximeter (WristOx2® 3150, Nonin, USA) were used to estimate and transmit continuous Heart Rate (HR), Respiratory Rate (RR), and peripheral blood Oxygen Saturation (SpO2) data from ambulatory patients on these isolation wards to nurse bays remote from these patients, with a view to minimising the risk of infection for nursing staff. Our virtual High-Dependency Unit (vHDU) system used a secure web-based architecture and protocols (HTTPS and encrypted WebSockets) to transmit the vital-sign data in real time from wireless Android tablet devices, operating as patient data collection devices by the bedside in the isolation rooms, into the clinician dashboard interface available remotely via any modern web-browser. Fault-tolerant software strategies were used to reconnect the wearables automatically, avoiding the need for nurses to enter the isolation ward to re-set the patient monitoring equipment. The remote dashboard also displayed the vital-sign observations recorded by the nurses, using a separate electronic observation system, allowing them to review both sources of vital-sign data in one integrated chart. System usage was found to follow the trend of the number of local COVID-19 infections during the first wave of the pandemic in the UK (March to June 2020), with almost half of the patients on the isolation ward monitored with wearables during the peak of hospital admissions in the local area. Patients were monitored for a median of 31.5 [8.8, 75.4] hours, representing 88.1 [62.5, 94.5]% of the median time they were registered in the system. This indicates the system was being used in the isolation ward during this period. An updated version of the system has now also been used throughout the second and third waves of the pandemic in the UK.

Cross-sectional centiles of blood pressure by age and sex: a four-hospital database retrospective observational analysis.

OBJECTIVES: National guidelines for identifying physiological deterioration and sepsis in hospitals depend on thresholds for blood pressure that do not account for age or sex. In populations outside hospital, differences in blood pressure are known to occur with both variables. Whether these differences remain in the hospitalised population is unknown. This database analysis study aims to generate representative centiles to quantify variations in blood pressure by age and sex in hospitalised patients. DESIGN: Retrospective cross-sectional observational database analysis. SETTING: Four near-sea-level hospitals between April 2015 and April 2017 PARTICIPANTS: 75 342 adult patients who were admitted to the hospitals and had at least one set of documented vital sign observations within 24 hours before discharge were eligible for inclusion. Patients were excluded if they died in hospital, had no vital signs 24 hours prior to discharge, were readmitted within 7 days of discharge, had missing age or sex or had no blood pressure recorded. RESULTS: Systolic blood pressure (SBP) for hospitalised patients increases with age for both sexes. Median SBP increases from 122 (CI: 121.1 to 122.1) mm Hg to 132 (CI: 130.9 to 132.2) mm Hg in men, and 114 (CI: 113.1 to 114.4) mm Hg to 135 (CI: 134.5 to 136.2) mm Hg in women, between the ages of 20 and 90 years. Diastolic blood pressure peaked around 50 years for men 76 (CI: 75.5 to 75.9) mm Hg and women 69 (CI: 69.0 to 69.4) mm Hg. The blood pressure criterion for sepsis, systolic <100 mm Hg, was met by 2.3% of younger (20-30 years) men and 3.5% of older men (81-90 years). In comparison, the criterion was met by 9.7% of younger women and 2.6% of older women. CONCLUSION: We have quantified variations in blood pressure by age and sex in hospitalised patients that have implications for recognition of deterioration. Nearly 10% of younger women met the blood pressure criterion for sepsis at hospital discharge.

Trajectories of vital signs in patients with COVID-19.

BACKGROUND: The global pandemic of coronavirus disease 2019 (COVID-19) has placed a huge strain on UK hospitals. Early studies suggest that patients can deteriorate quickly after admission to hospital. The aim of this study was to model changes in vital signs for patients hospitalised with COVID-19. METHODS: This was a retrospective observational study of adult patients with COVID-19 admitted to one acute hospital trust in the UK (CV) and a cohort of patients admitted to the same hospital between 2013-2017 with viral pneumonia (VI). The primary outcome was the start of continuous positive airway pressure/non-invasive positive pressure ventilation, ICU admission or death in hospital. We used non-linear mixed-effects models to compare changes in vital sign observations prior to the primary outcome. Using observations and FiO2 measured at discharge in the VI cohort as the model of normality, we also combined individual vital signs into a single novelty score. RESULTS: There were 497 cases of COVID-19, of whom 373 had been discharged from hospital. 135 (36.2%) of patients experienced the primary outcome, of whom 99 died in hospital. In-hospital mortality was over 4-times higher in the CV than the VI cohort (26.5% vs 6%). For those patients who experienced the primary outcome, CV patients became increasingly hypoxaemic, with a median estimated FiO2 (0.75) higher than that of the VI cohort (estimated FiO2 of 0.35). Prior to the primary outcome, blood pressure remained within normal range, and there was only a small rise in heart rate. The novelty score showed that patients with COVID-19 deteriorated more rapidly that patients with viral pneumonia. CONCLUSIONS: Patients with COVID-19 who deteriorate in hospital experience rapidly-worsening respiratory failure, with low SpO2 and high FiO2, but only minor abnormalities in other vital signs. This has potential implications for the ability of early warning scores to identify deteriorating patients.

Protocol for a prospective, controlled, cross-sectional, diagnostic accuracy study to evaluate the specificity and sensitivity of ambulatory monitoring systems in the prompt detection of hypoxia and during movement.

INTRODUCTION: Automated continuous ambulatory monitoring may provide an alternative to intermittent manual vital signs monitoring. This has the potential to improve frequency of measurements, timely escalation of care and patient safety. However, a major barrier to the implementation of these wearable devices in the ward environment is their uncertain reliability, efficiency and data fidelity. The purpose of this study is to test performance of selected devices in a simulated clinical setting including during movement and low levels of peripheral oxygen saturation. METHODS AND ANALYSIS: This is a single centre, prospective, controlled, cross-sectional, diagnostic accuracy study to determine the specificity and sensitivity of currently available ambulatory vital signs monitoring equipment in the detection of hypoxia and the effect of movement on data acquisition. We will recruit up to 45 healthy volunteers who will attend a single study visit; starting with a movement phase and followed by the hypoxia exposure phase where we will gradually decrease saturation levels down to 80%. We will simultaneously test one chest patch, one wrist worn only and three wrist worn with finger probe devices against 'clinical standard 'and 'gold standard' references. We will measure peripheral oxygen saturations, pulse rate, heart rate and respiratory rate continuously and arterial blood gases intermittently throughout the study. ETHICS AND DISSEMINATION: This study has received ethical approval by the East of Scotland Research Ethics Service REC 2 (19/ES/0008). The results will be broadly distributed through conference presentations and peer-reviewed publications. TRIAL REGISTRATION NUMBER: ISRCTN61535692 registered on 10/06/2019.

Remote health diagnosis and monitoring in the time of COVID-19.

Coronavirus disease (COVID-19), caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), is rapidly spreading across the globe. The clinical spectrum of SARS-CoV-2 pneumonia requires early detection and monitoring, within a clinical environment for critical cases and remotely for mild cases, with a large spectrum of symptoms. The fear of contamination in clinical environments has led to a dramatic reduction in on-site referrals for routine care. There has also been a perceived need to continuously monitor non-severe COVID-19 patients, either from their quarantine site at home, or dedicated quarantine locations (e.g. hotels). In particular, facilitating contact tracing with proximity and location tracing apps was adopted in many countries very rapidly. Thus, the pandemic has driven incentives to innovate and enhance or create new routes for providing healthcare services at distance. In particular, this has created a dramatic impetus to find innovative ways to remotely and effectively monitor patient health status. In this paper, we present a review of remote health monitoring initiatives taken in 20 states during the time of the pandemic. We emphasize in the discussion particular aspects that are common ground for the reviewed states, in particular the future impact of the pandemic on remote health monitoring and consideration on data privacy.

Unsupervised Bayesian Inference to Fuse Biosignal Sensory Estimates for Personalizing Care.

The role of sensing technologies, such as wearables, in delivering precision care is becoming widely acceptable. Given the very large quantities of sensor data that rapidly accumulate, there is a need to employ automated algorithms to label biosignal sensor data. In many real-life clinical applications, no such expert labels are available, and algorithms for processing sensor data must be relied upon, without access to the "ground truth." It is therefore extremely difficult to choose which algorithms to trust or discard at any point in time, where different algorithms may be optimal for different patients, or even for different points in time for the same patient. We propose two fully Bayesian approaches for fusing labels from independent and potentially correlated annotators (i.e., algorithms or, where available, experts). These are generative models to aggregate labels (i.e., the outputs of the algorithms, such as identified ECG morphology) in an unsupervised manner, to estimate jointly the assumed bias and precision of each algorithm without access to the ground truth. The latter fused estimate may then be used to infer the underlying ground truth. For the first time in the biomedical context, we show that modeling correlations between annotators, and fusing information concerning task difficulty (such as the estimated quality of the sensor data), improve these estimates with respect to commonly employed strategies in the literature. Also, we adopt a strongly Bayesian approach to inference using Gibbs sampling to improve estimates over the existing state of the art. We present results from applying the proposed pair of models to simulated and two publicly available biomedical datasets, to demonstrate proof-of-principle. We show that our proposed models outperform all existing approaches recreated from the literature. We also show that the proposed methods are robust when dealing with missing values (as often occurs in real-life biomedical applications), and that they are suitably efficient for use in real-time applications, thereby providing the basis for the reliable use of sensors for personalizing the care of the individual.

The effect of fractional inspired oxygen concentration on early warning score performance: A database analysis.

OBJECTIVES: To calculate fractional inspired oxygen concentration (FiO2) thresholds in ward patients and add these to the National Early Warning Score (NEWS). To evaluate the performance of NEWS-FiO2 against NEWS when predicting in-hospital death and unplanned intensive care unit (ICU) admission. METHODS: A multi-centre, retrospective, observational cohort study was carried out in five hospitals from two UK NHS Trusts. Adult admissions with at least one complete set of vital sign observations recorded electronically were eligible. The primary outcome measure was an 'adverse event' which comprised either in-hospital death or unplanned ICU admission. Discrimination was assessed using the Area Under the Receiver Operating Characteristic curve (AUROC). RESULTS: A cohort of 83,304 patients from a total of 271,363 adult admissions were prescribed oxygen. In this cohort, NEWS-FiO2 (AUROC 0.823, 95% CI 0.819-0.824) outperformed NEWS (AUORC 0.811, 95% CI 0.809-0.814) when predicting in-hospital death or unplanned ICU admission within 24 h of a complete set of vital sign observations. CONCLUSIONS: NEWS-FiO2 generates a performance gain over NEWS when studied in ward patients requiring oxygen. This warrants further study, particularly in patients with respiratory disorders.

A comparison of the ability of the National Early Warning Score and the National Early Warning Score 2 to identify patients at risk of in-hospital mortality: A multi-centre database study.

AIMS: To compare the ability of the National Early Warning Score (NEWS) and the National Early Warning Score 2 (NEWS2) to identify patients at risk of in-hospital mortality and other adverse outcomes. METHODS: We undertook a multi-centre retrospective observational study at five acute hospitals from two UK NHS Trusts. Data were obtained from completed adult admissions who were not fit enough to be discharged alive on the day of admission. Diagnostic coding and oxygen prescriptions were used to identify patients with type II respiratory failure (T2RF). The primary outcome was in-hospital mortality within 24 h of a vital signs observation. Secondary outcomes included unanticipated intensive care unit admission or cardiac arrest within 24 h of a vital signs observation. Discrimination was assessed using the c-statistic. RESULTS: Among 251,266 adult admissions, 48,898 were identified to be at risk of T2RF by diagnostic coding. In this group, NEWS2 showed statistically significant lower discrimination (c-statistic, 95% CI) for identifying in-hospital mortality within 24 h (0.860, 0.857-0.864) than NEWS (0.881, 0.878-0.884). For 1394 admissions with documented T2RF, discrimination was similar for both systems: NEWS2 (0.841, 0.827-0.855), NEWS (0.862, 0.848-0.875). For all secondary endpoints, NEWS2 showed no improvements in discrimination. CONCLUSIONS: NEWS2 modifications to NEWS do not improve discrimination of adverse outcomes in patients with documented T2RF and decrease discrimination in patients at risk of T2RF. Further evaluation of the relationship between SpO2 values, oxygen therapy and risk should be investigated further before wide-scale adoption of NEWS2.

Manual centile-based early warning scores derived from statistical distributions of observational vital-sign data.

AIMS OF STUDY: To develop and validate a centile-based early warning score using manually-recorded data (mCEWS). To compare mCEWS performance with a centile-based early warning score derived from continuously-acquired data (from bedside monitors, cCEWS), and with other published early warning scores. MATERIALS AND METHODS: We used an unsupervised approach to investigate the statistical properties of vital signs in an in-hospital patient population and construct an early-warning score from a "development" dataset. We evaluated scoring systems on a separate "validation" dataset. We assessed the ability of scores to discriminate patients at risk of cardiac arrest, unanticipated intensive care unit admission, or death, each within 24 h of a given vital-sign observation, using metrics including the area under the receiver-operating characteristic curve (AUC). RESULTS: The development dataset contained 301,644 vital sign observations from 12,153 admissions (median age (IQR): 63 (49-73); 49.2% females) March 2014-September 2015. The validation dataset contained 1,459,422 vital-sign observations from 53,395 admissions (median age (IQR): 68 (48-81), 51.4% females) October 2015-May 2017. The AUC (95% CI) for the mCEWS was 0.868 (0.864-0.872), comparable with the National EWS, 0.867 (0.863-0.871), and other recently proposed scores. The AUC for cCEWS was 0.808 (95% CI, 0.804-0.812). The improvement in performance in comparison to the continuous CEWS was mainly explained by respiratory rate threshold differences. CONCLUSIONS: Performance of an EWS is highly dependent on the database from which itis derived. Our unsupervised statistical approach provides a straightforward, reproducible method to enable the rapid development of candidate EWS systems.

A Robust Fusion Model for Estimating Respiratory Rate From Photoplethysmography and Electrocardiography.

OBJECTIVE: Respiratory rate (RR) estimation algorithms based on the photoplethymogram (PPG) and electrocardiogram (ECG) lack clinical robustness. This is because the PPG and ECG respiratory modulations are dependent on patient physiology, regardless of general signal quality. The present work describes an RR estimation algorithm using respiratory quality indices (RQIs) that assess the presence or absence of the PPG- and ECG-derived respiratory modulations. METHODS: Six respiratory waveforms are derived from the amplitude modulation, frequency modulation, and baseline wander of the PPG and ECG. The respiratory quality of each modulation is assessed by using RQIs based on the fast Fourier transform, autoregression, and autocorrelation. The individual RQIs are fused to obtain a single RQI per modulation per time window. Based on a tunable threshold, the RQIs are used to discard poor modulations and weight the remaining modulations to provide a single RR estimation per time window. RESULTS: The proposed method was tested on two independent datasets and found that using a conservative threshold, the mean absolute error was 0.71 $\pm$ 0.89 and 3.12 $\pm$ 4.39 brpm while discarding only 1.3% and 23.2% of all time windows, for each dataset, respectively. CONCLUSION: These errors are either better than or comparable to current methods, and the number of windows discarded is far lower demonstrating improved robustness. SIGNIFICANCE: This work describes a novel preprocessing algorithm that can be implemented in conjunction with other RR estimation techniques to improve robustness by specifically considering the quality of the respiratory information.

Breathing Rate Estimation From the Electrocardiogram and Photoplethysmogram: A Review.

Breathing rate (BR) is a key physiological parameter used in a range of clinical settings. Despite its diagnostic and prognostic value, it is still widely measured by counting breaths manually. A plethora of algorithms have been proposed to estimate BR from the electrocardiogram (ECG) and pulse oximetry (photoplethysmogram, PPG) signals. These BR algorithms provide opportunity for automated, electronic, and unobtrusive measurement of BR in both healthcare and fitness monitoring. This paper presents a review of the literature on BR estimation from the ECG and PPG. First, the structure of BR algorithms and the mathematical techniques used at each stage are described. Second, the experimental methodologies that have been used to assess the performance of BR algorithms are reviewed, and a methodological framework for the assessment of BR algorithms is presented. Third, we outline the most pressing directions for future research, including the steps required to use BR algorithms in wearable sensors, remote video monitoring, and clinical practice.

Predicting in-hospital mortality and unanticipated admissions to the intensive care unit using routinely collected blood tests and vital signs: Development and validation of a multivariable model.

AIM: The National Early Warning System (NEWS) is based on vital signs; the Laboratory Decision Tree Early Warning Score (LDT-EWS) on laboratory test results. We aimed to develop and validate a new EWS (the LDTEWS:NEWS risk index) by combining the two and evaluating the discrimination of the primary outcome of unanticipated intensive care unit (ICU) admission or in-hospital mortality, within 24 h. METHODS: We studied emergency medical admissions, aged 16 years or over, admitted to Oxford University Hospitals (OUH) and Portsmouth Hospitals (PH). Each admission had vital signs and laboratory tests measured within their hospital stay. We combined LDT-EWS and NEWS values using a linear time-decay weighting function imposed on the most recent blood tests. The LDTEWS:NEWS risk index was developed using data from 5 years of admissions to PH, and validated on a year of data from both PH and OUH. We tested the risk index's ability to discriminate the primary outcome using the c-statistic. RESULTS: The development cohort contained 97,933 admissions (median age = 73 years) of which 4723 (4.8%) resulted inhospital death and 1078 (1.1%) in unanticipated ICU admission. We validated the risk index using data from PH (n = 21,028) and OUH (n = 16,383). The risk index showed a higher discrimination in the validation sets (c-statistic value (95% CI)) (PH, 0.901 (0.898-0.905); OUH, 0.916 (0.911-0.921)), than NEWS alone (PH, 0.877 (0.873-0.882); OUH, 0.898 (0.893-0.904)). CONCLUSIONS: The LDTEWS:NEWS risk index increases the ability to identify patients at risk of deterioration, compared to NEWS alone.

Toward a Robust Estimation of Respiratory Rate From Pulse Oximeters.

GOAL: Current methods for estimating respiratory rate (RR) from the photoplethysmogram (PPG) typically fail to distinguish between periods of high- and low-quality input data, and fail to perform well on independent "validation" datasets. The lack of robustness of existing methods directly results in a lack of penetration of such systems into clinical practice. The present work proposes an alternative method to improve the robustness of the estimation of RR from the PPG. METHODS: The proposed algorithm is based on the use of multiple autoregressive models of different orders for determining the dominant respiratory frequency in the three respiratory-induced variations (frequency, amplitude, and intensity) derived from the PPG. The algorithm was tested on two different datasets comprising 95 eight-minute PPG recordings (in total) acquired from both children and adults in different clinical settings, and its performance using two window sizes (32 and 64 seconds) was compared with that of existing methods in the literature. RESULTS: The proposed method achieved comparable accuracy to existing methods in the literature, with mean absolute errors (median, 25[Formula: see text]-75[Formula: see text] percentiles for a window size of 32 seconds) of 1.5 (0.3-3.3) and 4.0 (1.8-5.5) breaths per minute (for each dataset respectively), whilst providing RR estimates for a greater proportion of windows (over 90% of the input data are kept). CONCLUSION: Increased robustness of RR estimation by the proposed method was demonstrated. SIGNIFICANCE: This work demonstrates that the use of large publicly available datasets is essential for improving the robustness of wearable-monitoring algorithms for use in clinical practice.