1
|
Gerry S, Bedford J, Redfern OC, Rutter H, Chester-Jones M, Knight M, Kelly T, Watkinson PJ. Development of a national maternity early warning score: centile based score development and Delphi informed escalation pathways. BMJ MEDICINE 2024; 3:e000748. [PMID: 38756669 PMCID: PMC11097818 DOI: 10.1136/bmjmed-2023-000748] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 09/05/2023] [Accepted: 04/05/2024] [Indexed: 05/18/2024]
Abstract
Objective To derive a new maternity early warning score (MEWS) from prospectively collected data on maternity vital signs and to design clinical response pathways with a Delphi consensus exercise. Design Centile based score development and Delphi informed escalation pathways. Setting Pregnancy Physiology Pattern Prediction (4P) prospective UK cohort study, 1 August 2012 to 28 December 2016. Participants Pregnant people from the 4P study, recruited before 20 weeks' gestation at three UK maternity centres (Oxford, Newcastle, and London). 841, 998, and 889 women provided data in the early antenatal, antenatal, and postnatal periods. Main outcome measures Development of a new national MEWS, assigning numerical weights to measurements in the lower and upper extremes of distributions of individual vital signs from the 4P prospective cohort study. Comparison of escalation rates of the new national MEWS with the Scottish and Irish MEWS systems from 18 to 40 weeks' gestation. Delphi consensus exercise to agree clinical responses to raised scores. Results A new national MEWS was developed by assigning numerical weights to measurements in the lower and upper extremes (5%, 1%) of distributions of vital signs, except for oxygen saturation where lower centiles (10%, 2%) were used. For the new national MEWS, in a healthy population, 56% of observation sets resulted in a total score of 0 points, 26% a score of 1 point, 12% a score of 2 points, and 18% a score of ≥2 points (escalation of care is triggered at a total score of ≥2 points). Corresponding values for the Irish MEWS were 37%, 25%, 22%, and 38%, respectively; and for the Scottish MEWS, 50%, 18%, 21%, and 32%, respectively. All three MEWS were similar at the beginning of pregnancy, averaging 0.7-0.9 points. The new national MEWS had a lower mean score for the rest of pregnancy, with the mean score broadly constant (0.6-0.8 points). The new national MEWS had an even distribution of healthy population alerts across the antenatal period. In the postnatal period, heart rate threshold values were adjusted to align with postnatal changes. The centile based score derivation approach meant that each vital sign component in the new national MEWS had a similar alert rate. Suggested clinical responses to different MEWS values were agreed by consensus of an independent expert panel. Conclusions The centile based MEWS alerted escalation of care evenly across the antenatal period in a healthy population, while reducing alerts in healthy women compared with other MEWS systems. How well the tool predicted adverse outcomes, however, was not assessed and therefore external validation studies in large datasets are needed. Unlike other MEWS systems, the new national MEWS was developed with prospectively collected data on vital signs and used a systematic, expert informed process to design an associated escalation protocol.
Collapse
Affiliation(s)
- Stephen Gerry
- Nuffield Department of Orthopaedics, Rheumatology, and Musculoskeletal Sciences, University of Oxford, Oxford, UK
| | - Jonathan Bedford
- University of Oxford Nuffield Department of Clinical Neurosciences, Oxford, UK
- Milton Keynes University Hospital NHS Foundation Trust, Milton Keynes, UK
| | - Oliver C Redfern
- University of Oxford Nuffield Department of Clinical Neurosciences, Oxford, UK
| | - Hannah Rutter
- Maternity and Neonatal Safety Improvement Programme, NHS England, London, UK
| | - Mae Chester-Jones
- Nuffield Department of Orthopaedics, Rheumatology, and Musculoskeletal Sciences, University of Oxford, Oxford, UK
| | - Marian Knight
- National Perinatal Epidemiology Unit, University of Oxford, Oxford, UK
| | - Tony Kelly
- Maternity and Neonatal Safety Improvement Programme, NHS England, London, UK
| | - Peter J Watkinson
- University of Oxford Nuffield Department of Clinical Neurosciences, Oxford, UK
- National Institute for Health and Care Research (NIHR) Oxford Biomedical Research Centre, Oxford, UK
| |
Collapse
|
2
|
Pimentel MAF, Johnson A, Darbyshire JL, Tarassenko L, Clifton DA, Walden A, Rechner I, Watkinson PJ, Young JD. 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. BMJ Open 2024; 14:e074604. [PMID: 38609314 PMCID: PMC11029184 DOI: 10.1136/bmjopen-2023-074604] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/11/2023] [Accepted: 03/05/2024] [Indexed: 04/14/2024] Open
Abstract
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.
Collapse
Affiliation(s)
| | - Alistair Johnson
- Institute of Medical Engineering & Science, Massachusetts Institute of Technology, Cambridge, Massachusetts, USA
| | | | | | - David A Clifton
- Department of Engineering Science, University of Oxford, Oxford, UK
| | | | - Ian Rechner
- Royal Berkshire NHS Foundation Trust, Reading, UK
| | - Peter J Watkinson
- Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, UK
| | - J Duncan Young
- Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, UK
| |
Collapse
|
3
|
Ramgopal S, Sepanski RJ, Crowe RP, Okubo M, Callaway CW, Martin-Gill C. Correlation of vital sign centiles with in-hospital outcomes among adults encountered by emergency medical services. Acad Emerg Med 2024; 31:210-219. [PMID: 37845192 DOI: 10.1111/acem.14821] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/04/2023] [Revised: 10/05/2023] [Accepted: 10/09/2023] [Indexed: 10/18/2023]
Abstract
BACKGROUND Vital signs are a critical component of the prehospital assessment. Prior work has suggested that vital signs may vary in their distribution by age. These differences in vital signs may have implications on in-hospital outcomes or be utilized within prediction models. We sought to (1) identify empirically derived (unadjusted) cut points for vital signs for adult patients encountered by emergency medical services (EMS), (2) evaluate differences in age-adjusted cutoffs for vital signs in this population, and (3) evaluate unadjusted and age-adjusted vital signs measures with in-hospital outcomes. METHODS We used two multiagency EMS data sets to derive (National EMS Information System from 2018) and assess agreement (ESO, Inc., from 2019 to 2021) of vital signs cutoffs among adult EMS encounters. We compared unadjusted to age-adjusted cutoffs. For encounters within the ESO sample that had in-hospital data, we compared the association of unadjusted cutoffs and age-adjusted cutoffs with hospitalization and in-hospital mortality. RESULTS We included 13,405,858 and 18,682,684 encounters in the derivation and validation samples, respectively. Both extremely high and extremely low vital signs demonstrated stepwise increases in admission and in-hospital mortality. When evaluating age-based centiles with vital signs, a gradual decline was noted at all extremes of heart rate (HR) with increasing age. Extremes of systolic blood pressure at upper and lower margins were greater in older age groups relative to younger age groups. Respiratory rate (RR) cut points were similar for all adult age groups. Compared to unadjusted vital signs, age-adjusted vital signs had slightly increased accuracy for HR and RR but lower accuracy for SBP for outcomes of mortality and hospitalization. CONCLUSIONS We describe cut points for vital signs for adults in the out-of-hospital setting that are associated with both mortality and hospitalization. While we found age-based differences in vital signs cutoffs, this adjustment only slightly improved model performance for in-hospital outcomes.
Collapse
Affiliation(s)
- Sriram Ramgopal
- Division of Emergency Medicine, Ann & Robert H. Lurie Children's Hospital of Chicago, Northwestern University Feinberg School of Medicine, Chicago, Illinois, USA
| | - Robert J Sepanski
- Department of Quality & Safety, Children's Hospital of The King's Daughters, Norfolk, Virginia, USA
- Department of Pediatrics, Eastern Virginia Medical School, Norfolk, Virginia, USA
| | | | - Masashi Okubo
- Department of Emergency Medicine, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania, USA
| | - Clifton W Callaway
- Department of Emergency Medicine, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania, USA
| | - Christian Martin-Gill
- Department of Emergency Medicine, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania, USA
| |
Collapse
|
4
|
Briggs J, Kostakis I, Meredith P, Dall'ora C, Darbyshire J, Gerry S, Griffiths P, Hope J, Jones J, Kovacs C, Lawrence R, Prytherch D, Watkinson P, Redfern O. Safer and more efficient vital signs monitoring protocols to identify the deteriorating patients in the general hospital ward: an observational study. HEALTH AND SOCIAL CARE DELIVERY RESEARCH 2024; 12:1-143. [PMID: 38551079 DOI: 10.3310/hytr4612] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 04/02/2024]
Abstract
Background The frequency at which patients should have their vital signs (e.g. blood pressure, pulse, oxygen saturation) measured on hospital wards is currently unknown. Current National Health Service monitoring protocols are based on expert opinion but supported by little empirical evidence. The challenge is finding the balance between insufficient monitoring (risking missing early signs of deterioration and delays in treatment) and over-observation of stable patients (wasting resources needed in other aspects of care). Objective Provide an evidence-based approach to creating monitoring protocols based on a patient's risk of deterioration and link these to nursing workload and economic impact. Design Our study consisted of two parts: (1) an observational study of nursing staff to ascertain the time to perform vital sign observations; and (2) a retrospective study of historic data on patient admissions exploring the relationships between National Early Warning Score and risk of outcome over time. These were underpinned by opinions and experiences from stakeholders. Setting and participants Observational study: observed nursing staff on 16 randomly selected adult general wards at four acute National Health Service hospitals. Retrospective study: extracted, linked and analysed routinely collected data from two large National Health Service acute trusts; data from over 400,000 patient admissions and 9,000,000 vital sign observations. Results Observational study found a variety of practices, with two hospitals having registered nurses take the majority of vital sign observations and two favouring healthcare assistants or student nurses. However, whoever took the observations spent roughly the same length of time. The average was 5:01 minutes per observation over a 'round', including time to locate and prepare the equipment and travel to the patient area. Retrospective study created survival models predicting the risk of outcomes over time since the patient was last observed. For low-risk patients, there was little difference in risk between 4 hours and 24 hours post observation. Conclusions We explored several different scenarios with our stakeholders (clinicians and patients), based on how 'risk' could be managed in different ways. Vital sign observations are often done more frequently than necessary from a bald assessment of the patient's risk, and we show that a maximum threshold of risk could theoretically be achieved with less resource. Existing resources could therefore be redeployed within a changed protocol to achieve better outcomes for some patients without compromising the safety of the rest. Our work supports the approach of the current monitoring protocol, whereby patients' National Early Warning Score 2 guides observation frequency. Existing practice is to observe higher-risk patients more frequently and our findings have shown that this is objectively justified. It is worth noting that important nurse-patient interactions take place during vital sign monitoring and should not be eliminated under new monitoring processes. Our study contributes to the existing evidence on how vital sign observations should be scheduled. However, ultimately, it is for the relevant professionals to decide how our work should be used. Study registration This study is registered as ISRCTN10863045. Funding This award was funded by the National Institute for Health and Care Research (NIHR) Health and Social Care Delivery Research programme (NIHR award ref: 17/05/03) and is published in full in Health and Social Care Delivery Research; Vol. 12, No. 6. See the NIHR Funding and Awards website for further award information.
Collapse
Affiliation(s)
- Jim Briggs
- Centre for Healthcare Modelling and Informatics, University of Portsmouth, Portsmouth, UK
| | - Ina Kostakis
- Centre for Healthcare Modelling and Informatics, University of Portsmouth, Portsmouth, UK
| | - Paul Meredith
- Research Department, Portsmouth Hospitals University NHS Trust, Portsmouth, UK
| | | | - Julie Darbyshire
- Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, UK
| | - Stephen Gerry
- Centre for Statistics in Medicine, University of Oxford, Oxford, UK
| | | | - Jo Hope
- Health Sciences, University of Southampton, Southampton, UK
| | - Jeremy Jones
- Health Sciences, University of Southampton, Southampton, UK
| | - Caroline Kovacs
- Centre for Healthcare Modelling and Informatics, University of Portsmouth, Portsmouth, UK
| | | | - David Prytherch
- Centre for Healthcare Modelling and Informatics, University of Portsmouth, Portsmouth, UK
| | - Peter Watkinson
- Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, UK
| | - Oliver Redfern
- Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, UK
| |
Collapse
|
5
|
Kovoor JG, Bacchi S, Stretton B, Gupta AK, Lam L, Jiang M, Lee S, To MS, Ovenden CD, Hewitt JN, Goh R, Gluck S, Reid JL, Hugh TJ, Dobbins C, Padbury RT, Hewett PJ, Trochsler MI, Flabouris A, Maddern GJ. Vital signs and medical emergency response (MER) activation predict in-hospital mortality in general surgery patients: a study of 15 969 admissions. ANZ J Surg 2023; 93:2426-2432. [PMID: 37574649 DOI: 10.1111/ans.18648] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/09/2023] [Revised: 06/28/2023] [Accepted: 07/21/2023] [Indexed: 08/15/2023]
Abstract
BACKGROUND The applicability of the vital signs prompting medical emergency response (MER) activation has not previously been examined specifically in a large general surgical cohort. This study aimed to characterize the distribution, and predictive performance, of four vital signs selected based on Australian guidelines (oxygen saturation, respiratory rate, systolic blood pressure and heart rate); with those of the MER activation criteria. METHODS A retrospective cohort study was conducted including patients admitted under general surgical services of two hospitals in South Australia over 2 years. Likelihood ratios for patients meeting MER activation criteria, or a vital sign in the most extreme 1% for general surgery inpatients (<0.5th percentile or > 99.5th percentile), were calculated to predict in-hospital mortality. RESULTS 15 969 inpatient admissions were included comprising 2 254 617 total vital sign observations. The 0.5th and 99.5th centile for heart rate was 48 and 133, systolic blood pressure 85 and 184, respiratory rate 10 and 31, and oxygen saturations 89% and 100%, respectively. MER activation criteria with the highest positive likelihood ratio for in-hospital mortality were heart rate ≤ 39 (37.65, 95% CI 27.71-49.51), respiratory rate ≥ 31 (15.79, 95% CI 12.82-19.07), and respiratory rate ≤ 7 (10.53, 95% CI 6.79-14.84). These MER activation criteria likelihood ratios were similar to those derived when applying a threshold of the most extreme 1% of vital signs. CONCLUSIONS This study demonstrated that vital signs within Australian guidelines, and escalation to MER activation, appropriately predict in-hospital mortality in a large cohort of patients admitted to general surgical services in South Australia.
Collapse
Affiliation(s)
- Joshua G Kovoor
- University of Adelaide, Discipline of Surgery, The Queen Elizabeth Hospital, Adelaide, South Australia, Australia
- Royal Australasian College of Surgeons, Adelaide, South Australia, Australia
- Health and Information, Adelaide, South Australia, Australia
| | - Stephen Bacchi
- Health and Information, Adelaide, South Australia, Australia
- University of Adelaide, Adelaide, South Australia, Australia
- Flinders Medical Centre, Adelaide, South Australia, Australia
- Royal Adelaide Hospital, Adelaide, South Australia, Australia
| | - Brandon Stretton
- Health and Information, Adelaide, South Australia, Australia
- University of Adelaide, Adelaide, South Australia, Australia
- Royal Adelaide Hospital, Adelaide, South Australia, Australia
| | - Aashray K Gupta
- Health and Information, Adelaide, South Australia, Australia
- University of Adelaide, Adelaide, South Australia, Australia
- Gold Coast University Hospital, Gold Coast, Queensland, Australia
| | - Lydia Lam
- Health and Information, Adelaide, South Australia, Australia
- University of Adelaide, Adelaide, South Australia, Australia
| | - Melinda Jiang
- Health and Information, Adelaide, South Australia, Australia
- University of Adelaide, Adelaide, South Australia, Australia
- Royal Adelaide Hospital, Adelaide, South Australia, Australia
| | - Shane Lee
- Health and Information, Adelaide, South Australia, Australia
- University of Adelaide, Adelaide, South Australia, Australia
- Royal Adelaide Hospital, Adelaide, South Australia, Australia
| | - Minh-Son To
- Health and Information, Adelaide, South Australia, Australia
- Flinders Medical Centre, Adelaide, South Australia, Australia
| | - Christopher D Ovenden
- Health and Information, Adelaide, South Australia, Australia
- University of Adelaide, Adelaide, South Australia, Australia
- Royal Adelaide Hospital, Adelaide, South Australia, Australia
| | - Joseph N Hewitt
- University of Adelaide, Discipline of Surgery, The Queen Elizabeth Hospital, Adelaide, South Australia, Australia
- Health and Information, Adelaide, South Australia, Australia
- Royal Adelaide Hospital, Adelaide, South Australia, Australia
| | - Rudy Goh
- Health and Information, Adelaide, South Australia, Australia
- University of Adelaide, Adelaide, South Australia, Australia
- Royal Adelaide Hospital, Adelaide, South Australia, Australia
| | - Samuel Gluck
- University of Adelaide, Adelaide, South Australia, Australia
| | - Jessica L Reid
- University of Adelaide, Discipline of Surgery, The Queen Elizabeth Hospital, Adelaide, South Australia, Australia
| | - Thomas J Hugh
- University of Sydney, Sydney, New South Wales, Australia
- Royal North Shore Hospital, Sydney, New South Wales, Australia
| | - Christopher Dobbins
- University of Adelaide, Adelaide, South Australia, Australia
- Royal Adelaide Hospital, Adelaide, South Australia, Australia
| | | | - Peter J Hewett
- University of Adelaide, Discipline of Surgery, The Queen Elizabeth Hospital, Adelaide, South Australia, Australia
| | - Markus I Trochsler
- University of Adelaide, Discipline of Surgery, The Queen Elizabeth Hospital, Adelaide, South Australia, Australia
| | - Arthas Flabouris
- University of Adelaide, Adelaide, South Australia, Australia
- Royal Adelaide Hospital, Adelaide, South Australia, Australia
| | - Guy J Maddern
- University of Adelaide, Discipline of Surgery, The Queen Elizabeth Hospital, Adelaide, South Australia, Australia
- Royal Australasian College of Surgeons, Adelaide, South Australia, Australia
| |
Collapse
|
6
|
Candel BGJ, Nissen SK, Nickel CH, Raven W, Thijssen W, Gaakeer MI, Lassen AT, Brabrand M, Steyerberg EW, de Jonge E, de Groot B. Development and External Validation of the International Early Warning Score for Improved Age- and Sex-Adjusted In-Hospital Mortality Prediction in the Emergency Department. Crit Care Med 2023; 51:881-891. [PMID: 36951452 PMCID: PMC10262984 DOI: 10.1097/ccm.0000000000005842] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/24/2023]
Abstract
OBJECTIVES Early Warning Scores (EWSs) have a great potential to assist clinical decision-making in the emergency department (ED). However, many EWS contain methodological weaknesses in development and validation and have poor predictive performance in older patients. The aim of this study was to develop and externally validate an International Early Warning Score (IEWS) based on a recalibrated National Early warning Score (NEWS) model including age and sex and evaluate its performance independently at arrival to the ED in three age categories (18-65, 66-80, > 80 yr). DESIGN International multicenter cohort study. SETTING Data was used from three Dutch EDs. External validation was performed in two EDs in Denmark. PATIENTS All consecutive ED patients greater than or equal to 18 years in the Netherlands Emergency department Evaluation Database (NEED) with at least two registered vital signs were included, resulting in 95,553 patients. For external validation, 14,809 patients were included from a Danish Multicenter Cohort (DMC). MEASUREMENTS AND MAIN RESULTS Model performance to predict in-hospital mortality was evaluated by discrimination, calibration curves and summary statistics, reclassification, and clinical usefulness by decision curve analysis. In-hospital mortality rate was 2.4% ( n = 2,314) in the NEED and 2.5% ( n = 365) in the DMC. Overall, the IEWS performed significantly better than NEWS with an area under the receiving operating characteristic of 0.89 (95% CIs, 0.89-0.90) versus 0.82 (0.82-0.83) in the NEED and 0.87 (0.85-0.88) versus 0.82 (0.80-0.84) at external validation. Calibration for NEWS predictions underestimated risk in older patients and overestimated risk in the youngest, while calibration improved for IEWS with a substantial reclassification of patients from low to high risk and a standardized net benefit of 5-15% in the relevant risk range for all age categories. CONCLUSIONS The IEWS substantially improves in-hospital mortality prediction for all ED patients greater than or equal to18 years.
Collapse
Affiliation(s)
- Bart Gerard Jan Candel
- Department of Emergency Medicine, Leiden University Medical Center, Leiden, The Netherlands
- Department of Emergency Medicine, Máxima Medical Center, Veldhoven, The Netherlands
| | - Søren Kabell Nissen
- Institute of Regional Health Research, Center South-West Jutland, University of Southern Denmark, Esbjerg, Denmark
- Department of Emergency Medicine, Odense University Hospital, Odense, Denmark
| | - Christian H Nickel
- Department of Emergency Medicine, University Hospital Basel, University of Basel, Basel, Switzerland
| | - Wouter Raven
- Department of Emergency Medicine, Leiden University Medical Center, Leiden, The Netherlands
| | - Wendy Thijssen
- Department of Emergency Medicine, Catharina Hospital Eindhoven, Eindhoven, The Netherlands
| | - Menno I Gaakeer
- Department of Emergency Medicine, Admiraal de Ruyter Hospital, Goes, The Netherlands
| | | | - Mikkel Brabrand
- Institute of Regional Health Research, Center South-West Jutland, University of Southern Denmark, Esbjerg, Denmark
- Department of Emergency Medicine, Odense University Hospital, Odense, Denmark
- Department of Emergency Medicine, Hospital of South-West Jutland, Esbjerg, Denmark
| | - Ewout W Steyerberg
- Department of Public Health, Erasmus University Medical Center, Rotterdam, The Netherlands
- Department of Biomedical Data Sciences, Leiden University Medical Center, Leiden, The Netherlands
| | - Evert de Jonge
- Department of Intensive Care Medicine, Leiden University Medical Center, Leiden, The Netherlands
| | - Bas de Groot
- Department of Emergency Medicine, Radboud University Medical Center, Nijmegen, The Netherlands
| |
Collapse
|
7
|
Placido D, Thorsen-Meyer HC, Kaas-Hansen BS, Reguant R, Brunak S. Development of a dynamic prediction model for unplanned ICU admission and mortality in hospitalized patients. PLOS DIGITAL HEALTH 2023; 2:e0000116. [PMID: 37294826 PMCID: PMC10256150 DOI: 10.1371/journal.pdig.0000116] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/25/2022] [Accepted: 04/24/2023] [Indexed: 06/11/2023]
Abstract
Frequent assessment of the severity of illness for hospitalized patients is essential in clinical settings to prevent outcomes such as in-hospital mortality and unplanned admission to the intensive care unit (ICU). Classical severity scores have been developed typically using relatively few patient features. Recently, deep learning-based models demonstrated better individualized risk assessments compared to classic risk scores, thanks to the use of aggregated and more heterogeneous data sources for dynamic risk prediction. We investigated to what extent deep learning methods can capture patterns of longitudinal change in health status using time-stamped data from electronic health records. We developed a deep learning model based on embedded text from multiple data sources and recurrent neural networks to predict the risk of the composite outcome of unplanned ICU transfer and in-hospital death. The risk was assessed at regular intervals during the admission for different prediction windows. Input data included medical history, biochemical measurements, and clinical notes from a total of 852,620 patients admitted to non-intensive care units in 12 hospitals in Denmark's Capital Region and Region Zealand during 2011-2016 (with a total of 2,241,849 admissions). We subsequently explained the model using the Shapley algorithm, which provides the contribution of each feature to the model outcome. The best model used all data modalities with an assessment rate of 6 hours, a prediction window of 14 days and an area under the receiver operating characteristic curve of 0.898. The discrimination and calibration obtained with this model make it a viable clinical support tool to detect patients at higher risk of clinical deterioration, providing clinicians insights into both actionable and non-actionable patient features.
Collapse
Affiliation(s)
- Davide Placido
- Novo Nordisk Foundation Center for Protein Research, University of Copenhagen, Denmark
| | - Hans-Christian Thorsen-Meyer
- Novo Nordisk Foundation Center for Protein Research, University of Copenhagen, Denmark
- Department of Intensive Care Medicine, Copenhagen University Hospital, Rigshospitalet, Copenhagen, Denmark
| | - Benjamin Skov Kaas-Hansen
- Department of Intensive Care Medicine, Copenhagen University Hospital, Rigshospitalet, Copenhagen, Denmark
- Section for Biostatistics, Department of Public Health, University of Copenhagen, Denmark
| | - Roc Reguant
- Novo Nordisk Foundation Center for Protein Research, University of Copenhagen, Denmark
- Australian e-Health Research Centre, Commonwealth Scientific and Industrial Research Organisation, New South Wales, Sydney, Australia
| | - Søren Brunak
- Novo Nordisk Foundation Center for Protein Research, University of Copenhagen, Denmark
- Copenhagen University Hospital, Rigshospitalet, Copenhagen, Denmark
| |
Collapse
|
8
|
Li XL, Adi D, Zhao Q, Aizezi A, Keremu M, Li YP, Liu F, Ma X, Li XM, Azhati A, Ma YT. Development and validation of nomogram for unplanned ICU admission in patients with dilated cardiomyopathy. Front Cardiovasc Med 2023; 10:1043274. [PMID: 37008312 PMCID: PMC10060526 DOI: 10.3389/fcvm.2023.1043274] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/13/2022] [Accepted: 02/22/2023] [Indexed: 03/18/2023] Open
Abstract
Objective Unplanned admission to the intensive care unit (ICU) is the major in-hospital adverse event for patients with dilated cardiomyopathy (DCM). We aimed to establish a nomogram of individualized risk prediction for unplanned ICU admission in DCM patients. Methods A total of 2,214 patients diagnosed with DCM from the First Affiliated Hospital of Xinjiang Medical University from January 01, 2010, to December 31, 2020, were retrospectively analyzed. Patients were randomly divided into training and validation groups at a 7:3 ratio. The least absolute shrinkage and selection operator and multivariable logistic regression analysis were used for nomogram model development. The area under the receiver operating characteristic curve, calibration curves, and decision curve analysis (DCA) were used to evaluate the model. The primary outcome was defined as unplanned ICU admission. Results A total of 209 (9.44%) patients experienced unplanned ICU admission. The variables in our final nomogram included emergency admission, previous stroke, New York Heart Association Class, heart rate, neutrophil count, and levels of N-terminal pro b-type natriuretic peptide. In the training group, the nomogram showed good calibration (Hosmer-Lemeshow χ 2 = 14.40, P = 0.07) and good discrimination, with an optimal-corrected C-index of 0.76 (95% confidence interval: 0.72-0.80). DCA confirmed the clinical net benefit of the nomogram model, and the nomogram maintained excellent performances in the validation group. Conclusion This is the first risk prediction model for predicting unplanned ICU admission in patients with DCM by simply collecting clinical information. This model may assist physicians in identifying individuals at a high risk of unplanned ICU admission for DCM inpatients.
Collapse
Affiliation(s)
- Xiao-Lei Li
- State Key Laboratory of Pathogenesis, Prevention and Treatment of High Incidence Diseases in Central Asia, Department of Cardiology, First Affiliated Hospital of Xinjiang Medical University, Urumqi, China
- Xinjiang Key Laboratory of Cardiovascular Disease, Clinical Medical Research Institute, First Affiliated Hospital of Xinjiang Medical University, Urumqi, China
| | - Dilare Adi
- State Key Laboratory of Pathogenesis, Prevention and Treatment of High Incidence Diseases in Central Asia, Department of Cardiology, First Affiliated Hospital of Xinjiang Medical University, Urumqi, China
- Xinjiang Key Laboratory of Cardiovascular Disease, Clinical Medical Research Institute, First Affiliated Hospital of Xinjiang Medical University, Urumqi, China
| | - Qian Zhao
- State Key Laboratory of Pathogenesis, Prevention and Treatment of High Incidence Diseases in Central Asia, Department of Cardiology, First Affiliated Hospital of Xinjiang Medical University, Urumqi, China
- Xinjiang Key Laboratory of Cardiovascular Disease, Clinical Medical Research Institute, First Affiliated Hospital of Xinjiang Medical University, Urumqi, China
| | - Aibibanmu Aizezi
- State Key Laboratory of Pathogenesis, Prevention and Treatment of High Incidence Diseases in Central Asia, Department of Cardiology, First Affiliated Hospital of Xinjiang Medical University, Urumqi, China
- Xinjiang Key Laboratory of Cardiovascular Disease, Clinical Medical Research Institute, First Affiliated Hospital of Xinjiang Medical University, Urumqi, China
| | - Munawaer Keremu
- State Key Laboratory of Pathogenesis, Prevention and Treatment of High Incidence Diseases in Central Asia, Department of Cardiology, First Affiliated Hospital of Xinjiang Medical University, Urumqi, China
- Xinjiang Key Laboratory of Cardiovascular Disease, Clinical Medical Research Institute, First Affiliated Hospital of Xinjiang Medical University, Urumqi, China
| | - Yan-Peng Li
- State Key Laboratory of Pathogenesis, Prevention and Treatment of High Incidence Diseases in Central Asia, Department of Cardiology, First Affiliated Hospital of Xinjiang Medical University, Urumqi, China
- Xinjiang Key Laboratory of Cardiovascular Disease, Clinical Medical Research Institute, First Affiliated Hospital of Xinjiang Medical University, Urumqi, China
| | - Fen Liu
- State Key Laboratory of Pathogenesis, Prevention and Treatment of High Incidence Diseases in Central Asia, Department of Cardiology, First Affiliated Hospital of Xinjiang Medical University, Urumqi, China
- Xinjiang Key Laboratory of Cardiovascular Disease, Clinical Medical Research Institute, First Affiliated Hospital of Xinjiang Medical University, Urumqi, China
| | - Xiang Ma
- State Key Laboratory of Pathogenesis, Prevention and Treatment of High Incidence Diseases in Central Asia, Department of Cardiology, First Affiliated Hospital of Xinjiang Medical University, Urumqi, China
- Xinjiang Key Laboratory of Cardiovascular Disease, Clinical Medical Research Institute, First Affiliated Hospital of Xinjiang Medical University, Urumqi, China
| | - Xiao-Mei Li
- State Key Laboratory of Pathogenesis, Prevention and Treatment of High Incidence Diseases in Central Asia, Department of Cardiology, First Affiliated Hospital of Xinjiang Medical University, Urumqi, China
- Xinjiang Key Laboratory of Cardiovascular Disease, Clinical Medical Research Institute, First Affiliated Hospital of Xinjiang Medical University, Urumqi, China
| | - Adila Azhati
- The Emergency Center, First Affiliated Hospital of Xinjiang Medical University, Urumqi, China
| | - Yi-Tong Ma
- State Key Laboratory of Pathogenesis, Prevention and Treatment of High Incidence Diseases in Central Asia, Department of Cardiology, First Affiliated Hospital of Xinjiang Medical University, Urumqi, China
- Xinjiang Key Laboratory of Cardiovascular Disease, Clinical Medical Research Institute, First Affiliated Hospital of Xinjiang Medical University, Urumqi, China
| |
Collapse
|
9
|
Martín-Rodríguez F, Sanz-García A, Ortega GJ, Delgado Benito JF, Aparicio Obregon S, Martínez Fernández FT, González Crespo P, Otero de la Torre S, Castro Villamor MA, López-Izquierdo R. Tracking the National Early Warning Score 2 from Prehospital Care to the Emergency Department: A Prospective, Ambulance-Based, Observational Study. PREHOSP EMERG CARE 2023; 27:75-83. [PMID: 34846982 DOI: 10.1080/10903127.2021.2011995] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/05/2023]
Abstract
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.
Collapse
Affiliation(s)
- Francisco Martín-Rodríguez
- Centro de Simulación Clínica Avanzada, Departamento de Medicina, Dermatología y Toxicología, Universidad de Valladolid. Gerencia de Emergencias Sanitarias, Gerencia Regional de Salud de Castilla y León (SACYL), Valladolid, Spain
| | - Ancor Sanz-García
- Unidad de Análisis de Datos (UAD), del Instituto de Investigación Sanitaria del Hospital de la Princesa (IIS-IP), Madrid, Spain
| | - Guillermo J Ortega
- Unidad de Análisis de Datos (UAD), del Instituto de Investigación Sanitaria del Hospital de la Princesa (IIS-IP), Madrid, Spain.,Consejo Nacional de Investigaciones Científicas y Técnicas, CONICET, Argentina
| | - Juan F Delgado Benito
- Gerencia de Emergencias Sanitarias, Gerencia Regional de Salud de Castilla y León (SACYL), Valladolid, Spain
| | - Silvia Aparicio Obregon
- Parque Científico y Tecnológico de Cantabria, Universidad Europea del Atlántico, Santander, Spain
| | | | - Pilar González Crespo
- Gerencia de Emergencias Sanitarias, Gerencia Regional de Salud de Castilla y León (SACYL), Valladolid, Spain
| | - Santiago Otero de la Torre
- Gerencia de Emergencias Sanitarias, Gerencia Regional de Salud de Castilla y León (SACYL), Valladolid, Spain
| | - Miguel A Castro Villamor
- Centro de Simulación Clínica Avanzada, Departamento de Medicina, Dermatología y Toxicología, Universidad de Valladolid, Spain
| | - Raúl López-Izquierdo
- Servicio de Urgencias, Hospital Universitario Rio Hortega de Valladolid, Gerencia Regional de Salud de Castilla y León (SACYL), Valladolid, Spain
| |
Collapse
|
10
|
Liu H. Financial Risk Intelligent Early Warning System of a Municipal Company Based on Genetic Tabu Algorithm and Big Data Analysis. INTERNATIONAL JOURNAL OF INFORMATION TECHNOLOGIES AND SYSTEMS APPROACH 2022. [DOI: 10.4018/ijitsa.307027] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/09/2022]
Abstract
This paper proposes an intelligent early warning system for financial risk of listed companies based on genetic tabu algorithm and big data analysis. Establish the role application, analyze and complete the financial risk intelligent early warning system of listed companies and query the analysis results. Through the early warning source data management module, financial early warning module and countermeasure management module, the hardware part of the system is designed, the functional modules are divided, the relationship between the internal functions of the system is clear, and the hierarchical structure and call relationship between the modules are established. The key technology of CBR retrieve the matching case. Genetic tabu algorithm establish fitness function, search fitness measure, optimize attribute weight, and design system software. The experimental results show that the financial risk intelligent early warning system has high early warning accuracy, can effectively shorten the early warning time, and meet the needs of financial risk management of listed companies.
Collapse
Affiliation(s)
- Hui Liu
- Huzhou Vocational and Technical College, China
| |
Collapse
|
11
|
Patient Deterioration on General Care Units: A Concept Analysis. ANS Adv Nurs Sci 2022; 45:E56-E68. [PMID: 34879020 DOI: 10.1097/ans.0000000000000396] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/25/2022]
Abstract
Patient deterioration is a phenomenon that occurs from the inability to recognize it or respond to a change in condition. Despite the published reports on recognizing a deteriorating patient on general care floors, a gap remains in the ability of nurses to describe the concept, affecting patient outcomes. Walker and Avant's approach was applied to analyze patient deterioration. The aim of this article was to explore and clarify the meaning of patient deterioration and identify attributes, antecedents, and consequences. The defining attributes were compared to early warning scores. An operational definition was developed and its value to nurses established.
Collapse
|
12
|
Stey AM, Kanzaria HK, Dudley RA, Bilimoria KY, Knudson MM, Callcut RA. Emergency Department Length of Stay and Mortality in Critically Injured Patients. J Intensive Care Med 2022; 37:278-287. [PMID: 33641512 DOI: 10.1177/0885066621995426] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/17/2022]
Abstract
OBJECTIVE Multicenter data from 2 decades ago demonstrated that critically ill and injured patients spending more than 6 hours in the emergency department (ED) before transfer to the intensive care unit (ICU) had higher mortality rates. A contemporary analysis of ED length of stay in critically injured patients at American College of Surgeons' Trauma Quality Improvement Program (ACS-TQIP) centers was performed to test whether prolonged ED length of stay is still associated with mortality. METHODS This was an observational cohort study of critically injured patients admitted directly to ICU from the ED in ACS-TQIP centers from 2010-2015. Spending more than 6 hours in the ED was defined as prolonged ED length of stay. Patients with prolonged ED length of stay were matched to those with non-prolonged ED length of stay and mortality was compared. MAIN RESULTS A total of 113,097 patients were directly admitted from the ED to the ICU following injury. The median ED length of stay was 167 minutes. Prolonged ED length of stay occurred in 15,279 (13.5%) of patients. Women accounted for 29.4% of patients with prolonged ED length of stay but only 25.8% of patients with non-prolonged ED length of stay, P < 0.0001. Mortality rates were similar after matching-4.5% among patients with prolonged ED length of stay versus 4.2% among matched controls. Multivariable logistic regression of the matched cohorts demonstrated prolonged ED length of stay was not associated with mortality. However, women had higher adjusted mortality compared to men Odds Ratio = 1.41, 95% Confidence Interval 1.28 -1.61, P < 0.0001. CONCLUSION Prolonged ED length of stay is no longer associated with mortality among critically injured patients. Women are more likely to have prolonged ED length of stay and mortality.
Collapse
Affiliation(s)
- Anne M Stey
- Northwestern University Feinberg School of Medicine, IL, Chicago
| | - Hemal K Kanzaria
- University of California San Francisco, San Francisco, CA
- Zuckerberg San Francisco General Hospital, San Francisco, CA
| | | | - Karl Y Bilimoria
- Northwestern University Feinberg School of Medicine, IL, Chicago
| | - M Margaret Knudson
- University of California San Francisco, San Francisco, CA
- Zuckerberg San Francisco General Hospital, San Francisco, CA
| | | |
Collapse
|
13
|
Elgwairi E, Yang S, Nugent K. Association of the All-Patient Refined Diagnosis-Related Groups Severity of Illness and Risk of Mortality Classification with Outcomes. South Med J 2021; 114:668-674. [PMID: 34599349 DOI: 10.14423/smj.0000000000001306] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/23/2022]
Abstract
OBJECTIVES Diagnosis-related groups (DRGs) is a patient classification system used to characterize the types of patients that the hospital manages and to compare the resources needed during hospitalization. The DRG classification is based on International Classification of Diseases diagnoses, procedures, demographics, discharge status, and complications or comorbidities and compares hospital resources and outcomes used to determine how much Medicare pays the hospital for each "product/medical condition." The All-Patient Refined DRG (APR-DRG) incorporated severity of illness (SOI) and risk of mortality (ROM) into the DRG system to adjust for patient complexity to compare resource utilization, complication rates, and lengths of stay. METHODS This study included 18,478 adult patients admitted to a tertiary care center in Lubbock, Texas during a 1-year period. We recorded the APR-DRG SOI and ROM and some clinical information on these patients, including age, sex, admission shock index, admission glucose and lactate levels, diagnoses based on International Classification of Diseases, Tenth Revision discharge coding, length of stay, and mortality. We compared the levels of SOI and ROM across this clinical information. RESULTS As the levels of SOI and ROM increase (which indicates increased disease severity and risk of mortality), age, glucose levels, lactate levels, shock index, length of stay, and mortality increased significantly (P < 0.001). Multiple logistic regression analysis demonstrated that each unit increase in ROM and SOI level was significantly associated with an 11.45 and a 10.37 times increase in the odds of in-hospital mortality, respectively. The C-statistics for the corresponding models are 0.947 and 0.929, respectively. When both ROM and SOI were included in the model, the magnitudes of increase in odds of in-hospital mortality were 5.61 and 1.17 times for ROM and SOI, respectively. The C-statistic is 0.949. CONCLUSIONS This study indicates that the APR-DRG SOI and ROM scores provide a classification system that is associated with mortality and correlates with other clinical variables, such as the shock index and lactate levels, which are available on admission.
Collapse
Affiliation(s)
- Emadeldeen Elgwairi
- From the Department of Internal Medicine, Texas Tech University Health Sciences Center, Lubbock, and the Department of Biostatistics, Pennington Biomedical Research Center, Baton Rouge, Louisiana
| | - Shengping Yang
- From the Department of Internal Medicine, Texas Tech University Health Sciences Center, Lubbock, and the Department of Biostatistics, Pennington Biomedical Research Center, Baton Rouge, Louisiana
| | - Kenneth Nugent
- From the Department of Internal Medicine, Texas Tech University Health Sciences Center, Lubbock, and the Department of Biostatistics, Pennington Biomedical Research Center, Baton Rouge, Louisiana
| |
Collapse
|
14
|
Pimentel MAF, Redfern OC, Malycha J, Meredith P, Prytherch D, Briggs J, Young JD, Clifton DA, Tarassenko L, Watkinson PJ. Detecting Deteriorating Patients in the Hospital: Development and Validation of a Novel Scoring System. Am J Respir Crit Care Med 2021; 204:44-52. [PMID: 33525997 PMCID: PMC8437126 DOI: 10.1164/rccm.202007-2700oc] [Citation(s) in RCA: 17] [Impact Index Per Article: 5.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/07/2020] [Accepted: 02/01/2021] [Indexed: 12/23/2022] Open
Abstract
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.
Collapse
Affiliation(s)
| | - Oliver C. Redfern
- Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, United Kingdom
| | - James Malycha
- Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, United Kingdom
| | - Paul Meredith
- Research and Innovation Department, Portsmouth Hospitals University National Health Service Trust, Portsmouth, United Kingdom
| | - David Prytherch
- Centre for Healthcare Modelling and Informatics, University of Portsmouth, Portsmouth, United Kingdom; and
| | - Jim Briggs
- Centre for Healthcare Modelling and Informatics, University of Portsmouth, Portsmouth, United Kingdom; and
| | - J. Duncan Young
- Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, United Kingdom
| | - David A. Clifton
- Institute of Biomedical Engineering, Department of Engineering Science, and
| | - Lionel Tarassenko
- Institute of Biomedical Engineering, Department of Engineering Science, and
| | - Peter J. Watkinson
- Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, United Kingdom
- Kadoorie Centre for Critical Care Research and Education, Oxford University Hospitals National Health Service Trust, Oxford, United Kingdom
| |
Collapse
|
15
|
Youssef A, Kouchaki S, Shamout F, Armstrong J, El-Bouri R, Taylor T, Birrenkott D, Vasey B, Soltan A, Zhu T, Clifton DA, Eyre DW. Development and validation of early warning score systems for COVID-19 patients. Healthc Technol Lett 2021; 8:105-117. [PMID: 34221413 PMCID: PMC8239612 DOI: 10.1049/htl2.12009] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/08/2020] [Revised: 02/22/2021] [Accepted: 03/19/2021] [Indexed: 12/15/2022] Open
Abstract
COVID‐19 is a major, urgent, and ongoing threat to global health. Globally more than 24 million have been infected and the disease has claimed more than a million lives as of November 2020. Predicting which patients will need respiratory support is important to guiding individual patient treatment and also to ensuring sufficient resources are available. The ability of six common Early Warning Scores (EWS) to identify respiratory deterioration defined as the need for advanced respiratory support (high‐flow nasal oxygen, continuous positive airways pressure, non‐invasive ventilation, intubation) within a prediction window of 24 h is evaluated. It is shown that these scores perform sub‐optimally at this specific task. Therefore, an alternative EWS based on the Gradient Boosting Trees (GBT) algorithm is developed that is able to predict deterioration within the next 24 h with high AUROC 94% and an accuracy, sensitivity, and specificity of 70%, 96%, 70%, respectively. The GBT model outperformed the best EWS (LDTEWS:NEWS), increasing the AUROC by 14%. Our GBT model makes the prediction based on the current and baseline measures of routinely available vital signs and blood tests.
Collapse
Affiliation(s)
- Alexey Youssef
- Department of Engineering Science Institute of Biomedical Engineering University of Oxford Oxford UK
| | - Samaneh Kouchaki
- Department of Engineering Science Institute of Biomedical Engineering University of Oxford Oxford UK.,Centre for Vision, Speech, and Signal Processing University of Surrey Guildford UK
| | - Farah Shamout
- Engineering Division New York University Abu Dhabi Abu Dhabi United Arab Emirates
| | - Jacob Armstrong
- Department of Engineering Science Institute of Biomedical Engineering University of Oxford Oxford UK.,Big Data Institute Nuffield Department of Population Health University of Oxford Oxford UK
| | - Rasheed El-Bouri
- Department of Engineering Science Institute of Biomedical Engineering University of Oxford Oxford UK
| | - Thomas Taylor
- Department of Engineering Science Institute of Biomedical Engineering University of Oxford Oxford UK
| | - Drew Birrenkott
- Stanford School of Medicine Stanford University Palo Alto USA
| | - Baptiste Vasey
- Department of Engineering Science Institute of Biomedical Engineering University of Oxford Oxford UK.,Nuffield Department of Surgical Sciences University of Oxford Oxford UK
| | - Andrew Soltan
- John Radcliffe Hospital Oxford University Hospitals NHS Foundation Trust Oxford UK.,Division of Cardiovascular Medicine Radcliffe Department of Medicine John Radcliffe Hospital University of Oxford Oxford UK
| | - Tingting Zhu
- Department of Engineering Science Institute of Biomedical Engineering University of Oxford Oxford UK
| | - David A Clifton
- Department of Engineering Science Institute of Biomedical Engineering University of Oxford Oxford UK.,Oxford-Suzhou Centre for Advanced Research Suzhou China
| | - David W Eyre
- Big Data Institute Nuffield Department of Population Health University of Oxford Oxford UK.,John Radcliffe Hospital Oxford University Hospitals NHS Foundation Trust Oxford UK
| |
Collapse
|
16
|
Froom P, Shimoni Z, Benbassat J, Silke B. A simple index predicting mortality in acutely hospitalized patients. QJM 2021; 114:99-104. [PMID: 33079191 DOI: 10.1093/qjmed/hcaa293] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/24/2020] [Revised: 09/10/2020] [Indexed: 12/13/2022] Open
Abstract
BACKGROUND Mortality rates used to evaluate and improve the quality of hospital care are adjusted for comorbidity and disease severity. Comorbidity, measured by International Classification of Diseases codes, do not reflect the severity of the medical condition, that requires clinical assessments not available in electronic databases, and/or laboratory data with clinically relevant ranges to permit extrapolation from one setting to the next. AIM To propose a simple index predicting mortality in acutely hospitalized patients. DESIGN Retrospective cohort study with internal and external validation. METHODS The study populations were all acutely admitted patients in 2015-16, and in January 2019-November 2019 to internal medicine, cardiology and intensive care departments at the Laniado Hospital in Israel, and in 2002-19, at St. James Hospital, Ireland. Predictor variables were age and admission laboratory tests. The outcome variable was in-hospital mortality. Using logistic regression of the data in the 2015-16 Israeli cohort, we derived an index that included age groups and significant laboratory data. RESULTS In the Israeli 2015-16 cohort, the index predicted mortality rates from 0.2% to 32.0% with a c-statistic (area under the receiver operator characteristic curve) of 0.86. In the Israeli 2019 validation cohort, the index predicted mortality rates from 0.3% to 38.9% with a c-statistic of 0.87. An abbreviated index performed similarly in the Irish 2002-19 cohort. CONCLUSIONS Hospital mortality can be predicted by age and selected admission laboratory data without acquiring information from the patient's medical records. This permits an inexpensive comparison of performance of hospital departments.
Collapse
Affiliation(s)
- P Froom
- From the Clinical Utility Department, Sanz Medical Center, Laniado Hospital, Netanya 4244916, Israel
- School of Public Health, University of Tel Aviv, Israel
| | - Z Shimoni
- Department of Internal Medicine B, Laniado Hospital, Netanya 4244916, Israel
- Ruth and Bruce Rappaport School of Medicine, Haifa, Israel
| | - J Benbassat
- Department of Medicine (retired), Hadassah University Hospital, Jerusalem, Israel
| | - B Silke
- Division of Internal Medicine, St. James' Hospital, Dublin 8, Ireland
| |
Collapse
|
17
|
Green LJ, Pullon R, Mackillop LH, Gerry S, Birks J, Salvi D, Davidson S, Loerup L, Tarassenko L, Mossop J, Edwards C, Gauntlett R, Harding K, Chappell LC, Knight M, Watkinson PJ. Postpartum-Specific Vital Sign Reference Ranges. Obstet Gynecol 2021; 137:295-304. [PMID: 33417320 PMCID: PMC7813441 DOI: 10.1097/aog.0000000000004239] [Citation(s) in RCA: 13] [Impact Index Per Article: 4.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/03/2020] [Revised: 10/16/2020] [Accepted: 10/22/2020] [Indexed: 11/25/2022]
Abstract
OBJECTIVE To estimate normal ranges for postpartum maternal vital signs. METHODS We conducted a multicenter prospective longitudinal cohort study in the United Kingdom. We recruited women before 20 weeks of gestation without significant comorbidities and with accurately dated singleton pregnancies. Women recorded their own blood pressure, heart rate, oxygen saturation and temperature daily for 2 weeks postpartum. Trained midwives measured participants' vital signs including respiratory rate around postpartum days 1, 7, and 14. RESULTS From August 2012 to September 2016, we screened 4,279 pregnant women; 1,054 met eligibility criteria and chose to take part. Postpartum vital sign data were available for 909 women (86.2%). Median, or 50th centile (3rd-97th centile), systolic and diastolic blood pressures increased from the day of birth: 116 mm Hg (88-147) and 74 mm Hg (59-93) to a maximum median of 121 mm Hg (102-143) and 79 mm Hg (63-94) on days 5 and 6 postpartum, respectively, an increase of 5 mm Hg (95% CI 3-7) and 5 mm Hg (95% CI 4-6), respectively. Median (3rd-97th centile) systolic and diastolic blood pressure returned to 116 mm Hg (98-137) and 75 mm Hg (61-91) by day 14 postpartum. The median (3rd-97th centile) heart rate was highest on the day of birth, 84 beats per minute (bpm) (59-110) decreasing to a minimum of 75 bpm (55-101) 14 days postpartum. Oxygen saturation, respiratory rate, and temperature did not change in the 2 weeks postbirth. Median (3rd-97th centile) day-of-birth oxygen saturation was 96% (93-98). Median (3rd-97th centile) day-of-birth respiratory rate was 15 breaths per minute (10-22). Median (3rd-97th centile) day-of-birth temperature was 36.7°C (35.6-37.6). CONCLUSION We present widely relevant, postpartum, day-specific reference ranges which may facilitate early detection of abnormal blood pressure, heart rate, respiratory rate, oxygen saturation and temperature during the puerperium. Our findings could inform construction of an evidence-based modified obstetric early warning system to better identify unwell postpartum women. CLINICAL TRIAL REGISTRATION ISRCTN, 10838017.
Collapse
Affiliation(s)
- Lauren J Green
- Nuffield Department of Clinical Neurosciences, the Institute of Biomedical Engineering, Department of Engineering Science, the Nuffield Department of Women's & Reproductive Health, and the Centre for Statistics in Medicine, University of Oxford, Oxford, United Kingdom; the Department of Anaesthesia, Wellington Hospital, Wellington, New Zealand; and Guy's and St Thomas' NHS Foundation Trust and the Department of Women and Children's Health, King's College, London, and the National Perinatal Epidemiology Unit and the Oxford National Institute for Health Research Biomedical Research Centre, Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, United Kingdom
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
Collapse
|
18
|
Abstract
Clinical decision-making in healthcare is already being influenced by predictions or recommendations made by data-driven machines. Numerous machine learning applications have appeared in the latest clinical literature, especially for outcome prediction models, with outcomes ranging from mortality and cardiac arrest to acute kidney injury and arrhythmia. In this review article, we summarize the state-of-the-art in related works covering data processing, inference, and model evaluation, in the context of outcome prediction models developed using data extracted from electronic health records. We also discuss limitations of prominent modeling assumptions and highlight opportunities for future research.
Collapse
|
19
|
Zhu Y, Chiu YD, Villar SS, Brand JW, Patteril MV, Morrice DJ, Clayton J, Mackay JH. Dynamic individual vital sign trajectory early warning score (DyniEWS) versus snapshot national early warning score (NEWS) for predicting postoperative deterioration. Resuscitation 2020; 157:176-184. [PMID: 33181231 PMCID: PMC7762721 DOI: 10.1016/j.resuscitation.2020.10.037] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/26/2020] [Revised: 10/15/2020] [Accepted: 10/28/2020] [Indexed: 12/12/2022]
Abstract
Aims International early warning scores (EWS) including the additive National Early Warning Score (NEWS) and logistic EWS currently utilise physiological snapshots to predict clinical deterioration. We hypothesised that a dynamic score including vital sign trajectory would improve discriminatory power. Methods Multicentre retrospective analysis of electronic health record data from postoperative patients admitted to cardiac surgical wards in four UK hospitals. Least absolute shrinkage and selection operator-type regression (LASSO) was used to develop a dynamic model (DyniEWS) to predict a composite adverse event of cardiac arrest, unplanned intensive care re-admission or in-hospital death within 24 h. Results A total of 13,319 postoperative adult cardiac patients contributed 442,461 observations of which 4234 (0.96%) adverse events in 24 h were recorded. The new dynamic model (AUC = 0.80 [95% CI 0.78−0.83], AUPRC = 0.12 [0.10−0.14]) outperforms both an updated snapshot logistic model (AUC = 0.76 [0.73−0.79], AUPRC = 0.08 [0.60−0.10]) and the additive National Early Warning Score (AUC = 0.73 [0.70−0.76], AUPRC = 0.05 [0.02−0.08]). Controlling for the false alarm rates to be at current levels using NEWS cut-offs of 5 and 7, DyniEWS delivers a 7% improvement in balanced accuracy and increased sensitivities from 41% to 54% at NEWS 5 and 18% to –30% at NEWS 7. Conclusions Using an advanced statistical approach, we created a model that can detect dynamic changes in risk of unplanned readmission to intensive care, cardiac arrest or in-hospital mortality and can be used in real time to risk-prioritise clinical workload.
Collapse
Affiliation(s)
- Yajing Zhu
- MRC Biostatistics Unit, School of Clinical Medicine, University of Cambridge, Cambridge, UK.
| | - Yi-Da Chiu
- MRC Biostatistics Unit, School of Clinical Medicine, University of Cambridge, Cambridge, UK; Research and Development, Royal Papworth Hospital, Cambridge, UK.
| | - Sofia S Villar
- MRC Biostatistics Unit, School of Clinical Medicine, University of Cambridge, Cambridge, UK; Research and Development, Royal Papworth Hospital, Cambridge, UK.
| | - Jonathan W Brand
- Department of Anaesthesia and Critical Care, James Cook University Hospital, Middlesbrough, UK.
| | - Mathew V Patteril
- Department of Anaesthesia and Critical Care, University Hospitals Coventry and Warwickshire, Coventry, UK.
| | - David J Morrice
- Department of Anaesthesia and Critical Care, New Cross Hospital, Wolverhampton, UK.
| | - James Clayton
- Clinical Governance, Royal Papworth Hospital, Cambridge, UK.
| | - Jonathan H Mackay
- Department of Anaesthesia and Critical Care, Royal Papworth Hospital, Cambridge, UK.
| |
Collapse
|
20
|
Fang AHS, Lim WT, Balakrishnan T. Early warning score validation methodologies and performance metrics: a systematic review. BMC Med Inform Decis Mak 2020; 20:111. [PMID: 32552702 PMCID: PMC7301346 DOI: 10.1186/s12911-020-01144-8] [Citation(s) in RCA: 22] [Impact Index Per Article: 5.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/17/2019] [Accepted: 06/03/2020] [Indexed: 01/06/2023] Open
Abstract
BACKGROUND Early warning scores (EWS) have been developed as clinical prognostication tools to identify acutely deteriorating patients. In the past few years, there has been a proliferation of studies that describe the development and validation of novel machine learning-based EWS. Systematic reviews of published studies which focus on evaluating performance of both well-established and novel EWS have shown conflicting conclusions. A possible reason is the heterogeneity in validation methods applied. In this review, we aim to examine the methodologies and metrics used in studies which perform EWS validation. METHODS A systematic review of all eligible studies from the MEDLINE database and other sources, was performed. Studies were eligible if they performed validation on at least one EWS and reported associations between EWS scores and inpatient mortality, intensive care unit (ICU) transfers, or cardiac arrest (CA) of adults. Two reviewers independently did a full-text review and performed data abstraction by using standardized data-worksheet based on the TRIPOD (Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis) checklist. Meta-analysis was not performed due to heterogeneity. RESULTS The key differences in validation methodologies identified were (1) validation dataset used, (2) outcomes of interest, (3) case definition, time of EWS use and aggregation methods, and (4) handling of missing values. In terms of case definition, among the 48 eligible studies, 34 used the patient episode case definition while 12 used the observation set case definition, and 2 did the validation using both case definitions. Of those that used the patient episode case definition, 18 studies validated the EWS at a single point of time, mostly using the first recorded observation. The review also found more than 10 different performance metrics reported among the studies. CONCLUSIONS Methodologies and performance metrics used in studies performing validation on EWS were heterogeneous hence making it difficult to interpret and compare EWS performance. Standardizing EWS validation methodology and reporting can potentially address this issue.
Collapse
Affiliation(s)
| | - Wan Tin Lim
- Department of Internal Medicine, Singapore General Hospital, Singapore, Singapore
| | | |
Collapse
|
21
|
Gerry S, Bonnici T, Birks J, Kirtley S, Virdee PS, Watkinson PJ, Collins GS. Early warning scores for detecting deterioration in adult hospital patients: systematic review and critical appraisal of methodology. BMJ 2020; 369:m1501. [PMID: 32434791 PMCID: PMC7238890 DOI: 10.1136/bmj.m1501] [Citation(s) in RCA: 136] [Impact Index Per Article: 34.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Accepted: 03/25/2020] [Indexed: 12/30/2022]
Abstract
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.
Collapse
Affiliation(s)
- Stephen Gerry
- Centre for Statistics in Medicine, Nuffield Department of Orthopaedics, Rheumatology and Musculoskeletal Sciences, University of Oxford, Oxford OX3 7LD, UK
| | - Timothy Bonnici
- Critical Care Division, University College London Hospitals NHS Trust, London, UK
| | - Jacqueline Birks
- Centre for Statistics in Medicine, Nuffield Department of Orthopaedics, Rheumatology and Musculoskeletal Sciences, University of Oxford, Oxford OX3 7LD, UK
- Oxford University Hospitals NHS Foundation Trust, Oxford, UK
| | - Shona Kirtley
- Centre for Statistics in Medicine, Nuffield Department of Orthopaedics, Rheumatology and Musculoskeletal Sciences, University of Oxford, Oxford OX3 7LD, UK
| | - Pradeep S Virdee
- Centre for Statistics in Medicine, Nuffield Department of Orthopaedics, Rheumatology and Musculoskeletal Sciences, University of Oxford, Oxford OX3 7LD, UK
| | - Peter J Watkinson
- Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, UK
| | - Gary S Collins
- Centre for Statistics in Medicine, Nuffield Department of Orthopaedics, Rheumatology and Musculoskeletal Sciences, University of Oxford, Oxford OX3 7LD, UK
- Oxford University Hospitals NHS Foundation Trust, Oxford, UK
| |
Collapse
|
22
|
Fu LH, Schwartz J, Moy A, Knaplund C, Kang MJ, Schnock KO, Garcia JP, Jia H, Dykes PC, Cato K, Albers D, Rossetti SC. Development and validation of early warning score system: A systematic literature review. J Biomed Inform 2020; 105:103410. [PMID: 32278089 PMCID: PMC7295317 DOI: 10.1016/j.jbi.2020.103410] [Citation(s) in RCA: 43] [Impact Index Per Article: 10.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/12/2019] [Revised: 03/19/2020] [Accepted: 03/21/2020] [Indexed: 12/23/2022]
Abstract
OBJECTIVES 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. METHODOLOGY 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. RESULTS 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. CONCLUSION 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.
Collapse
Affiliation(s)
- Li-Heng Fu
- Department of Biomedical Informatics, Columbia University, New York, NY, United States.
| | - Jessica Schwartz
- School of Nursing, Columbia University, New York, NY, United States
| | - Amanda Moy
- Department of Biomedical Informatics, Columbia University, New York, NY, United States
| | - Chris Knaplund
- Department of Biomedical Informatics, Columbia University, New York, NY, United States
| | - Min-Jeoung Kang
- Division of General Internal Medicine and Primary Care, Brigham and Women's Hospital, Boston, MA, United States; Harvard Medical School, Boston, MA, United States
| | - Kumiko O Schnock
- Division of General Internal Medicine and Primary Care, Brigham and Women's Hospital, Boston, MA, United States; Harvard Medical School, Boston, MA, United States
| | - Jose P Garcia
- Division of General Internal Medicine and Primary Care, Brigham and Women's Hospital, Boston, MA, United States
| | - Haomiao Jia
- School of Nursing, Columbia University, New York, NY, United States; Department of Biostatistics, Mailman School of Public Health, Columbia University, New York, NY, United States
| | - Patricia C Dykes
- Division of General Internal Medicine and Primary Care, Brigham and Women's Hospital, Boston, MA, United States; Harvard Medical School, Boston, MA, United States
| | - Kenrick Cato
- School of Nursing, Columbia University, New York, NY, United States
| | - David Albers
- Department of Biomedical Informatics, Columbia University, New York, NY, United States; Department of Pediatrics, Section of Informatics and Data Science, University of Colorado, Aurora, CO, United States
| | - Sarah Collins Rossetti
- Department of Biomedical Informatics, Columbia University, New York, NY, United States; School of Nursing, Columbia University, New York, NY, United States
| |
Collapse
|
23
|
Green LJ, Mackillop LH, Salvi D, Pullon R, Loerup L, Tarassenko L, Mossop J, Edwards C, Gerry S, Birks J, Gauntlett R, Harding K, Chappell LC, Watkinson PJ. Gestation-Specific Vital Sign Reference Ranges in Pregnancy. Obstet Gynecol 2020; 135:653-664. [DOI: 10.1097/aog.0000000000003721] [Citation(s) in RCA: 43] [Impact Index Per Article: 10.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/05/2023]
|
24
|
Chiu Y, Villar SS, Brand JW, Patteril MV, Morrice DJ, Clayton J, Mackay JH. Logistic early warning scores to predict death, cardiac arrest or unplanned intensive care unit re-admission after cardiac surgery. Anaesthesia 2020; 75:162-170. [PMID: 31270799 PMCID: PMC6954099 DOI: 10.1111/anae.14755] [Citation(s) in RCA: 19] [Impact Index Per Article: 4.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 06/04/2019] [Indexed: 01/05/2023]
Abstract
NHS England recently mandated that the National Early Warning Score of vital signs be used in all acute hospital trusts in the UK despite limited validation in the postoperative setting. We undertook a multicentre UK study of 13,631 patients discharged from intensive care after risk-stratified cardiac surgery in four centres, all of which used VitalPACTM to electronically collect postoperative National Early Warning Score vital signs. We analysed 540,127 sets of vital signs to generate a logistic score, the discrimination of which we compared with the national additive score for the composite outcome of: in-hospital death; cardiac arrest; or unplanned intensive care admission. There were 578 patients (4.2%) with an outcome that followed 4300 sets of observations (0.8%) in the preceding 24 h: 499 out of 578 (86%) patients had unplanned re-admissions to intensive care. Discrimination by the logistic score was significantly better than the additive score. Respective areas (95%CI) under the receiver-operating characteristic curve with 24-h and 6-h vital signs were: 0.779 (0.771-0.786) vs. 0.754 (0.746-0.761), p < 0.001; and 0.841 (0.829-0.853) vs. 0.813 (0.800-0.825), p < 0.001, respectively. Our proposed logistic Early Warning Score was better than the current National Early Warning Score at discriminating patients who had an event after cardiac surgery from those who did not.
Collapse
Affiliation(s)
- Y.‐D. Chiu
- Department of Anaesthesia and Intensive CareRoyal Papworth HospitalCambridgeUK
- MRC Biostatistics UnitSchool of Clinical MedicineUniversity of CambridgeUK
| | - S. S. Villar
- MRC Biostatistics UnitSchool of Clinical MedicineUniversity of CambridgeUK
| | - J. W. Brand
- Department of Anaesthesia and Critical CareJames Cook University HospitalMiddlesbroughUK
| | - M. V. Patteril
- Department of Anaesthesia and Critical CareUniversity Hospitals Coventry and WarwickshireCoventryUK
| | - D. J. Morrice
- Department of Anaesthesia and Critical CareNew Cross HospitalWolverhamptonUK
| | - J. Clayton
- Department of Anaesthesia and Intensive CareRoyal Papworth HospitalCambridgeUK
| | - J. H. Mackay
- Department of Anaesthesia and Intensive CareRoyal Papworth HospitalCambridgeUK
| |
Collapse
|
25
|
Shamout F, Zhu T, Clifton L, Briggs J, Prytherch D, Meredith P, Tarassenko L, Watkinson PJ, Clifton DA. Early warning score adjusted for age to predict the composite outcome of mortality, cardiac arrest or unplanned intensive care unit admission using observational vital-sign data: a multicentre development and validation. BMJ Open 2019; 9:e033301. [PMID: 31748313 PMCID: PMC6887005 DOI: 10.1136/bmjopen-2019-033301] [Citation(s) in RCA: 16] [Impact Index Per Article: 3.2] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/01/2019] [Revised: 09/18/2019] [Accepted: 10/16/2019] [Indexed: 02/06/2023] Open
Abstract
OBJECTIVES Early warning scores (EWS) alerting for in-hospital deterioration are commonly developed using routinely collected vital-sign data from the whole in-hospital population. As these in-hospital populations are dominated by those over the age of 45 years, resultant scores may perform less well in younger age groups. We developed and validated an age-specific early warning score (ASEWS) derived from statistical distributions of vital signs. DESIGN Observational cohort study. SETTING Oxford University Hospitals (OUH) July 2013 to March 2018 and Portsmouth Hospitals (PH) NHS Trust January 2010 to March 2017 within the Hospital Alerting Via Electronic Noticeboard database. PARTICIPANTS Hospitalised patients with electronically documented vital-sign observations OUTCOME: Composite outcome of unplanned intensive care unit admission, mortality and cardiac arrest. METHODS AND RESULTS Statistical distributions of vital signs were used to develop an ASEWS to predict the composite outcome within 24 hours. The OUH development set consisted of 2 538 099 vital-sign observation sets from 142 806 admissions (mean age (SD): 59.8 (20.3)). We compared the performance of ASEWS to the National Early Warning Score (NEWS) and our previous EWS (MCEWS) on an OUH validation set consisting of 581 571 observation sets from 25 407 emergency admissions (mean age (SD): 63.0 (21.4)) and a PH validation set consisting of 5 865 997 observation sets from 233 632 emergency admissions (mean age (SD): 64.3 (21.1)). ASEWS performed better in the 16-45 years age group in the OUH validation set (AUROC 0.820 (95% CI 0.815 to 0.824)) and PH validation set (AUROC 0.840 (95% CI 0.839 to 0.841)) than NEWS (AUROC 0.763 (95% CI 0.758 to 0.768) and AUROC 0.836 (95% CI 0.835 to 0.838) respectively) and MCEWS (AUROC 0.808 (95% CI 0.803 to 0.812) and AUROC 0.833 (95% CI 0.831 to 0.834) respectively). Differences in performance were not consistent in the elder age group. CONCLUSIONS Accounting for age-related vital sign changes can more accurately detect deterioration in younger patients.
Collapse
Affiliation(s)
- Farah Shamout
- Institute of Biomedical Engineering, University of Oxford, Oxford, UK
| | - Tingting Zhu
- Institute of Biomedical Engineering, University of Oxford, Oxford, UK
| | - Lei Clifton
- Nuffield Department of Population Health, University of Oxford, Oxford, UK
| | - Jim Briggs
- Centre for Healthcare Modelling and Informatics, University of Portsmouth, Portsmouth, UK
| | - David Prytherch
- Centre for Healthcare Modelling and Informatics, University of Portsmouth, Portsmouth, UK
| | - Paul Meredith
- Research and Innovation Department, Portsmouth Hospitals NHS Trust, Portsmouth, UK
| | - Lionel Tarassenko
- Institute of Biomedical Engineering, University of Oxford, Oxford, UK
| | - Peter J Watkinson
- Nuffield Department of Clinical Neurosciences, Oxford University Hospitals NHS Trust, Oxford, UK
| | - David A Clifton
- Institute of Biomedical Engineering, University of Oxford, Oxford, UK
| |
Collapse
|
26
|
Increasing Cardiovascular Data Sampling Frequency and Referencing It to Baseline Improve Hemorrhage Detection. Crit Care Explor 2019; 1:e0058. [PMID: 32166238 PMCID: PMC7063895 DOI: 10.1097/cce.0000000000000058] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/20/2023] Open
Abstract
Supplemental Digital Content is available in the text. We hypothesize that knowledge of a stable personalized baseline state and increased data sampling frequency would markedly improve the ability to detect progressive hypovolemia during hemorrhage earlier and with a lower false positive rate than when using less granular data.
Collapse
|
27
|
Shamout FE, Zhu T, Sharma P, Watkinson PJ, Clifton DA. Deep Interpretable Early Warning System for the Detection of Clinical Deterioration. IEEE J Biomed Health Inform 2019; 24:437-446. [PMID: 31545746 DOI: 10.1109/jbhi.2019.2937803] [Citation(s) in RCA: 30] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/09/2022]
Abstract
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.
Collapse
|
28
|
Malycha J, Farajidavar N, Pimentel MAF, Redfern O, Clifton DA, Tarassenko L, Meredith P, Prytherch D, Ludbrook G, Young JD, Watkinson PJ. The effect of fractional inspired oxygen concentration on early warning score performance: A database analysis. Resuscitation 2019; 139:192-199. [PMID: 31005587 PMCID: PMC6547016 DOI: 10.1016/j.resuscitation.2019.04.002] [Citation(s) in RCA: 14] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/24/2019] [Revised: 03/05/2019] [Accepted: 04/01/2019] [Indexed: 11/21/2022]
Abstract
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.
Collapse
Affiliation(s)
- James Malycha
- Kadoorie Centre for Critical Care Research and Education, Nuffield Department of Clinical Neurosciences, University of Oxford, Level 3, John Radcliffe Hospital, Headley Way, Oxford, OX3 9DU, United Kingdom.
| | - Nazli Farajidavar
- James Black Centre, King's College London, London SE5 9NU, United Kingdom.
| | - Marco A F Pimentel
- Institute of Biomedical Engineering, Department of Engineering Science University of Oxford, Old Road Campus Roosevelt Drive, Oxford OX3 7DQ, United Kingdom.
| | - Oliver Redfern
- Kadoorie Centre for Critical Care Research and Education, Nuffield Department of Clinical Neurosciences, University of Oxford, Level 3, John Radcliffe Hospital, Headley Way, Oxford, OX3 9DU, United Kingdom.
| | - David A Clifton
- Institute of Biomedical Engineering, Department of Engineering Science University of Oxford, Old Road Campus Roosevelt Drive, Oxford OX3 7DQ, United Kingdom.
| | - Lionel Tarassenko
- Institute of Biomedical Engineering, Department of Engineering Science University of Oxford, Old Road Campus Roosevelt Drive, Oxford OX3 7DQ, United Kingdom.
| | - Paul Meredith
- Research and Innovation Department, Portsmouth Hospitals NHS Trust, Portsmouth PO6 3LY, United Kingdom.
| | - David Prytherch
- Centre for Healthcare Modelling & Informatics, School of Computing, University of Portsmouth, Portsmouth PO1 2UP, United Kingdom.
| | - Guy Ludbrook
- University of Adelaide, Faculty of Health and Medical Science, North Terrace, AHMS Floor 8, 5000, Australia.
| | - J Duncan Young
- Kadoorie Centre for Critical Care Research and Education, Nuffield Department of Clinical Neurosciences, University of Oxford, Level 3, John Radcliffe Hospital, Headley Way, Oxford, OX3 9DU, United Kingdom.
| | - Peter J Watkinson
- NIHR Biomedical Research Centre Oxford, Kadoorie Centre for Critical Care Research and Education, Nuffield Department of Clinical Neurosciences, University of Oxford, Level 3, John Radcliffe Hospital, Headley Way, Oxford OX3 9DU, United Kingdom.
| |
Collapse
|
29
|
Postanesthesia care by remote monitoring of vital signs in surgical wards. Curr Opin Anaesthesiol 2018; 31:716-722. [DOI: 10.1097/aco.0000000000000650] [Citation(s) in RCA: 17] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/29/2022]
|