Dataset Information

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

ABSTRACT:

Background

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

Objective

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

Methods

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

Results

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

Conclusions

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

SUBMITTER: Muralitharan S

PROVIDER: S-EPMC7892287 | biostudies-literature | 2021 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

Muralitharan Sankavi S Nelson Walter W Di Shuang S McGillion Michael M Devereaux P J PJ Barr Neil Grant NG Petch Jeremy J

Journal of medical Internet research 20210204 2

<h4>Background</h4>Timely identification of patients at a high risk of clinical deterioration is key to prioritizing care, allocating resources effectively, and preventing adverse outcomes. Vital signs-based, aggregate-weighted early warning systems are commonly used to predict the risk of outcomes related to cardiorespiratory instability and sepsis, which are strong predictors of poor outcomes and mortality. Machine learning models, which can incorporate trends and capture relationships among p ...[more]

PMID: 33538696

Similar Datasets

Project description:AimWe conducted a systematic review and meta-analysis to answer the question: Does the implementation of Paediatric Early Warning Systems (PEWS) in the hospital setting reduce mortality, cardiopulmonary arrests, unplanned codes and critical deterioration events among children, as compared to usual care without PEWS?MethodsWe conducted a comprehensive search using Medline, EMBASE, Cochrane Central Register of Controlled Trials, Cumulative Index to Nursing and Allied Health Literature and Web of Science. We included studies published between January 2006 and April 2022 on children <18 years old performed in inpatient units and emergency departments, and compared patient populations with PEWS to those without PEWS. We excluded studies without a comparator, case control studies, systematic reviews, and studies published in non-English languages. We employed a random effects meta-analysis and synthesised the risk and rate ratios from individual studies. We used the Scottish Intercollegiate Guidelines Network (SIGN) to appraise the risk of bias.ResultsAmong 911 articles screened, 15 were included for descriptive analysis. Fourteen of the 15 studies were pre- versus post-implementation studies and one was a multi-centre cluster randomised controlled trial (RCT). Among 10 studies (580,604 hospital admissions) analysed for mortality, we found an increased risk (pooled RR 1.18, 95% CI 1.01-1.38, p = 0.036) in the group without PEWS compared to the group with PEWS. The sensitivity analysis performed without the RCT (436,065 hospital admissions) showed a non-significant relationship (pooled RR 1.17, 95% CI 0.98-1.40, p = 0.087). Among four studies (168,544 hospital admissions) analysed for unplanned code events, there was an increased risk in the group without PEWS (pooled RR 1.73, 95%CI 1.01-2.96, p = 0.046) There were no differences in the rate of cardiopulmonary arrests or critical deterioration events between groups. Our findings were limited by potential confounders and imprecision among included studies.ConclusionsHealthcare systems that implemented PEWS were associated with reduced mortality and code rates. We recognise that these gains vary depending on resource availability and efferent response systems.PROSPERO registration: CRD42021269579.

Project description:IntroductionSeveral versions of Early Warning Systems (EWS) are used in obstetrics to detect and treat early clinical deterioration to avert morbidity and mortality. EWS can potentially be useful to improve the quality of care and reduce the risk of maternal mortality in resource-limited settings. We conducted a systematic literature review of published obstetric early warning systems, define their predictive accuracy for morbidity and mortality, and their effectiveness in triggering corrective actions and improving health outcomes.MethodsWe systematically searched for primary research articles on obstetric EWS published in peer-reviewed journals between January 1997 and March 2018 in Medline, CINAHL, SCOPUS, Science Direct, and Science Citation Index. We also searched reference lists of relevant articles and websites of professional societies. We included studies that assessed the predictive accuracy of EWS to detect clinical deterioration, or/and their effectiveness in improving clinical outcomes in obstetric inpatients. We excluded studies with a paediatric or non-obstetric adult population. Cross-sectional and qualitative studies were also excluded. We performed a narrative synthesis since the outcomes reported were heterogeneous.ResultsA total of 381 papers were identified, 17 of which met the inclusion criteria. Eleven of the included studies evaluated the predictive accuracy of EWS for obstetric morbidity and mortality, 5 studies assessed the effectiveness of EWS in improving clinical outcomes, while one study addressed both. Sixteen published EWS versions were reviewed, 14 of which included five basic clinical observations (pulse rate, respiratory rate, temperature, blood pressure, and consciousness level). The obstetric EWS identified had very high median (inter-quartile range) sensitivity-89% (72% to 97%) and specificity-85% (67% to 98%) but low median (inter-quartile range) positive predictive values-41% (25% to 74%) for predicting morbidity or ICU admission. Obstetric EWS had a very high accuracy in predicting death (AUROC >0.80) among critically ill obstetric patients. Obstetric EWS improves the frequency of routine vital sign observation, reduces the interval between the recording of specifically defined abnormal clinical observations and corrective clinical actions, and can potentially reduce the severity of obstetric morbidity.ConclusionObstetric EWS are effective in predicting severe morbidity (in general obstetric population) and mortality (in critically ill obstetric patients). EWS can contribute to improved quality of care, prevent progressive obstetric morbidity and improve health outcomes. There is limited evidence of the effectiveness of EWS in reducing maternal death across all settings. Clinical parameters in most obstetric EWS versions are routinely collected in resource-limited settings, therefore implementing EWS may be feasible in such settings.

Project description:ObjectiveTo assess (1) how well validated existing paediatric track and trigger tools (PTTT) are for predicting adverse outcomes in hospitalised children, and (2) how effective broader paediatric early warning systems are at reducing adverse outcomes in hospitalised children.DesignSystematic review.Data sourcesBritish Nursing Index, Cumulative Index of Nursing and Allied Health Literature, Cochrane Central Register of Controlled Trials, Database of Abstracts of Reviews of Effectiveness, EMBASE, Health Management Information Centre, Medline, Medline in Process, Scopus and Web of Knowledge searched through May 2018.Eligibility criteriaWe included (1) papers reporting on the development or validation of a PTTT or (2) the implementation of a broader early warning system in paediatric units (age 0-18 years), where adverse outcome metrics were reported. Several study designs were considered.Data extraction and synthesisData extraction was conducted by two independent reviewers using template forms. Studies were quality assessed using a modified Downs and Black rating scale.Results36 validation studies and 30 effectiveness studies were included, with 27 unique PTTT identified. Validation studies were largely retrospective case-control studies or chart reviews, while effectiveness studies were predominantly uncontrolled before-after studies. Metrics of adverse outcomes varied considerably. Some PTTT demonstrated good diagnostic accuracy in retrospective case-control studies (primarily for predicting paediatric intensive care unit transfers), but positive predictive value was consistently low, suggesting potential for alarm fatigue. A small number of effectiveness studies reported significant decreases in mortality, arrests or code calls, but were limited by methodological concerns. Overall, there was limited evidence of paediatric early warning system interventions leading to reductions in deterioration.ConclusionThere are several fundamental methodological limitations in the PTTT literature, and the predominance of single-site studies carried out in specialist centres greatly limits generalisability. With limited evidence of effectiveness, calls to make PTTT mandatory across all paediatric units are not supported by the evidence base.Prospero registration numberCRD42015015326.

Project description:ObjectiveTo provide an overview and critical appraisal of early warning scores for adult hospital patients.DesignSystematic review.Data sourcesMedline, CINAHL, PsycInfo, and Embase until June 2019.Eligibility criteria for study selectionStudies describing the development or external validation of an early warning score for adult hospital inpatients.Results13 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.ConclusionsEarly 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 registrationPROSPERO CRD42017053324.

Dataset Information

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

Background

Objective

Methods

Results

Conclusions

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets