Advancing In-Hospital Clinical Deterioration Prediction Models.
Ontology highlight
ABSTRACT:
SUBMITTER: Jeffery AD
PROVIDER: S-EPMC6141236 | biostudies-literature | 2018 Sep
REPOSITORIES: biostudies-literature
Publications
Advancing In-Hospital Clinical Deterioration Prediction Models.
Jeffery Alvin D AD Dietrich Mary S MS Fabbri Daniel D Kennedy Betsy B Novak Laurie L LL Coco Joseph J Mion Lorraine C LC
American journal of critical care : an official publication, American Association of Critical-Care Nurses 20180901 5
<h4>Background</h4>Early warning systems lack robust evidence that they improve patients' outcomes, possibly because of their limitation of predicting binary rather than time-to-event outcomes.<h4>Objectives</h4>To compare the prediction accuracy of 2 statistical modeling strategies (logistic regression and Cox proportional hazards regression) and 2 machine learning strategies (random forest and random survival forest) for in-hospital cardiopulmonary arrest.<h4>Methods</h4>Retrospective cohort s ...[more]
Similar Datasets
Project description:IntroductionFalls remain one of the most prevalent adverse events in hospitals and are associated with substantial negative health impacts and costs. Approaches to assess patients' fall risk have been implemented in hospitals internationally, ranging from brief screening questions to multifactorial risk assessments and complex prediction models, despite a lack of clear evidence of effect in reducing falls in acute hospital environments. The increasing digitisation of hospital systems provides new opportunities to understand and predict falls using routinely recorded data, with potential to integrate fall prediction models into real-time or near-real-time computerised decision support for clinical teams seeking to mitigate fall risk. However, the use of non-traditional approaches to fall risk prediction, including machine learning using integrated electronic medical records, has not yet been reviewed relative to more traditional fall prediction models. This scoping review will summarise methodologies used to develop existing hospital fall prediction models, including reporting quality assessment.Methods and analysisThis scoping review will follow the Arksey and O'Malley framework and its recent advances, and will be reported using Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews recommendations. Four electronic databases (CINAHL via EBSCOhost, PubMed, IEEE Xplore and Embase) will be initially searched for studies up to 12 November 2020, and searches may be updated prior to final reporting. Additional studies will be identified by reference list review and citation analysis of included studies. No restriction will be placed on the date or language of identified studies. Screening of search results and extraction of data will be performed by two independent reviewers. Reporting quality will be assessed by the adherence to the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis.Ethics and disseminationEthical approval is not required for this study. Findings will be disseminated through peer-reviewed publication and scientific conferences.
| S-EPMC8438847 | biostudies-literature
Project description:In materials science, accurately computing properties like viscosity, melting point, and glass transition temperatures solely through physics-based models is challenging. Data-driven machine learning (ML) also poses challenges in constructing ML models, especially in the material science domain where data is limited. To address this, we integrate physics-informed descriptors from molecular dynamics (MD) simulations to enhance the accuracy and interpretability of ML models. Our current study focuses on accurately predicting viscosity in liquid systems using MD descriptors. In this work, we curated a comprehensive dataset of over 4000 small organic molecules' viscosities from scientific literature, publications, and online databases. This dataset enabled us to develop quantitative structure-property relationships (QSPR) consisting of descriptor-based and graph neural network models to predict temperature-dependent viscosities for a wide range of viscosities. The QSPR models reveal that including MD descriptors improves the prediction of experimental viscosities, particularly at the small data set scale of fewer than a thousand data points. Furthermore, feature importance tools reveal that intermolecular interactions captured by MD descriptors are most important for viscosity predictions. Finally, the QSPR models can accurately capture the inverse relationship between viscosity and temperature for six battery-relevant solvents, some of which were not included in the original data set. Our research highlights the effectiveness of incorporating MD descriptors into QSPR models, which leads to improved accuracy for properties that are difficult to predict when using physics-based models alone or when limited data is available.
| S-EPMC10938832 | biostudies-literature
Project description:BackgroundEarly recognition of severe COVID-19 is essential for timely patient triage.AimsTo report clinical and laboratory findings and patient outcomes at a tertiary hospital in Melbourne, Australia.MethodsThis is a retrospective study of adult inpatients with COVID-19 admitted to Northern Health from March to September 2020. Data were extracted from electronic medical records.ResultsKey admission data were available for 182 patients (median age 67.0 years (interquartile range, 47.9-83.1); 51.1% female). Fifty-six (30.8%) were from residential care. One hundred and seventeen (64.3%) patients were assigned Goals of Patient Care (GOPC) A or B and 65 (35.7%) GOPC C or D. Comorbidities were present in 135 patients (74.2%). 63.2% of patients received antibiotics, 6.6% had antivirals, 45.6% received systemic glucocorticoid and 3.3% had tocilizumab. Fifty-six (30.8%) developed clinical deterioration (24 requiring ventilation, 21 receiving critical care, 34 died). Overall, inhospital clinical deterioration was significantly associated with older age (P < 0.001), history of diabetes (P = 0.038), lower lymphocyte count (P = 0.002) and platelet count (P = 0.004), higher neutrophil-to-lymphocyte ratio (P = 0.002), elevated fibrinogen (P = 0.004), higher serum ferritin (P = 0.027) and C-reactive protein (CRP; P = 0.002). The accuracy of the 4C Deterioration model was moderate, with an area under the curve (AUC) of 0.79 (95% confidence interval (CI), 0.68-0.90) compared with an AUC of 0.77 (95% CI, 0.76-0.78) in the original validation cohort.ConclusionsIn the present study, high neutrophil-to-lymphocyte ratio, abnormal d-dimer, high serum CRP and ferritin appear to be useful prognostic markers.
| S-EPMC9011432 | biostudies-literature
Project description: Not available
| S-EPMC10786836 | biostudies-literature
Project description:BackgroundHospitalized adults whose condition deteriorates while they are in wards (outside the intensive care unit [ICU]) have considerable morbidity and mortality. Early identification of patients at risk for clinical deterioration has relied on manually calculated scores. Outcomes after an automated detection of impending clinical deterioration have not been widely reported.MethodsOn the basis of a validated model that uses information from electronic medical records to identify hospitalized patients at high risk for clinical deterioration (which permits automated, real-time risk-score calculation), we developed an intervention program involving remote monitoring by nurses who reviewed records of patients who had been identified as being at high risk; results of this monitoring were then communicated to rapid-response teams at hospitals. We compared outcomes (including the primary outcome, mortality within 30 days after an alert) among hospitalized patients (excluding those in the ICU) whose condition reached the alert threshold at hospitals where the system was operational (intervention sites, where alerts led to a clinical response) with outcomes among patients at hospitals where the system had not yet been deployed (comparison sites, where a patient's condition would have triggered a clinical response after an alert had the system been operational). Multivariate analyses adjusted for demographic characteristics, severity of illness, and burden of coexisting conditions.ResultsThe program was deployed in a staggered fashion at 19 hospitals between August 1, 2016, and February 28, 2019. We identified 548,838 non-ICU hospitalizations involving 326,816 patients. A total of 43,949 hospitalizations (involving 35,669 patients) involved a patient whose condition reached the alert threshold; 15,487 hospitalizations were included in the intervention cohort, and 28,462 hospitalizations in the comparison cohort. Mortality within 30 days after an alert was lower in the intervention cohort than in the comparison cohort (adjusted relative risk, 0.84, 95% confidence interval, 0.78 to 0.90; P<0.001).ConclusionsThe use of an automated predictive model to identify high-risk patients for whom interventions by rapid-response teams could be implemented was associated with decreased mortality. (Funded by the Gordon and Betty Moore Foundation and others.).
| S-EPMC7787261 | biostudies-literature
Project description:BackgroundRapid identification of high-risk polytrauma patients is crucial for early intervention and improved outcomes. This study aimed to develop and validate machine learning models for predicting 72 h mortality in adult polytrauma patients using readily available clinical parameters.MethodsA retrospective analysis was conducted on polytrauma patients from the Dryad database and our institution. Missing values pertinent to eligible individuals within the Dryad database were compensated for through the k-nearest neighbor algorithm, subsequently randomizing them into training and internal validation factions on a 7:3 ratio. The patients of our institution functioned as external validation cohorts. The predictive efficacy of random forest (RF), neural network, and XGBoost models was assessed through an exhaustive suite of performance indicators. The SHapley Additive exPlanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME) methods were engaged to explain the supreme-performing model. Conclusively, restricted cubic spline analysis and multivariate logistic regression were employed as sensitivity analyses to verify the robustness of the findings.ResultsParameters including age, body mass index, Glasgow Coma Scale, Injury Severity Score, pH, base excess, and lactate emerged as pivotal predictors of 72 h mortality. The RF model exhibited unparalleled performance, boasting an area under the receiver operating characteristic curve (AUROC) of 0.87 (95% confidence interval [CI] 0.84-0.89), an area under the precision-recall curve (AUPRC) of 0.67 (95% CI 0.61-0.73), and an accuracy of 0.83 (95% CI 0.81-0.86) in the internal validation cohort, paralleled by an AUROC of 0.98 (95% CI 0.97-0.99), an AUPRC of 0.88 (95% CI 0.83-0.93), and an accuracy of 0.97 (95% CI 0.96-0.98) in the external validation cohort. It provided the highest net benefit in the decision curve analysis in relation to the other models. The outcomes of the sensitivity examinations were congruent with those inferred from SHAP and LIME.ConclusionsThe RF model exhibited the best performance in predicting 72 h mortality in adult polytrauma patients and has the potential to aid clinicians in identifying high-risk patients and guiding clinical decision-making.
| S-EPMC10518974 | biostudies-literature
Project description:Introduction Consumer escalation systems allow patients and families to escalate concerns about acute clinical deterioration. Hospital staff can impact upon the success of this process. As part of evaluation processes within a Local Health Network, where a consumer escalation system was introduced in accordance with National requirements, we sought to explore clinicians’ understanding and perceptions of consumer escalation. Methods Voluntary and anonymous staff surveys pre, and post, system introduction. Quantitative data was analysed using descriptive statistics, chi-square independence, and non-parametric independent samples median tests. Qualitative data was evaluated using content analysis and cross-referenced with quantitative responses. Results Respondent’s (pre: 215; post: 89) area of work varied significantly between survey periods. Most agreed that patients/families have a sound knowledge of a patient’s typical health status (pre: 192/215 (89.3%); post 82/88 (93.2%)) and that patients/families should be encouraged to escalate concerns of deterioration to ward staff (pre: 209/212 (98.6%); post: 85/89 (95.5%)). Respondent perceptions of patient/family ability to recognise clinical deterioration varied. Staff agreement towards local response expectations decreased as the degree of clinical requirement increased. Staff concerns of increased workloads (pre: 90/214 (42.1%); post 12/72 (16.7%), p<0.001) and conflict generation (pre: 71/213 (33.3%); post: 7/71 (9.9%), p = 0.001) decreased significantly following system introduction. However, clinician perceptions of positive system effects also decreased (patient-staff rapport pre: 163/213 (76.5%); post: 38/72 (52.8%), p = 0.001; patient centred care pre: 188/214 (87.9%); post: 53/72 (73.6%), p = 0.012; patient safety pre: 173/214 (80.8%); post: 49/72 (68.1%), p = 0.077). Only 53% of respondents (pre: 112/213 (52.6%); post: 48/88 (54.5%)) perceived that patient/family have sufficient confidence to escalate concerns. Conclusion Consumer escalation systems require staff support. Staff perceptions may indicate, and act as, barriers to the operation of consumer escalation processes. Further exploration in identifying and managing staff barriers is crucial to the success of consumer escalation.
| S-EPMC9202900 | biostudies-literature
Project description:BackgroundInterest in developing machine learning models that use electronic health record data to predict patients' risk of suicidal behavior has recently proliferated. However, whether and how such models might be implemented and useful in clinical practice remain unknown. To ultimately make automated suicide risk-prediction models useful in practice, and thus better prevent patient suicides, it is critical to partner with key stakeholders, including the frontline providers who will be using such tools, at each stage of the implementation process.ObjectiveThe aim of this focus group study is to inform ongoing and future efforts to deploy suicide risk-prediction models in clinical practice. The specific goals are to better understand hospital providers' current practices for assessing and managing suicide risk; determine providers' perspectives on using automated suicide risk-prediction models in practice; and identify barriers, facilitators, recommendations, and factors to consider.MethodsWe conducted 10 two-hour focus groups with a total of 40 providers from psychiatry, internal medicine and primary care, emergency medicine, and obstetrics and gynecology departments within an urban academic medical center. Audio recordings of open-ended group discussions were transcribed and coded for relevant and recurrent themes by 2 independent study staff members. All coded text was reviewed and discrepancies were resolved in consensus meetings with doctoral-level staff.ResultsAlthough most providers reported using standardized suicide risk assessment tools in their clinical practices, existing tools were commonly described as unhelpful and providers indicated dissatisfaction with current suicide risk assessment methods. Overall, providers' general attitudes toward the practical use of automated suicide risk-prediction models and corresponding clinical decision support tools were positive. Providers were especially interested in the potential to identify high-risk patients who might be missed by traditional screening methods. Some expressed skepticism about the potential usefulness of these models in routine care; specific barriers included concerns about liability, alert fatigue, and increased demand on the health care system. Key facilitators included presenting specific patient-level features contributing to risk scores, emphasizing changes in risk over time, and developing systematic clinical workflows and provider training. Participants also recommended considering risk-prediction windows, timing of alerts, who will have access to model predictions, and variability across treatment settings.ConclusionsProviders were dissatisfied with current suicide risk assessment methods and were open to the use of a machine learning-based risk-prediction system to inform clinical decision-making. They also raised multiple concerns about potential barriers to the usefulness of this approach and suggested several possible facilitators. Future efforts in this area will benefit from incorporating systematic qualitative feedback from providers, patients, administrators, and payers on the use of these new approaches in routine care, especially given the complex, sensitive, and unfortunately still stigmatized nature of suicide risk.
| S-EPMC8956996 | biostudies-literature
Project description:Background While many clinical prediction models (CPMs) exist to guide valvular heart disease treatment decisions, the relative performance of these CPMs is largely unknown. We systematically describe the CPMs available for patients with valvular heart disease with specific attention to performance in external validations. Methods and Results A systematic review identified 49 CPMs for patients with valvular heart disease treated with surgery (n=34), percutaneous interventions (n=12), or no intervention (n=3). There were 204 external validations of these CPMs. Only 35 (71%) CPMs have been externally validated. Sixty-five percent (n=133) of the external validations were performed on distantly related populations. There was substantial heterogeneity in model performance and a median percentage change in discrimination of -27.1% (interquartile range, -49.4%--5.7%). Nearly two-thirds of validations (n=129) demonstrate at least a 10% relative decline in discrimination. Discriminatory performance of EuroSCORE II and Society of Thoracic Surgeons (2009) models (accounting for 73% of external validations) varied widely: EuroSCORE II validation c-statistic range 0.50 to 0.95; Society of Thoracic Surgeons (2009) Models validation c-statistic range 0.50 to 0.86. These models performed well when tested on related populations (median related validation c-statistics: EuroSCORE II, 0.82 [0.76, 0.85]; Society of Thoracic Surgeons [2009], 0.72 [0.67, 0.79]). There remain few (n=9) external validations of transcatheter aortic valve replacement CPMs. Conclusions Many CPMs for patients with valvular heart disease have never been externally validated and isolated external validations appear insufficient to assess the trustworthiness of predictions. For surgical valve interventions, there are existing predictive models that perform reasonably well on related populations. For transcatheter aortic valve replacement (CPMs additional external validations are needed to broadly understand the trustworthiness of predictions.
| S-EPMC6818049 | biostudies-literature
Project description:Early detection of patients at risk for clinical deterioration is crucial for timely intervention. Traditional detection systems rely on a limited set of variables and are unable to predict the time of decline. We describe a machine learning model called MEWS++ that enables the identification of patients at risk of escalation of care or death six hours prior to the event. A retrospective single-center cohort study was conducted from July 2011 to July 2017 of adult (age > 18) inpatients excluding psychiatric, parturient, and hospice patients. Three machine learning models were trained and tested: random forest (RF), linear support vector machine, and logistic regression. We compared the models' performance to the traditional Modified Early Warning Score (MEWS) using sensitivity, specificity, and Area Under the Curve for Receiver Operating Characteristic (AUC-ROC) and Precision-Recall curves (AUC-PR). The primary outcome was escalation of care from a floor bed to an intensive care or step-down unit, or death, within 6 h. A total of 96,645 patients with 157,984 hospital encounters and 244,343 bed movements were included. Overall rate of escalation or death was 3.4%. The RF model had the best performance with sensitivity 81.6%, specificity 75.5%, AUC-ROC of 0.85, and AUC-PR of 0.37. Compared to traditional MEWS, sensitivity increased 37%, specificity increased 11%, and AUC-ROC increased 14%. This study found that using machine learning and readily available clinical data, clinical deterioration or death can be predicted 6 h prior to the event. The model we developed can warn of patient deterioration hours before the event, thus helping make timely clinical decisions.
| S-EPMC7073544 | biostudies-literature