Predicting Admissions From a Paediatric Emergency Department - Protocol for Developing and Validating a Low-Dimensional Machine Learning Prediction Model.
Ontology highlight
ABSTRACT:
SUBMITTER: Leonard F
PROVIDER: S-EPMC8085432 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:ObjectivesTo set up a prediction model for the 7-day in-hospital mortality of patients admitted from the emergency department (ED) because it is high but no appropriate initial alarm score is available.DesignThis is a prospective cohort study for prediction model development.SettingIn a tertiary referred hospital in northern Taiwan.ParticipantsED-admitted medical patients in hospitalist care wards were enrolled during May 2010 to October 2016. Two-thirds of them were randomly assigned to a derivation cohort for development of the model and cross-validation was performed in the validation cohort.Primary outcome measured7-day in-hospital mortality.ResultsDuring the study period, 8649 patients were enrolled for analysis. The mean age was 71.05 years, and 51.91% were male. The most common admission diagnoses were pneumonia (36%) and urinary tract infection (20.05%). In the derivation cohort, multivariable Cox proportional hazard regression revealed that a low Barthel Index Score, triage level 1 at the ED, presence of cancer, metastasis and admission diagnoses of pneumonia and sepsis were independently associated with 7 days in-hospital mortality. Based on the probability developed from the multivariable model, the area under the receiver operating characteristic curve in the derivation group was 0.81 (0.79-0.85). The result in the validation cohort was comparable. The prediction score modified by the six independent factors had high sensitivity of 88.03% and a negative predictive value of 99.51% for a cut-off value of 4, whereas the specificity and positive predictive value were 89.61% and 10.55%, respectively, when the cut-off value was a score of 6.ConclusionThe 7-day in-hospital mortality in the hospitalist care ward is 2.8%. The initial alarm score could help clinicians to prioritise or exclude patients who need urgent and intensive care.
| S-EPMC7783526 | biostudies-literature
Project description:ObjectiveTo predict hospital admission at the time of ED triage using patient history in addition to information collected at triage.MethodsThis retrospective study included all adult ED visits between March 2014 and July 2017 from one academic and two community emergency rooms that resulted in either admission or discharge. A total of 972 variables were extracted per patient visit. Samples were randomly partitioned into training (80%), validation (10%), and test (10%) sets. We trained a series of nine binary classifiers using logistic regression (LR), gradient boosting (XGBoost), and deep neural networks (DNN) on three dataset types: one using only triage information, one using only patient history, and one using the full set of variables. Next, we tested the potential benefit of additional training samples by training models on increasing fractions of our data. Lastly, variables of importance were identified using information gain as a metric to create a low-dimensional model.ResultsA total of 560,486 patient visits were included in the study, with an overall admission risk of 29.7%. Models trained on triage information yielded a test AUC of 0.87 for LR (95% CI 0.86-0.87), 0.87 for XGBoost (95% CI 0.87-0.88) and 0.87 for DNN (95% CI 0.87-0.88). Models trained on patient history yielded an AUC of 0.86 for LR (95% CI 0.86-0.87), 0.87 for XGBoost (95% CI 0.87-0.87) and 0.87 for DNN (95% CI 0.87-0.88). Models trained on the full set of variables yielded an AUC of 0.91 for LR (95% CI 0.91-0.91), 0.92 for XGBoost (95% CI 0.92-0.93) and 0.92 for DNN (95% CI 0.92-0.92). All algorithms reached maximum performance at 50% of the training set or less. A low-dimensional XGBoost model built on ESI level, outpatient medication counts, demographics, and hospital usage statistics yielded an AUC of 0.91 (95% CI 0.91-0.91).ConclusionMachine learning can robustly predict hospital admission using triage information and patient history. The addition of historical information improves predictive performance significantly compared to using triage information alone, highlighting the need to incorporate these variables into prediction models.
| S-EPMC6054406 | biostudies-literature
Project description:BACKGROUND:The recent literature reports promising results from using intelligent systems to support decision making in healthcare operations. Using these systems may lead to improved diagnostic and treatment protocols and to predict hospital bed demand. Predicting hospital bed demand in emergency department (ED) attendances could help resource allocation and reduce pressure on busy hospitals. However, there is still limited knowledge on whether intelligent systems can operate as fully autonomous, user-independent systems. OBJECTIVE:Compare the performance of a computer-based algorithm and humans in predicting hospital bed demand (admissions and discharges) based on the initial SOAP (Subjective, Objective, Assessment, Plan) records of the ED. METHODS:This was a retrospective cohort study that compared the performance of humans and machines in predicting hospital bed demand from an ED. It considered electronic medical records (EMR) of 9030 patients (230 used as a testing set, and hence evaluated both by humans and by an algorithm, and 8800 used as a training set exclusively by the algorithm) who visited the ED of a tertiary care and teaching public hospital located in Porto Alegre, Brazil between January and December 2014. The machine role was played by Support Vector Machine Classifier and the human prediction was performed by four ED physicians. Predictions were compared in terms of sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve (AUROC). RESULTS:All graders achieved similar accuracies. The accuracy by AUROC for the testing set was 0.82 [95% confidence interval (CI) of 0.77-0.87], 0.80 (95% CI: 0.75-0.85), 0.76 (95% CI: 0.71-0.81) for novice physicians, machine, experienced physicians, respectively. Processing time per test EMR was 0.00812±0.0009 seconds. In contrast, novice physicians took on average 156.80 seconds per test EMR, while experienced physicians took on average 56.40 seconds per test EMR. CONCLUSIONS:Our data indicated that the system could predict patient admission or discharge states with 80% accuracy, which was similar the performance of novice and experienced physicians. These results suggested that the algorithm could operate as an autonomous and independent system to complete this task.
| S-EPMC7451657 | biostudies-literature
Project description:BackgroundUrinary tract infection (UTI) is a common emergency department (ED) diagnosis with reported high diagnostic error rates. Because a urine culture, part of the gold standard for diagnosis of UTI, is usually not available for 24-48 hours after an ED visit, diagnosis and treatment decisions are based on symptoms, physical findings, and other laboratory results, potentially leading to overutilization, antibiotic resistance, and delayed treatment. Previous research has demonstrated inadequate diagnostic performance for both individual laboratory tests and prediction tools.ObjectiveOur aim, was to train, validate, and compare machine-learning based predictive models for UTI in a large diverse set of ED patients.MethodsSingle-center, multi-site, retrospective cohort analysis of 80,387 adult ED visits with urine culture results and UTI symptoms. We developed models for UTI prediction with six machine learning algorithms using demographic information, vitals, laboratory results, medications, past medical history, chief complaint, and structured historical and physical exam findings. Models were developed with both the full set of 211 variables and a reduced set of 10 variables. UTI predictions were compared between models and to proxies of provider judgment (documentation of UTI diagnosis and antibiotic administration).ResultsThe machine learning models had an area under the curve ranging from 0.826-0.904, with extreme gradient boosting (XGBoost) the top performing algorithm for both full and reduced models. The XGBoost full and reduced models demonstrated greatly improved specificity when compared to the provider judgment proxy of UTI diagnosis OR antibiotic administration with specificity differences of 33.3 (31.3-34.3) and 29.6 (28.5-30.6), while also demonstrating superior sensitivity when compared to documentation of UTI diagnosis with sensitivity differences of 38.7 (38.1-39.4) and 33.2 (32.5-33.9). In the admission and discharge cohorts using the full XGboost model, approximately 1 in 4 patients (4109/15855) would be re-categorized from a false positive to a true negative and approximately 1 in 11 patients (1372/15855) would be re-categorized from a false negative to a true positive.ConclusionThe best performing machine learning algorithm, XGBoost, accurately diagnosed positive urine culture results, and outperformed previously developed models in the literature and several proxies for provider judgment. Future prospective validation is warranted.
| S-EPMC5841824 | biostudies-literature
Project description:ObjectiveThis study aimed to describe the impact of the coronavirus disease (COVID-19) pandemic on emergency department (ED) admissions for urgent diagnoses.MethodsFrom January 1, 2019, until December 31, 2020, patients older than 18 years who attended the ED at University Hospital of Leuven (UZ Leuven, Belgium) were included. Urgent diagnoses selected in the First Hour Quintet were collected. The periods of the pandemic waves in 2020 were analyzed and compared with the same time period in 2019.ResultsDuring the first wave of the pandemic, 16 075 patients attended the ED compared with 16 893 patients during the comparison period in 2019. The proportion of patients having one of the diagnoses of the First Hour Quintet was similar between the periods (4.4% vs 4.5%). During the second wave, 14 739 patients attended the ED compared with 18 704 patients during the same period in 2019; 5.6% of patients had a diagnosis of the First Hour Quintet compared with 4.3% of patients in the comparison period.ConclusionThis study showed a decrease in the number of patients attending the ED during the COVID-19 pandemic. Further studies are needed to determine for which conditions patients visited the ED less.
| S-EPMC9343343 | biostudies-literature
Project description:BackgroundDevelopment of emergency department (ED) triage systems that accurately differentiate and prioritize critically ill from stable patients remains challenging. We used machine learning models to predict clinical outcomes, and then compared their performance with that of a conventional approach-the Emergency Severity Index (ESI).MethodsUsing National Hospital and Ambulatory Medical Care Survey (NHAMCS) ED data, from 2007 through 2015, we identified all adult patients (aged ??18?years). In the randomly sampled training set (70%), using routinely available triage data as predictors (e.g., demographics, triage vital signs, chief complaints, comorbidities), we developed four machine learning models: Lasso regression, random forest, gradient boosted decision tree, and deep neural network. As the reference model, we constructed a logistic regression model using the five-level ESI data. The clinical outcomes were critical care (admission to intensive care unit or in-hospital death) and hospitalization (direct hospital admission or transfer). In the test set (the remaining 30%), we measured the predictive performance, including area under the receiver-operating-characteristics curve (AUC) and net benefit (decision curves) for each model.ResultsOf 135,470 eligible ED visits, 2.1% had critical care outcome and 16.2% had hospitalization outcome. In the critical care outcome prediction, all four machine learning models outperformed the reference model (e.g., AUC, 0.86 [95%CI 0.85-0.87] in the deep neural network vs 0.74 [95%CI 0.72-0.75] in the reference model), with less under-triaged patients in ESI triage levels 3 to 5 (urgent to non-urgent). Likewise, in the hospitalization outcome prediction, all machine learning models outperformed the reference model (e.g., AUC, 0.82 [95%CI 0.82-0.83] in the deep neural network vs 0.69 [95%CI 0.68-0.69] in the reference model) with less over-triages in ESI triage levels 1 to 3 (immediate to urgent). In the decision curve analysis, all machine learning models consistently achieved a greater net benefit-a larger number of appropriate triages considering a trade-off with over-triages-across the range of clinical thresholds.ConclusionsCompared to the conventional approach, the machine learning models demonstrated a superior performance to predict critical care and hospitalization outcomes. The application of modern machine learning models may enhance clinicians' triage decision making, thereby achieving better clinical care and optimal resource utilization.
| S-EPMC6387562 | biostudies-literature
Project description:ObjectivesThis study aims to develop and internally validate a low-dimensional model to predict outcomes (admission or discharge) using commonly entered data up to the post-triage process to improve patient flow in the pediatric emergency department (ED). In hospital settings where electronic data are limited, a low-dimensional model with fewer variables may be easier to implement.MethodsThis prognostic study included ED attendances in 2017 and 2018. The Cross Industry Standard Process for Data Mining methodology was followed. Eligibility criteria was applied to the data set, splitting into 70% train and 30% test. Sampling techniques were compared. Gradient boosting machine (GBM), logistic regression, and naïve Bayes models were created. Variables of importance were obtained from the model with the highest area under the curve (AUC) and used to create a low-dimensional model.ResultsEligible attendances totaled 72,229 (15% admission rate). The AUC was 0.853 (95% confidence interval [CI], 0.846-0.859) for GBM, 0.845 (95% CI, 0.838-0.852) for logistic regression and 0.813 (95% CI, 0.806-0.821) for naïve Bayes. Important predictors in the GBM model used to create a low-dimensional model were presenting complaint, triage category, referral source, registration month, location type (resuscitation/other), distance traveled, admission history, and weekday (AUC 0.835 [95% CI, 0.829-0.842]).ConclusionsAdmission and discharge probability can be predicted early in a pediatric ED using 8 variables. Future work could analyze the false positives and false negatives to gain an understanding of the implementation of these predictions.
| S-EPMC9286530 | biostudies-literature
Project description:Study objectiveOur institution experienced a change in SARS-CoV-2 testing policy as well as substantial changes in local COVID-19 prevalence, allowing for a unique examination of the relationship between SARS-CoV-2 testing and emergency department (ED) length of stay.MethodsThis was an observational interrupted time series of all patients admitted to an academic health system between March 15, 2020, and September 30, 2020. Given testing limitations from March 15 to April 24, all patients receiving SARS-CoV-2 tests were symptomatic. On April 24, testing was expanded to all ED admissions. The primary and secondary outcomes were ED length of stay and number needed to test to obtain a positive, respectively.ResultsA total of 70,856 patients were cared for in the EDs during the 7-month period. The testing change increased admission length of stay by 1.89 hours (95% confidence interval 1.39 to 2.38). The number needed to test was 2.5 patients and was highest yield on April 1, 2020, when the state positivity rate was 39.7%; however, the number needed to test exceeded 170 patients by Sept 1, 2020, at which point the state positivity rate was 0.5%.ConclusionAlthough universal SARS-CoV-2 testing of ED admissions may meaningfully support mitigation and containment efforts, the clinical cost of testing all admissions amid low community positivity is notable. In our system, universal ED SARS-CoV-2 testing was associated with a 24% increase in admission length of stay alongside the detection of only 1 positive case every other day. Given the known harms and risks of ED boarding and crowding, solutions must be developed to support regular operational flow while balancing infection prevention needs.
| S-EPMC8424016 | biostudies-literature
Project description:Several approaches exist today for developing predictive models across multiple clinical sites, yet there is a lack of comparative data on their performance, especially within the context of EHR-based prediction models. We set out to provide a framework for prediction across healthcare settings. As a case study, we examined an ED disposition prediction model across three geographically and demographically diverse sites. We conducted a 1-year retrospective study, including all visits in which the outcome was either discharge-to-home or hospitalization. Four modeling approaches were compared: a ready-made model trained at one site and validated at other sites, a centralized uniform model incorporating data from all sites, multiple site-specific models, and a hybrid approach of a ready-made model re-calibrated using site-specific data. Predictions were performed using XGBoost. The study included 288,962 visits with an overall admission rate of 16.8% (7.9-26.9%). Some risk factors for admission were prominent across all sites (e.g., high-acuity triage emergency severity index score, high prior admissions rate), while others were prominent at only some sites (multiple lab tests ordered at the pediatric sites, early use of ECG at the adult site). The XGBoost model achieved its best performance using the uniform and site-specific approaches (AUC = 0.9-0.93), followed by the calibrated-model approach (AUC = 0.87-0.92), and the ready-made approach (AUC = 0.62-0.85). Our results show that site-specific customization is a key driver of predictive model performance.
| S-EPMC8674364 | biostudies-literature
Project description:Emergency department (ED) crowding is linked with poor quality of care and worse outcomes, including higher mortality. With the growing emphasis on hospital performance measures, there is additional concern whether inadequate care during crowded periods increases a patient's likelihood of subsequent inpatient admission. We sought to determine if ED crowding during the index visit was associated with these "bounceback" admissions.We used comprehensive, nonpublic, statewide ED and inpatient discharge data from the California Office of Statewide Health Planning and Development from 2007 to identify index outpatient ED visits and bounceback admissions within 7 days. We further used ambulance diversion data collected from California local emergency medical services agencies to identify crowded days using intrahospital daily diversion hour quartiles. Using a hierarchical logistic regression model, we then determined if patients visiting on crowded days were more likely to have a subsequent bounceback admission.We analyzed 3,368,527 index visits across 202 hospitals, of which 596,471 (17.7%) observations were on crowded days. We found no association between ED crowding and bounceback admissions. This lack of relationship persisted in both a discrete (high/low) model (OR, 1.01; 95% CI, 0.99, 1.02) and a secondary model using ambulance diversion hours as a continuous predictor (OR, 1.00; 95% CI, 1.00, 1.00).Crowding as measured by ambulance diversion does not have an association with hospitalization within 7 days of an ED visit discharge. Therefore, bounceback admission may be a poor measure of delayed or worsened quality of care due to crowding.
| S-EPMC3839788 | biostudies-literature