Machine learning for real-time aggregated prediction of hospital admission for emergency patients.
Ontology highlight
ABSTRACT:
SUBMITTER: King Z
PROVIDER: S-EPMC9321296 | biostudies-literature | 2022 Jul
REPOSITORIES: biostudies-literature
Publications
Machine learning for real-time aggregated prediction of hospital admission for emergency patients.
King Zella Z Farrington Joseph J Utley Martin M Kung Enoch E Elkhodair Samer S Harris Steve S Sekula Richard R Gillham Jonathan J Li Kezhi K Crowe Sonya S
NPJ digital medicine 20220726 1
Machine learning for hospital operations is under-studied. We present a prediction pipeline that uses live electronic health-records for patients in a UK teaching hospital's emergency department (ED) to generate short-term, probabilistic forecasts of emergency admissions. A set of XGBoost classifiers applied to 109,465 ED visits yielded AUROCs from 0.82 to 0.90 depending on elapsed visit-time at the point of prediction. Patient-level probabilities of admission were aggregated to forecast the num ...[more]
Similar Datasets
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:ObjectiveTo develop prediction models for intensive care unit (ICU) vs non-ICU level-of-care need within 24 hours of inpatient admission for emergency department (ED) patients using electronic health record data.Materials and methodsUsing records of 41 654 ED visits to a tertiary academic center from 2015 to 2019, we tested 4 algorithms-feed-forward neural networks, regularized regression, random forests, and gradient-boosted trees-to predict ICU vs non-ICU level-of-care within 24 hours and at the 24th hour following admission. Simple-feature models included patient demographics, Emergency Severity Index (ESI), and vital sign summary. Complex-feature models added all vital signs, lab results, and counts of diagnosis, imaging, procedures, medications, and lab orders.ResultsThe best-performing model, a gradient-boosted tree using a full feature set, achieved an AUROC of 0.88 (95%CI: 0.87-0.89) and AUPRC of 0.65 (95%CI: 0.63-0.68) for predicting ICU care need within 24 hours of admission. The logistic regression model using ESI achieved an AUROC of 0.67 (95%CI: 0.65-0.70) and AUPRC of 0.37 (95%CI: 0.35-0.40). Using a discrimination threshold, such as 0.6, the positive predictive value, negative predictive value, sensitivity, and specificity were 85%, 89%, 30%, and 99%, respectively. Vital signs were the most important predictors.Discussion and conclusionsUndertriaging admitted ED patients who subsequently require ICU care is common and associated with poorer outcomes. Machine learning models using readily available electronic health record data predict subsequent need for ICU admission with good discrimination, substantially better than the benchmarking ESI system. The results could be used in a multitiered clinical decision-support system to improve ED triage.
| S-EPMC8510323 | biostudies-literature
Project description:AimsPatients visiting the emergency department (ED) or hospitalized for heart failure (HF) are at increased risk for subsequent adverse outcomes, however effective risk stratification remains challenging. We utilized a machine-learning (ML)-based approach to identify HF patients at risk of adverse outcomes after an ED visit or hospitalization using a large regional administrative healthcare data system.Methods and resultsPatients visiting the ED or hospitalized with HF between 2002-2016 in Alberta, Canada were included. Outcomes of interest were 30-day and 1-year HF-related ED visits, HF hospital readmission or all-cause mortality. We applied a feature extraction method using deep feature synthesis from multiple sources of health data and compared performance of a gradient boosting algorithm (CatBoost) with logistic regression modelling. The area under receiver operating characteristic curve (AUC-ROC) was used to assess model performance. We included 50,630 patients with 93,552 HF ED visits/hospitalizations. At 30-day follow-up in the holdout validation cohort, the AUC-ROC for the combined endpoint of HF ED visit, HF hospital readmission or death for the Catboost and logistic regression models was 74.16 (73.18-75.11) versus 62.25 (61.25-63.18), respectively. At 1-year follow-up corresponding values were 76.80 (76.1-77.47) versus 69.52 (68.77-70.26), respectively. AUC-ROC values for the endpoint of all-cause death alone at 30-days and 1-year follow-up were 83.21 (81.83-84.41) versus 69.53 (67.98-71.18), and 85.73 (85.14-86.29) versus 69.40 (68.57-70.26), for the CatBoost and logistic regression models, respectively.ConclusionsML-based modelling with deep feature synthesis provided superior risk stratification for HF patients at 30-days and 1-year follow-up after an ED visit or hospitalization using data from a large administrative regional healthcare system.
| S-EPMC11508085 | biostudies-literature
Project description:ObjectiveThis study aims to develop and compare different models to predict the Length of Stay (LoS) and the Prolonged Length of Stay (PLoS) of inpatients admitted through the emergency department (ED) in general patient settings. This aim is not only to promote any specific model but rather to suggest a decision-supporting tool (i.e., a prediction framework).MethodsWe analyzed a dataset of patients admitted through the ED to the "Sant"Orsola Malpighi University Hospital of Bologna, Italy, between January 1 and October 26, 2022. PLoS was defined as any hospitalization with LoS longer than 6 days. We deployed six classification algorithms for predicting PLoS: Random Forest (RF), Support Vector Machines (SVM), Gradient Boosting (GB), AdaBoost, K-Nearest Neighbors (KNN), and logistic regression (LoR). We evaluated the performance of these models with the Brier score, the area under the ROC curve (AUC), accuracy, sensitivity (recall), specificity, precision, and F1-score. We further developed eight regression models for LoS prediction: Linear Regression (LR), including the penalized linear models Least Absolute Shrinkage and Selection Operator (LASSO), Ridge and Elastic-net regression, Support vector regression, RF regression, KNN, and eXtreme Gradient Boosting (XGBoost) regression. The model performances were measured by their mean square error, mean absolute error, and mean relative error. The dataset was randomly split into a training set (70%) and a validation set (30%).ResultsA total of 12,858 eligible patients were included in our study, of whom 60.88% had a PloS. The GB classifier best predicted PloS (accuracy 75%, AUC 75.4%, Brier score 0.181), followed by LoR classifier (accuracy 75%, AUC 75.2%, Brier score 0.182). These models also showed to be adequately calibrated. Ridge and XGBoost regressions best predicted LoS, with the smallest total prediction error. The overall prediction error is between 6 and 7 days, meaning there is a 6-7 day mean difference between actual and predicted LoS.ConclusionOur results demonstrate the potential of machine learning-based methods to predict LoS and provide valuable insights into the risks behind prolonged hospitalizations. In addition to physicians' clinical expertise, the results of these models can be utilized as input to make informed decisions, such as predicting hospitalizations and enhancing the overall performance of a public healthcare system.
| S-EPMC10426288 | biostudies-literature
Project description:BackgroundSepsis is a leading cause of death in patients with trauma, and the risk of mortality increases significantly for each hour of delay in treatment. A hypermetabolic baseline and explosive inflammatory immune response mask clinical signs and symptoms of sepsis in trauma patients, making early diagnosis of sepsis more challenging. Machine learning-based predictive modeling has shown great promise in evaluating and predicting sepsis risk in the general intensive care unit (ICU) setting, but there has been no sepsis prediction model specifically developed for trauma patients so far.ObjectiveTo develop a machine learning model to predict the risk of sepsis at an hourly scale among ICU-admitted trauma patients.MethodsWe extracted data from adult trauma patients admitted to the ICU at Beth Israel Deaconess Medical Center between 2008 and 2019. A total of 42 raw variables were collected, including demographics, vital signs, arterial blood gas, and laboratory tests. We further derived a total of 485 features, including measurement pattern features, scoring features, and time-series variables, from the raw variables by feature engineering. The data set was randomly split into 70% for model development with stratified 5-fold cross-validation, 15% for calibration, and 15% for testing. An Extreme Gradient Boosting (XGBoost) model was developed to predict the hourly risk of sepsis at prediction windows of 4, 6, 8, 12, and 24 hours. We evaluated model performance for discrimination and calibration both at time-step and outcome levels. Clinical applicability of the model was evaluated with varying levels of precision, and the potential clinical net benefit was assessed with decision curve analysis (DCA). A Shapley additive explanation algorithm was applied to show the effect of features on the prediction model. In addition, we trained an L2-regularized logistic regression model to compare its performance with XGBoost.ResultsWe included 4603 trauma patients in the study, 1196 (26%) of whom developed sepsis. The XGBoost model achieved an area under the receiver operating characteristics curve (AUROC) ranging from 0.83 to 0.88 at the 4-to-24-hour prediction window in the test set. With a ratio of 9 false alerts for every true alert, it predicted 73% (386/529) of sepsis-positive timesteps and 91% (163/179) of sepsis events in the subsequent 6 hours. The DCA showed our model had a positive net benefit in the threshold probability range of 0 to 0.6. In comparison, the logistic regression model achieved lower performance, with AUROC ranging from 0.76 to 0.84 at the 4-to-24-hour prediction window.ConclusionsThe machine learning-based model had good discrimination and calibration performance for sepsis prediction in critical trauma patients. Using the model in clinical practice might help to identify patients at risk of sepsis in a time window that enables personalized intervention and early treatment.
| S-EPMC10131736 | biostudies-literature
Project description:ObjectiveProlonged Emergency Department (ED) wait times lead to diminished healthcare quality. Utilizing machine learning (ML) to predict patient wait times could aid in ED operational management. Our aim is to perform a comprehensive analysis of ML models for ED wait time prediction, identify key feature importance and associations with prolonged wait times, and interpret prediction model clinical relevance among ED patients.MethodsThis is a single-centered retrospective study. We included ED patients assigned an Emergency Severity Index (ESI) level of 3 at triage. Patient wait times were categorized as <30 minutes and ≥30 minutes (prolonged wait time). We employed five ML algorithms - cross-validation logistic regression (CVLR), random forest (RF), extreme gradient boosting (XGBoost), artificial neural network (ANN), and support vector machine (SVM) - for predicting patient prolonged wait times. Performance assessment utilized accuracy, recall, precision, F1 score, false positive rate (FPR), and false negative rate (FNR). Furthermore, using XGBoost as an example, model key features and partial dependency plots (PDP) of these key features were illustrated. Shapley additive explanations (SHAP) were employed to interpret model outputs. Additionally, a top key feature interaction analysis was conducted.ResultsAmong total 177,665 patients, nearly half of them (48.20%, 85,632) experienced prolonged ED wait times. Though all five ML models exhibited similar performance, minimizing FNR is associated with the most clinical relevance for wait time predictions. The top features influencing patient wait times and gaining the top ranked interactions were ED crowding condition and patient mode of arrival.ConclusionsNearly half of the patients experienced prolonged wait times in the ED. ML models demonstrated acceptable performance, particularly in minimizing FNR when predicting ED wait times. The prediction of prolonged wait times was influenced by multiple interacting factors. Proper application of ML models to clinical practice requires interpreting their predictions of prolonged wait times in the context of clinical significance.
| S-EPMC11917090 | biostudies-literature
Project description:The wide-ranging adoption of quantum technologies requires practical, high-performance advances in our ability to maintain quantum coherence while facing the challenge of state collapse under measurement. Here we use techniques from control theory and machine learning to predict the future evolution of a qubit's state; we deploy this information to suppress stochastic, semiclassical decoherence, even when access to measurements is limited. First, we implement a time-division multiplexed approach, interleaving measurement periods with periods of unsupervised but stabilised operation during which qubits are available, for example, in quantum information experiments. Second, we employ predictive feedback during sequential but time delayed measurements to reduce the Dick effect as encountered in passive frequency standards. Both experiments demonstrate significant improvements in qubit-phase stability over 'traditional' measurement-based feedback approaches by exploiting time domain correlations in the noise processes. This technique requires no additional hardware and is applicable to all two-level quantum systems where projective measurements are possible.
| S-EPMC5241809 | biostudies-literature
Project description:Patients with frequent hospitalizations generate a disproportionate share of hospital visits and costs. Accurate determination of patients who might benefit from interventions is challenging: most patients with frequent admissions in 1 year would not continue to have them in the next. Our objective was to employ a validated regression algorithm to case-find Medicaid patients at high-risk for hospitalization in the next 12 months and identify intervention-amenable characteristics to reduce hospitalization risk. We obtained encounter data for 36,457 Medicaid patients with any visit to an urban public hospital from 2001 to 2006 and generated an algorithm-based score for hospitalization risk in the subsequent 12 months for each patient (0 = lowest, 100 = highest). To determine medical and social contributors to the current admission, we conducted in-depth interviews with high-risk hospitalized patients (scores >50) and analyzed associated Medicaid claims data. An algorithm-based risk score >50 was attained in 2,618 (7.2%) patients. The algorithm's positive predictive value was equal to 0.67. During the study period, 139 high-risk patients were admitted: 60 met inclusion criteria and 50 were interviewed. Fifty-six percent cited the Emergency Department as their usual source of care or had none. Sixty-eight percent had >1 chronic medical conditions, and 42% were admitted for conditions related to substance use. Sixty percent were homeless or precariously housed. Mean Medicaid expenditures for the interviewed patients were $39,188 and $84,040 per patient for the years immediately prior to and following study participation, respectively. Findings including high rates of substance use, homelessness, social isolation, and lack of a medical home will inform the design of interventions to improve community-based care and reduce hospitalizations and associated costs.
| S-EPMC2648879 | biostudies-other
Project description:IntroductionThe closest emergency department (ED) may not always be the optimal hospital for certain stable high acuity patients if further distanced ED's can provide specialized care or are less overcrowded. Machine learning (ML) predictions may support paramedic decision-making to transport a subgroup of emergent patients to a more suitable, albeit more distanced, ED if hospital admission is unlikely. We examined whether characteristics known to paramedics in the prehospital setting were predictive of hospital admission in emergent acuity patients.Materials and methodsWe conducted a population-level cohort study using four ML algorithms to analyze ED visits of the National Ambulatory Care Reporting System from January 1, 2018 to December 31, 2019 in Ontario, Canada. We included all adult patients (≥18 years) transported to the ED by paramedics with an emergent Canadian Triage Acuity Scale score. We included eight characteristic classes as model predictors that are recorded at ED triage. All ML algorithms were trained and assessed using 10-fold cross-validation to predict hospital admission from the ED. Predictive model performance was determined using the area under curve (AUC) with 95% confidence intervals and probabilistic accuracy using the Brier Scaled score. Variable importance scores were computed to determine the top 10 predictors of hospital admission.ResultsAll machine learning algorithms demonstrated acceptable accuracy in predicting hospital admission (AUC 0.77-0.78, Brier Scaled 0.22-0.24). The characteristics most predictive of admission were age between 65 to 105 years, referral source from a residential care facility, presenting with a respiratory complaint, and receiving home care.DiscussionHospital admission was accurately predicted based on patient characteristics known prehospital to paramedics prior to arrival. Our results support consideration of policy modification to permit certain emergent acuity patients to be transported to a further distanced ED. Additionally, this study demonstrates the utility of ML in paramedic and prehospital research.
| S-EPMC10449470 | biostudies-literature
Project description:BackgroundAlthough multiple prediction models have been developed to predict hospital admission to emergency departments (EDs) to address overcrowding and patient safety, only a few studies have examined prediction models for prehospital use. Development of institution-specific prediction models is feasible in this age of data science, provided that predictor-related information is readily collectable.ObjectiveWe aimed to develop a hospital admission prediction model based on patient information that is commonly available during ambulance transport before hospitalization.MethodsPatients transported by ambulance to our ED from April 2018 through March 2019 were enrolled. Candidate predictors were age, sex, chief complaint, vital signs, and patient medical history, all of which were recorded by emergency medical teams during ambulance transport. Patients were divided into two cohorts for derivation (3601/5145, 70.0%) and validation (1544/5145, 30.0%). For statistical models, logistic regression, logistic lasso, random forest, and gradient boosting machine were used. Prediction models were developed in the derivation cohort. Model performance was assessed by area under the receiver operating characteristic curve (AUROC) and association measures in the validation cohort.ResultsOf 5145 patients transported by ambulance, including deaths in the ED and hospital transfers, 2699 (52.5%) required hospital admission. Prediction performance was higher with the addition of predictive factors, attaining the best performance with an AUROC of 0.818 (95% CI 0.792-0.839) with a machine learning model and predictive factors of age, sex, chief complaint, and vital signs. Sensitivity and specificity of this model were 0.744 (95% CI 0.716-0.773) and 0.745 (95% CI 0.709-0.776), respectively.ConclusionsFor patients transferred to EDs, we developed a well-performing hospital admission prediction model based on routinely collected prehospital information including chief complaints.
| S-EPMC7655472 | biostudies-literature