Dataset Information

Disparities in adherence and emergency department utilization among people with epilepsy: A machine learning approach.

ABSTRACT:

Purpose

We used a machine learning approach to identify the combinations of factors that contribute to lower adherence and high emergency department (ED) utilization.

Methods

Using Medicaid claims, we identified adherence to anti-seizure medications and the number of ED visits for people with epilepsy in a 2-year follow up period. We used three years of baseline data to identify demographics, disease severity and management, comorbidities, and county-level social factors. Using Classification and Regression Tree (CART) and random forest analyses we identified combinations of baseline factors that predicted lower adherence and ED visits. We further stratified these models by race and ethnicity.

Results

From 52,175 people with epilepsy, the CART model identified developmental disabilities, age, race and ethnicity, and utilization as top predictors of adherence. When stratified by race and ethnicity, there was variation in the combinations of comorbidities including developmental disabilities, hypertension, and psychiatric comorbidities. Our CART model for ED utilization included a primary split among those with previous injuries, followed by anxiety and mood disorders, headache, back problems, and urinary tract infections. When stratified by race and ethnicity we saw that for Black individuals headache was a top predictor of future ED utilization although this did not appear in other racial and ethnic groups.

Conclusions

ASM adherence differed by race and ethnicity, with different combinations of comorbidities predicting lower adherence across racial and ethnic groups. While there were not differences in ED use across races and ethnicity, we observed different combinations of comorbidities that predicted high ED utilization.

SUBMITTER: Bensken WP

PROVIDER: S-EPMC10528555 | biostudies-literature | 2023 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Disparities in adherence and emergency department utilization among people with epilepsy: A machine learning approach.

Bensken Wyatt P WP Vaca Guadalupe Fernandez-Baca GF Williams Scott M SM Khan Omar I OI Jobst Barbara C BC Stange Kurt C KC Sajatovic Martha M Koroukian Siran M SM

Seizure 20230628

<h4>Purpose</h4>We used a machine learning approach to identify the combinations of factors that contribute to lower adherence and high emergency department (ED) utilization.<h4>Methods</h4>Using Medicaid claims, we identified adherence to anti-seizure medications and the number of ED visits for people with epilepsy in a 2-year follow up period. We used three years of baseline data to identify demographics, disease severity and management, comorbidities, and county-level social factors. Using Cl ...[more]

PMID: 37393863

Similar Datasets

Project description:The relationship between weather and acute coronary syndrome (ACS) incidence has been the subject of considerable research, with varying conclusions. Harnessing machine learning techniques, our study explores the relationship between meteorological factors and ACS presentations in the emergency department (ED), offering insights into seasonal variations and inter-day fluctuations to optimize patient care and resource allocation. A retrospective cohort analysis was conducted, encompassing ACS presentations to Dutch EDs from 2010 to 2017. Temporal patterns were analyzed using heat-maps and time series plots. Multivariable linear regression (MLR) and Random Forest (RF) regression models were employed to forecast daily ACS presentations with prediction horizons of one, three, seven, and thirty days. Model performance was assessed using the coefficient of determination (R²), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE). The study included 214,953 ACS presentations, predominantly unstable angina (UA) (94,272; 44%), non-ST-elevated myocardial infarction (NSTEMI) (78,963; 37%), and ST-elevated myocardial infarction (STEMI) (41,718; 19%). A decline in daily ACS admissions over time was observed, with notable inter-day (estimated median difference: 41 (95%CI = 37-43, p = < 0.001) and seasonal variations (estimated median difference: 9 (95%CI 6-12, p = < 0.001). Both MLR and RF models demonstrated similar predictive capabilities, with MLR slightly outperforming RF. The models showed moderate explanatory power for ACS incidence (adjusted R² = 0.66; MAE (MAPE): 7.8 (11%)), with varying performance across subdiagnoses. Prediction of UA incidence resulted in the best-explained variability (adjusted R² = 0.80; MAE (MAPE): 5.3 (19.1%)), followed by NSTEMI and STEMI diagnoses. All models maintained consistent performance over extended prediction horizons. Our findings indicate that ACS presentation exhibits distinctive seasonal changes and inter-day differences, with marked reductions in incidence during the summer months and a distinct peak prevalence on Mondays. The predictive performance of our model was moderate. Nonetheless, we obtained good explanatory power for UA presentations. Our model emerges as a potentially valuable supplementary tool to enhance ED resource allocation or future predictive models predicting ACS incidence in the ED.

Project description:ObjectivesHospital emergency departments (EDs) are a place where many Americans seek treatment of dental conditions. Racial and ethnic minorities consistently have higher rates of ED utilization than whites for dental conditions. The reasons for these disparities and significant public health concerns are investigated less often. In this paper, we measure trends in racial disparities in ED discharges for dental conditions in Maryland from 2010 to 2013. To understand these disparities, we also describe differences between racial groups in age, gender, income, location, payer, comorbidities, and the availability of dental care.Methods2010-2013 State Emergency Department Data for Maryland were used in the analysis. Rates per 100,000 of the population are calculated using information from census population estimates. Cost-to-charge ratios are used to estimate the costs of ED discharges. Dental/oral health-related conditions (DOHRC) are defined as discharge diagnoses of ICD-9-CM codes 520.0 through 529.9. Descriptive statistics and fixed effects logistic regression models with a rare event correction are used to analyze the data.ResultsBlacks, especially females aged 25-34, have larger proportions of total ED discharges due to DOHRC, and higher population rates of DOHRC, than any other racial or ethnic group. In 2013, Blacks represented 30% of Maryland's population and accounted for 52% of ED costs for DOHRC. Hispanics and those of other races have much lower rates of DOHRC discharges. The regression results show that the high proportion of DOHRC discharges among Blacks may be explained by the concentration of Blacks in low-income central cities with less access to dental care.ConclusionThere are significant racial disparities in the ED utilization for DOHRC in Maryland. These disparities reflect the lack of access to dental care due to both cost and geographic limitations. This results in high healthcare costs and ineffective solutions for patients. Addressing oral health disparities will require policy solutions that are targeted to the populations most at need, and action plans that combine community and state level efforts.

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.

Project description:ObjectiveTo improve the performance of International Classification of Disease (ICD) code rule-based algorithms for identifying low acuity Emergency Department (ED) visits by using machine learning methods and additional covariates.Data sourcesWe used secondary data on ED visits from the National Hospital Ambulatory Medical Survey (NHAMCS), from 2016 to 2020.Study designWe established baseline performance metrics with seven published algorithms consisting of International Classification of Disease, Tenth Revision codes used to identify low acuity ED visits. We then trained logistic regression, random forest, and gradient boosting (XGBoost) models to predict low acuity ED visits. Each model was trained on five different covariate sets of demographic and clinical data. Model performance was compared using a separate validation dataset. The primary performance metric was the probability that a visit identified by an algorithm as low acuity did not experience significant testing, treatment, or disposition (positive predictive value, PPV). Subgroup analyses assessed model performance across age, sex, and race/ethnicity.Data collectionWe used 2016-2019 NHAMCS data as the training set and 2020 NHAMCS data for validation.Principal findingsThe training and validation data consisted of 53,074 and 9542 observations, respectively. Among seven rule-based algorithms, the highest-performing had a PPV of 0.35 (95% CI [0.33, 0.36]). All model-based algorithms outperformed existing algorithms, with the least effective-random forest using only age and sex-improving PPV by 26% (up to 0.44; 95% CI [0.40, 0.48]). Logistic regression and XGBoost trained on all variables improved PPV by 83% (to 0.64; 95% CI [0.62, 0.66]). Multivariable models also demonstrated higher PPV across all three demographic subgroups.ConclusionsMachine learning models substantially outperform existing algorithms based on ICD codes in predicting low acuity ED visits. Variations in model performance across demographic groups highlight the need for further research to ensure their applicability and fairness across diverse populations.

Project description:BackgroundUnintentional injury is the leading cause of death in young children. Emergency department (ED) diagnoses are a useful source of information for injury epidemiological surveillance purposes. However, ED data collection systems often use free-text fields to report patient diagnoses. Machine learning techniques (MLTs) are powerful tools for automatic text classification. The MLT system is useful to improve injury surveillance by speeding up the manual free-text coding tasks of ED diagnoses.ObjectiveThis research aims to develop a tool for automatic free-text classification of ED diagnoses to automatically identify injury cases. The automatic classification system also serves for epidemiological purposes to identify the burden of pediatric injuries in Padua, a large province in the Veneto region in the Northeast Italy.MethodsThe study includes 283,468 pediatric admissions between 2007 and 2018 to the Padova University Hospital ED, a large referral center in Northern Italy. Each record reports a diagnosis by free text. The records are standard tools for reporting patient diagnoses. An expert pediatrician manually classified a randomly extracted sample of approximately 40,000 diagnoses. This study sample served as the gold standard to train an MLT classifier. After preprocessing, a document-term matrix was created. The machine learning classifiers, including decision tree, random forest, gradient boosting method (GBM), and support vector machine (SVM), were tuned by 4-fold cross-validation. The injury diagnoses were classified into 3 hierarchical classification tasks, as follows: injury versus noninjury (task A), intentional versus unintentional injury (task B), and type of unintentional injury (task C), according to the World Health Organization classification of injuries.ResultsThe SVM classifier achieved the highest performance accuracy (94.14%) in classifying injury versus noninjury cases (task A). The GBM method produced the best results (92% accuracy) for the unintentional and intentional injury classification task (task B). The highest accuracy for the unintentional injury subclassification (task C) was achieved by the SVM classifier. The SVM, random forest, and GBM algorithms performed similarly against the gold standard across different tasks.ConclusionsThis study shows that MLTs are promising techniques for improving epidemiological surveillance, allowing for the automatic classification of pediatric ED free-text diagnoses. The MLTs revealed a suitable classification performance, especially for general injuries and intentional injury classification. This automatic classification could facilitate the epidemiological surveillance of pediatric injuries by also reducing the health professionals' efforts in manually classifying diagnoses for research purposes.

Dataset Information

Disparities in adherence and emergency department utilization among people with epilepsy: A machine learning approach.

Purpose

Methods

Results

Conclusions

Publications

Disparities in adherence and emergency department utilization among people with epilepsy: A machine learning approach.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets