Predicting all-cause risk of 30-day hospital readmission using artificial neural networks.
Ontology highlight
ABSTRACT:
SUBMITTER: Jamei M
PROVIDER: S-EPMC5510858 | biostudies-other | 2017
REPOSITORIES: biostudies-other
Similar Datasets
Project description:Reduction in 30-day readmission rate is an important quality factor for hospitals as it can reduce the overall cost of care and improve patient post-discharge outcomes. While deep-learning-based studies have shown promising empirical results, several limitations exist in prior models for hospital readmission prediction, such as: (a) only patients with certain conditions are considered, (b) do not leverage data temporality, (c) individual admissions are assumed independent of each other, which ignores patient similarity, (d) limited to single modality or single center data. In this study, we propose a multimodal, spatiotemporal graph neural network (MM-STGNN) for prediction of 30-day all-cause hospital readmission, which fuses in-patient multimodal, longitudinal data and models patient similarity using a graph. Using longitudinal chest radiographs and electronic health records from two independent centers, we show that MM-STGNN achieved an area under the receiver operating characteristic curve (AUROC) of 0.79 on both datasets. Furthermore, MM-STGNN significantly outperformed the current clinical reference standard, LACE+ (AUROC=0.61), on the internal dataset. For subset populations of patients with heart disease, our model significantly outperformed baselines, such as gradient-boosting and Long Short-Term Memory models (e.g., AUROC improved by 3.7 points in patients with heart disease). Qualitative interpretability analysis indicated that while patients' primary diagnoses were not explicitly used to train the model, features crucial for model prediction may reflect patients' diagnoses. Our model could be utilized as an additional clinical decision aid during discharge disposition and triaging high-risk patients for closer post-discharge follow-up for potential preventive measures.
| S-EPMC11073780 | biostudies-literature
Project description:Reducing unplanned readmissions is a major focus of current hospital quality efforts. In order to avoid unfair penalization, administrators and policymakers use prediction models to adjust for the performance of hospitals from healthcare claims data. Regression-based models are a commonly utilized method for such risk-standardization across hospitals; however, these models often suffer in accuracy. In this study we, compare four prediction models for unplanned patient readmission for patients hospitalized with acute myocardial infarction (AMI), congestive health failure (HF), and pneumonia (PNA) within the Nationwide Readmissions Database in 2014. We evaluated hierarchical logistic regression and compared its performance with gradient boosting and two models that utilize artificial neural networks. We show that unsupervised Global Vector for Word Representations embedding representations of administrative claims data combined with artificial neural network classification models improves prediction of 30-day readmission. Our best models increased the AUC for prediction of 30-day readmissions from 0.68 to 0.72 for AMI, 0.60 to 0.64 for HF, and 0.63 to 0.68 for PNA compared to hierarchical logistic regression. Furthermore, risk-standardized hospital readmission rates calculated from our artificial neural network model that employed embeddings led to reclassification of approximately 10% of hospitals across categories of hospital performance. This finding suggests that prediction models that incorporate new methods classify hospitals differently than traditional regression-based approaches and that their role in assessing hospital performance warrants further investigation.
| S-EPMC7159221 | biostudies-literature
Project description:BackgroundEarly hospital readmission for patients with cirrhosis continues to challenge the healthcare system. Risk stratification may help tailor resources, but existing models were designed using small, single-institution cohorts or had modest performance.AimsWe leveraged a large clinical database from the Department of Veterans Affairs (VA) to design a readmission risk model for patients hospitalized with cirrhosis. Additionally, we analyzed potentially modifiable or unexplored readmission risk factors.MethodsA national VA retrospective cohort of patients with a history of cirrhosis hospitalized for any reason from January 1, 2006, to November 30, 2013, was developed from 123 centers. Using 174 candidate variables within demographics, laboratory results, vital signs, medications, diagnoses and procedures, and healthcare utilization, we built a 47-variable penalized logistic regression model with the outcome of all-cause 30-day readmission. We excluded patients who left against medical advice, transferred to a non-VA facility, or if the hospital length of stay was greater than 30 days. We evaluated calibration and discrimination across variable volume and compared the performance to recalibrated preexisting risk models for readmission.ResultsWe analyzed 67,749 patients and 179,298 index hospitalizations. The 30-day readmission rate was 23%. Ascites was the most common cirrhosis-related cause of index hospitalization and readmission. The AUC of the model was 0.670 compared to existing models (0.649, 0.566, 0.577). The Brier score of 0.165 showed good calibration.ConclusionOur model achieved better discrimination and calibration compared to existing models, even after local recalibration. Assessment of calibration by variable parsimony revealed performance improvements for increasing variable inclusion well beyond those detectable for discrimination.
| S-EPMC7073276 | biostudies-literature
Project description:Heart failure (HF) is one of the leading causes of hospital admissions in the US. Readmission within 30 days after a HF hospitalization is both a recognized indicator for disease progression and a source of considerable financial burden to the healthcare system. Consequently, the identification of patients at risk for readmission is a key step in improving disease management and patient outcome. In this work, we used a large administrative claims dataset to (1) explore the systematic application of neural network-based models versus logistic regression for predicting 30 days all-cause readmission after discharge from a HF admission, and (2) to examine the additive value of patients' hospitalization timelines on prediction performance. Based on data from 272,778 (49% female) patients with a mean (SD) age of 73 years (14) and 343,328 HF admissions (67% of total admissions), we trained and tested our predictive readmission models following a stratified 5-fold cross-validation scheme. Among the deep learning approaches, a recurrent neural network (RNN) combined with conditional random fields (CRF) model (RNNCRF) achieved the best performance in readmission prediction with 0.642 AUC (95% CI, 0.640-0.645). Other models, such as those based on RNN, convolutional neural networks and CRF alone had lower performance, with a non-timeline based model (MLP) performing worst. A competitive model based on logistic regression with LASSO achieved a performance of 0.643 AUC (95% CI, 0.640-0.646). We conclude that data from patient timelines improve 30 day readmission prediction, that a logistic regression with LASSO has equal performance to the best neural network model and that the use of administrative data result in competitive performance compared to published approaches based on richer clinical datasets.
| S-EPMC6595068 | biostudies-literature
Project description:Unplanned hospital readmissions mean a significant burden for health systems. Accurately estimating the patient's readmission risk could help to optimise the discharge decision-making process by smartly ordering patients based on a severity score, thus helping to improve the usage of clinical resources. A great number of heterogeneous factors can influence the readmission risk, which makes it highly difficult to be estimated by a human agent. However, this score could be achieved with the help of AI models, acting as aiding tools for decision support systems. In this paper, we propose a machine learning classification and risk stratification approach to assess the readmission problem and provide a decision support system based on estimated patient risk scores.
| S-EPMC9286269 | biostudies-literature
Project description:BackgroundLowering hospital readmission rates has become a primary target for the Centers for Medicare & Medicaid Services, but studies of the relationship between adherence to the recommended hospital care processes and readmission rates have provided inconsistent and inconclusive results.ObjectiveTo examine the association between hospital performance on Medicare's Hospital Compare process quality measures and 30-day readmission rates for patients with acute myocardial infarction (AMI), heart failure and pneumonia, and for those undergoing major surgery.Design, setting and participantsWe assessed hospital performance on process measures using the 2007 Hospital Inpatient Quality Reporting Program. The process measures for each condition were aggregated in two separate measures: Overall Measure (OM) and Appropriate Care Measure (ACM) scores. Readmission rates were calculated using Medicare claims.Main outcome measureRisk-standardized 30-day all-cause readmission rate was calculated as the ratio of predicted to expected rate standardized by the overall mean readmission rate. We calculated predicted readmission rate using hierarchical generalized linear models and adjusting for patient-level factors.ResultsAmong patients aged ≥ 66 years, the median OM score ranged from 79.4 % for abdominal surgery to 95.7 % for AMI, and the median ACM scores ranged from 45.8 % for abdominal surgery to 87.9 % for AMI. We observed a statistically significant, but weak, correlation between performance scores and readmission rates for pneumonia (correlation coefficient R = 0.07), AMI (R = 0.10), and orthopedic surgery (R = 0.06). The difference in the mean readmission rate between hospitals in the 1st and 4th quartiles of process measure performance was statistically significant only for AMI (0.25 percentage points) and pneumonia (0.31 percentage points). Performance on process measures explained less than 1 % of hospital-level variation in readmission rates.ConclusionsHospitals with greater adherence to recommended care processes did not achieve meaningfully better 30-day hospital readmission rates compared to those with lower levels of performance.
| S-EPMC3579957 | biostudies-literature
Project description:IntroductionHospital readmission rates are an indicator of the health care quality provided by hospitals. Applying machine learning (ML) to a hospital readmission database offers the potential to identify patients at the highest risk for readmission. However, few studies applied ML methods to predict hospital readmission. This study sought to assess ML as a tool to develop prediction models for all-cause 90-day hospital readmission for dental patients.MethodsUsing the 2013 Nationwide Readmissions Database (NRD), the study identified 9260 cases for all-cause 90-day index admission for dental patients. Five ML classification algorithms including decision tree, logistic regression, support vector machine, k-nearest neighbors, and artificial neural network (ANN) were implemented to build predictive models. The model performance was estimated and compared by using area under the receiver operating characteristic curve (AUC), and accuracy, sensitivity, specificity, and precision.ResultsHospital readmission within 90 days occurred in 1746 cases (18.9%). Total charges, number of diagnosis, age, number of chronic conditions, length of hospital stays, number of procedures, primary expected payer, and severity of illness emerged as the top eight important features in all-cause 90-day hospital readmission. All models had similar performance with ANN (AUC = 0.743) slightly outperforming the rest.ConclusionThis study demonstrates a potential annual saving of over $500 million if all of the 90-day readmission cases could be prevented for 21 states represented in the NRD. Among the methods used, the prediction model built by ANN exhibited the best performance. Further testing using ANN and other methods can help to assess important readmission risk factors and to target interventions to those at the greatest risk.
| S-EPMC7822935 | biostudies-literature
Project description:BackgroundReducing hospital readmissions, including preventable healthcare-associated infections, is a national priority. The proportion of readmissions due to infections is not well-understood. Better understanding of hospital risk factors for readmissions and infection-related readmissions may help optimize interventions to prevent readmissions.MethodsRetrospective cohort study of California acute care hospitals and their patient populations discharged between 2009 and 2011. Demographics, comorbidities, and socioeconomic status were entered into a hierarchical generalized linear mixed model predicting all-cause and infection-related readmissions. Crude verses adjusted hospital rankings were compared using Cohen's kappa.ResultsWe assessed 30-day readmission rates from 323 hospitals, accounting for 213 879 194 post-discharge person-days of follow-up. Infection-related readmissions represented 28% of all readmissions and were associated with discharging a high proportion of patients to skilled nursing facilities. Hospitals serving populations with high proportions of males, comorbidities, prolonged length of stay, and populations living in a federal poverty area, had higher all-cause and infection-related readmission rates. Academic hospitals had higher all-cause and infection-related readmission rates (odds ratio 1.24 and 1.15, respectively). When comparing adjusted vs crude hospital rankings for infection-related readmission rates, adjustment revealed 31% of hospitals changed performance category for infection-related readmissions.ConclusionsInfection-related readmissions accounted for nearly 30% of all-cause readmissions. High hospital infection-related readmissions were associated with serving a high proportion of patients with comorbidities, long lengths of stay, discharge to skilled nursing facility, and those living in federal poverty areas. Preventability of these infections needs to be assessed.
| S-EPMC4583583 | biostudies-literature
Project description:ObjectiveTo assess the reliability of risk-standardized readmission rates (RSRRs) for medical conditions and surgical procedures used in the Hospital Readmission Reduction Program (HRRP).Data sourcesState Inpatient Databases for six states from 2011 to 2013 were used to identify patient cohorts for the six conditions used in the HRRP, which was augmented with hospital characteristic and HRRP penalty data.Study designHierarchical logistic regression models estimated hospital-level RSRRs for each condition, the reliability of each RSRR, and the extent to which socioeconomic and hospital factors further explain RSRR variation. We used publicly available data to estimate payments for excess readmissions in hospitals with reliable and unreliable RSRRs.Principal findingsOnly RSRRs for surgical procedures exceeded the reliability benchmark for most hospitals, whereas RSRRs for medical conditions were typically below the benchmark. Additional adjustment for socioeconomic and hospital factors modestly explained variation in RSRRs. Approximately 25 percent of payments for excess readmissions were tied to unreliable RSRRs.ConclusionsMany of the RSRRs employed by the HRRP are unreliable, and one quarter of payments for excess readmissions are associated with unreliable RSRRs. Unreliable measures blur the connection between hospital performance and incentives, and threaten the success of the HRRP.
| S-EPMC5134200 | biostudies-literature
Project description:BackgroundPredictive models based on electronic health records (EHRs) are used to identify patients at high risk for 30-day hospital readmission. However, these models' ability to accurately detect who could benefit from inclusion in prevention interventions, also termed "perceived impactibility", has yet to be realized.ObjectiveWe aimed to explore healthcare providers' perspectives of patient characteristics associated with decisions about which patients should be referred to readmission prevention programs (RPPs) beyond the EHR preadmission readmission detection model (PREADM).DesignThis cross-sectional study employed a multi-source mixed-method design, combining EHR data with nurses' and physicians' self-reported surveys from 15 internal medicine units in three general hospitals in Israel between May 2016 and June 2017, using a mini-Delphi approach.ParticipantsNurses and physicians were asked to provide information about patients 65 years or older who were hospitalized at least one night.Main measuresWe performed a decision-tree analysis to identify characteristics for consideration when deciding whether a patient should be included in an RPP.Key resultsWe collected 817 questionnaires on 435 patients. PREADM score and RPP inclusion were congruent in 65% of patients, whereas 19% had a high PREADM score but were not referred to an RPP, and 16% had a low-medium PREADM score but were referred to an RPP. The decision-tree analysis identified five patient characteristics that were statistically associated with RPP referral: high PREADM score, eligibility for a nursing home, having a condition not under control, need for social-services support, and need for special equipment at home.ConclusionsOur study provides empirical evidence for the partial congruence between classifications of a high PREADM score and perceived impactibility. Findings emphasize the need for additional research to understand the extent to which combining EHR data with provider insights leads to better selection of patients for RPP inclusion.
| S-EPMC7210355 | biostudies-literature