Claims data-driven modeling of hospital time-to-readmission risk with latent heterogeneity

Patient Readmission for Ischemic Stroke: Risk Factors and Impact on Mortality

Patient readmission for ischemic stroke significantly strains the healthcare and medical insurance systems. Current understanding of the risk factors associated with these readmissions, as well as their subsequent impact on mortality within China, remains insufficient. This is particularly evident in the context of comprehensive, contemporary population studies. This 4-year retrospective cohort study included 125 397 hospital admissions for ischemic stroke from 838 hospitals located in 22 regions (13 urban and 9 rural) of a major city in western China, between January 1, 2015 and December 31, 2018. The Chi-square tests were used in univariate analysis. Accounting for intra-subject correlations of patients' readmissions, accelerated failure time (AFT) shared frailty models were used to examine readmission events and pure AFT models for mortality. Risk factors for patient readmission after ischemic stroke include frequent admission history, male gender, employee's insurance, advanced age, residence in urban areas, index hospitalization in low-level hospitals, extended length of stay (LOS) during index hospitalization, specific comorbidities and subtypes of ischemic stroke. Furthermore, our findings indicated that an additional admission for ischemic stroke increased patient mortality by 16.4% (P < .001). Stroke readmission contributed to an increased risk of hospital mortality. Policymakers can establish more effective and targeted policies to reduce readmissions for stroke by controlling these risk factors.

Predicting Hospital Readmissions in a Commercially Insured Population over Varying Time Horizons

BACKGROUND

Reducing hospital readmissions is a federal policy priority, and predictive models of hospital readmissions have proliferated in recent years; however, most such models tend to focus on the 30-day readmission time horizon and do not consider readmission over shorter (or longer) windows.

OBJECTIVES

To evaluate the performance of a predictive model of hospital readmissions over three different readmission timeframes in a commercially insured population.

DESIGN

Retrospective multivariate logistic regression with an 80/20 train/test split.

PARTICIPANTS

A total of 2,213,832 commercially insured inpatient admissions from 2016 to 2017 comprising 782,768 unique patients from the Health Care Cost Institute.

MAIN MEASURES

Outcomes are readmission within 14 days, 15-30 days, and 31-60 days from discharge. Predictor variables span six different domains: index admission, condition history, demographic, utilization history, pharmacy, and environmental controls.

KEY RESULTS

Our model generates C-statistics for holdout samples ranging from 0.618 to 0.915. The model's discriminative power declines with readmission time horizon: discrimination for readmission predictions within 14 days following discharge is higher than for readmissions 15-30 days following discharge, which in turn is higher than predictions 31-60 days following discharge. Additionally, the model's predictive power increases nonlinearly with the inclusion of successive risk factor domains: patient-level measures of utilization and condition history add substantially to the discriminative power of the model, while demographic information, pharmacy utilization, and environmental risk factors add relatively little.

CONCLUSION

It is more difficult to predict distant readmissions than proximal readmissions, and the more information the model uses, the better the predictions. Inclusion of utilization-based risk factors add substantially to the discriminative ability of the model, much more than any other included risk factor domain. Our best-performing models perform well relative to other published readmission prediction models. It is possible that these predictions could have operational utility in targeting readmission prevention interventions among high-risk individuals.

Using Routinely Collected Electronic Health Record Data to Predict Readmission and Target Care Coordination

ABSTRACT

Patients with chronic renal failure (CRF) are at high risk of being readmitted to hospitals within 30 days. Routinely collected electronic health record (EHR) data may enable hospitals to predict CRF readmission and target interventions to increase quality and reduce readmissions. We compared the ability of manually extracted variables to predict readmission compared with EHR-based prediction using multivariate logistic regression on 1 year of admission data from an academic medical center. Categorizing three routinely collected variables (creatinine, B-type natriuretic peptide, and length of stay) increased readmission prediction by 30% compared with paper-based methods as measured by C-statistic (AUC). Marginal effects analysis using the final multivariate model provided patient-specific risk scores from 0% to 44.3%. These findings support the use of routinely collected EHR data for effectively stratifying readmission risk for patients with CRF. Generic readmission risk tools may be evidence-based but are designed for general populations and may not account for unique traits of specific patient populations-such as those with CRF. Routinely collected EHR data are a rapid, more efficient strategy for risk stratifying and strategically targeting care. Earlier risk stratification and reallocation of clinician effort may reduce readmissions. Testing this risk model in additional populations and settings is warranted.

Healthcare Warranty Policies Optimization for Chronic Diseases Based on Delay Time Concept

Warranties for healthcare can be greatly beneficial for cost reductions and improvements in patient satisfaction. Under healthcare warranties, healthcare providers receive a lump sum payment for the entire care episode, which covers a bundle of healthcare services, including treatment decisions during initial hospitalization and subsequent readmissions, as well as disease-monitoring plans composed of periodic follow-ups. Higher treatment intensities and more radical monitoring strategies result in higher medical costs, but high treatment intensities reduce the baseline readmission rates. This study intends to provide a systematic optimization framework for healthcare warranty policies. In this paper, the proposed model allows healthcare providers to determine the optimal combination of treatment decisions and disease-monitoring policies to minimize the total expected healthcare warranty cost over the prespecified period. Given the nature of the disease progression, we introduced a delay time model to simulate the progression of chronic diseases. Based on this, we formulated an accumulated age model to measure the effect of follow-up on the patient's readmission risk. By means of the proposed model, the optimal treatment intensity and the monitoring policy can be derived. A case study of pediatric type 1 diabetes mellitus is presented to illustrate the applicability of the proposed model. The findings could form the basis of developing effective healthcare warranty policies for patients with chronic diseases.

Care Strategies for Reducing Hospital Readmissions Using Stochastic Programming

A hospital readmission occurs when a patient has an unplanned admission to a hospital within a specific time period of discharge from an earlier or initial hospital stay. Preventable readmissions have turned into a critical challenge for the healthcare system globally, and hospitals seek care strategies that reduce the readmission burden. Some countries have developed hospital readmission reduction policies, and in some cases, these policies impose financial penalties for hospitals with high readmission rates. Decision models are needed to help hospitals identify care strategies that avoid financial penalties, yet maintain balance among quality of care, the cost of care, and the hospital’s readmission reduction goals. We develop a multi-condition care strategy model to help hospitals prioritize treatment plans and allocate resources. The stochastic programming model has probabilistic constraints to control the expected readmission probability for a set of patients. The model determines which care strategies will be the most cost-effective and the extent to which resources should be allocated to those initiatives to reach the desired readmission reduction targets and maintain high quality of care. A sensitivity analysis was conducted to explore the value of the model for low- and high-performing hospitals and multiple health conditions. Model outputs are valuable to hospitals as they examine the expected cost of hitting its target and the expected improvement to its readmission rates.

Data Science Methods for Nursing-Relevant Patient Outcomes and Clinical Processes: The 2019 Literature Year in Review

Data science continues to be recognized and used within healthcare due to the increased availability of large data sets and advanced analytics. It can be challenging for nurse leaders to remain apprised of this rapidly changing landscape. In this article, we describe our findings from a scoping literature review of papers published in 2019 that use data science to explore, explain, and/or predict 15 phenomena of interest to nurses. Fourteen of the 15 phenomena were associated with at least one paper published in 2019. We identified the use of many contemporary data science methods (eg, natural language processing, neural networks) for many of the outcomes. We found many studies exploring Readmissions and Pressure Injuries. The topics of Artificial Intelligence/Machine Learning Acceptance, Burnout, Patient Safety, and Unit Culture were poorly represented. We hope that the studies described in this article help readers: (1) understand the breadth and depth of data science's ability to improve clinical processes and patient outcomes that are relevant to nurses and (2) identify gaps in the literature that are in need of exploration.

Factors affecting in-hospital cost and mortality of patients with stroke: Evidence from a case study in a tertiary hospital in China

OBJECTIVE

The study aims to investigate the factors causing the difference of stroke patients' in-hospital cost and study these factors on health outcome in terms of mortality.

METHODS

Eight hundred and sixty-two in-patients with stroke in a tertiary hospital in China from 2017 to 2019 were included in the database. Descriptive statistics indexes were used to describe patients' in-hospital cost and mortality. Based on Elixhauser coding algorithms, multiple linear regression and logistic regressions (LRs) were used to evaluate the impact of factors identified from univariate analysis on in-hospital cost and mortality, respectively. In addition to LRs, a comparison study was then carried out with random forest, gradient boosting decision tree and artificial neural network.

RESULTS

Factors affecting both cost and mortality are age, discharged day-of-week, length of stay, stroke subtype, other neurological disorders, renal failure, fluid and electrolyte disorders and total number of comorbidities.

CONCLUSION

With the increase of age, the mortality rate of in-patients (except for the juvenile) with stroke increases and the cost of hospitalization decreases. Intracerebral haemorrhage is the most devastating stroke for its highest mortality in short length of stay. Medical services should focus on these specific comorbidities.