Risk of 30-Day Hospital Readmission Among Patients Discharged to Skilled Nursing Facilities: Development and Validation of a Risk-Prediction Model

Abstract

Objectives: Patients discharged to a skilled nursing facility (SNF) for postacute care have a high risk of hospital readmission. We aimed to develop and validate a risk-prediction model to prospectively quantify the risk of 30-day hospital readmission at the time of discharge to a SNF.Design: Retrospective cohort study.Setting: Ten independent SNFs affiliated with the postacute care practice of an integrated health care delivery system.Participants: We evaluated 6,032 patients who were discharged to a SNF for postacute care after hospitalization. Measurements:The primary outcome was all-cause 30-day hospital readmission. Patient demographics, medical comorbidity, prior use of health care, and clinical parameters during the index hospitalization were analyzed by using gradient boosting machine multivariable analysis to build a predictive model for 30-day hospital readmission. Area under the receiver-operator curve (AUC) was assessed on out-of-sample observations under 10-fold cross-validation.

Telehealth Use and Hospital Readmission Rates in Long-term Care Facilities in Southeastern Minnesota During the COVID-19 Pandemic

“…We found that the overall rate of hospital readmissions was lower than the rate we have seen historically in our population. In our previous studies, we had found that the overall hospital readmission rate was 18.2%, 17 whereas readmission in this study was 10.5%. This reduction in hospital readmission likely reflects the changes in the hospital admission practices with COVID-19 compared with the efficacy of the telemedicine visit practice.…”

“…Residents were evaluated for potentially more aggressive management depending on their illness. 17 The senior services division provides coordination for recommendations on standard practice, protocols, staffing, and guidance for the facilities. Especially, many protocols involve admission orders and infection control.…”

Current Trends in Readmission Prediction: An Overview of Approaches

“…Moreover, not all data are readily available across different EMRs in different health institutions [ 14 ]. Most notably, a number of studies suggested that existing predictors are sufficient to discern the highest-risk patients [ 93 , 96 , 97 , 99 , 105 ]. Readmissions associated with specific diseases are difficult to compare because they are affected by different risk factors [ 109 ].…”

“…The authors of [ 94 , 95 ] used LR and produced low to moderate performance (AUC = 0.712 and 0.661, respectively). GBM gave an AUC of 0.699 in predicting readmission among patients in skilled nursing facilities [ 96 ]. However, LR with lasso was shown to perform better than GBM in another research [ 97 ].…”

Data Science Methods for Nursing-Relevant Patient Outcomes and Clinical Processes

“…The populations studied were primarily adult; however, three papers focused on inpatients <18 years of age 21,131,148 or special populations such as surgical 88,93,134,137,[139][140][141][142]153,[156][157][158] and trauma 160 , medical conditions such as heart failure 129,143,144,155,161 , heart failure or myocardial infarction 159 , COPD 135 , diabetes 142 , IV 150 , falls 160 , antimicrobial therapy 134 , and skilled nursing facility discharge 132,163 . The majority of papers applied logistic regression in prediction models with 22 papers using development and validation cohorts, boot-strapped internal validation, or cross validation 21,91,93,129,[131][132][133][134]136,138,[140][141][142][143][144]147,…”