Comparison of predictive modeling approaches for 30-day all-cause non-elective readmission risk.

BACKGROUND: This paper explores the importance of electronic medical records (EMR) for predicting 30-day all-cause non-elective readmission risk of patients and presents a comparison of prediction performance of commonly used methods. METHODS: The data are extracted from eight Advocate Health Care hospitals. Index admissions are excluded from the cohort if they are observation, inpatient admissions for psychiatry, skilled nursing, hospice, rehabilitation, maternal and newborn visits, or if the patient expires during the index admission. Data are randomly and repeatedly divided into fitting and validating sets for cross validations. Approaches including LACE, STEPWISE logistic, LASSO logistic, and AdaBoost, are compared with sample sizes varying from 2,500 to 80,000. RESULTS: Our results confirm that LACE has moderate discrimination power with the area under receiver operating characteristic curve (AUC) around 0.65-0.66, which can be improved to 0.73-0.74 when additional variables from EMR are considered. These variables include Inpatient in the last six months, Number of emergency room visits or inpatients in the last year, Braden score, Polypharmacy, Employment status, Discharge disposition, Albumin level, and medical condition variables such as Leukemia, Malignancy, Renal failure with hemodialysis, History of alcohol substance abuse, Dementia and Trauma. When sample size is small (≤5000), LASSO is the best; when sample size is large (≥20,000), the predictive performance is similar. The STEPWISE method has a slightly lower AUC (0.734) comparing to LASSO (0.737) and AdaBoost (0.737). More than one half of the selected predictors can be false positives when using a single method and a single division of fitting/validating data. CONCLUSIONS: True predictors can be identified by repeatedly dividing data into fitting/validating subsets and referring the final model based on summarizing results. LASSO is a better alternative to the STEPWISE logistic regression, especially when sample size is not large. The evidence for adequate sample size can be explored by fitting models on gradually reduced samples. Our model comparison strategy is not only good for 30-day all-cause non-elective readmission risk predictions, but also applicable to other types of predictive models in clinical studies.

The association between outpatient follow-up visits and all-cause non-elective 30-day readmissions: A retrospective observational cohort study.

BACKGROUND: As an effort to reduce hospital readmissions, early follow-up visits were recommended by the Society of Hospital Medicine. However, published literature on the effect of follow-up visits is limited with mixed conclusions. Our goal here is to fully explore the relationship between follow-up visits and the all-cause non-elective 30-day readmission rate (RR) after adjusting for confounders. METHODS AND RESULTS: To conduct this retrospective observational study, we extracted data for 55,378 adult inpatients from Advocate Health Care, a large, multi-hospital system serving a diverse population in a major metropolitan area. These patients were discharged to Home or Home with Home Health services between June 1, 2013 and April 30, 2015. Our findings from time-dependent Cox proportional hazard models showed that follow-up visits were significantly associated with a reduced RR (adjusted hazard ratio: 0.86; 95% CI: 0.82-0.91), but in a complicated way because the interaction between follow-up visits and a readmission risk score was significant with p-value < 0.001. Our analysis using logistic models on an adjusted data set confirmed the above findings with the following additional results. First, time matter. Follow-up visits within 2 days were associated with the greatest reduction in RR (adjusted odds ratio: 0.72; 95% CI: 0.63-0.83). Visits beyond 2 days were also associated with a reduction in RR, but the strength of the effect decreased as the time between discharge and follow-up visit increased. Second, the strength of such association varied for patients with different readmission risk scores. Patients with a risk score of 0.113, high but not extremely high risk, had the greatest reduction in RR from follow-up visits. Patients with an extremely high risk score (> 0.334) saw no RR reduction from follow-up visits. Third, a patient was much more likely to have a 2-day follow-up visit if that visit was scheduled before the patient was discharged from the hospital (30% versus < 5%). CONCLUSIONS: Follow-up visits are associated with a reduction in readmission risk. The timing of follow-up visits can be important: beyond two days, the earlier, the better. The effect of follow-up visits is more significant for patients with a high but not extremely high risk of readmission.

A public-private partnership develops and externally validates a 30-day hospital readmission risk prediction model.

INTRODUCTION: Preventing the occurrence of hospital readmissions is needed to improve quality of care and foster population health across the care continuum. Hospitals are being held accountable for improving transitions of care to avert unnecessary readmissions. Advocate Health Care in Chicago and Cerner (ACC) collaborated to develop all-cause, 30-day hospital readmission risk prediction models to identify patients that need interventional resources. Ideally, prediction models should encompass several qualities: they should have high predictive ability; use reliable and clinically relevant data; use vigorous performance metrics to assess the models; be validated in populations where they are applied; and be scalable in heterogeneous populations. However, a systematic review of prediction models for hospital readmission risk determined that most performed poorly (average C-statistic of 0.66) and efforts to improve their performance are needed for widespread usage. METHODS: The ACC team incorporated electronic health record data, utilized a mixed-method approach to evaluate risk factors, and externally validated their prediction models for generalizability. Inclusion and exclusion criteria were applied on the patient cohort and then split for derivation and internal validation. Stepwise logistic regression was performed to develop two predictive models: one for admission and one for discharge. The prediction models were assessed for discrimination ability, calibration, overall performance, and then externally validated. RESULTS: The ACC Admission and Discharge Models demonstrated modest discrimination ability during derivation, internal and external validation post-recalibration (C-statistic of 0.76 and 0.78, respectively), and reasonable model fit during external validation for utility in heterogeneous populations. CONCLUSIONS: The ACC Admission and Discharge Models embody the design qualities of ideal prediction models. The ACC plans to continue its partnership to further improve and develop valuable clinical models.