BackgroundThis 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.MethodsThe 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.ResultsOur 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.ConclusionsTrue 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.

It is possible to enroll and maintain urban, minority, low-income families in a family-based behavioral group treatment program for pediatric obesity. Outcome data indicate that these families achieve significant outcomes on zBMI, and that children who remain available for assessment maintain this at 1 year, which is an improvement over previous research using other intervention methodologies with this population.

Delay of gratification tasks require an individual to forgo an immediate reward and wait for a more desirable delayed reward. This study used an ecologically valid measure of delayed gratification to test the hypothesis that preadolescents with higher BMI would be less likely to delay gratification. Healthy Hawks is a 12‐week educational/behavioral obesity intervention at the University of Kansas Medical Center. Each week, children earn a point if they complete their goals worksheet. They can spend that point immediately on a small toy prize or save points to use on a larger prize. We retrospectively calculated the percentage of points saved over the 12 weeks for 59 children (28 females) ages 8–12 years old (mean = 10.29 ± 1.39). Spearman correlation revealed that higher BMI percentile was associated with reduced point savings (r = 0.33, P = 0.01). Similarly, obese preadolescents saved significantly fewer points than healthy weight (HW) and overweight preadolescents (t (57) = 3.14, P < 0.01). Results from our ecologically valid measure support the theory that obese children are less likely to delay gratification than overweight and HW children. Even for nonfood rewards, preadolescent children with higher BMIs prefer the immediate reward over a delayed, larger reward. This has implications for developing specific strategies within obesity treatments aimed at improving delayed gratification.