Search

Background: The use of post-acute care (PAC) for cardiovascular conditions is highly variable across geographical regions. Although PAC benefits include lower readmission rates, better clinical outcomes, and lower mortality, referral patterns vary widely, raising concerns about substandard care and inflated costs. The objective of this study is to identify factors associated with PAC referral decisions at acute care discharge.Methods: This study is a retrospective Electronic Health Records (EHR) based review of a cohort of patients with coronary artery bypass graft (CABG) and valve replacement (VR). EHR records were extracted from the Cerner Health-Facts Data warehouse and covered 49 hospitals in the United States of America (U.S.) from January 2010 to December 2015. Multinomial logistic regression was used to identify associations of 29 variables comprising patient characteristics, hospital profiles, and patient conditions at discharge.Results: The cohort had 14,224 patients with mean age 63.5 years, with 10,234 (71.9%) male and 11,946 (84%) Caucasian, with 5827 (40.96%) being discharged to home without additional care (Home), 5226 (36.74%) to home health care (HHC), 1721 (12.10%) to skilled nursing facilities (SNF), 1168 (8.22%) to inpatient rehabilitation facilities (IRF), 164 (1.15%) to long term care hospitals (LTCH), and 118 (0.83%) to other locations. Census division, hospital size, teaching hospital status, gender, age, marital status, length of stay, and Charlson comorbidity index were identified as highly significant variables (p- values < 0.001) that influence the PAC referral decision. Overall model accuracy was 62.6%, and multiclass Area Under the Curve (AUC) values were for Home: 0.72; HHC: 0.72; SNF: 0.58; IRF: 0.53; LTCH: 0.52, and others: 0.46.Conclusions: Census location of the acute care hospital was highly associated with PAC referral practices, as was hospital capacity, with larger hospitals referring patients to PAC at a greater rate than smaller hospitals. Race and gender were also statistically significant, with Asians, Hispanics, and Native Americans being less likely to be referred to PAC compared to Caucasians, and female patients being more likely to be referred than males. Additional analysis indicated that PAC referral practices are also influenced by the mix of PAC services offered in each region. [ABSTRACT FROM AUTHOR]

Diabetes is a large healthcare burden worldwide. There is substantial evidence that lifestyle modifications and drug intervention can prevent diabetes, therefore, an early identification of high risk individuals is important to design targeted prevention strategies. In this paper, we present an automatic tool that uses machine learning techniques to predict the development of type 2 diabetes mellitus (T2DM). Data generated from an oral glucose tolerance test (OGTT) was used to develop a predictive model based on the support vector machine (SVM). We trained and validated the models using the OGTT and demographic data of 1,492 healthy individuals collected during the San Antonio Heart Study. This study collected plasma glucose and insulin concentrations before glucose intake and at three time-points thereafter (30, 60 and 120 min). Furthermore, personal information such as age, ethnicity and body-mass index was also a part of the data-set. Using 11 OGTT measurements, we have deduced 61 features, which are then assigned a rank and the top ten features are shortlisted using minimum redundancy maximum relevance feature selection algorithm. All possible combinations of the 10 best ranked features were used to generate SVM based prediction models. This research shows that an individual's plasma glucose levels, and the information derived therefrom have the strongest predictive performance for the future development of T2DM. Significantly, insulin and demographic features do not provide additional performance improvement for diabetes prediction. The results of this work identify the parsimonious clinical data needed to be collected for an efficient prediction of T2DM. Our approach shows an average accuracy of 96.80% and a sensitivity of 80.09% obtained on a holdout set., Competing Interests: The authors have declared that no competing interests exist.

Since 2013, the Centers for Disease Control and Prevention (CDC) has hosted an annual influenza season forecasting challenge. The 2015-2016 challenge consisted of weekly probabilistic forecasts of multiple targets, including fourteen models submitted by eleven teams. Forecast skill was evaluated using a modified logarithmic score. We averaged submitted forecasts into a mean ensemble model and compared them against predictions based on historical trends. Forecast skill was highest for seasonal peak intensity and short-term forecasts, while forecast skill for timing of season onset and peak week was generally low. Higher forecast skill was associated with team participation in previous influenza forecasting challenges and utilization of ensemble forecasting techniques. The mean ensemble consistently performed well and outperformed historical trend predictions. CDC and contributing teams will continue to advance influenza forecasting and work to improve the accuracy and reliability of forecasts to facilitate increased incorporation into public health response efforts.