Digital Commons Network^™

Using An Automated Model To Identify Older Patients At Risk For 30-Day Hospital Readmission And 30-Day Mortality, Ariba Khan, Mary L. Hook, Maharaj Singh, Marsha Vollbrecht, Aaron Malsch, Michael L. Malone

Mary Hook

Background: A real-time electronic health record (EHR) predictive model that identifies older patients at risk for readmission and mortality may assist the health care team in improved patient care.

Purpose: This study was performed to generate an automated 30-day readmission and 30-day mortality risk model using data from the EHR in hospitalized older adults.

Methods: This was a retrospective cohort study. Included were patients age 65 years and older admitted to the hospital from July 2012 to December 2013. An automated predictive model was derived from variables collected from the EHR including socioeconomic factors, medical diagnoses and health care utilization. …

Outcomes Of Transcutaneous Aortic Valve Replacement Among High Risk Wv Sample Population., George M. Yousef, Julia Poe, Cameron Killmer, Basel Edris, Jason Mader, Ellen A. Thompson, Daniel Snavely, Silvestre Cansino, Joseph I. Shapiro, Mark A. Studeny

Joseph I Shapiro MD

Introduction:Transcatheter aortic valve replacement (TAVR) is a relatively new strategy for replacing the aortic valve. We elected to review our early experience to see if we could identify clinical characteristics at baseline or immediately following the procedure that would predict death within one year.

Methods:Charts for all patients assigned to receive TAVR procedure at St Mary’s medical center, Huntington, West Virginia between April, 2013 till November, 2016 were identified and reviewed. A total of seventy-two (72) cases were included.

Results: All cause mortality rate at index hospitalization, 30 days, and 12 months was 5.6%(N=4), 6.9%(N=5), 19.4%(N=14) respectively. Stroke …

Predicting Adverse Outcomes In End Stage Renal Disease: Machine Learning Applied To The United States Renal Data System, Zeid Khitan, Alexis D. Jacob, Courtney Balentine, Adam N. Jacob, Juan R. Sanabria, Joseph I. Shapiro

Joseph I Shapiro MD

We examined machine learning methods to predict death within six months using data derived from the United States Renal Data System (USRDS). We specifically evaluated a generalized linear model, a support vector machine, a decision tree and a random forest evaluated within the context of K-10 fold validation using the CARET package available within the open source architecture R program. We compared these models with the feed forward neural network strategy that we previously reported on with this data set.

Predicting Adverse Outcomes In End Stage Renal Disease: Machine Learning Applied To The United States Renal Data System, Zeid Khitan, Alexis D. Jacob, Courtney Balentine, Adam N. Jacob, Juan R. Sanabria, Joseph I. Shapiro

Joseph I Shapiro MD

We examined machine learning methods to predict death within six months using data derived from the United States Renal Data System (USRDS). We specifically evaluated a generalized linear model, a support vector machine, a decision tree and a random forest evaluated within the context of K-10 fold validation using the CARET package available within the open source architecture R program. We compared these models with the feed forward neural network strategy that we previously reported on with this data set.

Predicting Adverse Outcomes In End Stage Renal Disease: Machine Learning Applied To The United States Renal Data System, Zeid Khitan, Alexis D. Jacob, Courtney Balentine, Adam N. Jacob, Juan R. Sanabria, Joseph I. Shapiro

Juan R. Sanabria

We examined machine learning methods to predict death within six months using data derived from the United States Renal Data System (USRDS). We specifically evaluated a generalized linear model, a support vector machine, a decision tree and a random forest evaluated within the context of K-10 fold validation using the CARET package available within the open source architecture R program. We compared these models with the feed forward neural network strategy that we previously reported on with this data set.