Nephrology Commons^™

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 Chronic Kidney Disease Using Machine Learning Methods: Data From The Modification Of Diet In Renal Disease, Zeid Khitan, Anna P. Shapiro, Preeya T. Shah, Juan R. Sanabria, Prasanna Santhanam, Komal Sodhi, Nader G. Abraham, Joseph I. Shapiro

Joseph I Shapiro MD

Background: Understanding factors which predict progression of renal failure is of great interest to clinicians. Objectives: We examined machine learning methods to predict the composite outcome of death, dialysis or doubling of serum creatinine using the modification of diet in renal disease (MDRD) data set. Methods: We specifically evaluated a generalized linear model, a support vector machine, a decision tree, a feed-forward neural network and a random forest evaluated within the context of 10 fold validation using the CARET package available within the open source architecture R program. Results: We found that using clinical parameters available at entry into the …

Why Does Obesity Lead To Hypertension? Further Lessons From The Intersalt Study., Preeya T. Shah, Anna P. Shapiro, Zeid Khitan Md, Prasanna Santhanam Md, Joseph I. Shapiro Md

Joseph I Shapiro MD

Objectives To analyze correlations between major determinants of blood pressure (BP), in efforts to generate and compare predictive models that explain for variance in systolic, diastolic, and mean BP amongst participants of the Intersalt study. Methods Data from the Intersalt study, consisting of nearly 10,000 subjects from 32 different countries, were reviewed and analyzed. Published mean values of 24 hour urinary electrolyte excretion (Na+, K+), 24 hour urine creatinine excretion, body mass index (BMI, kg/m^2), and blood pressure data were extracted and imported into Matlab™ for stepwise linear regression analysis. Results As shown earlier, strong correlations between urinary sodium excretion …

Use Of Surface-Enhanced Laser Desorption/Ionization With Time Of Flight (Seldi-Tof) Of The Urine In The Assessment Of Acute Kidney Injury (Aki), David J. Kennedy, Phd, Joseph M. Chan, Dinkar Kaw, Md, Anand M. Ravindaran, Md, Shobha Ratnam, Md, Phd, Deepak Malhotra, Md, Phd, Joseph I. Shapiro Md

Joseph I Shapiro MD

Background: Urinalysis is an important component in the assessment of acute kidney injury (AKI). Proteonomics is a rapidly developing approach in the analysis of physiological states. Several techniques have been developed to screen for protein populations. In this regard SELDI-TOF is a technique based on mass spectroscopy that is being utilized in proteonomics research.

Methods:For this study, clean catch or catheterized urine was collected from normals (n=18) and patients referred to the renal service with AKI. Based upon urine and serum chemistries, clinical parameters, and microscopic urinalysis, the urines were separated into those consistent with prerenal azotemia (n=17) and acute …

Use Of Surface-Enhanced Laser Desorption/Ionization With Time Of Flight (Seldi-Tof) Of The Urine In The Assessment Of Acute Kidney Injury (Aki), David Kennedy, Joseph M. Chan, Dinkar Kaw, Anand M. Ravindaran, Deepak Malhotra, Joseph I. Shapiro Md

Joseph I Shapiro MD

Urine SELDI spectra from patients with prerenal azotemia (PRE, lower panels) and acute tubular necrosis (ATN, upper panels) contrasted over ranges between 1.1 and 1.5 KD (left panels) and 2 and 5 KD (right panels).

Gender Differences In The Development Of Uremic Cardiomyopathy Following Partial Nephrectomy: Role Of Progesterone, Christopher A. Drummond, George Buddny, Steven T. Haller, Jiang Liu, Yanling Yan, Zijian Xie, Deepak Malhotra, Joseph I. Shapiro Md, Jiang Tian

Joseph I Shapiro MD

Gender difference has been suggested as a risk factor for developing cardiovascular and renal diseases in humans and experimental animals. As a major sex hormone, progesterone was reported to compete with cardiotonic steroid binding to Na/K-ATPase. Our previous publication demonstrated that cardiotonic steroids (e.g., marinobufagenin) play an important role in the development of experimental uremic cardiomyopathy. We also observed that the putative mineralocorticoid antagonists, spironolactone and its major metabolite canrenone, antagonize binding of cardiotonic steroids to Na/K-ATPase in a competitive manner and also ameliorate experimental uremic cardiomyopathy induced by partial nephrectomy. In the following studies, we noted that progesterone displayed …