Nonstandard Measurements in Electronic Medical Records
*Ani Eloyan, Johns Hopkins University
Electronic medical records can be used as an integral part of statistical models for improved disease diagnoses. In this talk, I will describe difficulties of incorporating nonstandard measurements, such as imaging data, into statistical models for analyzing patient medical records directed at models for disease diagnosis. I will show results of the use of dimension reduction of computed tomography (CT) image intensities to inform the statistical analyses of disease progression and diagnoses. I will present the results of the proposed methods on a real data set containing medical records and CT images for a group of patients with respiratory issues.