Kevin Chikai Ma MS, Presenter: Nothing to Disclose

Ximing Wang MS, Abstract Co-Author: Nothing to Disclose

Mark S. Shiroishi MD, Abstract Co-Author: Nothing to Disclose

Alexander Lerner MD, Abstract Co-Author: Nothing to Disclose

Lilyana Amezcua MD, Abstract Co-Author: Consultant, Biogen Idec Inc Consultant, Bayer AG Consultant, Teva Pharmaceutical Industries Ltd Consultant, Merck KGaA Consultant, Pfizer Inc Advisory Board, Biogen Idec Inc Advisory Board, Bayer AG Advisory Board, Teva Pharmaceutical Industries Ltd Advisory Board, Pfizer Inc Advisory Board, Merck KGaA Speaker, Biogen Idec Inc Speaker, Bayer AG Speaker, Teva Pharmaceutical Industries Ltd Speaker, Merck KGaA Speaker, Pfizer Inc

Brent Julius Liu PhD, Abstract Co-Author: Nothing to Disclose

Previously, we have demonstrated a multiple sclerosis eFolder that integrates clinical, imaging, and white matter lesion quantitative data. We have developed a web-based user interface and database to store and view patient data. This year, we aim to fully demonstrate its capability of handling big data analysis and data mining for MS patient treatment and tracking. While data storing and data viewing has been demonstrated before, we will introduce data mining based on patients’ clinical, ethnicity, social and environmental information, and lesion characteristics. Big data analysis results are used to predict MS disease trends and patterns in Hispanic and Caucasian populations. The discovery of disease patterns among the two ethnicities will lead to personalized patient care and treatment planning.

Data from 72 matching Hispanic and Caucasian patients are collected. Quantitative lesion analysis, including lesion volumes, number of lesions, lesion locations, and brain parenchyma ratio, are performed by the CAD program and neuroradiologists. Relationships between disease/lesion progression, treatment types and length of treatments, social and environmental factors, and lesion volumes, sizes, and locations are observed in the two ethnicity groups in the database. The GUI is modified to display patient’s longitudinal image comparisons and lesion tracking across multiple studies to show disease progression with lesion changes, clinical result changes, and symptom progressions. 

The integrated longitudinal study viewer is successfully demonstrated. Patient profiles have been stored and displayed in the eFolder system. Data analysis has been performed, and different lesion characteristics with ethnic differences of the patients are shown in our pilot study.

We have demonstrated how an imaging informatics-based system can handle big data analysis using our MS eFolder, and the system provides data mining, longitudinal disease tracking, monitoring of disease progressions for personalized patient care, and displaying of comprehensive patient profile on a web-based user interface. Results are used to predict MS disease patterns in two different ethnicities from our pilot study. 

Ma, K, Wang, X, Shiroishi, M, Lerner, A, Amezcua, L, Liu, B, Big Data in Multiple Sclerosis Analysis: Data Mining and Analysis using a Web-based Longitudinal Study Viewer in an Imaging Informatics-based eFolder System.  Radiological Society of North America 2014 Scientific Assembly and Annual Meeting, - ,Chicago IL. http://archive.rsna.org/2014/14015540.html