好色先生

好色先生

Explore the latest content from across our publications
Join The AAN

Log In

Forgot Password?
Create New Account

Loading... please wait

Abstract Details

Leveraging Electronic Health Records for Modeling Disease Activity in Multiple Sclerosis
MS and Related Diseases
P03 - (-)
209
BACKGROUND: MS research studies based on traditional cohorts are limited by cost and size.
DESIGN/METHODS: We created a "data-mart" containing the complete medical records of 22,610 patients with ?1 MS-related ICD9 code at Partners HealthCare and randomly selected 595 patients for "training". Two neurologists independently reviewed the records of "training" patients and found 251 MS cases. From codified and narrative EHR data on symptoms, medications, tests, and neuroimaging reports extracted using natural language processing, we performed 20-fold cross-validation using logistic regression on the training-set to select informative variables for predicting MS. The algorithm was then applied to the data-mart to identify patients with high probability of MS. Additional algorithms were developed similarly to model outcomes of disease activity using a subset of patients enrolled in Partners MS Center and calculated variance explained by the models (R2).
RESULTS: We developed a robust EHR-based algorithm to classify MS. Setting the specificity at 95%, the algorithm has an area under the curve=0.958, sensitivity=83%, positive predictive value=92% and negative predictive value=89%. We captured 5,495 MS patients from the EHR, including 1153 patients enrolled in the Partners MS Center. Using this patient-subset with available disease activity measures as gold-standard, we developed algorithms based on EHR variables to impute brain volume (R2=0.43) and MS severity score (R2=0.34).
CONCLUSIONS: Incorporation of sophisticated structured and free-text EHR data allows improved identification of MS patients. EHR-derived cohorts, when linked with biobanks of discarded biological material, provide novel resources to rapidly implement studies of MS disease activity, comorbidities, pharmacogenomics and presymptomatic disease. If replicated, our novel informatics methods offer promise towards efficient and cost-effective development of multi-center cohorts for translational and clinical research in MS.
Authors/Disclosures
Zongqi Xia, MD, PhD
PRESENTER 		The institution of Dr. Xia has received research support from National Institute of Health. The institution of Dr. Xia has received research support from Genentech/Roche.
Lori Chibnik No disclosure on file
No disclosure on file
Patricia K. Coyle, MD, FAAN (SUNY At Stony Brook) Dr. Coyle has received personal compensation in the range of $500-$4,999 for serving as a Consultant for Accordant. Dr. Coyle has received personal compensation in the range of $500-$4,999 for serving as a Consultant for Amgen. Dr. Coyle has received personal compensation in the range of $50,000-$99,999 for serving as a Consultant for Sanofi Genzyme. Dr. Coyle has received personal compensation in the range of $10,000-$49,999 for serving as a Consultant for Novartis. Dr. Coyle has received personal compensation in the range of $10,000-$49,999 for serving as a Consultant for GlaxoSmithKline. Dr. Coyle has received personal compensation in the range of $10,000-$49,999 for serving as a Consultant for Horizon Therapeutics. The institution of Dr. Coyle has received research support from CorEvitas LLC. The institution of Dr. Coyle has received research support from Genentech/Roche. The institution of Dr. Coyle has received research support from NINDS. The institution of Dr. Coyle has received research support from Sanofi Genzyme. The institution of Dr. Coyle has received research support from Cleveland Clinic.
Philip De Jager, MD, PhD (Columbia University Irving Medical Center) Dr. De Jager has received personal compensation in the range of $500-$4,999 for serving as a Consultant for Puretech. Dr. De Jager has received personal compensation in the range of $5,000-$9,999 for serving on a Scientific Advisory or Data Safety Monitoring board for roche. Dr. De Jager has received personal compensation in the range of $5,000-$9,999 for serving on a Scientific Advisory or Data Safety Monitoring board for biogen. The institution of Dr. De Jager has received research support from roche. The institution of Dr. De Jager has received research support from puretech.