Modeling Disease Severity in Multiple Sclerosis Using Electronic Health Records
Objective: To optimally leverage the scalability and unique features of the electronic health records (EHR) for research that would ultimately improve patient care, we need to accurately identify patients and extract clinically meaningful measures. Using multiple sclerosis (MS) as a proof of princi...
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Public Library of Science
2014
|
| Online Access: | http://hdl.handle.net/1721.1/86009 https://orcid.org/0000-0001-8411-6403 |
| _version_ | 1826203189378023424 |
|---|---|
| author | Xia, Zongqi Secor, Elizabeth Chibnik, Lori B. Bove, Riley M. Cheng, Suchun Chitnis, Tanuja Cagan, Andrew Gainer, Vivian Chen, Pei Liao, Katherine P. Shaw, Stanley Y. Ananthakrishnan, Ashwin N. Szolovits, Peter Weiner, Howard L. Karlson, Elizabeth W. Murphy, Shawn N. Savova, Guergana K. Cai, Tianxi Churchill, Susanne Plenge, Robert M. Kohane, Isaac De Jager, Philip L. |
| author2 | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science |
| author_facet | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Xia, Zongqi Secor, Elizabeth Chibnik, Lori B. Bove, Riley M. Cheng, Suchun Chitnis, Tanuja Cagan, Andrew Gainer, Vivian Chen, Pei Liao, Katherine P. Shaw, Stanley Y. Ananthakrishnan, Ashwin N. Szolovits, Peter Weiner, Howard L. Karlson, Elizabeth W. Murphy, Shawn N. Savova, Guergana K. Cai, Tianxi Churchill, Susanne Plenge, Robert M. Kohane, Isaac De Jager, Philip L. |
| author_sort | Xia, Zongqi |
| collection | MIT |
| description | Objective:
To optimally leverage the scalability and unique features of the electronic health records (EHR) for research that would ultimately improve patient care, we need to accurately identify patients and extract clinically meaningful measures. Using multiple sclerosis (MS) as a proof of principle, we showcased how to leverage routinely collected EHR data to identify patients with a complex neurological disorder and derive an important surrogate measure of disease severity heretofore only available in research settings.
Methods:
In a cross-sectional observational study, 5,495 MS patients were identified from the EHR systems of two major referral hospitals using an algorithm that includes codified and narrative information extracted using natural language processing. In the subset of patients who receive neurological care at a MS Center where disease measures have been collected, we used routinely collected EHR data to extract two aggregate indicators of MS severity of clinical relevance multiple sclerosis severity score (MSSS) and brain parenchymal fraction (BPF, a measure of whole brain volume).
Results:
The EHR algorithm that identifies MS patients has an area under the curve of 0.958, 83% sensitivity, 92% positive predictive value, and 89% negative predictive value when a 95% specificity threshold is used. The correlation between EHR-derived and true MSSS has a mean R[superscript 2] = 0.38±0.05, and that between EHR-derived and true BPF has a mean R[superscript 2] = 0.22±0.08. To illustrate its clinical relevance, derived MSSS captures the expected difference in disease severity between relapsing-remitting and progressive MS patients after adjusting for sex, age of symptom onset and disease duration (p = 1.56×10[superscript −12]).
Conclusion:
Incorporation of sophisticated codified and narrative EHR data accurately identifies MS patients and provides estimation of a well-accepted indicator of MS severity that is widely used in research settings but not part of the routine medical records. Similar approaches could be applied to other complex neurological disorders. |
| first_indexed | 2024-09-23T12:33:02Z |
| format | Article |
| id | mit-1721.1/86009 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T12:33:02Z |
| publishDate | 2014 |
| publisher | Public Library of Science |
| record_format | dspace |
| spelling | mit-1721.1/860092022-09-28T08:28:24Z Modeling Disease Severity in Multiple Sclerosis Using Electronic Health Records Xia, Zongqi Secor, Elizabeth Chibnik, Lori B. Bove, Riley M. Cheng, Suchun Chitnis, Tanuja Cagan, Andrew Gainer, Vivian Chen, Pei Liao, Katherine P. Shaw, Stanley Y. Ananthakrishnan, Ashwin N. Szolovits, Peter Weiner, Howard L. Karlson, Elizabeth W. Murphy, Shawn N. Savova, Guergana K. Cai, Tianxi Churchill, Susanne Plenge, Robert M. Kohane, Isaac De Jager, Philip L. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology. Laboratory for Computer Science Szolovits, Peter Objective: To optimally leverage the scalability and unique features of the electronic health records (EHR) for research that would ultimately improve patient care, we need to accurately identify patients and extract clinically meaningful measures. Using multiple sclerosis (MS) as a proof of principle, we showcased how to leverage routinely collected EHR data to identify patients with a complex neurological disorder and derive an important surrogate measure of disease severity heretofore only available in research settings. Methods: In a cross-sectional observational study, 5,495 MS patients were identified from the EHR systems of two major referral hospitals using an algorithm that includes codified and narrative information extracted using natural language processing. In the subset of patients who receive neurological care at a MS Center where disease measures have been collected, we used routinely collected EHR data to extract two aggregate indicators of MS severity of clinical relevance multiple sclerosis severity score (MSSS) and brain parenchymal fraction (BPF, a measure of whole brain volume). Results: The EHR algorithm that identifies MS patients has an area under the curve of 0.958, 83% sensitivity, 92% positive predictive value, and 89% negative predictive value when a 95% specificity threshold is used. The correlation between EHR-derived and true MSSS has a mean R[superscript 2] = 0.38±0.05, and that between EHR-derived and true BPF has a mean R[superscript 2] = 0.22±0.08. To illustrate its clinical relevance, derived MSSS captures the expected difference in disease severity between relapsing-remitting and progressive MS patients after adjusting for sex, age of symptom onset and disease duration (p = 1.56×10[superscript −12]). Conclusion: Incorporation of sophisticated codified and narrative EHR data accurately identifies MS patients and provides estimation of a well-accepted indicator of MS severity that is widely used in research settings but not part of the routine medical records. Similar approaches could be applied to other complex neurological disorders. National Institute of General Medical Sciences (U.S.) (NIH U54-LM008748) 2014-04-03T19:42:09Z 2014-04-03T19:42:09Z 2013-11 2013-05 Article http://purl.org/eprint/type/JournalArticle 1932-6203 http://hdl.handle.net/1721.1/86009 Xia, Zongqi, Elizabeth Secor, Lori B. Chibnik, Riley M. Bove, Suchun Cheng, Tanuja Chitnis, Andrew Cagan, et al. “Modeling Disease Severity in Multiple Sclerosis Using Electronic Health Records.” Edited by Wang Zhan. PLoS ONE 8, no. 11 (November 11, 2013): e78927. https://orcid.org/0000-0001-8411-6403 en_US http://dx.doi.org/10.1371/journal.pone.0078927 PLoS ONE Creative Commons Attribution http://creativecommons.org/licenses/by/4.0/ application/pdf Public Library of Science PLoS |
| spellingShingle | Xia, Zongqi Secor, Elizabeth Chibnik, Lori B. Bove, Riley M. Cheng, Suchun Chitnis, Tanuja Cagan, Andrew Gainer, Vivian Chen, Pei Liao, Katherine P. Shaw, Stanley Y. Ananthakrishnan, Ashwin N. Szolovits, Peter Weiner, Howard L. Karlson, Elizabeth W. Murphy, Shawn N. Savova, Guergana K. Cai, Tianxi Churchill, Susanne Plenge, Robert M. Kohane, Isaac De Jager, Philip L. Modeling Disease Severity in Multiple Sclerosis Using Electronic Health Records |
| title | Modeling Disease Severity in Multiple Sclerosis Using Electronic Health Records |
| title_full | Modeling Disease Severity in Multiple Sclerosis Using Electronic Health Records |
| title_fullStr | Modeling Disease Severity in Multiple Sclerosis Using Electronic Health Records |
| title_full_unstemmed | Modeling Disease Severity in Multiple Sclerosis Using Electronic Health Records |
| title_short | Modeling Disease Severity in Multiple Sclerosis Using Electronic Health Records |
| title_sort | modeling disease severity in multiple sclerosis using electronic health records |
| url | http://hdl.handle.net/1721.1/86009 https://orcid.org/0000-0001-8411-6403 |
| work_keys_str_mv | AT xiazongqi modelingdiseaseseverityinmultiplesclerosisusingelectronichealthrecords AT secorelizabeth modelingdiseaseseverityinmultiplesclerosisusingelectronichealthrecords AT chibniklorib modelingdiseaseseverityinmultiplesclerosisusingelectronichealthrecords AT boverileym modelingdiseaseseverityinmultiplesclerosisusingelectronichealthrecords AT chengsuchun modelingdiseaseseverityinmultiplesclerosisusingelectronichealthrecords AT chitnistanuja modelingdiseaseseverityinmultiplesclerosisusingelectronichealthrecords AT caganandrew modelingdiseaseseverityinmultiplesclerosisusingelectronichealthrecords AT gainervivian modelingdiseaseseverityinmultiplesclerosisusingelectronichealthrecords AT chenpei modelingdiseaseseverityinmultiplesclerosisusingelectronichealthrecords AT liaokatherinep modelingdiseaseseverityinmultiplesclerosisusingelectronichealthrecords AT shawstanleyy modelingdiseaseseverityinmultiplesclerosisusingelectronichealthrecords AT ananthakrishnanashwinn modelingdiseaseseverityinmultiplesclerosisusingelectronichealthrecords AT szolovitspeter modelingdiseaseseverityinmultiplesclerosisusingelectronichealthrecords AT weinerhowardl modelingdiseaseseverityinmultiplesclerosisusingelectronichealthrecords AT karlsonelizabethw modelingdiseaseseverityinmultiplesclerosisusingelectronichealthrecords AT murphyshawnn modelingdiseaseseverityinmultiplesclerosisusingelectronichealthrecords AT savovaguerganak modelingdiseaseseverityinmultiplesclerosisusingelectronichealthrecords AT caitianxi modelingdiseaseseverityinmultiplesclerosisusingelectronichealthrecords AT churchillsusanne modelingdiseaseseverityinmultiplesclerosisusingelectronichealthrecords AT plengerobertm modelingdiseaseseverityinmultiplesclerosisusingelectronichealthrecords AT kohaneisaac modelingdiseaseseverityinmultiplesclerosisusingelectronichealthrecords AT dejagerphilipl modelingdiseaseseverityinmultiplesclerosisusingelectronichealthrecords |