{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T18:19:22Z","timestamp":1787941162002,"version":"build-2784847793"},"reference-count":35,"publisher":"Public Library of Science (PLoS)","issue":"8","license":[{"start":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T00:00:00Z","timestamp":1787875200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000065","name":"National Institute of Neurological Disorders and Stroke","doi-asserted-by":"publisher","award":["R01NS098023"],"award-info":[{"award-number":["R01NS098023"]}],"id":[{"id":"10.13039\/100000065","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosdigitalhealth.org"],"crossmark-restriction":false},"short-container-title":["PLOS Digit Health"],"abstract":"<jats:p>\n                    The multiple sclerosis (MS) therapeutic landscape has evolved over time. We conducted a knowledge graph-guided analysis of MS-specific disease-modifying therapy (DMT) prescription trends using longitudinal real-world clinical data. We analyzed registry-linked electronic health record (EHR) data from two large independent healthcare systems between 2004 and 2022, including both academic and community practices. We developed an unsupervised phenotyping algorithm that leverages a publicly available knowledge graph and informative EHR features to identify patients with MS. After identifying MS cases, we combined the two cohorts and constructed annual time-varying knowledge graphs that capture co-occurrence patterns between DMTs and MS diagnosis. For each year, we analyzed co-occurrence patterns between DMTs and MS diagnosis using Shifted Positive Pointwise Mutual Information transformation and singular value decomposition to generate embeddings. We computed patient-wise cosine similarities and confidence intervals to quantify\n                    <jats:italic>MS<\/jats:italic>\n                    -\n                    <jats:italic>specific<\/jats:italic>\n                    DMT usage patterns. The phenotyping algorithm achieved robust performance in predicting MS diagnosis (AUROC: MGB\u2009=\u20090.994, UPMC\u2009=\u20090.922), identifying 29,169 MS patients in the combined dataset. Among commonly used standard-effectiveness DMTs, MS-specific prescriptions declined after 2011 for interferon-beta (DMT-MS cosine similarity slope = \u22120.019 \u00b1 0.011, p = 0.002) and glatiramer acetate (slope = \u22120.013 \u00b1 0.012, p = 0.026), from 2013\u20132020 for fumarates (slope = \u22120.028 \u00b1 0.015, p = 0.004), and after 2014 for S1P receptor modulators (slope = \u22120.026 \u00b1 0.016, p = 0.005). Among commonly used higher-effectiveness DMTs, B-cell depletion therapies (slope\u2009=\u20090.051\u2009\u00b1\u20090.027, p\u2009=\u20090.001), particularly ocrelizumab (slope\u2009=\u20090.020\u2009\u00b1\u20090.016, p\u2009=0.032), showed a marked increase since 2018. Natalizumab usage peaked in 2011 (slope\n                    <jats:sub>pre-2011<\/jats:sub>\n                    \u2009=\u20090.063\u2009\u00b1\u20090.013, p\n                    <jats:sub>pre-2011<\/jats:sub>\n                    \u2009&lt;\u20090.001; slope\n                    <jats:sub>post-2011<\/jats:sub>\n                    = \u22120.027\u2009\u00b1\u20090.008, p\n                    <jats:sub>post-2011<\/jats:sub>\n                    \u2009&lt;\u20090.001). Other DMT classes such as cell proliferation inhibitors and chemotherapy agents, showed low usage during follow-up. These findings provide real-world evidence from two large EHR-based MS cohorts, highlighting distinct temporal shifts in the complex MS therapeutic landscape toward higher-effectiveness DMTs, particularly B-cell depletion therapy.\n                  <\/jats:p>","DOI":"10.1371\/journal.pdig.0001554","type":"journal-article","created":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T17:46:41Z","timestamp":1787939201000},"page":"e0001554","update-policy":"https:\/\/doi.org\/10.1371\/journal.pdig.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Knowledge graph-guided multiple sclerosis identification and therapeutic trend analysis: Real-world evidence from two large healthcare systems"],"prefix":"10.1371","volume":"5","author":[{"given":"Ziming","family":"Gan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wen","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weijing","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sara Morini","family":"Sweet","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michele","family":"Morris","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunqing","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenyi","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junwei","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emily","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohammed","family":"Moro","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shyam","family":"Visweswaran","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianrun","family":"Cai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tanuja","family":"Chitnis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianxi","family":"Cai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1500-2589","authenticated-orcid":true,"given":"Zongqi","family":"Xia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,8,28]]},"reference":[{"issue":"10422","key":"pdig.0001554.ref001","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1016\/S0140-6736(23)01473-3","article-title":"Multiple sclerosis","volume":"403","author":"D Jakimovski","year":"2024","journal-title":"Lancet"},{"issue":"3","key":"pdig.0001554.ref002","doi-asserted-by":"crossref","first-page":"1147","DOI":"10.1007\/s40120-022-00358-4","article-title":"Patterns of Utilization and Expenditure Across Multiple Sclerosis Disease-Modifying Therapies: A Retrospective Cohort Study Using Claims Data from a Commercially Insured Population in the United States, 2010-2019","volume":"11","author":"W Zhu","year":"2022","journal-title":"Neurol Ther"},{"issue":"10","key":"pdig.0001554.ref003","doi-asserted-by":"crossref","DOI":"10.1212\/WNL.0000000000007043","article-title":"Validation of an algorithm for identifying MS cases in administrative health claims datasets","volume":"92","author":"WJ Culpepper","year":"2019","journal-title":"Neurology"},{"issue":"11","key":"pdig.0001554.ref004","doi-asserted-by":"crossref","first-page":"1235","DOI":"10.3390\/electronics8111235","article-title":"A Review of Automatic Phenotyping Approaches using Electronic Health Records","volume":"8","author":"H Alzoubi","year":"2019","journal-title":"Electronics"},{"issue":"2","key":"pdig.0001554.ref005","article-title":"Data Quality in Electronic Health Record Research: An Approach for Validation and Quantitative Bias Analysis for Imperfectly Ascertained Health Outcomes Via Diagnostic Codes","volume":"4","author":"ND Goldstein","year":"2022","journal-title":"Harv Data Sci Rev"},{"issue":"2","key":"pdig.0001554.ref006","doi-asserted-by":"crossref","first-page":"367","DOI":"10.1093\/jamia\/ocac216","article-title":"Machine learning approaches for electronic health records phenotyping: a methodical review","volume":"30","author":"S Yang","year":"2023","journal-title":"J Am Med Inform Assoc"},{"key":"pdig.0001554.ref007","article-title":"Knowledge-Driven Online Multimodal Automated Phenotyping System.","author":"X Xiong","year":"2023","journal-title":"medRxiv"},{"issue":"3","key":"pdig.0001554.ref008","doi-asserted-by":"crossref","first-page":"365","DOI":"10.1097\/WCO.0000000000000700","article-title":"Current therapeutic landscape in multiple sclerosis: an evolving treatment paradigm","volume":"32","author":"BAC Cree","year":"2019","journal-title":"Curr Opin Neurol"},{"issue":"4","key":"pdig.0001554.ref009","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1038\/s41582-021-00476-x","article-title":"Assessing long-term effectiveness of MS treatment - a matter of debate","volume":"17","author":"M Trojano","year":"2021","journal-title":"Nat Rev Neurol"},{"issue":"1","key":"pdig.0001554.ref010","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1007\/s00415-023-11969-8","article-title":"Multiple sclerosis: time for early treatment with high-efficacy drugs","volume":"271","author":"K Selmaj","year":"2024","journal-title":"J Neurol"},{"issue":"8","key":"pdig.0001554.ref011","doi-asserted-by":"crossref","first-page":"765","DOI":"10.1001\/jama.2020.26858","article-title":"Diagnosis and Treatment of Multiple Sclerosis: A Review","volume":"325","author":"MP McGinley","year":"2021","journal-title":"JAMA"},{"issue":"1","key":"pdig.0001554.ref012","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1186\/s12911-023-02287-0","article-title":"Acquisition of temporal patterns from electronic health records: an application to multimorbid patients","volume":"23","author":"A Ageno","year":"2023","journal-title":"BMC Med Inform Decis Mak"},{"key":"pdig.0001554.ref013","doi-asserted-by":"crossref","first-page":"104861","DOI":"10.1016\/j.jbi.2025.104861","article-title":"A review on knowledge graphs for healthcare: Resources, applications, and promises","volume":"169","author":"H Cui","year":"2025","journal-title":"J Biomed Inform"},{"key":"pdig.0001554.ref014","doi-asserted-by":"crossref","unstructured":"Chaturvedi R. Temporal Knowledge Graph Extraction and Modeling across Multiple Documents for Health Risk Prediction. In: Companion Proceedings of the ACM Web Conference 2024, 2024. 1182\u20135. https:\/\/doi.org\/10.1145\/3589335.3651256","DOI":"10.1145\/3589335.3651256"},{"issue":"11","key":"pdig.0001554.ref015","article-title":"Modeling Disease Severity in Multiple Sclerosis Using Electronic Health Records.","volume":"8","author":"Z Xia","year":"2013","journal-title":"PLoS ONE."},{"issue":"6","key":"pdig.0001554.ref016","doi-asserted-by":"crossref","DOI":"10.1212\/NXI.0000000000000864","article-title":"Phenome-wide examination of comorbidity burden and multiple sclerosis disease severity.","volume":"7","author":"T Zhang","year":"2020","journal-title":"Neurology Neuroimmunology & Neuroinflammation."},{"issue":"4","key":"pdig.0001554.ref017","doi-asserted-by":"crossref","first-page":"800","DOI":"10.1002\/acn3.51324","article-title":"Leveraging electronic health records data to predict multiple sclerosis disease activity.","volume":"8","author":"Y Ahuja","year":"2021","journal-title":"Annals of Clinical and Translational Neurology."},{"issue":"11","key":"pdig.0001554.ref018","article-title":"Comparison of Dimethyl Fumarate vs Fingolimod and Rituximab vs Natalizumab for Treatment of Multiple Sclerosis.","volume":"4","author":"J Hou","year":"2021","journal-title":"JAMA Network Open."},{"key":"pdig.0001554.ref019","doi-asserted-by":"crossref","first-page":"103333","DOI":"10.1016\/j.msard.2021.103333","article-title":"Temporal trends of multiple sclerosis disease activity: Electronic health records indicators.","volume":"57","author":"L Liang","year":"2021","journal-title":"Multiple Sclerosis and Related Disorders."},{"issue":"12","key":"pdig.0001554.ref020","doi-asserted-by":"crossref","first-page":"3426","DOI":"10.1038\/s41596-019-0227-6","article-title":"High-throughput phenotyping with electronic medical record data using a common semi-supervised approach (PheCAP)","volume":"14","author":"Y Zhang","year":"2019","journal-title":"Nat Protoc"},{"issue":"4","key":"pdig.0001554.ref021","doi-asserted-by":"crossref","first-page":"624","DOI":"10.1373\/49.4.624","article-title":"LOINC, a universal standard for identifying laboratory observations: a 5-year update","volume":"49","author":"CJ McDonald","year":"2003","journal-title":"Clin Chem"},{"key":"pdig.0001554.ref022","first-page":"17","article-title":"RxNorm: prescription for electronic drug information exchange","volume":"7","author":"S Liu","year":"2005","journal-title":"Prof"},{"key":"pdig.0001554.ref023","article-title":"NILE: Fast Natural Language Processing for Electronic Health Records","author":"S Yu","year":"2013","journal-title":"arXiv"},{"issue":"2","key":"pdig.0001554.ref024","first-page":"170","article-title":"The UMLS project: making the conceptual connection between users and the information they need","volume":"81","author":"BL Humphreys","year":"1993","journal-title":"Bull Med Libr Assoc"},{"issue":"1","key":"pdig.0001554.ref025","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1038\/s41746-021-00519-z","article-title":"Clinical knowledge extraction via sparse embedding regression (KESER) with multi-center large scale electronic health record data","volume":"4","author":"C Hong","year":"2021","journal-title":"NPJ Digit Med"},{"issue":"19","key":"pdig.0001554.ref026","doi-asserted-by":"crossref","first-page":"3055","DOI":"10.1002\/sim.1545","article-title":"Estimating regression models with unknown break-points","volume":"22","author":"VMR Muggeo","year":"2003","journal-title":"Stat Med"},{"issue":"2","key":"pdig.0001554.ref027","doi-asserted-by":"crossref","DOI":"10.1136\/bmjno-2025-001108","article-title":"Real-world use of disease-modifying therapy in persons with multiple sclerosis aged 55 and over","volume":"7","author":"M Staniki\u0107","year":"2025","journal-title":"BMJ Neurol Open"},{"issue":"4","key":"pdig.0001554.ref028","doi-asserted-by":"crossref","first-page":"35","DOI":"10.3390\/sclerosis3040035","article-title":"Evaluation of Early Initiation of Disease-Modifying Treatment for Patients with Multiple Sclerosis Within a Real-World Population for Long-Term Outcomes","volume":"3","author":"M McDonald","year":"2025","journal-title":"Sclerosis"},{"key":"pdig.0001554.ref029","doi-asserted-by":"crossref","DOI":"10.3389\/fneur.2022.844873","article-title":"Treatment Challenges in Multiple Sclerosis \u2013 A Continued Role for Glatiramer Acetate?","volume":"13","author":"M Mirabella","year":"2022","journal-title":"Front Neurol"},{"issue":"1","key":"pdig.0001554.ref030","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1136\/ejhpharm-2017-001286","article-title":"Persistence and adherence to interferon and glatiramer acetate in patients with multiple sclerosis","volume":"26","author":"E Bartolom\u00e9-Garc\u00eda","year":"2019","journal-title":"Eur J Hosp Pharm"},{"key":"pdig.0001554.ref031","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1016\/j.jns.2018.09.020","article-title":"Long-term follow-up for multiple sclerosis patients initially treated with interferon-beta and glatiramer acetate","volume":"394","author":"BC Healy","year":"2018","journal-title":"J Neurol Sci"},{"issue":"1","key":"pdig.0001554.ref032","doi-asserted-by":"crossref","DOI":"10.1101\/cshperspect.a032011","article-title":"Oral Therapies for Multiple Sclerosis","volume":"9","author":"S Faissner","year":"2019","journal-title":"Cold Spring Harb Perspect Med"},{"key":"pdig.0001554.ref033","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1001\/jamaneurol.2019.2670","article-title":"Progressive Multifocal Leukoencephalopathy Incidence and Risk Stratification Among Natalizumab Users in France","volume":"77","author":"S Vukusic","year":"2020","journal-title":"JAMA Neurol"},{"issue":"8","key":"pdig.0001554.ref034","doi-asserted-by":"crossref","first-page":"775","DOI":"10.1001\/jamaneurol.2023.1079","article-title":"New Approaches to Challenge Old Assumptions-B-Cell Depletion in Multiple Sclerosis","volume":"80","author":"L Oommen","year":"2023","journal-title":"JAMA Neurol"},{"issue":"3","key":"pdig.0001554.ref035","doi-asserted-by":"crossref","first-page":"1147","DOI":"10.1007\/s40120-022-00358-4","article-title":"Patterns of Utilization and Expenditure Across Multiple Sclerosis Disease-Modifying Therapies: A Retrospective Cohort Study Using Claims Data from a Commercially Insured Population in the United States, 2010\u20132019.","volume":"11","author":"W Zhu","year":"2022","journal-title":"Neurology and Therapy."}],"container-title":["PLOS Digital Health"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pdig.0001554","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T17:46:53Z","timestamp":1787939213000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pdig.0001554"}},"subtitle":[],"editor":[{"given":"Xiaoli","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,8,28]]},"references-count":35,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,8,28]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pdig.0001554","relation":{},"ISSN":["2767-3170"],"issn-type":[{"value":"2767-3170","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,28]]}}}