{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"medRxiv"}],"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T22:39:46Z","timestamp":1778711986378,"version":"3.51.4"},"posted":{"date-parts":[[2025,11,14]]},"group-title":"Neurology","reference-count":27,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T00:00:00Z","timestamp":1763078400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.medrxiv.org\/about\/FAQ#license"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2025,11,14]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:sec>\n                  <jats:title>Background<\/jats:title>\n                  <jats:p>The multiple sclerosis (MS) therapeutic landscape has evolved over time.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Objective<\/jats:title>\n                  <jats:p>We conducted a knowledge graph-guided analysis of MS-specific disease-modifying therapy (DMT) prescription trends using longitudinal real-world clinical data.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Methods<\/jats:title>\n                  <jats:p>We utilized registry-linked electronic health records (EHR) data from two large independent healthcare systems encompassing both academic and community practices (2004-2022). We applied a novel and efficient Knowledge-driven Online Multimodal Automated Phenotyping (KOMAP) algorithm to identify patients diagnosed with MS and evaluated algorithm performance against chart-reviewed and registry-recorded diagnosis labels. To assess temporal trends in DMT prescriptions, we combined the two cohorts and constructed time-varying temporal knowledge graphs using the patient-level EHR data segmented by calendar year. For each year, we analyzed co-occurrence patterns between DMTs and MS diagnosis by using Shifted Positive Pointwise Mutual Information transformation and singular value decomposition to generate embeddings. We computed patient-wise cosine similarities and confidence intervals.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>\n                    The phenotyping algorithm achieved robust performance in predicting MS diagnosis (AUROC: MGB=0.994, UPMC=0.922), identifying 29,169 MS patients in the combined dataset. Among commonly used standard-effectiveness DMTs, prescriptions for interferon-beta (slope=-0.018\u00b10.011, p&lt;0.001) and glatiramer acetate (slope=-0.013\u00b10.012, p=0.026) and fumarates (slope=-0.031\u00b10.010, p&lt;0.001) declined after 2013. Use of S1P receptor modulators (slope=-0.026\u00b10.016, p=0.005) declined after 2015. Among commonly used higher-effectiveness DMTs, B-cell depletion therapies (slope=0.051\u00b10.027, p&lt;0.001), particularly ocrelizumab (slope=0.020\u00b10.016, p&lt;0.001), showed a marked increase since 2017. Natalizumab usage peaked in 2012 (slope\n                    <jats:sub>pre-2012<\/jats:sub>\n                    =0.063\u00b10.012, p\n                    <jats:sub>pre-2012<\/jats:sub>\n                    &lt;0.001; slope\n                    <jats:sub>post-2012<\/jats:sub>\n                    =-0.027\u00b10.008, p\n                    <jats:sub>post-2012<\/jats:sub>\n                    &lt;0.001). Other DMT classes such as cell proliferation inhibitors, chemotherapy agents, and purine blockers, showed low usage during follow-up.\n                  <\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Conclusion<\/jats:title>\n                  <jats:p>Real-world evidence from two large EHR-based MS cohorts highlights distinct temporal shifts in the MS therapeutic landscape toward higher-effectiveness DMTs, particularly B-cell depletion therapy.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Key Messages<\/jats:title>\n                  <jats:list list-type=\"order\">\n                    <jats:list-item>\n                      <jats:p>Accurate identification of patients diagnosed with multiple sclerosis (MS) from real-world clinical data is essential for tracking longitudinal prescription patterns at scale and understanding the evolution of the MS therapeutic landscape.<\/jats:p>\n                    <\/jats:list-item>\n                    <jats:list-item>\n                      <jats:p>Leveraging electronic health records (EHR) data, our knowledge graph-guided unsupervised algorithm accurately and efficiently identified MS patients from two large, independent healthcare systems.<\/jats:p>\n                    <\/jats:list-item>\n                    <jats:list-item>\n                      <jats:p>Temporal analysis using knowledge graph-guided methods revealed major shifts in MS-related disease-modifying therapy (DMT) prescriptions, including a decline in early injectable use and increased adoption of B-cell depletion therapies.<\/jats:p>\n                    <\/jats:list-item>\n                    <jats:list-item>\n                      <jats:p>These findings confirm a growing preference for higher-effectiveness DMTs in MS and provide a scalable framework for evaluating long-term treatment patterns across healthcare systems.<\/jats:p>\n                    <\/jats:list-item>\n                  <\/jats:list>\n                <\/jats:sec>","DOI":"10.1101\/2025.11.12.25340116","type":"posted-content","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T21:45:15Z","timestamp":1763156715000},"source":"Crossref","is-referenced-by-count":2,"title":["Knowledge Graph-Guided Identification of Multiple Sclerosis and Therapeutic Trend Analysis: Real-World Evidence from Two Large Healthcare Systems"],"prefix":"10.64898","author":[{"given":"Ziming","family":"Gan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wen","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weijing","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sara Morini","family":"Sweet","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michele","family":"Morris","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunqing","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenyi","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junwei","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emily","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohammed","family":"Moro","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shyam","family":"Visweswaran","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianrun","family":"Cai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tanuja","family":"Chitnis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianxi","family":"Cai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zongqi","family":"Xia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"54368","reference":[{"key":"2025111722501416000_2025.11.12.25340116v1.1","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(23)01473-3"},{"key":"2025111722501416000_2025.11.12.25340116v1.2","doi-asserted-by":"publisher","DOI":"10.1007\/s40120-022-00358-4"},{"key":"2025111722501416000_2025.11.12.25340116v1.3","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.0000000000007043"},{"key":"2025111722501416000_2025.11.12.25340116v1.4","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","year":"2019","journal-title":"Electronics"},{"key":"2025111722501416000_2025.11.12.25340116v1.5","doi-asserted-by":"publisher","DOI":"10.1162\/99608f92.cbe67e91"},{"key":"2025111722501416000_2025.11.12.25340116v1.6","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocac216"},{"key":"2025111722501416000_2025.11.12.25340116v1.7","doi-asserted-by":"crossref","unstructured":"Xiong X , Sweet SM , Liu M , et al. Knowledge-Driven Online Multimodal Automated Phenotyping System. medRxiv 2023; 2023.09.29.23296239.","DOI":"10.1101\/2023.09.29.23296239"},{"key":"2025111722501416000_2025.11.12.25340116v1.8","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","year":"2019","journal-title":"Curr Opin Neurol"},{"key":"2025111722501416000_2025.11.12.25340116v1.9","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1038\/s41582-021-00476-x","article-title":"Assessing long-term effectiveness of MS treatment \u2014 a matter of debate","volume":"17","year":"2021","journal-title":"Nat Rev Neurol"},{"key":"2025111722501416000_2025.11.12.25340116v1.10","doi-asserted-by":"publisher","DOI":"10.1007\/s00415-023-11969-8"},{"key":"2025111722501416000_2025.11.12.25340116v1.11","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2020.26858"},{"key":"2025111722501416000_2025.11.12.25340116v1.12","doi-asserted-by":"crossref","unstructured":"Ageno A , Catal\u00e0 N , Pons M . Acquisition of temporal patterns from electronic health records: an application to multimorbid patients. BMC M\u00e9d Inform Decis Mak 2023; 23: 189.","DOI":"10.1186\/s12911-023-02287-0"},{"key":"2025111722501416000_2025.11.12.25340116v1.13","doi-asserted-by":"crossref","unstructured":"Cui H , Lu J , Xu R , et al. A review on knowledge graphs for healthcare: Resources, applications, and promises. J Biomed Inform 2025; 169: 104861.","DOI":"10.1016\/j.jbi.2025.104861"},{"key":"2025111722501416000_2025.11.12.25340116v1.14","doi-asserted-by":"crossref","unstructured":"Chaturvedi R . Temporal Knowledge Graph Extraction and Modeling across Multiple Documents for Health Risk Prediction. Companion Proc ACM Web Conf 2024 2024; 1182\u20131185.","DOI":"10.1145\/3589335.3651256"},{"key":"2025111722501416000_2025.11.12.25340116v1.15","doi-asserted-by":"publisher","DOI":"10.1038\/s41596-019-0227-6"},{"key":"2025111722501416000_2025.11.12.25340116v1.16","doi-asserted-by":"publisher","DOI":"10.1373\/49.4.624"},{"key":"2025111722501416000_2025.11.12.25340116v1.17","first-page":"17","article-title":"RxNorm: prescription for electronic drug information exchange","volume":"7","year":"2005","journal-title":"Prof"},{"key":"2025111722501416000_2025.11.12.25340116v1.18","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1311.6063"},{"key":"2025111722501416000_2025.11.12.25340116v1.19","first-page":"170","article-title":"The UMLS project: making the conceptual connection between users and the information they need","volume":"81","year":"1993","journal-title":"Bull M\u00e9d Libr Assoc"},{"key":"2025111722501416000_2025.11.12.25340116v1.20","doi-asserted-by":"crossref","unstructured":"Hong C , Rush E , Liu M , et al. Clinical knowledge extraction via sparse embedding regression (KESER) with multi-center large scale electronic health record data. npj Digit Med 2021; 4: 151.","DOI":"10.1038\/s41746-021-00519-z"},{"key":"2025111722501416000_2025.11.12.25340116v1.21","doi-asserted-by":"publisher","DOI":"10.1002\/sim.1545"},{"key":"2025111722501416000_2025.11.12.25340116v1.22","doi-asserted-by":"publisher","DOI":"10.1136\/ejhpharm-2017-001286"},{"key":"2025111722501416000_2025.11.12.25340116v1.23","doi-asserted-by":"crossref","unstructured":"Mirabella M , Annovazzi P , Brownlee W , et al. Treatment Challenges in Multiple Sclerosis \u2013 A Continued Role for Glatiramer Acetate? Front Neurol 2022; 13: 844873.","DOI":"10.3389\/fneur.2022.844873"},{"key":"2025111722501416000_2025.11.12.25340116v1.24","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","year":"2018","journal-title":"J Neurol Sci"},{"key":"2025111722501416000_2025.11.12.25340116v1.25","doi-asserted-by":"crossref","unstructured":"Faissner S , Gold R . Oral Therapies for Multiple Sclerosis. Cold Spring Harb Perspect Med 2018; 9: a032011.","DOI":"10.1101\/cshperspect.a032011"},{"key":"2025111722501416000_2025.11.12.25340116v1.26","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","year":"2020","journal-title":"JAMA Neurol"},{"key":"2025111722501416000_2025.11.12.25340116v1.27","doi-asserted-by":"crossref","first-page":"775","DOI":"10.1001\/jamaneurol.2023.1079","article-title":"New Approaches to Challenge Old Assumptions\u2014B-Cell Depletion in Multiple Sclerosis","volume":"80","year":"2023","journal-title":"JAMA Neurol"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2025.11.12.25340116","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T20:51:10Z","timestamp":1768510270000},"score":1,"resource":{"primary":{"URL":"http:\/\/medrxiv.org\/lookup\/doi\/10.1101\/2025.11.12.25340116"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,14]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1101\/2025.11.12.25340116","relation":{},"subject":[],"published":{"date-parts":[[2025,11,14]]},"subtype":"preprint"}}