{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,21]],"date-time":"2026-11-21T17:12:56Z","timestamp":1795281176135,"version":"4.10.3"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,7,16]],"date-time":"2023-07-16T00:00:00Z","timestamp":1689465600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,7,16]],"date-time":"2023-07-16T00:00:00Z","timestamp":1689465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Diabetes is a heterogenous, multimorbid disorder with a large variation in manifestations, trajectories, and outcomes. The aim of this study is to validate a novel machine learning method for the phenotyping of diabetes in the context of comorbidities. Data from 9967 multimorbid patients with a new diagnosis of diabetes were extracted from Clinical Practice Research Datalink. First, using BEHRT (a transformer-based deep learning architecture), the embeddings corresponding to diabetes were learned. Next, topological data analysis (TDA) was carried out to test how different areas in high-dimensional manifold correspond to different risk profiles. The following endpoints were considered when profiling risk trajectories: major adverse cardiovascular events (MACE), coronary artery disease (CAD), stroke (CVA), heart failure (HF), renal failure (RF), diabetic neuropathy, peripheral arterial disease, reduced visual acuity and all-cause mortality. Kaplan Meier curves were plotted for each derived phenotype. Finally, we tested the performance of an established risk prediction model (QRISK) by adding TDA-derived features. We identified four subgroups of patients with diabetes and divergent comorbidity patterns differing in their risk of future cardiovascular, renal, and other microvascular outcomes. Phenotype 1 (young with chronic inflammatory conditions) and phenotype 2 (young with CAD) included relatively younger patients with diabetes compared to phenotypes 3 (older with hypertension and renal disease) and 4 (older with previous CVA), and those subgroups had a higher frequency of pre-existing cardio-renal diseases. Within ten years of follow-up, 2592 patients (26%) experienced MACE, 2515 patients (25%) died, and 2020 patients (20%) suffered RF. QRISK3 model\u2019s AUC was augmented from 67.26% (CI 67.25\u201367.28%) to 67.67% (CI 67.66\u201367.69%) by adding specific TDA-derived phenotype and the distances to both extremities of the TDA graph improving its performance in the prediction of CV outcomes. We confirmed the importance of accounting for multimorbidity when risk stratifying heterogenous cohort of patients with new diagnosis of diabetes. Our unsupervised machine learning method improved the prediction of clinical outcomes.<\/jats:p>","DOI":"10.1038\/s41598-023-38251-1","type":"journal-article","created":{"date-parts":[[2023,7,16]],"date-time":"2023-07-16T15:01:37Z","timestamp":1689519697000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Stratification of diabetes in the context of comorbidities, using representation learning and topological data analysis"],"prefix":"10.1038","volume":"13","author":[{"given":"Malgorzata","family":"Wamil","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abdelaali","family":"Hassaine","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shishir","family":"Rao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yikuan","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohammad","family":"Mamouei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dexter","family":"Canoy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Milad","family":"Nazarzadeh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zeinab","family":"Bidel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emma","family":"Copland","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kazem","family":"Rahimi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gholamreza","family":"Salimi-Khorshidi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,7,16]]},"reference":[{"key":"38251_CR1","volume-title":"Classification of Diabetes Mellitus","author":"WH Organization","year":"2019","unstructured":"Organization, W. H. Classification of Diabetes Mellitus (WHO, 2019)."},{"key":"38251_CR2","doi-asserted-by":"publisher","first-page":"1575","DOI":"10.1136\/bmj.i1575","volume":"353","author":"H McGuire","year":"2016","unstructured":"McGuire, H., Longson, D., Adler, A., Farmer, A. & Lewin, I. Management of type 2 diabetes in adults: summary of updated NICE guidance. Bmj 353, 1575 (2016).","journal-title":"Bmj"},{"issue":"1","key":"38251_CR3","doi-asserted-by":"publisher","first-page":"3","DOI":"10.2337\/dci21-0051","volume":"45","author":"WT Cefalu","year":"2021","unstructured":"Cefalu, W. T. et al. Heterogeneity of diabetes: \u03b2-Cells, phenotypes, and precision medicine: Proceedings of an international symposium of the canadian institutes of health research\u2019s institute of nutrition, metabolism and Diabetes and the U.S. National Institutes of Health\u2019s. Diabetes Care. 45(1), 3\u201322. https:\/\/doi.org\/10.2337\/dci21-0051 (2021).","journal-title":"Diabetes Care."},{"issue":"190","key":"38251_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.mad.2020.111325","volume":"1","author":"A Hassaine","year":"2020","unstructured":"Hassaine, A., Salimi-Khorshidi, G., Canoy, D. & Rahimi, K. Untangling the complexity of multimorbidity with machine learning. Mech. Ageing Dev. 1(190), 111325 (2020).","journal-title":"Mech. Ageing Dev."},{"key":"38251_CR5","doi-asserted-by":"publisher","first-page":"103337","DOI":"10.1016\/j.jbi.2019.103337","volume":"101","author":"JR Ayala Solares","year":"2019","unstructured":"Ayala Solares, J. R. et al. Deep learning for electronic health records: A comparative review of multiple deep neural architectures. J. Biomed. Inform. 101, 103337. https:\/\/doi.org\/10.1016\/j.jbi.2019.103337 (2019).","journal-title":"J. Biomed. Inform."},{"key":"38251_CR6","unstructured":"Devlin, J., Chang, M.-W., Lee, K. & Toutanova, K. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. NAACL HLT 2019: 2019 Conf North Am Chapter Assoc Comput Linguist Hum Lang Technol\u2014Proc Conf. 1, 4171\u20134186 (2018)."},{"key":"38251_CR7","unstructured":"Devlin, J., Chang, M.-W., Lee, K. & Toutanova, K. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. http:\/\/arxiv.org\/abs\/1810.04805 (2018)."},{"key":"38251_CR8","unstructured":"Singh, G., M\u00e9moli, F. & Carlsson, G. Topological methods for the analysis of high dimensional data sets and 3D object recognition. Eurographics Symp Point-Based Graph (2007)."},{"key":"38251_CR9","unstructured":"NICE. Type 2 Diabetes in Adults: Management NICE Guideline. www.nice.org.uk\/guidance\/ng28 [2015]."},{"issue":"3","key":"38251_CR10","doi-asserted-by":"publisher","first-page":"385","DOI":"10.7326\/M20-5938","volume":"174","author":"SD Navaneethan","year":"2021","unstructured":"Navaneethan, S. D. et al. Diabetes management in chronic kidney disease: Synopsis of the 2020 KDIGO clinical practice guideline. Ann. Intern. Med. 174(3), 385\u2013394 (2021).","journal-title":"Ann. Intern. Med."},{"issue":"311","key":"38251_CR11","doi-asserted-by":"publisher","first-page":"9364","DOI":"10.1126\/scitranslmed.aaa9364","volume":"7","author":"L Li","year":"2015","unstructured":"Li, L. et al. Identification of type 2 diabetes subgroups through topological analysis of patient similarity. Sci. Transl. Med. 7(311), 9364 (2015).","journal-title":"Sci. Transl. Med."},{"key":"38251_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2020.101930","volume":"108","author":"A Dagliati","year":"2020","unstructured":"Dagliati, A. et al. Using topological data analysis and pseudo time series to infer temporal phenotypes from electronic health records. Artif. Intell. Med. 108, 101930 (2020).","journal-title":"Artif. Intell. Med."},{"key":"38251_CR13","unstructured":"Young, K. G. Disease Endotypes of Type 1 Diabetes: Exploration Through Machine Learning and Topological Data Analysis (2019)."},{"issue":"3","key":"38251_CR14","doi-asserted-by":"publisher","first-page":"827","DOI":"10.1093\/ije\/dyv098","volume":"44","author":"E Herrett","year":"2015","unstructured":"Herrett, E. et al. Data resource profile: Clinical practice research datalink (CPRD). Int. J. Epidemiol. 44(3), 827\u2013836 (2015).","journal-title":"Int. J. Epidemiol."},{"key":"38251_CR15","unstructured":"Clinical Practice Research Datalink | CPRD. Clinical Practice Research Datalink (CPRD, 2020). https:\/\/www.cprd.com\/, https:\/\/www.cprd.com\/."},{"issue":"1","key":"38251_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13073-015-0166-y","volume":"7","author":"WQ Wei","year":"2015","unstructured":"Wei, W. Q. & Denny, J. C. Extracting research-quality phenotypes from electronic health records to support precision medicine. Genome Med. 7(1), 1\u201314. https:\/\/doi.org\/10.1186\/s13073-015-0166-y (2015).","journal-title":"Genome Med."},{"issue":"4","key":"38251_CR17","doi-asserted-by":"publisher","first-page":"1700391","DOI":"10.1183\/13993003.00391-2017","volume":"50","author":"IR K\u00f6nig","year":"2017","unstructured":"K\u00f6nig, I. R., Fuchs, O., Hansen, G., von Mutius, E. & Kopp, M. V. What is precision medicine?. Eur. Respir. J. 50(4), 1700391 (2017).","journal-title":"Eur. Respir. J."},{"key":"38251_CR18","unstructured":"Roberto, J. et al. Transfer Learning in Electronic Health Records through Clinical Concept Embedding. https:\/\/arxiv.org\/abs\/2107.12919v1 (2021)."},{"key":"38251_CR19","unstructured":"Read Codes - NHS Digital. https:\/\/digital.nhs.uk\/services\/terminology-and-classifications\/read-codes"},{"issue":"3","key":"38251_CR20","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1046\/j.1365-2532.1994.1130177.x","volume":"11","author":"N Booth","year":"1994","unstructured":"Booth, N. What are the read codes?. Health Libr. Rev. 11(3), 177\u2013182 (1994).","journal-title":"Health Libr. Rev."},{"issue":"2","key":"38251_CR21","doi-asserted-by":"publisher","first-page":"e63","DOI":"10.1016\/S2589-7500(19)30012-3","volume":"1","author":"V Kuan","year":"2019","unstructured":"Kuan, V. et al. A chronological map of 308 physical and mental health conditions from 4 million individuals in the English National Health Service. Lancet Digit. Health 1(2), e63-77 (2019).","journal-title":"Lancet Digit. Health"},{"issue":"1","key":"38251_CR22","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-019-56847-4","volume":"10","author":"Y Li","year":"2020","unstructured":"Li, Y. et al. BEHRT: Transformer for electronic health records. Sci. Rep. 10(1), 1\u201312 (2020).","journal-title":"Sci. Rep."},{"issue":"1","key":"38251_CR23","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1006\/jpdc.1997.1404","volume":"48","author":"G Karypis","year":"1998","unstructured":"Karypis, G. & Kumar, V. Multilevel k-way partitioning scheme for irregular graphs. J. Parallel Distrib. Comput. 48(1), 96\u2013129 (1998).","journal-title":"J. Parallel Distrib. Comput."},{"key":"38251_CR24","unstructured":"Karypis, G. & Kumar, V. METIS: A Software Package for Partitioning Unstructured Graphs, Partitioning Meshes, and Computing Fill-Reducing Orderings of Sparse Matrices. http:\/\/conservancy.umn.edu\/handle\/11299\/215346 (1997)."},{"issue":"387","key":"38251_CR25","doi-asserted-by":"publisher","first-page":"653","DOI":"10.1080\/01621459.1984.10478093","volume":"79","author":"LJ Wei","year":"1984","unstructured":"Wei, L. J. & Lachin, J. M. Two-sample asymptotically distribution-free tests for incomplete multivariate observations. J. Am. Stat. Assoc. 79(387), 653\u2013661 (1984).","journal-title":"J. Am. Stat. Assoc."},{"issue":"1","key":"38251_CR26","doi-asserted-by":"publisher","first-page":"202","DOI":"10.2307\/2347934","volume":"40","author":"RW Makuch","year":"1991","unstructured":"Makuch, R. W. & Escobar, M. Algorithm AS 262: A two-sample test for incomplete multivariate data. Appl. Stat. 40(1), 202 (1991).","journal-title":"Appl. Stat."},{"key":"38251_CR27","unstructured":"Davidson-Pilon C. Lifelines, Survival Analysis in Python. https:\/\/zenodo.org\/record\/5745573 (2021)."},{"issue":"Supplement_1","key":"38251_CR28","doi-asserted-by":"publisher","first-page":"S14","DOI":"10.2337\/dc20-S002","volume":"43","author":"AD Association","year":"2019","unstructured":"Association, A. D. Classification and diagnosis of diabetes: Standards of medical care in diabetes\u20142020. Diabetes Care 43(Supplement_1), S14-31 (2019).","journal-title":"Diabetes Care"},{"issue":"1","key":"38251_CR29","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1007\/s11136-015-1061-0","volume":"25","author":"MC Adriaanse","year":"2016","unstructured":"Adriaanse, M. C., Drewes, H. W., van der Heide, I., Struijs, J. N. & Baan, C. A. The impact of comorbid chronic conditions on quality of life in type 2 diabetes patients. Qual. Life Res. 25(1), 175 (2016).","journal-title":"Qual. Life Res."},{"issue":"1","key":"38251_CR30","doi-asserted-by":"publisher","first-page":"906","DOI":"10.1186\/s12955-018-0906-y","volume":"16","author":"JN Zurita-Cruz","year":"2018","unstructured":"Zurita-Cruz, J. N. et al. Health and quality of life outcomes impairment of quality of life in type 2 diabetes mellitus: A cross-sectional study. Health Qual. Life Outcomes 16(1), 906 (2018).","journal-title":"Health Qual. Life Outcomes"},{"issue":"1","key":"38251_CR31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-021-90379-0","volume":"11","author":"S Eilat-Tsanani","year":"2021","unstructured":"Eilat-Tsanani, S., Margalit, A. & Golan, L. N. Occurrence of comorbidities in newly diagnosed type 2 diabetes patients and their impact after 11 years\u2019 follow-up. Sci. Rep. 11(1), 1\u201310 (2021).","journal-title":"Sci. Rep."},{"issue":"9","key":"38251_CR32","doi-asserted-by":"publisher","first-page":"1671","DOI":"10.1007\/s00125-020-05181-w","volume":"63","author":"WK Chung","year":"2020","unstructured":"Chung, W. K. et al. Precision medicine in diabetes: A Consensus Report from the American Diabetes Association (ADA) and the European Association for the Study of Diabetes (EASD). Diabetologia 63(9), 1671\u20131693 (2020).","journal-title":"Diabetologia"},{"issue":"2","key":"38251_CR33","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1093\/eurheartj\/ehz486","volume":"41","author":"F Cosentino","year":"2020","unstructured":"Cosentino, F. et al. 2019 ESC Guidelines on diabetes, pre-diabetes, and cardiovascular diseases developed in collaboration with the EASD: The Task Force for diabetes, pre-diabetes, and cardiovascular diseases of the European Society of Cardiology (ESC) and the European Associ. Eur. Heart J. 41(2), 255\u2013323. https:\/\/doi.org\/10.1093\/eurheartj\/ehz486 (2020).","journal-title":"Eur. Heart J."},{"issue":"10313","key":"38251_CR34","doi-asserted-by":"publisher","first-page":"1803","DOI":"10.1016\/S0140-6736(21)01920-6","volume":"398","author":"M Nazarzadeh","year":"2021","unstructured":"Nazarzadeh, M. et al. Blood pressure lowering and risk of new-onset type 2 diabetes: An individual participant data meta-analysis. Lancet 398(10313), 1803\u20131810 (2021).","journal-title":"Lancet"},{"key":"38251_CR35","doi-asserted-by":"publisher","first-page":"501","DOI":"10.1146\/annurev-statistics-031017-100045","volume":"5","author":"L Wasserman","year":"2018","unstructured":"Wasserman, L. Topological data analysis. Annu. Rev. Stat. 5, 501\u201332. https:\/\/doi.org\/10.1146\/annurev-statistics-031017-100045 (2018).","journal-title":"Annu. Rev. Stat."},{"issue":"17","key":"38251_CR36","doi-asserted-by":"publisher","first-page":"7265","DOI":"10.1073\/pnas.1102826108","volume":"108","author":"M Nicolau","year":"2011","unstructured":"Nicolau, M., Levine, A. J. & Carlsson, G. Topology based data analysis identifies a subgroup of breast cancers with a unique mutational profile and excellent survival. Proc. Natl. Acad. Sci. U S A 108(17), 7265\u20137270 (2011).","journal-title":"Proc. Natl. Acad. Sci. U S A"},{"issue":"2","key":"38251_CR37","first-page":"584","volume":"14","author":"M Joshi","year":"2019","unstructured":"Joshi, M. & Joshi, D. A survey of topological data analysis methods for Big data in healthcare intelligence. Int. J. Appl. Eng. Res. 14(2), 584\u2013588 (2019).","journal-title":"Int. J. Appl. Eng. Res."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-38251-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-38251-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-38251-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,16]],"date-time":"2023-07-16T15:01:54Z","timestamp":1689519714000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-38251-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,16]]},"references-count":37,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["38251"],"URL":"https:\/\/doi.org\/10.1038\/s41598-023-38251-1","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,16]]},"assertion":[{"value":"15 December 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 July 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 July 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"KR reports personal fees from BMJ Heart and PLOS Medicine outside the submitted work. All other authors report no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"11478"}}