{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T11:38:41Z","timestamp":1775821121252,"version":"3.50.1"},"reference-count":34,"publisher":"Oxford University Press (OUP)","issue":"2","license":[{"start":{"date-parts":[[2022,11,7]],"date-time":"2022-11-07T00:00:00Z","timestamp":1667779200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001321","name":"National Research Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]},{"name":"AI Singapore Programme","award":["AISG-GC-2019-001-2A"],"award-info":[{"award-number":["AISG-GC-2019-001-2A"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,1,18]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Objective<\/jats:title>\n                  <jats:p>This study aims to develop a convolutional neural network-based learning framework called domain knowledge-infused convolutional neural network (DK-CNN) for retrieving clinically similar patient and to personalize the prediction of macrovascular complication using the retrieved patients.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Materials and Methods<\/jats:title>\n                  <jats:p>We use the electronic health records of 169\u00a0434 patients with diabetes, hypertension, and\/or lipid disorder. Patients are partitioned into 7 subcohorts based on their comorbidities. DK-CNN integrates both domain knowledge and disease trajectory of patients over multiple visits to retrieve similar patients. We use normalized discounted cumulative gain (nDCG) and macrovascular complication prediction performance to evaluate the effectiveness of DK-CNN compared to state-of-the-art models. Ablation studies are conducted to compare DK-CNN with reduced models that do not use domain knowledge as well as models that do not consider short-term, medium-term, and long-term trajectory over multiple visits.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>Key findings from this study are: (1) DK-CNN is able to retrieve clinically similar patients and achieves the highest nDCG values in all 7 subcohorts; (2) DK-CNN outperforms other state-of-the-art approaches in terms of complication prediction performance in all 7 subcohorts; and (3) the ablation studies show that the full model achieves the highest nDCG compared with other 2 reduced models.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Discussion and Conclusions<\/jats:title>\n                  <jats:p>DK-CNN is a deep learning-based approach which incorporates domain knowledge and patient trajectory data to retrieve clinically similar patients. It can be used to assist physicians who may refer to the outcomes and past treatments of similar patients as a guide for choosing an effective treatment for patients.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/jamia\/ocac212","type":"journal-article","created":{"date-parts":[[2022,11,7]],"date-time":"2022-11-07T19:09:13Z","timestamp":1667848153000},"page":"273-281","source":"Crossref","is-referenced-by-count":4,"title":["Using similar patients to predict complication in patients with diabetes, hypertension, and lipid disorder: a domain knowledge-infused convolutional neural network approach"],"prefix":"10.1093","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3435-3421","authenticated-orcid":false,"given":"Ronald Wihal","family":"Oei","sequence":"first","affiliation":[{"name":"Institute of Data Science, National University of Singapore , Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4142-8893","authenticated-orcid":false,"given":"Wynne","family":"Hsu","sequence":"additional","affiliation":[{"name":"Institute of Data Science, National University of Singapore , Singapore"},{"name":"School of Computing, National University of Singapore , Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9636-388X","authenticated-orcid":false,"given":"Mong Li","family":"Lee","sequence":"additional","affiliation":[{"name":"Institute of Data Science, National University of Singapore , Singapore"},{"name":"School of Computing, National University of Singapore , Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ngiap Chuan","family":"Tan","sequence":"additional","affiliation":[{"name":"SingHealth Polyclinics, SingHealth , Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2022,11,7]]},"reference":[{"key":"2023011811051843400_ocac212-B1","doi-asserted-by":"crossref","first-page":"107843","DOI":"10.1016\/j.diabres.2019.107843","article-title":"Global and regional diabetes prevalence estimates for 2019 and projections for 2030 and 2045: results from the International Diabetes Federation Diabetes Atlas","volume":"157","author":"Saeedi","year":"2019","journal-title":"Diabetes Res Clin Pract"},{"issue":"4","key":"2023011811051843400_ocac212-B2","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1038\/s41581-019-0244-2","article-title":"The global epidemiology of hypertension","volume":"16","author":"Mills","year":"2020","journal-title":"Nat Rev Nephrol"},{"key":"2023011811051843400_ocac212-B3","author":"World Health Organization","year":"2008"},{"issue":"10159","key":"2023011811051843400_ocac212-B4","doi-asserted-by":"crossref","first-page":"1736","DOI":"10.1016\/S0140-6736(18)32203-7","article-title":"Global, regional, and national age-sex-specific mortality for 282 causes of death in 195 countries and territories, 1980\u20132017: a systematic analysis for the Global Burden of Disease Study 2017","volume":"392","author":"Roth","year":"2018","journal-title":"Lancet"},{"issue":"6","key":"2023011811051843400_ocac212-B5","doi-asserted-by":"crossref","first-page":"364","DOI":"10.1038\/s41574-021-00489-y","article-title":"Novel therapies with precision mechanisms for type 2 diabetes mellitus","volume":"17","author":"Perreault","year":"2021","journal-title":"Nat Rev Endocrinol"},{"issue":"21","key":"2023011811051843400_ocac212-B6","doi-asserted-by":"crossref","first-page":"2646","DOI":"10.1016\/j.jacc.2017.04.014","article-title":"Novel diabetes drugs and the cardiovascular specialist","volume":"69","author":"Sattar","year":"2017","journal-title":"J Am Coll Cardiol"},{"issue":"4","key":"2023011811051843400_ocac212-B7","first-page":"CD001841","article-title":"First-line drugs for hypertension","volume":"4","author":"Wright","year":"2018","journal-title":"Cochrane Database Syst Rev"},{"issue":"1","key":"2023011811051843400_ocac212-B8","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1080\/14728214.2019.1591372","article-title":"Emerging drugs for the treatment of hypercholesterolemia","volume":"24","author":"Bove","year":"2019","journal-title":"Expert Opin Emerg Drugs"},{"issue":"8","key":"2023011811051843400_ocac212-B9","doi-asserted-by":"crossref","first-page":"1102","DOI":"10.1592\/phco.27.8.1102","article-title":"Loss of glycemic control in patients with type 2 diabetes mellitus who were receiving initial metformin, sulfonylurea, or thiazolidinedione monotherapy","volume":"27","author":"Riedel","year":"2007","journal-title":"Pharmacotherapy"},{"issue":"22","key":"2023011811051843400_ocac212-B10","doi-asserted-by":"crossref","first-page":"2671","DOI":"10.1042\/CS20160407","article-title":"Personalized medicine\u2014a modern approach for the diagnosis and management of hypertension","volume":"131","author":"Savoia","year":"2017","journal-title":"Clin Sci (Lond)"},{"issue":"11","key":"2023011811051843400_ocac212-B11","doi-asserted-by":"crossref","first-page":"1386","DOI":"10.1016\/j.jacc.2016.12.036","article-title":"Statin intolerance and risk of coronary heart events and all-cause mortality following myocardial infarction","volume":"69","author":"Serban","year":"2017","journal-title":"J Am Coll Cardiol"},{"key":"2023011811051843400_ocac212-B12","first-page":"132","article-title":"Personalized predictive modeling and risk factor identification using patient similarity","volume":"2015","author":"Ng","year":"2015","journal-title":"AMIA Jt Summits Transl Sci Proc"},{"key":"2023011811051843400_ocac212-B13","author":"Zhang","year":"2021"},{"key":"2023011811051843400_ocac212-B14","doi-asserted-by":"crossref","first-page":"101900","DOI":"10.1016\/j.artmed.2020.101900","article-title":"Temporal tree representation for similarity computation between medical patients","volume":"108","author":"Pokharel","year":"2020","journal-title":"Artif Intell Med"},{"key":"2023011811051843400_ocac212-B15","doi-asserted-by":"crossref","first-page":"104073","DOI":"10.1016\/j.ijmedinf.2019.104073","article-title":"A patient-similarity-based model for diagnostic prediction","volume":"135","author":"Jia","year":"2020","journal-title":"Int J Med Inform"},{"issue":"3","key":"2023011811051843400_ocac212-B16","doi-asserted-by":"crossref","first-page":"588","DOI":"10.1093\/jamia\/ocaa247","article-title":"Precision population analytics: population management at the point-of-care","volume":"28","author":"Tang","year":"2021","journal-title":"J Am Med Inform Assoc"},{"issue":"11","key":"2023011811051843400_ocac212-B17","doi-asserted-by":"crossref","first-page":"1808","DOI":"10.1093\/jamia\/ocaa159","article-title":"Recommendations for patient similarity classes: results of the AMIA 2019 workshop on defining patient similarity","volume":"27","author":"Seligson","year":"2020","journal-title":"J Am Med Inform Assoc"},{"key":"2023011811051843400_ocac212-B18","author":"Suo","year":"2017"},{"issue":"5","key":"2023011811051843400_ocac212-B19","doi-asserted-by":"crossref","first-page":"e0127428","DOI":"10.1371\/journal.pone.0127428","article-title":"Personalized mortality prediction driven by electronic medical data and a patient similarity metric","volume":"10","author":"Lee","year":"2015","journal-title":"PLoS One"},{"issue":"9","key":"2023011811051843400_ocac212-B20","doi-asserted-by":"crossref","first-page":"e20645","DOI":"10.2196\/20645","article-title":"Marrying medical domain knowledge with deep learning on electronic health records: a deep visual analytics approach","volume":"22","author":"Li","year":"2020","journal-title":"J Med Internet Res"},{"issue":"11","key":"2023011811051843400_ocac212-B21","doi-asserted-by":"crossref","first-page":"e19612","DOI":"10.2196\/19612","article-title":"Amplifying domain expertise in clinical data pipelines","volume":"8","author":"Rahman","year":"2020","journal-title":"JMIR Med Inform"},{"issue":"8","key":"2023011811051843400_ocac212-B22","doi-asserted-by":"crossref","first-page":"699","DOI":"10.3390\/jpm11080699","article-title":"Using domain knowledge and data-driven insights for patient similarity analytics","volume":"11","author":"Oei","year":"2021","journal-title":"J Pers Med"},{"issue":"3","key":"2023011811051843400_ocac212-B23","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1109\/TNB.2018.2837622","article-title":"Deep patient similarity learning for personalized healthcare","volume":"17","author":"Suo","year":"2018","journal-title":"IEEE Trans Nanobiosci"},{"key":"2023011811051843400_ocac212-B24","author":"Zhu","year":"2016"},{"key":"2023011811051843400_ocac212-B25","author":"Ministry of Health Singapore","year":"2017"},{"key":"2023011811051843400_ocac212-B26","author":"Ministry of Health Singapore","year":"2016"},{"key":"2023011811051843400_ocac212-B27","author":"Ministry of Health Singapore","year":"2014"},{"key":"2023011811051843400_ocac212-B28","volume-title":"Joint European conference on machine learning and knowledge discovery in databases","author":"Bordes","year":"2014"},{"key":"2023011811051843400_ocac212-B29","first-page":"8026","article-title":"Pytorch: an imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Adv Neural Inf Process Syst"},{"key":"2023011811051843400_ocac212-B30","author":"Kingma","year":"2014"},{"issue":"3","key":"2023011811051843400_ocac212-B31","first-page":"257","article-title":"A unifying tool for linear multivariate statistical methods: the RV-coefficient","volume":"25","author":"Robert","year":"1976","journal-title":"J R Stat Soc Ser C Appl Stat"},{"issue":"1","key":"2023011811051843400_ocac212-B32","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1162\/003465302317331982","article-title":"Propensity score-matching methods for nonexperimental causal studies","volume":"84","author":"Dehejia","year":"2002","journal-title":"Rev Econ Stat"},{"issue":"6","key":"2023011811051843400_ocac212-B33","doi-asserted-by":"crossref","first-page":"476","DOI":"10.1590\/S0066-782X2004001800006","article-title":"Comparison of LDL-cholesterol direct measurement with the estimate using the Friedewald formula in a sample of 10,664 patients","volume":"83","author":"Cordova","year":"2004","journal-title":"Arq Bras Cardiol"},{"issue":"8","key":"2023011811051843400_ocac212-B34","doi-asserted-by":"crossref","first-page":"1283","DOI":"10.3390\/math10081283","article-title":"Mitigating the multicollinearity problem and its machine learning approach: a review","volume":"10","author":"Chan","year":"2022","journal-title":"Mathematics"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/30\/2\/273\/48754896\/ocac212.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/30\/2\/273\/48754896\/ocac212.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,18]],"date-time":"2023-01-18T11:05:54Z","timestamp":1674039954000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/30\/2\/273\/6809035"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,7]]},"references-count":34,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2022,11,7]]},"published-print":{"date-parts":[[2023,1,18]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocac212","relation":{},"ISSN":["1067-5027","1527-974X"],"issn-type":[{"value":"1067-5027","type":"print"},{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,2,1]]},"published":{"date-parts":[[2022,11,7]]}}}