{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,17]],"date-time":"2026-10-17T19:18:06Z","timestamp":1792264686488,"version":"4.4.0"},"reference-count":32,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,8,17]],"date-time":"2023-08-17T00:00:00Z","timestamp":1692230400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01EB022911"],"award-info":[{"award-number":["R01EB022911"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01MH126970"],"award-info":[{"award-number":["R01MH126970"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["T32CA101642"],"award-info":[{"award-number":["T32CA101642"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Big Data"],"abstract":"<jats:sec>\n                    <jats:title>Importance<\/jats:title>\n                    <jats:p>The comorbidity network represents multiple diseases and their relationships in a graph. Understanding comorbidity networks among critical care unit (CCU) patients can help doctors diagnose patients faster, minimize missed diagnoses, and potentially decrease morbidity and mortality.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>The main objective of this study was to identify the comorbidity network among CCU patients using a novel application of a machine learning method (graphical modeling method). The second objective was to compare the machine learning method with a traditional pairwise method in simulation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Method<\/jats:title>\n                    <jats:p>This cross-sectional study used CCU patients' data from Medical Information Mart for the Intensive Care-3 (MIMIC-3) dataset, an electronic health record (EHR) of patients with CCU hospitalizations within Beth Israel Deaconess Hospital from 2001 to 2012. A machine learning method (graphical modeling method) was applied to identify the comorbidity network of 654 diagnosis categories among 46,511 patients.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Out of the 654 diagnosis categories, the graphical modeling method identified a comorbidity network of 2,806 associations in 510 diagnosis categories. Two medical professionals reviewed the comorbidity network and confirmed that the associations were consistent with current medical understanding. Moreover, the strongest association in our network was between \u201cpoisoning by psychotropic agents\u201d and \u201caccidental poisoning by tranquilizers\u201d (logOR 8.16), and the most connected diagnosis was \u201cdisorders of fluid, electrolyte, and acid\u2013base balance\u201d (63 associated diagnosis categories). Our method outperformed traditional pairwise comorbidity network methods in simulation studies. Some strongest associations between diagnosis categories were also identified, for example, \u201cdiagnoses of mitral and aortic valve\u201d and \u201cother rheumatic heart disease\u201d (logOR: 5.15). Furthermore, our method identified diagnosis categories that were connected with most other diagnosis categories, for example, \u201cdisorders of fluid, electrolyte, and acid\u2013base balance\u201d was associated with 63 other diagnosis categories. Additionally, using a data-driven approach, our method partitioned the diagnosis categories into 14 modularity classes.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion and relevance<\/jats:title>\n                    <jats:p>Our graphical modeling method inferred a logical comorbidity network whose associations were consistent with current medical understanding and outperformed traditional network methods in simulation. Our comorbidity network method can potentially assist CCU doctors in diagnosing patients faster and minimizing missed diagnoses.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fdata.2023.846202","type":"journal-article","created":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T01:54:57Z","timestamp":1692323697000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":19,"title":["Comorbidity network analysis using graphical models for electronic health records"],"prefix":"10.3389","volume":"6","author":[{"given":"Bo","family":"Zhao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sarah","family":"Huepenbecker","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gen","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Suja S.","family":"Rajan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kayo","family":"Fujimoto","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xi","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2023,8,17]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"e145","DOI":"10.1097\/AOG.0000000000004397","article-title":"Multifetal gestations: twin, triplet, and higher-order multifetal pregnancies","volume":"137","year":"2021","journal-title":"Obstet Gynecol"},{"key":"B2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-020-59336-1","article-title":"MorbiNet: multimorbidity networks in adult general population. Analysis of type 2 diabetes mellitus comorbidity","volume":"10","author":"Aguado","year":"2020","journal-title":"Sci. Rep"},{"key":"B3","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1609\/icwsm.v3i1.13937","article-title":"\u201cGephi: an open source software for exploring and manipulating networks,\u201d","volume":"3","author":"Bastian","year":"2009","journal-title":"Proceedings of the International AAAI Conference on Web and Social Media"},{"key":"B4","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1093\/jamiaopen\/ooz067","article-title":"Sensitivity of comorbidity network analysis","volume":"3","author":"Brunson","year":"2020","journal-title":"JAMIA Open"},{"key":"B5","doi-asserted-by":"publisher","first-page":"389","DOI":"10.1001\/archinte.164.4.389","article-title":"Clinical and autopsy diagnoses in the intensive care unit: a prospective study","volume":"164","author":"Combes","year":"2004","journal-title":"Arch. Intern. Med"},{"key":"B6","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1017\/S0140525X09991567","article-title":"Comorbidity: a network perspective","volume":"33","author":"Cramer","year":"2010","journal-title":"Behav. Brain Sci"},{"key":"B7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3389\/fphys.2020.01009","article-title":"Comorbidity networks in cardiovascular diseases","volume":"11","author":"Cruz-\u00c1vila","year":"2020","journal-title":"Front. Physiol"},{"key":"B8","doi-asserted-by":"publisher","first-page":"528","DOI":"10.1177\/1948550617709827","article-title":"Network analysis on attitudes: a brief tutorial","volume":"8","author":"Dalege","year":"2017","journal-title":"Soc. Psychol. Personal. Sci"},{"key":"B9","doi-asserted-by":"publisher","first-page":"845","DOI":"10.1007\/s00127-015-1012-7","article-title":"Latent variable and network models of comorbidity: toward an empirically derived nosology","volume":"50","author":"Eaton","year":"2015","journal-title":"Soc. Psychiatry Psychiatr. Epidemiol"},{"key":"B10","doi-asserted-by":"publisher","first-page":"195","DOI":"10.3758\/s13428-017-0862-1","article-title":"Estimating psychological networks and their accuracy: a tutorial paper","volume":"50","author":"Epskamp","year":"2018","journal-title":"Behav. Res. Methods"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1007\/s41109-018-0101-4","article-title":"Statistical methods for constructing disease comorbidity networks from longitudinal inpatient data","author":"Fotouhi","year":"2018","journal-title":"Appl. Netw. Sci"},{"key":"B12","doi-asserted-by":"publisher","first-page":"1220","DOI":"10.1080\/15563650.2019.1677022","article-title":"2018 annual report of the american association of poison control centers' national poison data system (NPDS): 36th annual report","volume":"57","author":"Gummin","year":"2019","journal-title":"Clin. Toxicol"},{"key":"B13","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1093\/biomet\/57.1.97","article-title":"Monte carlo sampling methods using Markov chains and their applications","volume":"57","author":"Hastings","year":"1970","journal-title":"Biometrika"},{"key":"B14","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1097\/TA.0b013e3181a5e7fd","article-title":"Missed surgical intensive care unit billing: potential financial impact of 24\/7 faculty presence","volume":"67","author":"Hendershot","year":"2009","journal-title":"J. Trauma"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1000353","article-title":"Dynamic network approach for the study of human phenotypes","author":"Hidalgo","year":"2009","journal-title":"PLoS Comput. Biol"},{"key":"B16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/sdata.2016.35","article-title":"MIMIC-III, a freely accessible critical care database","volume":"3","author":"Johnson","year":"2016","journal-title":"Sci. Data"},{"key":"B17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.ijmedinf.2018.04.001","article-title":"Comorbidity network for chronic disease: a novel approach to understand type 2 diabetes progression","volume":"115","author":"Khan","year":"2018","journal-title":"Int. J. Med. Inform"},{"key":"B18","doi-asserted-by":"publisher","first-page":"72","DOI":"10.5049\/EBP.2010.8.2.72","article-title":"Fluid and electrolyte disturbances in critically ill patients","volume":"8","author":"Lee","year":"2010","journal-title":"Electrolyte Blood Press"},{"key":"B19","unstructured":"2022"},{"key":"B20","doi-asserted-by":"publisher","first-page":"953","DOI":"10.1016\/S0140-6736(11)61171-9","article-title":"Rheumatic heart disease","volume":"379","author":"Marijon","year":"2012","journal-title":"Lancet"},{"key":"B21","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1186\/s13613-020-00762-9","article-title":"Management of pharmaceutical and recreational drug poisoning","volume":"10","author":"M\u00e9garbane","year":"2020","journal-title":"Ann. Intensive Care"},{"key":"B22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/cc2832","article-title":"Scope of the problem: epidemiology of anemia and use of blood transfusions in critical care","volume":"8","author":"Napolitano","year":"2004","journal-title":"Crit. Care"},{"key":"B23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/cc5782","article-title":"Premortem clinical diagnoses and postmortem autopsy findings: discrepancies in critically ill cancer patients","volume":"11","author":"Pastores","year":"2007","journal-title":"Crit. Care"},{"key":"B24","doi-asserted-by":"publisher","first-page":"30","DOI":"10.3389\/fdata.2019.00030","article-title":"Significant EHR feature-driven t2d inference: predictive machine learning and networks","volume":"2","author":"Preo","year":"2019","journal-title":"Front. Big Data"},{"key":"B25","doi-asserted-by":"publisher","first-page":"521","DOI":"10.1016\/j.ccc.2017.03.002","article-title":"Assessment and management of toxidromes in the critical care unit","volume":"33","author":"Rasimas","year":"2017","journal-title":"Crit. Care Clin"},{"key":"B26","author":"Rosner","year":"2010","journal-title":"Fundamentals of Biostatistics"},{"key":"B27","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1007\/s00134-002-1576-z","article-title":"Characteristics of discrepancies between clinical and autopsy diagnoses in the intensive care unit: a 5-year review","volume":"29","author":"Silfvast","year":"2003","journal-title":"Intensive Care Med"},{"key":"B28","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1177\/1751143720914229","article-title":"Comorbidity and survival after admission to the intensive care unit: a population-based study of 41,230 patients","volume":"22","author":"Simpson","year":"2021","journal-title":"J. Intensive Care Soc"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.3390\/jpm11121382","article-title":"A network-based analysis of disease complication associations for obstetric disorders in the UK biobank","author":"Sriram","year":"2021","journal-title":"J. Pers. Med"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2288-12-16","article-title":"Graphical modeling of binary data using the LASSO: a simulation study","author":"Strobl","year":"2012","journal-title":"BMC Med. Res. Methodol"},{"key":"B31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-019-53708-y","article-title":"Comparing methods for comparing networks","volume":"9","author":"Tantardini","year":"2019","journal-title":"Sci. Rep"},{"key":"B32","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1111\/j.1467-9868.2005.00503.x","article-title":"Regularization and variable selection via the elastic net","volume":"67","author":"Zou","year":"2005","journal-title":"J. R. Stat. Soc. Series B Stat. Methodol"}],"container-title":["Frontiers in Big Data"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdata.2023.846202\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T01:55:04Z","timestamp":1692323704000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdata.2023.846202\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,17]]},"references-count":32,"alternative-id":["10.3389\/fdata.2023.846202"],"URL":"https:\/\/doi.org\/10.3389\/fdata.2023.846202","relation":{},"ISSN":["2624-909X"],"issn-type":[{"value":"2624-909X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,17]]},"article-number":"846202"}}