{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T21:44:16Z","timestamp":1767995056937,"version":"3.49.0"},"reference-count":40,"publisher":"BMJ","issue":"12","content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["BMJ Open"],"accepted":{"date-parts":[[2016,10,3]]},"published-print":{"date-parts":[[2016,12]]},"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>The current study was undertaken for use of the decision tree (DT) method for development of different prediction models for incidence of type 2 diabetes (T2D) and for exploring interactions between predictor variables in those models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Design<\/jats:title>\n                    <jats:p>Prospective cohort study.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Setting<\/jats:title>\n                    <jats:p>Tehran Lipid and Glucose Study (TLGS).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A total of 6647 participants (43.4% men) aged &gt;20\u2005years, without T2D at baselines ((1999\u20132001) and (2002\u20132005)), were followed until 2012. 2 series of models (with and without 2-hour postchallenge plasma glucose (2h-PCPG)) were developed using 3 types of DT algorithms. The performances of the models were assessed using sensitivity, specificity, area under the ROC curve (AUC), geometric mean (G-Mean) and F-Measure.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Primary outcome measure<\/jats:title>\n                    <jats:p>T2D was primary outcome which defined if fasting plasma glucose (FPG) was \u22657\u2005mmol\/L or if the 2h-PCPG was \u226511.1\u2005mmol\/L or if the participant was taking antidiabetic medication.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>During a median follow-up of 9.5\u2005years, 729 new cases of T2D were identified. The Quick Unbiased Efficient Statistical Tree (QUEST) algorithm had the highest sensitivity and G-Mean among all the models for men and women. The models that included 2h-PCPG had sensitivity and G-Mean of (78% and 0.75%) and (78% and 0.78%) for men and women, respectively. Both models achieved good discrimination power with AUC above 0.78. FPG, 2h-PCPG, waist-to-height ratio (WHtR) and mean arterial blood pressure (MAP) were the most important factors to incidence of T2D in both genders. Among men, those with an FPG\u22644.9\u2005mmol\/L and 2h-PCPG\u22647.7\u2005mmol\/L had the lowest risk, and those with an FPG&gt;5.3\u2005mmol\/L and 2h-PCPG&gt;4.4\u2005mmol\/L had the highest risk for T2D incidence. In women, those with an FPG\u22645.2\u2005mmol\/L and WHtR\u22640.55 had the lowest risk, and those with an FPG&gt;5.2\u2005mmol\/L and WHtR&gt;0.56 had the highest risk for T2D incidence.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Our study emphasises the utility of DT for exploring interactions between predictor variables.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/bmjopen-2016-013336","type":"journal-article","created":{"date-parts":[[2016,12,1]],"date-time":"2016-12-01T22:00:26Z","timestamp":1480629626000},"page":"e013336","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":39,"title":["Decision tree-based modelling for identification of potential interactions between type 2 diabetes risk factors: a decade follow-up in a Middle East prospective cohort study"],"prefix":"10.1136","volume":"6","author":[{"given":"Azra","family":"Ramezankhani","sequence":"first","affiliation":[{"name":"Prevention of Metabolic Disorders Research Center, Research Institute for Endocrine Science, Shahid Beheshti University of Medical Sciences, Tehran, Iran"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Esmaeil","family":"Hadavandi","sequence":"additional","affiliation":[{"name":"Industrial Engineering Department, Amirkabir University of Technology, Tehran, Iran"},{"name":"Department of Industrial Engineering, Birjand University of Technology, Birjand, Iran"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Omid","family":"Pournik","sequence":"additional","affiliation":[{"name":"Department of Community Medicine, School of Medicine, Iran University of Medical Sciences, Tehran, Iran"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jamal","family":"Shahrabi","sequence":"additional","affiliation":[{"name":"Industrial Engineering Department, Amirkabir University of Technology, Tehran, Iran"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fereidoun","family":"Azizi","sequence":"additional","affiliation":[{"name":"Endocrine Research Center, Research Institute for Endocrine Sciences, Shahid Beheshti University of Medical Sciences, Tehran, Iran"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Farzad","family":"Hadaegh","sequence":"additional","affiliation":[{"name":"Prevention of Metabolic Disorders Research Center, Research Institute for Endocrine Science, Shahid Beheshti University of Medical Sciences, Tehran, Iran"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"239","published-online":{"date-parts":[[2016,12,1]]},"reference":[{"key":"2025121402544053000_6.12.e013336.1","doi-asserted-by":"publisher","DOI":"10.1016\/j.diabres.2011.10.029"},{"key":"2025121402544053000_6.12.e013336.2","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.b880"},{"key":"2025121402544053000_6.12.e013336.3","doi-asserted-by":"publisher","DOI":"10.4093\/dmj.2011.35.1.12"},{"key":"2025121402544053000_6.12.e013336.4","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.d7163"},{"key":"2025121402544053000_6.12.e013336.5","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.e5900"},{"key":"2025121402544053000_6.12.e013336.6","doi-asserted-by":"publisher","DOI":"10.7326\/M14-0698"},{"key":"2025121402544053000_6.12.e013336.7","doi-asserted-by":"crossref","unstructured":"Kleinbaum DG , Klein M . Logistic regression: a self-learning text. Springer Science & Business Media, 2010.","DOI":"10.1007\/978-1-4419-1742-3"},{"key":"2025121402544053000_6.12.e013336.8","unstructured":"Han J , Kamber M , Pei J . Data mining: concepts and techniques. Elsevier, 2011."},{"key":"2025121402544053000_6.12.e013336.9","doi-asserted-by":"publisher","DOI":"10.1111\/insr.12016"},{"key":"2025121402544053000_6.12.e013336.10","doi-asserted-by":"crossref","unstructured":"Van Buuren S . Flexible imputation of missing data. CRC Press, 2012.","DOI":"10.1201\/b11826"},{"key":"2025121402544053000_6.12.e013336.11","doi-asserted-by":"crossref","unstructured":"Zhang H , Singer B . Recursive partitioning and applications. Springer Science & Business Media, 2010.","DOI":"10.1007\/978-1-4419-6824-1"},{"key":"2025121402544053000_6.12.e013336.12","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(05)67342-4"},{"key":"2025121402544053000_6.12.e013336.13","doi-asserted-by":"publisher","DOI":"10.1186\/1745-6215-10-5"},{"key":"2025121402544053000_6.12.e013336.14","doi-asserted-by":"publisher","DOI":"10.1007\/s000380200008"},{"key":"2025121402544053000_6.12.e013336.15","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2458-9-186"},{"key":"2025121402544053000_6.12.e013336.16","doi-asserted-by":"publisher","DOI":"10.1161\/01.CIR.96.1.308"},{"key":"2025121402544053000_6.12.e013336.17","doi-asserted-by":"publisher","DOI":"10.2337\/diacare.20.7.1183"},{"key":"2025121402544053000_6.12.e013336.18","unstructured":"Enders CK . Applied missing data analysis. Guilford Press, 2010."},{"key":"2025121402544053000_6.12.e013336.19","unstructured":"Steyerberg EW . Clinical prediction models: a practical approach to development, validation, and updating. Springer Science & Business Media, 2009."},{"key":"2025121402544053000_6.12.e013336.20","unstructured":"Akthar F, Hahne C. RapidMiner 5 Operator Reference (2012). https:\/\/rapidminer.com\/wp-content\/uploads\/ 2013\/10 \/RapidMiner_OperatorReference_en.pdf (accessed 12 Feb 2015)."},{"key":"2025121402544053000_6.12.e013336.21","doi-asserted-by":"crossref","unstructured":"Chawla NV , Lazarevic A , Hall LO , et al . SMOTEBoost: improving prediction of the minority class in boosting. In: Lavra\u010d N, Gamberger D, Todorovski L, et al. Knowledge discovery in databases: PKDD 2003. Berlin: Springer, 2003:107\u201319.","DOI":"10.1007\/978-3-540-39804-2_12"},{"key":"2025121402544053000_6.12.e013336.22","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE: Synthetic Minority Over-Sampling Technique","volume":"16","author":"Chawla","year":"2002","journal-title":"J Artif Intell Res"},{"key":"2025121402544053000_6.12.e013336.23","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2011.12.043"},{"key":"2025121402544053000_6.12.e013336.24","doi-asserted-by":"publisher","DOI":"10.1177\/0272989X14560647"},{"key":"2025121402544053000_6.12.e013336.25","doi-asserted-by":"crossref","unstructured":"John GH , Kohavi R , Pfleger K. eds . Irrelevant features and the subset selection problem. Machine Learning: Proceedings of the Eleventh International Conference. 1994.","DOI":"10.1016\/B978-1-55860-335-6.50023-4"},{"key":"2025121402544053000_6.12.e013336.26","doi-asserted-by":"crossref","unstructured":"Liu H , Motoda H . Computational methods of feature selection. CRC Press, 2007.","DOI":"10.1201\/9781584888796"},{"key":"2025121402544053000_6.12.e013336.27","doi-asserted-by":"crossref","unstructured":"Liu H , Motoda H . Feature selection for knowledge discovery and data mining. Springer, 1998.","DOI":"10.1007\/978-1-4615-5689-3"},{"key":"2025121402544053000_6.12.e013336.28","doi-asserted-by":"crossref","first-page":"361","DOI":"10.1111\/insr.12062","article-title":"To see the wood for the trees: discussion of \u201c50 years of classification and regression trees\u201d","volume":"82","author":"Rusch","year":"2014","journal-title":"Int Stat Rev"},{"key":"2025121402544053000_6.12.e013336.29","doi-asserted-by":"crossref","first-page":"2017","DOI":"10.1016\/j.eswa.2007.12.002","article-title":"Using Kaplan-Meier analysis together with decision tree methods (C&RT, CHAID, QUEST, C4. 5 and ID3) in determining recurrence-free survival of breast cancer patients","volume":"36","author":"Ture","year":"2009","journal-title":". Expert Syst Appl"},{"key":"2025121402544053000_6.12.e013336.30","unstructured":"Ville BD . Decision tree for business intelligence and data mining. SAS Publishing, 2006."},{"key":"2025121402544053000_6.12.e013336.31","first-page":"27","article-title":"Evaluation measures for models assessment over imbalanced data sets","volume":"3","author":"Bekkar","year":"2013","journal-title":"J Info Eng Appl"},{"key":"2025121402544053000_6.12.e013336.32","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2005.10.010"},{"key":"2025121402544053000_6.12.e013336.33","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-789X.2011.00952.x"},{"key":"2025121402544053000_6.12.e013336.34","doi-asserted-by":"publisher","DOI":"10.1016\/j.diabres.2015.01.027"},{"key":"2025121402544053000_6.12.e013336.35","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1007\/s00592-011-0298-5","article-title":"Fasting glucose cutoff point: where does the risk terminate? Tehran lipid and glucose study","volume":"49","author":"Bozorgmanesh","year":"2012","journal-title":"Acta Diabetol"},{"key":"2025121402544053000_6.12.e013336.36","doi-asserted-by":"crossref","first-page":"391","DOI":"10.1016\/j.diabres.2014.07.003","article-title":"Applying decision tree for identification of a low risk population for type 2 diabetes. Tehran Lipid and Glucose Study","volume":"105","author":"Ramezankhani","year":"2014","journal-title":"Diabetes Res Clin Pract"},{"key":"2025121402544053000_6.12.e013336.37","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1038\/jhh.2011.4","article-title":"Family history of diabetes modifies the effect of blood pressure for incident diabetes in Middle Eastern women: Tehran Lipid and Glucose Study","volume":"26","author":"Hatami","year":"2012","journal-title":"J Hum Hypertens"},{"key":"2025121402544053000_6.12.e013336.38","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1038\/nrcardio.2010.182","article-title":"Blood pressure lowering in patients with diabetes-one level might not fit all","volume":"8","author":"Cooper-DeHoff","year":"2011","journal-title":"Nat Rev Cardiol"},{"key":"2025121402544053000_6.12.e013336.39","doi-asserted-by":"publisher","DOI":"10.1093\/eurpub\/ckq074"},{"key":"2025121402544053000_6.12.e013336.40","doi-asserted-by":"publisher","DOI":"10.1023\/B:EJEP.0000036568.02655.f8"}],"container-title":["BMJ Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjopen-2016-013336","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,14]],"date-time":"2025-12-14T10:54:48Z","timestamp":1765709688000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmjopen.bmj.com\/lookup\/doi\/10.1136\/bmjopen-2016-013336"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,12]]},"references-count":40,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2016,12,1]]},"published-print":{"date-parts":[[2016,12]]}},"alternative-id":["10.1136\/bmjopen-2016-013336"],"URL":"https:\/\/doi.org\/10.1136\/bmjopen-2016-013336","relation":{},"ISSN":["2044-6055","2044-6055"],"issn-type":[{"value":"2044-6055","type":"print"},{"value":"2044-6055","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,12]]}}}