臺灣博碩士論文加值系統

Background: Type 2 diabetes mellitus is most common in adults, but an increasing number of children and adolescents are also affected. Individuals with diabetes are at a twofold to fivefold increased risk of stroke compared to non-diabetes. The purpose of this study was to develop machine learning-based models for predicting the personalized risk of developing stroke in diabetes patients at 12 months.
Method: A retrospective cohort design using the MJ database on 1,894 individuals aged ≥35 years with type 2 diabetes mellitus, between 2002 to 2017. Using a propensity score pair matching procedure of 10:1 ratio, 825 T2DM were selected, and the data was used to run our prediction models. Random Forest, K-Nearest Neighbor, and XGBoost classifier were developed to perform our predictions.
Result: A sample of 1,894 participants were included in this study in which 75(3.9%) had first-time stroke. A sub-sample of 825 recruited and analyzed after propensity matching of 10:1 ratio, with an overall median age of 37 years. The AUC was (XGB: 90%, RF: 88%, KNN: 85%)respectively.
Conclusion: BMI, uricemia, TyG-Index, and diastolic blood pressure were found to be the best predictors of stroke in our study owing to the high-performance accuracy of our machine learning models.

Background: Type 2 diabetes mellitus is most common in adults, but an increasing number of children and adolescents are also affected. Individuals with diabetes are at a twofold to fivefold increased risk of stroke compared to non-diabetes. The purpose of this study was to develop machine learning-based models for predicting the personalized risk of developing stroke in diabetes patients at 12 months.
Method: A retrospective cohort design using the MJ database on 1,894 individuals aged ≥35 years with type 2 diabetes mellitus, between 2002 to 2017. Using a propensity score pair matching procedure of 10:1 ratio, 825 T2DM were selected, and the data was used to run our prediction models. Random Forest, K-Nearest Neighbor, and XGBoost classifier were developed to perform our predictions.
Result: A sample of 1,894 participants were included in this study in which 75(3.9%) had first-time stroke. A sub-sample of 825 recruited and analyzed after propensity matching of 10:1 ratio, with an overall median age of 37 years. The AUC was (XGB: 90%, RF: 88%, KNN: 85%)respectively.
Conclusion: BMI, uricemia, TyG-Index, and diastolic blood pressure were found to be the best predictors of stroke in our study owing to the high-performance accuracy of our machine learning models.

Table of Contents
Acknowledgments..........III
Abstract.................IV
Table of Contents........VI
List of Tables...........VIII
List of Figures..........IX
List of Abbreviations....X
CHAPTER I: INTRODUCTION..1
1.1 Background and Motivation...........1
1.2 Study Rationale.....................6
2.2 Aim.................................6
2.2.1 Objective.........................6
CHAPTER II: LITERATURE REVIEW...........7
2.1 Diabetes (Type II)..................7
2.2 Stroke..............................8
2.3 Specific Risk Factor/s of Stroke....9
2.4 Machine Learning....................10
CHAPTER III: METHODS....................13
3.1 Data Source and Setting.............13
3.2 Study Design and Participants.......13
3.3 Criteria and Definition.............16
3.4 Follow-up...........................16
3.4 Propensity Score Pair Matching......16
3.5 Candidate Variables Extraction......17
3.6 Data Preprocessing..................18
3.6.1 Missing Value Identification and Removal.............18
3.6.2 Outlier Identification and Removal...................19
3.6.3 Feature Selection/Dimension Reduction................19
3.7 Outcome Measurement and Predictors.....................21
3.8 Resampling Technique...................................21
3.9 Dataset Train and Test Method..........................21
4.1 Design and Implementation of Classification Models.....22
4.1.1 Random Forest Classifier.............................22
4.1.2 K-Nearest Neighbor Classifier (KNN)..................23
4.1.3 Extreme Gradient Boosting Classifier (XGBoost).......23
4.2 Model Evaluation Validation and Performance............23
4.2.1 Accuracy.............................................24
4.2.2 Sensitivity..........................................25
4.2.3 Specificity..........................................25
4.2.4 F1 Score.............................................25
4.3 Statistical Analysis...................................25
4.4 Ethical Consideration..................................26
CHAPTER V: RESULTS.........................................27
4.1 Baseline Characteristics...............................27
4.2 Generalized Logistic Regression Analysis...............30
4.3 Risk Factors of Stroke.................................31
4.4 Incidence and Prevalence of Stroke.....................32
4.5 Machine Learning Model Performance.....................33
4.6 Comparing Models Performance Metrics...................34
4.7 Feature Importance.....................................35
CHAPTER VI: DISCUSSION.....................................36
5.1 Summary of Research Findings and Interpretation........36
5.2 Policy Implications and Recommendations................41
5.3 Study Limitations......................................41
5.4 Conclusion.............................................42
Reference..................................................43

LIST OF TABLES
Table 1: The Number of Missing Values...........................................18
Table 2: Feature Selection Using Principal Component Analysis...................20
Table 3: Hyperparameters for our Models.........................................22
Table 4: Distribution of Baseline Characteristics Before Matching............27-28
Table 5: Distribution of Baseline Characteristics After Propensity Pair Matching.....................................................................29-30
Table 6: Independent Risk Predictors of Stroke...............................30-31
Table 7: Comparing Risk Factors of Stroke with Previous Studies..............31-32
Table 8: Comparing the Incidence and Prevalence Rate of Stroke in T2DM.......32-33
Table 9: Models Classification Metrics..........................................34


LIST OF FIGURES
Figure 1: Consort Diagram of the Study Flow.....................................15
Figure 2: Propensity Score of Covariates Before and After Matching..............17
Figure 3: The Receiver Operating Characteristic Curve for Three Algorithms......34
Figure 4: Feature Importance....................................................35

Alpaydin, E. (2010). Introduction to machine learning 2nd ed. In: Cambridge, Mass.: MIT Press.
Anderson, A. E., Kerr, W. T., Thames, A., Li, T., Xiao, J., & Cohen, M. S. (2016). Electronic health record phenotyping improves detection and screening of type 2 diabetes in the general United States population: A cross-sectional, unselected, retrospective study. Journal of biomedical informatics, 60, 162-168.
Anguita, D., Ghelardoni, L., Ghio, A., Oneto, L., & Ridella, S. (2012). The ‘K’in K-fold cross validation. Paper presented at the 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN).
Appelros, P., Nydevik, I., Seiger, A., & Terént, A. (2002). Predictors of severe stroke: influence of preexisting dementia and cardiac disorders. Stroke, 33(10), 2357-2362.
Arbabshirani, M. R., Fornwalt, B. K., Mongelluzzo, G. J., Suever, J. D., Geise, B. D., Patel, A. A., & Moore, G. J. (2018). Advanced machine learning in action: identification of intracranial hemorrhage on computed tomography scans of the head with clinical workflow integration. NPJ digital medicine, 1(1), 1-7.
Arboix, A., Rivas, A., García-Eroles, L., de Marcos, L., Massons, J., & Oliveres, M. (2005). Cerebral infarction in diabetes: clinical pattern, stroke subtypes, and predictors of in-hospital mortality. BMC neurology, 5(1), 1-9.
Association, A. D. (2019). 2. Classification and diagnosis of diabetes: standards of medical care in diabetes—2019. Diabetes care, 42(Supplement_1), S13-S28.
Austin, P. C. (2011). An Introduction to Propensity Score Methods for Reducing the Effects of Confounding in Observational Studies. Multivariate Behavioral Research, 46(3), 399-424. doi:10.1080/00273171.2011.568786
Bazzano, L. A., Gu, D., Whelton, M. R., Wu, X., Chen, C.-S., Duan, X., . . . He, J. (2010). Body mass index and risk of stroke among Chinese men and women. Annals of neurology, 67(1), 11-20. doi:10.1002/ana.21950
Bentley, P., Ganesalingam, J., Jones, A. L. C., Mahady, K., Epton, S., Rinne, P., . . . Rueckert, D. (2014). Prediction of stroke thrombolysis outcome using CT brain machine learning. NeuroImage: Clinical, 4, 635-640.
Bogardus, C., Lillioja, S., Mott, D., Hollenbeck, C., & Reaven, G. (1985). Relationship between degree of obesity and in vivo insulin action in man. American Journal of Physiology-Endocrinology And Metabolism, 248(3), E286-E291.
Bolin, E., & Lam, W. (2013). A review of sensitivity, specificity, and likelihood ratios: evaluating the utility of the electrocardiogram as a screening tool in hypertrophic cardiomyopathy. Congenit Heart Dis, 8(5), 406-410. doi:10.1111/chd.12083
Campbell, B. C., Mitchell, P. J., Kleinig, T. J., Dewey, H. M., Churilov, L., Yassi, N., . . . Oxley, T. J. (2015). Endovascular therapy for ischemic stroke with perfusion-imaging selection. New England journal of medicine, 372(11), 1009-1018.
Chaudhary, A., Kolhe, S., & Kamal, R. (2016). An improved random forest classifier for multi-class classification. Information Processing in Agriculture, 3(4), 215-222.
Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002). SMOTE: synthetic minority over-sampling technique. Journal of artificial intelligence research, 16, 321-357.
Chen, R., Ovbiagele, B., & Feng, W. (2016). Diabetes and stroke: epidemiology, pathophysiology, pharmaceuticals and outcomes. The American journal of the medical sciences, 351(4), 380-386.
Chen, R., Ovbiagele, B., & Feng, W. (2016). Diabetes and Stroke: Epidemiology, Pathophysiology, Pharmaceuticals and Outcomes. Am J Med Sci, 351(4), 380-386. doi:10.1016/j.amjms.2016.01.011
Chen, T., & Guestrin, C. (2016). Xgboost: A scalable tree boosting system. Paper presented at the Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining.
Chen, X., Wang, Z.-X., & Pan, X.-M. (2019). HIV-1 tropism prediction by the XGboost and HMM methods. Scientific reports, 9(1), 1-8.
Chung, J. W., Kim, Y. C., Cha, J., Choi, E. H., Kim, B. M., Seo, W. K., . . . Bang, O. Y. (2019). Characterization of clot composition in acute cerebral infarct using machine learning techniques. Annals of clinical and translational neurology, 6(4), 739-747.
De Waard, D., de Borst, G., Bulbulia, R., Huibers, A., & Halliday, A. (2017). Diastolic blood pressure is a risk factor for peri-procedural stroke following carotid endarterectomy in asymptomatic patients. European Journal of Vascular and Endovascular Surgery, 53(5), 626-631.
DeFronzo, R. A., Tobin, J. D., & Andres, R. (1979). Glucose clamp technique: a method for quantifying insulin secretion and resistance. American Journal of Physiology-Endocrinology And Metabolism, 237(3), E214.
Dengler, N. F., Madai, V. I., Unteroberdörster, M., Zihni, E., Brune, S. C., Hilbert, A., . . . Frey, D. (2021). Outcome prediction in aneurysmal subarachnoid hemorrhage: a comparison of machine learning methods and established clinico-radiological scores. Neurosurgical Review, 1-10.
Dhar, R., Chen, Y., An, H., & Lee, J.-M. (2018). Application of machine learning to automated analysis of cerebral edema in large cohorts of ischemic stroke patients. Frontiers in neurology, 9, 687.
Du, T., Yuan, G., Zhang, M., Zhou, X., Sun, X., & Yu, X. (2014). Clinical usefulness of lipid ratios, visceral adiposity indicators, and the triglycerides and glucose index as risk markers of insulin resistance. Cardiovascular diabetology, 13(1), 1-10.
Feigin, V. L., Forouzanfar, M. H., Krishnamurthi, R., Mensah, G. A., Connor, M., Bennett, D. A., . . . Truelsen, T. (2014). Global and regional burden of stroke during 1990–2010: findings from the Global Burden of Disease Study 2010. The lancet, 383(9913), 245-255.
Feigin, V. L., Nichols, E., Alam, T., Bannick, M. S., Beghi, E., Blake, N., . . . Ellenbogen, R. G. (2019). Global, regional, and national burden of neurological disorders, 1990–2016: a systematic analysis for the Global Burden of Disease Study 2016. The Lancet Neurology, 18(5), 459-480.
Fekadu, G., Chelkeba, L., & Kebede, A. (2019). Risk factors, clinical presentations and predictors of stroke among adult patients admitted to stroke unit of Jimma university medical center, south west Ethiopia: prospective observational study. BMC neurology, 19(1), 187-187. doi:10.1186/s12883-019-1409-0
Feng, R., Badgeley, M., Mocco, J., & Oermann, E. K. (2018). Deep learning guided stroke management: a review of clinical applications. Journal of neurointerventional surgery, 10(4), 358-362.
Fernandez-Lozano, C., Hervella, P., Mato-Abad, V., Rodríguez-Yáñez, M., Suárez-Garaboa, S., López-Dequidt, I., . . . Castillo, J. (2021). Random forest-based prediction of stroke outcome. Scientific reports, 11(1), 1-12.
Fitzgibbons, T. P., & Czech, M. P. (2016). Emerging evidence for beneficial macrophage functions in atherosclerosis and obesity-induced insulin resistance. Journal of Molecular Medicine, 94(3), 267-275.
Géron, A. (2019). Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow: Concepts, tools, and techniques to build intelligent systems: O'Reilly Media.
Giorda, C. B., Avogaro, A., Maggini, M., Lombardo, F., Mannucci, E., Turco, S., . . . Ferrannini, E. (2007). Incidence and risk factors for stroke in type 2 diabetic patients: the DAI study. Stroke, 38(4), 1154-1160.
Glaros, A. G., & Kline, R. B. (1988). Understanding the accuracy of tests with cutting scores: the sensitivity, specificity, and predictive value model. J Clin Psychol, 44(6), 1013-1023. doi:10.1002/1097-4679(198811)44:6<1013::aid-jclp2270440627>3.0.co;2-z
Goutte, C., & Gaussier, E. (2005, 2005//). A Probabilistic Interpretation of Precision, Recall and F-Score, with Implication for Evaluation. Paper presented at the Advances in Information Retrieval, Berlin, Heidelberg.
Guerrero-Romero, F., Simental-Mendía, L. E., González-Ortiz, M., Martínez-Abundis, E., Ramos-Zavala, M. G., Hernández-González, S. O., . . . Rodríguez-Morán, M. (2010). The product of triglycerides and glucose, a simple measure of insulin sensitivity. Comparison with the euglycemic-hyperinsulinemic clamp. The Journal of Clinical Endocrinology & Metabolism, 95(7), 3347-3351.
Guerrero-Romero, F., Villalobos-Molina, R., Jiménez-Flores, J. R., Simental-Mendia, L. E., Méndez-Cruz, R., Murguía-Romero, M., & Rodríguez-Morán, M. (2016). Fasting triglycerides and glucose index as a diagnostic test for insulin resistance in young adults. Archives of medical research, 47(5), 382-387.
Guyon, I., & Elisseeff, A. (2003). An introduction to variable and feature selection. Journal of machine learning research, 3(Mar), 1157-1182.
Hacke, W., Kaste, M., Bluhmki, E., Brozman, M., Dávalos, A., Guidetti, D., . . . Machnig, T. (2008). Thrombolysis with alteplase 3 to 4.5 hours after acute ischemic stroke. New England journal of medicine, 359(13), 1317-1329.
Hankey, G. J., Anderson, N. E., Ting, R. D., Veillard, A. S., Romo, M., Wosik, M., . . . Keech, A. C. (2013). Rates and predictors of risk of stroke and its subtypes in diabetes: a prospective observational study. J Neurol Neurosurg Psychiatry, 84(3), 281-287. doi:10.1136/jnnp-2012-303365
Hawkins, D. M. (2004). The problem of overfitting. Journal of chemical information and computer sciences, 44(1), 1-12.
Heidenreich, P. A., Trogdon, J. G., Khavjou, O. A., Butler, J., Dracup, K., Ezekowitz, M. D., . . . Woo, Y. J. (2011). Forecasting the future of cardiovascular disease in the United States: a policy statement from the American Heart Association. Circulation, 123(8), 933-944. doi:10.1161/CIR.0b013e31820a55f5
Hilsted, J., Bonde-Petersen, F., Nørgaard, M.-B., Greniman, M., Christensen, N., Parving, H.-H., & Suzuki, M. (1984). Haemodynamic changes in insulin-induced hypoglycaemia in normal man. Diabetologia, 26(5), 328-332.
Ho, K. C., Speier, W., Zhang, H., Scalzo, F., El-Saden, S., & Arnold, C. W. (2019). A machine learning approach for classifying ischemic stroke onset time from imaging. IEEE transactions on medical imaging, 38(7), 1666-1676.
Hsieh, F.-I., & Chiou, H.-Y. (2014). Stroke: morbidity, risk factors, and care in taiwan. Journal of stroke, 16(2), 59-64. doi:10.5853/jos.2014.16.2.59
Hu, H. H., Chu, F. L., Chiang, B. N., Lan, C. F., Sheng, W. Y., Lo, Y. K., . . . Luk, Y. O. (1989). Prevalence of stroke in Taiwan. Stroke, 20(7), 858-863.
Huang, Y., McCullagh, P., Black, N., & Harper, R. (2007). Feature selection and classification model construction on type 2 diabetic patients’ data. Artificial intelligence in medicine, 41(3), 251-262.
Huang, Z.-S., Chiang, T.-L., & Lee, T.-K. (1997). Stroke prevalence in Taiwan: findings from the 1994 national health interview survey. Stroke, 28(8), 1579-1584.
Irace, C., Carallo, C., Scavelli, F., De Franceschi, M., Esposito, T., Tripolino, C., & Gnasso, A. (2013). Markers of insulin resistance and carotid atherosclerosis. A comparison of the homeostasis model assessment and triglyceride glucose index. International journal of clinical practice, 67(7), 665-672.
Jin, J.-L., Cao, Y.-X., Wu, L.-G., You, X.-D., Guo, Y.-L., Wu, N.-Q., . . . Zhang, H.-W. (2018). Triglyceride glucose index for predicting cardiovascular outcomes in patients with coronary artery disease. Journal of thoracic disease, 10(11), 6137.
Kahn, S. E., Cooper, M. E., & Del Prato, S. (2014). Pathophysiology and treatment of type 2 diabetes: perspectives on the past, present, and future. The Lancet, 383(9922), 1068-1083.
Kain, K., Catto, A., & Grant, P. (2003). Associations between insulin resistance and thrombotic risk factors in high‐risk South Asian subjects. Diabetic medicine, 20(8), 651-655.
Kang, B., Yang, Y., Lee, E., Yang, H., Kim, H., Lim, S., . . . Yoon, K. (2017). Triglycerides/glucose index is a useful surrogate marker of insulin resistance among adolescents. International journal of obesity, 41(5), 789-792.
Karapanayiotides, T., Piechowski-Jozwiak, B., van Melle, G., Bogousslavsky, J., & Devuyst, G. (2004). Stroke patterns, etiology, and prognosis in patients with diabetes mellitus. Neurology, 62(9), 1558-1562. doi:10.1212/01.wnl.0000123252.55688.05
Karapanayiotides, T., Piechowski-Jozwiak, B., Van Melle, G., Bogousslavsky, J., & Devuyst, G. (2004). Stroke patterns, etiology, and prognosis in patients with diabetes mellitus. Neurology, 62(9), 1558-1562.
Kernan, W., Inzucchi, S., Viscoli, C., Brass, L., Bravata, D., Shulman, G., . . . Horwitz, R. (2003). Impaired insulin sensitivity among nondiabetic patients with a recent TIA or ischemic stroke. Neurology, 60(9), 1447-1451.
Khanam, J. J., & Foo, S. Y. (2021). A comparison of machine learning algorithms for diabetes prediction. ICT Express, 7(4), 432-439.
Khoury, J. C., Kleindorfer, D., Alwell, K., Moomaw, C. J., Woo, D., Adeoye, O., . . . Kissela, B. M. (2013). Diabetes mellitus: a risk factor for ischemic stroke in a large biracial population. Stroke, 44(6), 1500-1504. doi:10.1161/strokeaha.113.001318
Kim, M. K., Ahn, C. W., Kang, S., Nam, J. S., Kim, K. R., & Park, J. S. (2017). Relationship between the triglyceride glucose index and coronary artery calcification in Korean adults. Cardiovascular diabetology, 16(1), 1-7.
Kim, M. K., Kim, J. H., Park, K., Lee, S. B., Nam, J. S., Kang, S., . . . Kim, Y. S. (2018). Relationship between the triglyceride glucose index and the presence and fibrosis of nonalcoholic fatty liver disease in Korean adults. Diabetes, 67(Supplement_1).
Kogan, E., Twyman, K., Heap, J., Milentijevic, D., Lin, J. H., & Alberts, M. (2020). Assessing stroke severity using electronic health record data: a machine learning approach. BMC medical informatics and decision making, 20(1), 1-8.
Lai, Y. J., Hu, H. Y., Lee, Y. L., Ku, P. W., Yen, Y. F., & Chu, D. (2017). A retrospective cohort study on the risk of stroke in relation to a priori health knowledge level among people with type 2 diabetes mellitus in Taiwan. BMC Cardiovasc Disord, 17(1), 130. doi:10.1186/s12872-017-0568-4
Lao, X. Q., Guo, C., Chang, L. Y., Bo, Y., Zhang, Z., Chuang, Y. C., . . . Chan, T. C. (2019). Long-term exposure to ambient fine particulate matter (PM(2.5)) and incident type 2 diabetes: a longitudinal cohort study. Diabetologia, 62(5), 759-769. doi:10.1007/s00125-019-4825-1
Lee, E. Y., Yang, H. K., Lee, J., Kang, B., Yang, Y., Lee, S.-H., . . . Yoon, K.-H. (2016). Triglyceride glucose index, a marker of insulin resistance, is associated with coronary artery stenosis in asymptomatic subjects with type 2 diabetes. Lipids in health and disease, 15(1), 1-7.
Lee, J.-W., Lim, N.-K., & Park, H.-Y. (2018). The product of fasting plasma glucose and triglycerides improves risk prediction of type 2 diabetes in middle-aged Koreans. BMC endocrine disorders, 18(1), 1-10.
Lee, M., Saver, J. L., Hong, K. S., Song, S., Chang, K. H., & Ovbiagele, B. (2012). Effect of pre-diabetes on future risk of stroke: meta-analysis. Bmj, 344, e3564. doi:10.1136/bmj.e3564
Lee, S. B., Ahn, C. W., Lee, B. K., Kang, S., Nam, J. S., You, J. H., . . . Park, J. S. (2018). Association between triglyceride glucose index and arterial stiffness in Korean adults. Cardiovascular diabetology, 17(1), 1-6.
Lehto, S., Niskanen, L., Ronnemaa, T., & Laakso, M. (1998). Serum uric acid is a strong predictor of stroke in patients with non–insulin-dependent diabetes mellitus. Stroke, 29(3), 635-639.
Lehto, S., Rönnemaa, T., Pyörälä, K., & Laakso, M. (1996). Predictors of stroke in middle-aged patients with non–insulin-dependent diabetes. Stroke, 27(1), 63-68.
Lever, J., Krzywinski, M., & Altman, N. (2017). Principal component analysis. Nature Methods, 14(7), 641-642. doi:10.1038/nmeth.4346
Lin, C.-H., Hsu, K.-C., Johnson, K. R., Fann, Y. C., Tsai, C.-H., Sun, Y., . . . Lin, C.-L. (2020). Evaluation of machine learning methods to stroke outcome prediction using a nationwide disease registry. Computer methods and programs in biomedicine, 190, 105381.
Lin, L.-Y., Lee, C.-H., Yu, C.-C., Tsai, C.-T., Lai, L.-P., Hwang, J.-J., . . . Lin, J.-L. (2011). Risk factors and incidence of ischemic stroke in Taiwanese with nonvalvular atrial fibrillation—a nation wide database analysis. Atherosclerosis, 217(1), 292-295.
Liu, J., Wu, J., Liu, S., Li, M., Hu, K., & Li, K. (2021). Predicting mortality of patients with acute kidney injury in the ICU using XGBoost model. PloS one, 16(2), e0246306.
Liu, J., Xu, H., Chen, Q., Zhang, T., Sheng, W., Huang, Q., . . . Li, Y. (2019). Prediction of hematoma expansion in spontaneous intracerebral hemorrhage using support vector machine. EBioMedicine, 43, 454-459.
Luitse, M. J., Biessels, G. J., Rutten, G. E., & Kappelle, L. J. (2012). Diabetes, hyperglycaemia, and acute ischaemic stroke. The Lancet Neurology, 11(3), 261-271.
Lv, L., Zhou, Y., Chen, X., Gong, L., Wu, J., Luo, W., . . . Wang, Z. (2021). Relationship Between the TyG Index and Diabetic Kidney Disease in Patients with Type-2 Diabetes Mellitus. Diabetes, Metabolic Syndrome and Obesity: Targets and Therapy, Volume 14, 3299-3306. doi:10.2147/DMSO.S318255
Ma, X., Dong, L., Shao, Q., Cheng, Y., Lv, S., Sun, Y., . . . Liu, X. (2020). Triglyceride glucose index for predicting cardiovascular outcomes after percutaneous coronary intervention in patients with type 2 diabetes mellitus and acute coronary syndrome. Cardiovascular diabetology, 19(1), 1-14.
Mainali, S., Darsie, M. E., & Smetana, K. S. (2021). Machine Learning in Action: Stroke Diagnosis and Outcome Prediction. Frontiers in neurology, 2153.
Manley, S., Meyer, L., Neil, H., Ross, I., Turner, R., & Holman, R. (1990). UKPDS 6: Complications in newly diagnosed type 2 diabetic patients and their association with different clinical and biologic risk factors. Diabetes Res, 13, 1-11.
Manrique, C., Lastra, G., Gardner, M., & Sowers, J. R. (2009). The renin angiotensin aldosterone system in hypertension: roles of insulin resistance and oxidative stress. Medical Clinics of North America, 93(3), 569-582.
Mao, Q., Zhou, D., Li, Y., Wang, Y., Xu, S.-C., & Zhao, X.-H. (2019). The triglyceride-glucose index predicts coronary artery disease severity and cardiovascular outcomes in patients with non-ST-segment elevation acute coronary syndrome. Disease markers, 2019.
Meads, C., Ahmed, I., & Riley, R. D. (2012). A systematic review of breast cancer incidence risk prediction models with meta-analysis of their performance. Breast cancer research and treatment, 132(2), 365-377.
Mezzatesta, S., Torino, C., De Meo, P., Fiumara, G., & Vilasi, A. (2019). A machine learning-based approach for predicting the outbreak of cardiovascular diseases in patients on dialysis. Computer methods and programs in biomedicine, 177, 9-15.
Mitchell, T. M. (2006). The discipline of machine learning (Vol. 9): Carnegie Mellon University, School of Computer Science, Machine Learning ….
Mooy, J. M., Grootenhuis, P. A., Vries, H. d., Valkenburg, H. A., Bouter, L. M., Kostense, P. J., & Heine, R. J. (1995). Prevalence and determinants of glucose intolerance in a Dutch Caucasian population: the Hoorn Study. Diabetes care, 18(9), 1270-1273.
Mykkanen, L., KUUSISTO, J., LAAKSO, M., & Pyorala, K. (1993). Microalbuminuria precedes the development of NIDDM. Paper presented at the Diabetes.
Ni, Y., Alwell, K., Moomaw, C. J., Woo, D., Adeoye, O., Flaherty, M. L., . . . Martini, S. (2018). Towards phenotyping stroke: Leveraging data from a large-scale epidemiological study to detect stroke diagnosis. PloS one, 13(2), e0192586.
Nielsen, A., Hansen, M. B., Tietze, A., & Mouridsen, K. (2018). Prediction of tissue outcome and assessment of treatment effect in acute ischemic stroke using deep learning. Stroke, 49(6), 1394-1401.
Nogueira, R. G., Jadhav, A. P., Haussen, D. C., Bonafe, A., Budzik, R. F., Bhuva, P., . . . Hanel, R. A. (2018). Thrombectomy 6 to 24 hours after stroke with a mismatch between deficit and infarct. New England journal of medicine, 378(1), 11-21.
Okamura, T., Hashimoto, Y., Hamaguchi, M., Obora, A., Kojima, T., & Fukui, M. (2019). Triglyceride–glucose index is a predictor of incident chronic kidney disease: a population-based longitudinal study. Clinical and experimental nephrology, 23(7), 948-955.
Organization, W. H. (2017). Global diffusion of eHealth: making universal health coverage achievable: report of the third global survey on eHealth: World Health Organization.
Osawa, I., Goto, T., Yamamoto, Y., & Tsugawa, Y. (2020). Machine-learning-based prediction models for high-need high-cost patients using nationwide clinical and claims data. NPJ digital medicine, 3(1), 148. doi:10.1038/s41746-020-00354-8
Ovbiagele, B., Goldstein, L. B., Higashida, R. T., Howard, V. J., Johnston, S. C., Khavjou, O. A., . . . Sacco, R. L. (2013). Forecasting the future of stroke in the United States: a policy statement from the American Heart Association and American Stroke Association. Stroke, 44(8), 2361-2375.
Park, E., Lee, K., Han, T., & Nam, H. S. (2020). Automatic grading of stroke symptoms for rapid assessment using optimized machine learning and 4-limb kinematics: clinical validation study. Journal of Medical Internet Research, 22(9), e20641.
Park, G.-M., Cho, Y.-R., Won, K.-B., Yang, Y. J., Park, S., Ann, S. H., . . . Lee, S.-G. (2020). Triglyceride glucose index is a useful marker for predicting subclinical coronary artery disease in the absence of traditional risk factors. Lipids in health and disease, 19(1), 1-7.
Park, K., Ahn, C. W., Lee, S. B., Kang, S., Nam, J. S., Lee, B. K., . . . Park, J. S. (2019). Elevated TyG index predicts progression of coronary artery calcification. Diabetes Care, 42(8), 1569-1573.
Polonsky, K., Sturis, J., & Bell, G. (1996). Seminars in Medicine of the Beth Israel Hospital, Boston. Non-insulin-dependent diabetes mellitus-a genetically programmed failure of the beta cell to compensate for insulin resistance. The New England Journal of Medicine, 334(12), 777-783.
Powers, W. J., Rabinstein, A. A., Ackerson, T., Adeoye, O. M., Bambakidis, N. C., Becker, K., . . . Hoh, B. (2018). 2018 guidelines for the early management of patients with acute ischemic stroke: a guideline for healthcare professionals from the American Heart Association/American Stroke Association. Stroke, 49(3), e46-e99.
Powers, W. J., Rabinstein, A. A., Ackerson, T., Adeoye, O. M., Bambakidis, N. C., Becker, K., . . . Hoh, B. (2019). Guidelines for the early management of patients with acute ischemic stroke: 2019 update to the 2018 guidelines for the early management of acute ischemic stroke: a guideline for healthcare professionals from the American Heart Association/American Stroke Association. Stroke, 50(12), e344-e418.
Putaala, J., Liebkind, R., Gordin, D., Thorn, L. M., Haapaniemi, E., Forsblom, C., . . . Tatlisumak, T. (2011). Diabetes mellitus and ischemic stroke in the young: clinical features and long-term prognosis. Neurology, 76(21), 1831-1837. doi:10.1212/WNL.0b013e31821cccc2
Ramos, L. A., van der Steen, W. E., Barros, R. S., Majoie, C. B., van den Berg, R., Verbaan, D., . . . Strijkers, G. J. (2019). Machine learning improves prediction of delayed cerebral ischemia in patients with subarachnoid hemorrhage. Journal of neurointerventional surgery, 11(5), 497-502.
Rautio, A., Eliasson, M., & Stegmayr, B. (2008). Favorable trends in the incidence and outcome in stroke in nondiabetic and diabetic subjects: findings from the Northern Sweden MONICA Stroke Registry in 1985 to 2003. Stroke, 39(12), 3137-3144.
Reaven, G. (2004). The metabolic syndrome or the insulin resistance syndrome? Different names, different concepts, and different goals. Endocrinology and Metabolism Clinics, 33(2), 283-303.
Rodríguez‐Morán, M., Simental‐Mendía, L., & Guerrero‐Romero, F. (2017). The triglyceride and glucose index is useful for recognising insulin resistance in children. Acta Paediatrica, 106(6), 979-983.
Roth, G. A., Abate, D., Abate, K. H., Abay, S. M., Abbafati, C., Abbasi, N., . . . Abdelalim, A. (2018). Global, regional, and national age-sex-specific mortality for 282 causes of death in 195 countries and territories, 1980–2017: a systematic analysis for the Global Burden of Disease Study 2017. The Lancet, 392(10159), 1736-1788.
Sakr, S., Elshawi, R., Ahmed, A., Qureshi, W. T., Brawner, C., Keteyian, S., . . . Al-Mallah, M. H. (2018). Using machine learning on cardiorespiratory fitness data for predicting hypertension: The Henry Ford ExercIse Testing (FIT) Project. PloS one, 13(4), e0195344. doi:10.1371/journal.pone.0195344
Salazar, J., Bermúdez, V., Calvo, M., Olivar, L. C., Luzardo, E., Navarro, C., . . . Wilches-Durán, S. (2017). Optimal cutoff for the evaluation of insulin resistance through triglyceride-glucose index: A cross-sectional study in a Venezuelan population. F1000Research, 6.
Samuel, A. L. (1959). Some studies in machine learning using the game of checkers. IBM Journal of research and development, 3(3), 210-229.
Sánchez-Iñigo, L., Navarro-González, D., Fernández-Montero, A., Pastrana-Delgado, J., & Martínez, J. (2017). Risk of incident ischemic stroke according to the metabolic health and obesity states in the Vascular-Metabolic CUN cohort. International Journal of Stroke, 12(2), 187-191.
Sánchez‐Íñigo, L., Navarro‐González, D., Fernández‐Montero, A., Pastrana‐Delgado, J., & Martínez, J. A. (2016). The TyG index may predict the development of cardiovascular events. European journal of clinical investigation, 46(2), 189-197.
Shi, W., Xing, L., Jing, L., Tian, Y., Yan, H., Sun, Q., . . . Liu, S. (2020). Value of triglyceride-glucose index for the estimation of ischemic stroke risk: insights from a general population. Nutrition, Metabolism and Cardiovascular Diseases, 30(2), 245-253.
Simental-Mendía, L. E., Rodríguez-Morán, M., & Guerrero-Romero, F. (2008). The product of fasting glucose and triglycerides as surrogate for identifying insulin resistance in apparently healthy subjects. Metabolic syndrome and related disorders, 6(4), 299-304.
Slyper, A., Rosenberg, H., Kabra, A., Weiss, M., Blech, B., Gensler, S., & Matsumura, M. (2014). Early atherogenesis and visceral fat in obese adolescents. International journal of obesity, 38(7), 954-958.
Stumvoll, M., Goldstein, B. J., & Van Haeften, T. W. (2005). Type 2 diabetes: principles of pathogenesis and therapy. The Lancet, 365(9467), 1333-1346.
Su, J., Hu, J., Jiang, J., Xie, J., Yang, Y., He, B., . . . Guan, Y. (2019). Extraction of risk factors for cardiovascular diseases from Chinese electronic medical records. Computer methods and programs in biomedicine, 172, 1-10.
Talaei-Khoei, A., & Wilson, J. M. (2018). Identifying people at risk of developing type 2 diabetes: A comparison of predictive analytics techniques and predictor variables. International journal of medical informatics, 119, 22-38.
Tseng, C. H., Chong, C. K., Sheu, J. J., Wu, T. H., & Tseng, C. P. (2005). Prevalence and risk factors for stroke in type 2 diabetic patients in Taiwan: a cross‐sectional survey of a national sample by telephone interview. Diabetic medicine, 22(4), 477-482.
Vasques, A. C. J., Novaes, F. S., de Oliveira, M. d. S., Souza, J. R. M., Yamanaka, A., Pareja, J. C., . . . Geloneze, B. (2011). TyG index performs better than HOMA in a Brazilian population: a hyperglycemic clamp validated study. Diabetes research and clinical practice, 93(3), e98-e100.
Vazzana, N., Ranalli, P., Cuccurullo, C., & Davì, G. (2012). Diabetes mellitus and thrombosis. Thrombosis research, 129(3), 371-377.
Wang, F., Han, L., & Hu, D. (2017). Fasting insulin, insulin resistance and risk of hypertension in the general population: a meta-analysis. Clinica Chimica Acta, 464, 57-63.
Won, K.-B., Park, E. J., Han, D., Lee, J. H., Choi, S.-Y., Chun, E. J., . . . Jung, H. O. (2020). Triglyceride glucose index is an independent predictor for the progression of coronary artery calcification in the absence of heavy coronary artery calcification at baseline. Cardiovascular diabetology, 19(1), 1-8.
Won, K.-B., Park, G.-M., Lee, S.-E., Cho, I.-J., Kim, H. C., Lee, B. K., & Chang, H.-J. (2018). Relationship of insulin resistance estimated by triglyceride glucose index to arterial stiffness. Lipids in health and disease, 17(1), 1-6.
Wu, J., Roy, J., & Stewart, W. F. (2010). Prediction modeling using EHR data: challenges, strategies, and a comparison of machine learning approaches. Medical care, S106-S113.
Wu, X., Tsai, S. P., Tsao, C. K., Chiu, M. L., Tsai, M. K., Lu, P. J., . . . Wen, C. P. (2017). Cohort Profile: The Taiwan MJ Cohort: half a million Chinese with repeated health surveillance data. Int J Epidemiol, 46(6), 1744-1744g. doi:10.1093/ije/dyw282
Yan, Z., Yu, D., Cai, Y., Shang, J., Qin, R., Xiao, J., . . . Simmons, D. (2019). Triglyceride glucose index predicting cardiovascular mortality in Chinese initiating peritoneal dialysis: a cohort study. Kidney and Blood Pressure Research, 44(4), 669-678.
Yang, Y., Zheng, J., Du, Z., Li, Y., & Cai, Y. (2021). Accurate Prediction of Stroke for Hypertensive Patients Based on Medical Big Data and Machine Learning Algorithms: Retrospective Study. JMIR Medical Informatics, 9(11), e30277.
Yu, Y., Xie, Y., Thamm, T., Gong, E., Ouyang, J., Huang, C., . . . Albers, G. W. (2020). Use of deep learning to predict final ischemic stroke lesions from initial magnetic resonance imaging. JAMA network open, 3(3), e200772-e200772.
Zhang, S., Du, T., Zhang, J., Lu, H., Lin, X., Xie, J., . . . Yu, X. (2017). The triglyceride and glucose index (TyG) is an effective biomarker to identify nonalcoholic fatty liver disease. Lipids in health and disease, 16(1), 1-8.
Zheng, H., Yuan, J., & Chen, L. (2017). Short-term load forecasting using EMD-LSTM neural networks with a Xgboost algorithm for feature importance evaluation. Energies, 10(8), 1168.
Zheng, R., & Mao, Y. (2017). Triglyceride and glucose (TyG) index as a predictor of incident hypertension: a 9-year longitudinal population-based study. Lipids in health and disease, 16(1), 1-7.
Zhou, M.-S., Wang, A., & Yu, H. (2014). Link between insulin resistance and hypertension: What is the evidence from evolutionary biology? Diabetology & metabolic syndrome, 6(1), 1-8.
Zhou, Y., Pan, Y., Yan, H., Wang, Y., Li, Z., Zhao, X., . . . Liu, L. (2020). Triglyceride glucose index and prognosis of patients with ischemic stroke. Frontiers in neurology, 11, 456.
Zhou, Y., Pan, Y., Yan, H., Wang, Y., Li, Z., Zhao, X., . . . Wang, Y. (2020). Triglyceride Glucose Index and Prognosis of Patients With Ischemic Stroke. Frontiers in neurology, 11, 456-456. doi:10.3389/fneur.2020.00456
Zhu, B., Wang, J., Chen, K., Yan, W., Wang, A., Wang, W., . . . Wan, Q. (2020). A high triglyceride glucose index is more closely associated with hypertension than lipid or glycemic parameters in elderly individuals: a cross-sectional survey from the reaction study. Cardiovascular diabetology, 19(1), 1-16.
Zimmet, P., Alberti, K., & Shaw, J. (2001). Global and societal implications of the diabetes epidemic. Nature, 414(6865), 782-787.