English  |  正體中文  |  简体中文  |  Post-Print筆數 : 27 |  Items with full text/Total items : 118199/149231 (79%)
Visitors : 74194808      Online Users : 426
RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Tips:
  • please add "double quotation mark" for query phrases to get precise results
  • please goto advance search for comprehansive author search
    •  Adv. Search
    Home ‧ Login ‧ Upload ‧ Help ‧ About ‧ Administer Goto mobile version


    Please use this identifier to cite or link to this item: https://nccur.lib.nccu.edu.tw/handle/140.119/159295


    Title: 基於多族裔相關疾病特徵之非糖尿病人群胰島素阻抗預測及表觀遺傳學關聯性的橫斷面研究
    A Cross-Sectional Study on the Prediction of Insulin Resistance Based on Multi-Ethnic Disease-Related Features and Its Epigenetic Associations in a Non-Diabetic Population
    Authors: 王世儒
    Wang, Shih-Ju
    Contributors: 張家銘
    Chang, Jia-Ming
    王世儒
    Wang, Shih-Ju
    Keywords: 胰島素阻抗
    機器學習
    美國國家健康營養調查 (NHANES)
    韓國國家健康營養調查 (KNHANES)
    臺灣人體生物資料庫 (TWB)
    DNA甲基化
    COL25A1
    PSMA6
    ERV3-1
    Insulin resistance
    Machine learning
    National Health and Nutrition Examination Survey (NHANES)
    Korea National Health and Nutrition Examination Survey (KNHANES)
    Taiwan Biobank (TWB)
    DNA methylation
    COL25A1
    PSMA6
    ERV3-1
    Date: 2025
    Issue Date: 2025-09-01 16:19:03 (UTC+8)
    Abstract: 目的：本研究旨在改進預測非糖尿病人群胰島素阻抗 (IR) 的機器學習模型，並探索相關的潛在 DNA 甲基化差異位點。

    方法：利用美國國家健康營養調查 (NHANES) 及韓國國家健康營養調查 (KNHANES) 資料進行模型訓練與測試，並以臺灣人體生物資料庫 (TWB) 進行外部驗證及 DNA 甲基化差異分析。整合相關疾病評估指標與常規代謝指標建立預測模型，採用基於梯度提升框架方法，並運用SHAP (Shapley Additive Explanations) 值分析變數對預測結果的影響。最後，我們參考差異表達分析方法及火山圖 (volcano plot) 探索 DNA 甲基化差異位點。

    結果：與先前研究相比，本研究模型維持相同 ROC AUC (0.88)，但敏感度由 0.64 提升至 0.785、陰性預測值 (Negative predictive value, NPV) 由 0.83 提升至 0.874，對樣本的 IR 狀態有更佳的識別及排除診斷能力。SHAP 分析確認肝功能指標 (SGOT/SGPT) 對預測有顯著的影響，證實代謝功能障礙相關脂肪性肝病 (MASLD) 與 IR 的關聯；DNA 甲基化分析發現 22 個顯著變異位點，涉及 12 個基因，部分位點與 IR 或代謝疾病相關且甲基化水準方向亦與過去研究一致，並證實位點 cg22266749 的高甲基化與胰島素阻抗及阿茲海默症(Alzheimer’s disease, AD) 的致病風險存在高度一致性。

    結論：本研究成功開發具有良好泛化能力的 IR 預測模型，並證實整合跨族裔資料及納入多元疾病特徵可提升模型表現。DNA 甲基化分析識別的差異位點為理解胰島素阻抗病理機制提供新方向，具重要臨床應用價值。
    Objective: To improve a machine learning model for predicting insulin resistance (IR) in non-diabetic populations and to explore potential differentially methylated sites associated with IR.

    Methods: We utilized data from the National Health and Nutrition Examination Survey (NHANES) and the Korean National Health and Nutrition Examination Survey (KNHANES) for model training and testing, and used the Taiwan Biobank (TWB) for external validation and differential DNA methylation analysis. We integrated relevant disease indicators with routine metabolic parameters to build prediction models based on gradient boosting frameworks, and used SHAP (Shapley Additive Explanations) values to analyze the influence of variables on prediction outcomes. Finally, we explored differential DNA methylation sites using differential expression analysis methods and visualized them with a volcano plot.

    Results: Compared to previous research, our model maintained the same ROC AUC (0.88) but improved sensitivity from 0.64 to 0.785, and negative predictive value (NPV) from 0.83 to 0.874, demonstrating better identification and differential diagnosis for IR status in samples. SHAP analysis confirmed that liver function indicators (SGOT/SGPT) had a significant impact on the predictions, supporting the association between Metabolic Dysfunction-Associated Steatotic Liver Disease (MASLD) and IR. DNA methylation analysis identified 22 significantly different sites involving 12 genes. Some of these sites were related to IR or metabolic diseases, and their methylation levels showed directional patterns consistent with previous studies. Furthermore, the analysis confirmed that hypermethylation at site cg22266749 showed high consistency with insulin resistance and the pathogenic risk of Alzheimer's disease (AD).

    Conclusion: This study successfully developed an IR prediction model with good generalization ability and demonstrated that integrating cross-ethnic data and including diverse disease features could enhance model performance. The differential sites identified through DNA methylation analysis offer new insights into the pathological mechanisms of IR and may have important clinical implications.
    Reference: [1] International Diabetes Federation. IDF Atlas 10th edition; 2021. Online; accessed 26 February 2025. https://diabetesatlas.org/.

    [2] National Institute of Diabetes and Digestive and Kidney Diseases. Insulin Resistance and Prediabetes; 2018. Online; accessed 26 February 2025. https://www.niddk.nih.gov/health-information/diabetes/overview/ what-is-diabetes/prediabetes-insulin-resistance#insulinresistance.

    [3] Wilcox G. Insulin and insulin resistance. Clin Biochem Rev. 2005 May;26(2):19-39.

    [4] Raygor V, Abbasi F, Lazzeroni L, Kim S, Ingelsson E, Reaven G, et al. Impact of race/ethnicity on insulin resistance and hypertriglyceridaemia. Diab Vasc Dis Res. 2019 Mar;16(2):153-9.

    [5] Kodama K, Tojjar D, Yamada S, Toda K, Patel C, Butte A. Ethnic differences in the relationship between insulin sensitivity and insulin response: a systematic review and meta-analysis. Diabetes Care. 2013 Jun;36(6):1789-96.

    [6] Fujimoto W. Overview of non-insulin-dependent diabetes mellitus (NIDDM) in different population groups. Diabet Med. 1996 Sep;13(9 Suppl 6):S7-10.

    [7] Park S, Kim C, Wu X. Development and Validation of an Insulin Resistance Predicting Model Using a Machine-Learning Approach in a Population-Based Cohort in Korea. Diagnostics (Basel). 2022 Jan;12(1):212.

    [8] Zhang S, Wang X, Li J, Wang X, Wang Y, Zhang Y, et al. Establishment and Validation of a New Predictive Model for Insulin Resistance based on 2 Chinese Cohorts: A Cross-Sectional Study. Int J Endocrinol. 2022 Oct;2022:8968793.

    [9] Tsai S, Yang C, Liu W, Lee C. Development and validation of an insulin resistance model for a population without diabetes mellitus and its clinical implication: a prospective cohort study. EClinicalMedicine. 2023 Apr;58:101934.

    [10] Li M, Chi X, Wang Y, Setrerrahmane S, Xie W, Xu H. Trends in insulin resistance: insights into mechanisms and therapeutic strategy. Signal Transduct Target Ther. 2022 Jul;7(1):216.

    [11] Liu C, Shao M, Lu L, Zhao C, Qiu L, Liu Z. Obesity, insulin resistance and their interaction on liver enzymes. PLoS One. 2021 Apr;16(4):e0249299.

    [12] Gu S, Wang A, Ning G, Zhang L, Mu Y. Insulin resistance is associated with urinary albumin-creatinine ratio in normal weight individuals with hypertension and diabetes: The REACTION study. J Diabetes. 2020 May;12(5):406-16.

    [13] Lee J, Hwang I, Ahn H. Association between blood urea nitrogen-to-creatinine ratio and insulin sensitivity. Diabetes Metab. 2024 Mar;50(2):101521.

    [14] Zhu Y, Hu Y, Huang T, Zhang Y, Li Z, Luo C, et al. High uric acid directly inhibits insulin signalling and induces insulin resistance. Biochem Biophys Res Commun. 2014 May;447(4):707-14.

    [15] Ferrannini E, Buzzigoli G, Bonadonna R, Giorico M, Oleggini M, Graziadei L, et al. Insulin resistance in essential hypertension. N Engl J Med. 1987 Aug;317(6):350-7.

    [16] Cheng Y, Tsao Y, Tzeng I, Chuang H, Li W, Tung T, et al. Body mass index and waist circumference are better predictors of insulin resistance than total body fat percentage in middle-aged and elderly Taiwanese. Medicine (Baltimore). 2017 Sep;96(39):e8126.

    [17] Dannecker C, Wagner R, Peter A, Hummel J, Vosseler A, Häring H, et al. Low-Density Lipoprotein Cholesterol Is Associated With Insulin Secretion. J Clin Endocrinol Metab. 2021 May;106(6):1576-84.

    [18] Rönn T, Ling C. DNA methylation as a diagnostic and therapeutic target in the battle against Type 2 diabetes. Epigenomics. 2015;7(3):451-60.

    [19] Zhao J, Goldberg J, Bremner J, Vaccarino V. Global DNA methylation is associated with insulin resistance: a monozygotic twin study. Diabetes. 2012 Feb;61(2):542-6.

    [20] Crujeiras A, Diaz-Lagares A, Moreno-Navarrete J, Sandoval J, Hervas D, Gomez A, et al. Genome-wide DNA methylation pattern in visceral adipose tissue differentiates insulin-resistant from insulin-sensitive obese subjects. Transl Res. 2016 Dec;178:13- 24.e5.

    [21] Centers for Disease Control and Prevention (CDC). About NHANES; 2024. Online; accessed 26 February 2025. https://www.cdc.gov/nchs/nhanes/about/index. html.

    [22] National Center for Health Statistics (NCHS). Sample Design; 2024. Online; accessed 26 February 2025. https://wwwn.cdc.gov/nchs/nhanes/tutorials/ sampledesign.aspx.

    [23] Kweon S, Kim Y, Jang M, Kim Y, Kim K, Choi S, et al. Data resource profile: the Korea National Health and Nutrition Examination Survey (KNHANES). Int J Epidemiol. 2014 Feb;43(1):69-77.

    [24] Feng Y, Chen C, Chen T, Kuo P, Hsu Y, Yang H, et al. Taiwan Biobank: A rich biomedical research database of the Taiwanese population. Cell Genom. 2022 Oct;2(11):100197.

    [25] Melgarejo J, Yang W, Thijs L, Li Y, Asayama K, Hansen T, et al. Association of Fatal and Nonfatal Cardiovascular Outcomes With 24-Hour Mean Arterial Pressure. Hypertension. 2021 Jan;77(1):39-48.

    [26] Wang H, Lo SH, Zheng T, Hu I. Interaction-based feature selection and classification for high-dimensional biological data. Bioinformatics. 2012 Nov;28(21):2834-42.

    [27] Oh S. Feature Interaction in Terms of Prediction Performance. Applied Sciences. 2019;9(23). Available from: https://www.mdpi.com/2076-3417/9/23/5191.

    [28] Shachar N, Mitelpunkt A, Kozlovski T, Galili T, Frostig T, Brill B, et al. The Importance of Nonlinear Transformations Use in Medical Data Analysis. JMIR Medical Informatics. 2018;6(2):e27.

    [29] Matthews D, Hosker J, Rudenski A, Naylor B, Treacher D, Turner R. Homeostasis model assessment: insulin resistance and beta-cell function from fasting plasma glucose and insulin concentrations in man. Diabetologia. 1985 Jul;28(7):412-9.

    [30] Wang Y, Gorrie-Stone T, Grant O, Andrayas A, Zhai X, McDonald-Maier K, et al. InterpolatedXY: a two-step strategy to normalize DNA methylation microarray data avoiding sex bias. Bioinformatics. 2022 Aug;38(16):3950-7.

    [31] Wang Y, Hannon E, Grant O, Gorrie-Stone T, Kumari M, Mill J, et al. DNA methylation-based sex classifier to predict sex and identify sex chromosome aneuploidy. BMC Genomics. 2021 Jun;22(1):484.

    [32] Chen T, Guestrin C. XGBoost: A Scalable Tree Boosting System. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. KDD ’16. New York, NY, USA: Association for Computing Machinery; 2016. p. 785–794. Available from: https://doi.org/10.1145/2939672. 2939785.

    [33] Ke G, Meng Q, Finley T, Wang T, Chen W, Ma W, et al. LightGBM: a highly efficient gradient boosting decision tree. In: Proceedings of the 31st International Conference on Neural Information Processing Systems. NIPS’17. Red Hook, NY, USA: Curran Associates Inc.; 2017. p. 3149–3157.

    [34] Prokhorenkova L, Gusev G, Vorobev A, Dorogush AV, Gulin A. CatBoost: unbiased boosting with categorical features. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems. NIPS’18. Red Hook, NY, USA: Curran Associates Inc.; 2018. p. 6639–6649.

    [35] Snoek J, Larochelle H, Adams RP. Practical Bayesian Optimization of Machine Learning Algorithms. In: Pereira F, Burges CJ, Bottou L, Weinberger KQ, editors. Advances in Neural Information Processing Systems. vol. 25. Curran Associates, Inc.; 2012. Available from: https://proceedings.neurips.cc/paper_files/paper/ 2012/file/05311655a15b75fab86956663e1819cd-Paper.pdf.

    [36] Shapley LS. Notes on the N-Person Game —II: The Value of an N-Person Game. Santa Monica, CA: RAND Corporation; 1951.

    [37] Lundberg SM, Erion G, Chen H, DeGrave A, Prutkin JM, Nair B, et al. From local explanations to global understanding with explainable AI for trees. Nature Machine Intelligence. 2020;2(1):2522-5839.

    [38] Youden WJ. Index for rating diagnostic tests. Cancer. 1950;3(1):32-5. Available from: https://acsjournals.onlinelibrary.wiley.com/doi/abs/10.1002/ 1097-0142(1950)3%3A1<32%3A%3AAID-CNCR2820030106>3.0.CO%3B2-3.

    [39] Cui X, Churchill G. Statistical tests for differential expression in cDNA microarray experiments. Genome Biol. 2003;4(4):210.

    [40] Benjamini Y, Hochberg Y. Controlling the False Discovery Rate: A Practical and Powerful Approach to Multiple Testing. Journal of the Royal Statistical Society: Series B (Methodological). 2018 12;57(1):289-300. Available from: https://doi. org/10.1111/j.2517-6161.1995.tb02031.x.

    [41] Saudek C, Brick J. The clinical use of hemoglobin A1c. J Diabetes Sci Technol. 2009 Jul;3(4):629-34.

    [42] Ference B, Ginsberg H, Graham I, Ray K, Packard C, Bruckert E, et al. Low-density lipoproteins cause atherosclerotic cardiovascular disease. 1. Evidence from genetic, epidemiologic, and clinical studies. A consensus statement from the European Atherosclerosis Society Consensus Panel. Eur Heart J. 2017 Aug;38(32):2459- 72.

    [43] Hall P, Cash J. What is the real function of the liver ’function’ tests? Ulster Med J. 2012 Jan;81(1):30-6.

    [44] Williams A, Hoofnagle J. Ratio of serum aspartate to alanine aminotransferase in chronic hepatitis. Relationship to cirrhosis. Gastroenterology. 1988 Sep;95(3):734-9.

    [45] Xuan Y, Wu D, Zhang Q, Yu Z, Yu J, Zhou D. Elevated ALT/AST ratio as a marker for NAFLD risk and severity: insights from a cross-sectional analysis in the United States. Front Endocrinol (Lausanne). 2024 Aug;15:1457598.

    [46] Esteghamati A, Noshad S, Khalilzadeh O, Khalili M, Zandieh A, Nakhjavani M. Insulin resistance is independently associated with liver aminotransferases in diabetic patients without ultrasound signs of nonalcoholic fatty liver disease. Metab Syndr Relat Disord. 2011 Apr;9(2):111-7.

    [47] Kawamoto R, Kohara K, Kusunoki T, Tabara Y, Abe M, Miki T. Alanine aminotransferase/ aspartate aminotransferase ratio is the best surrogate marker for insulin resistance in non-obese Japanese adults. Cardiovasc Diabetol. 2012 Oct;11:117.

    [48] Visaria A, Pai S, Cheung M, Ahlawat S. Association between aspartate aminotransferase-to-alanine aminotransferase ratio and insulin resistance among US adults. Eur J Gastroenterol Hepatol. 2022 Mar;34(3):316-23.

    [49] Han S, Seo M, Lee T, Kim M. Effectiveness of the ALT/AST ratio for predicting insulin resistance in a Korean population: A large-scale, cross-sectional cohort study. PLoS One. 2024 May;19(5):e0303333.

    [50] Iwani N, Jalaludin M, Zin R, Fuziah M, Hong J, Abqariyah Y, et al. Triglyceride to HDL-C Ratio is Associated with Insulin Resistance in Overweight and Obese Children. Sci Rep. 2017 Jan;7:40055.

    [51] Chiang J, Lai N, Chang J, Koo M. Predicting insulin resistance using the triglyceride-to-high-density lipoprotein cholesterol ratio in Taiwanese adults. Cardiovasc Diabetol. 2011 Oct;10:93.

    [52] McLaughlin T, Abbasi F, Cheal K, Chu J, Lamendola C, Reaven G. Use of metabolic markers to identify overweight individuals who are insulin resistant. Ann Intern Med. 2003 Nov;139(10):802-9.

    [53] McLaughlin T, Reaven G, Abbasi F, Lamendola C, Saad M, Waters D, et al. Is there a simple way to identify insulin-resistant individuals at increased risk of cardiovascular disease? Am J Cardiol. 2005 Aug;96(3):399-404.

    [54] Cohen J. Statistical Power Analysis for the Behavioral Sciences. Routledge; 1988.

    [55] Reaven G. Banting lecture 1988. Role of insulin resistance in human disease. Diabetes. 1988 Dec;37(12):1595-607.

    [56] Goldfarb T, Kodali VK, Pujar S, Brover V, Robbertse B, Farrell CM, et al. NCBI RefSeq: reference sequence standards through 25 years of curation and annotation. Nucleic Acids Research. 2025 Jan;53(D1):D243-57.

    [57] Tong Y, Xu Y, Scearce-Levie K, Ptácek L, Fu Y. COL25A1 triggers and promotes Alzheimer’s disease-like pathology in vivo. Neurogenetics. 2010 Feb;11(1):41-52.

    [58] Pellegrini C, Pirazzini C, Sala C, Sambati L, Yusipov I, Kalyakulina A, et al. A Meta-Analysis of Brain DNA Methylation Across Sex, Age, and Alzheimer’s Disease Points for Accelerated Epigenetic Aging in Neurodegeneration. Front Aging Neurosci. 2021 Mar;13:639428.

    [59] Breijyeh Z, Karaman R. Comprehensive Review on Alzheimer’s Disease: Causes and Treatment. Molecules. 2020 Dec;25(24):5789.

    [60] Sędzikowska A, Szablewski L. Insulin and Insulin Resistance in Alzheimer’s Disease. International Journal of Molecular Sciences. 2021 Sep;22(18):9987.

    [61] Kang T, Boland B, Jensen P, Alarcon C, Nawrocki A, Grimsby J, et al. Characterization of Signaling Pathways Associated with Pancreatic β-cell Adaptive Flexibility in Compensation of Obesity-linked Diabetes in db/db Mice. Mol Cell Proteomics. 2020 Jun;19(6):971-93.

    [62] Svikle Z, Paramonova N, Siliņš E, Pahirko L, Zariņa L, Baumane K, et al. DNA Methylation Profiles of PSMA6, PSMB5, KEAP1, and HIF1A Genes in Patients with Type 1 Diabetes and Diabetic Retinopathy. Biomedicines. 2024 Jun;12(6):1354.

    [63] Clark J, Podsiadło K, Sobalska-Kwapis M, Marciniak B, Rydzewska K, Ciechanowicz A, et al. rs67047829 genotypes of ERV3-1/ZNF117 are associated with lower body mass index in the Polish population. Sci Rep. 2023 Oct;13(1):17118.

    [64] MacCalman A, De Franco E, Franklin A, Flaxman C, Richardson S, Murrall K, et al. Developmentally dynamic changes in DNA methylation in the human pancreas. BMC Genomics. 2024 Jun;25(1):553.

    [65] Yong H, Toledo M, Nowakowski R, Wang Y. Sex Differences in the Molecular Programs of Pancreatic Cells Contribute to the Differential Risks of Type 2 Diabetes. Endocrinology. 2022 Oct;163(11):bqac156.
    Description: 碩士
    國立政治大學
    資訊科學系碩士在職專班
    112971006
    Source URI: http://thesis.lib.nccu.edu.tw/record/#G0112971006
    Data Type: thesis
    Appears in Collections:[資訊科學系碩士在職專班] 學位論文

    Files in This Item:

    File Description SizeFormat
    100601.pdf1829KbAdobe PDF0View/Open


    All items in 政大典藏 are protected by copyright, with all rights reserved.


    社群 sharing

    著作權政策宣告 Copyright Announcement
    1.本網站之數位內容為國立政治大學所收錄之機構典藏，無償提供學術研究與公眾教育等公益性使用，惟仍請適度，合理使用本網站之內容，以尊重著作權人之權益。商業上之利用，則請先取得著作權人之授權。
    The digital content of this website is part of National Chengchi University Institutional Repository. It provides free access to academic research and public education for non-commercial use. Please utilize it in a proper and reasonable manner and respect the rights of copyright owners. For commercial use, please obtain authorization from the copyright owner in advance.

    2.本網站之製作，已盡力防止侵害著作權人之權益，如仍發現本網站之數位內容有侵害著作權人權益情事者，請權利人通知本網站維護人員(nccur@nccu.edu.tw)，維護人員將立即採取移除該數位著作等補救措施。
    NCCU Institutional Repository is made to protect the interests of copyright owners. If you believe that any material on the website infringes copyright, please contact our staff(nccur@nccu.edu.tw). We will remove the work from the repository and investigate your claim.
    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback