Einzeltreffer — DigiBib

Type II diabetes mellitus (T2DM) is a rising global health burden due to its rapidly increasing prevalence worldwide, and can result in serious complications. Therefore, it is of utmost importance to identify individuals at risk as early as possible to avoid long-term T2DM complications. In this study, we developed an interpretable machine learning model leveraging baseline levels of biomarkers of oxidative stress (OS), inflammation, and mitochondrial dysfunction (MD) for identifying individuals at risk of developing T2DM. In particular, Isolation Forest (iForest) was applied as an anomaly detection algorithm to address class imbalance. iForest was trained on the control group data to detect cases of high risk for T2DM development as outliers. Two iForest models were trained and evaluated through ten-fold cross-validation, the first on traditional biomarkers (BMI, blood glucose levels (BGL) and triglycerides) alone and the second including the additional aforementioned biomarkers. The second model outperformed the first across all evaluation metrics, particularly for F1 score and recall, which were increased from 0.61 ± 0.05 to 0.81 ± 0.05 and 0.57 ± 0.06 to 0.81 ± 0.08, respectively. The feature importance scores identified a novel combination of biomarkers, including interleukin-10 (IL-10), 8-isoprostane, humanin (HN), and oxidized glutathione (GSSG), which were revealed to be more influential than the traditional biomarkers in the outcome prediction. These results reveal a promising method for simultaneously predicting and understanding the risk of T2DM development and suggest possible pharmacological intervention to address inflammation and OS early in disease progression.

Titel:	Exploratory risk prediction of type II diabetes with isolation forests and novel biomarkers.
Autor/in / Beteiligte Person:	Yousef, H ; Feng, SF ; Jelinek, HF
Link:	Full Text Finder (Volltext)
Zeitschrift:	Scientific reports, Jg. 14 (2024-06-22), Heft 1, S. 14409
Veröffentlichung:	London : Nature Publishing Group, copyright 2011-, 2024
Medientyp:	academicJournal
ISSN:	2045-2322 (electronic)
DOI:	10.1038/s41598-024-65044-x
Schlagwort:	Humans Male Female Middle Aged Risk Assessment methods Risk Factors Blood Glucose analysis Blood Glucose metabolism Inflammation Algorithms Diabetes Mellitus, Type 2 Biomarkers blood Machine Learning Oxidative Stress
Sonstiges:	Nachgewiesen in: MEDLINE Sprachen: English Publication Type: Journal Article Language: English [Sci Rep] 2024 Jun 22; Vol. 14 (1), pp. 14409. <i>Date of Electronic Publication: </i>2024 Jun 22. MeSH Terms: Diabetes Mellitus, Type 2* ; Biomarkers* / blood ; Machine Learning* ; Oxidative Stress* ; Humans ; Male ; Female ; Middle Aged ; Risk Assessment / methods ; Risk Factors ; Blood Glucose / analysis ; Blood Glucose / metabolism ; Inflammation ; Algorithms References: DeFronzo, R. A. et al. Type 2 diabetes mellitus. Nat. Rev. Dis. Primers 2015(1), 1–22 (2015). ; Safiri, S. et al. Prevalence, deaths and disability-adjusted-life-years (DALYs) due to type 2 diabetes and its attributable risk factors in 204 countries and territories, 1990–2019: Results from the global Burden of disease study 2019. Front. Endocrinol. (Lausanne) 13, 1–14 (2022). (PMID: 10.3389/fendo.2022.838027) ; Jelinek, H. F., Stranieri, A., Yatsko, A. & Venkatraman, S. Data analytics identify glycated haemoglobin co-markers for type 2 diabetes mellitus diagnosis. Comput. Biol. Med. 75, 90–97 (2016). (PMID: 10.1016/j.compbiomed.2016.05.00527268735) ; Mahat, R. K., Singh, N., Arora, M. & Rathore, V. Health risks and interventions in prediabetes: A review. Diabetes Metab. Syndr. Clin. Res. Rev. 13, 2803–2811 (2019). (PMID: 10.1016/j.dsx.2019.07.041) ; Yaribeygi, H., Sathyapalan, T., Atkin, S. L. & Sahebkar, A. Molecular Mechanisms Linking Oxidative Stress and Diabetes Mellitus. Oxid. Med. Cell Longev. 2020 (2020). ; Sangwung, P., Petersen, K. F., Shulman, G. I. & Knowles, J. W. Potential role of alterations in mitochondrial function in the pathogenesis of insulin resistance and type 2 diabetes. Endocrinology (United States) 161, 1–10. https://doi.org/10.1210/ENDOCR/BQAA017 (2021). (PMID: 10.1210/ENDOCR/BQAA017) ; Oguntibeju, O. O. Type 2 diabetes mellitus, oxidative stress and inflammation: examining the links. Int. J. Physiol. Pathophysiol. Pharmacol. 11, 45–63 (2019). (PMID: 313338086628012) ; Voigt, A. & Jelinek, H. F. Humanin: A mitochondrial signaling peptide as a biomarker for impaired fasting glucose-related oxidative stress. Physiol. Rep. 4, 1–5 (2016). (PMID: 10.14814/phy2.12796) ; Jelinek, H. F., Helf, C. & Khalaf, K. Human SHC-transforming protein 1 and its isoforms p66shc: A novel marker for prediabetes. J. Diabetes Investig. https://doi.org/10.1111/JDI.13551 (2021). (PMID: 10.1111/JDI.13551337593778504898) ; Maschirow, L., Khalaf, K., Al-Aubaidy, H. A. & Jelinek, H. F. Inflammation, coagulation, endothelial dysfunction and oxidative stress in prediabetes: Biomarkers as a possible tool for early disease detection for rural screening. Clin. Biochem. 48, 581–585 (2015). (PMID: 10.1016/j.clinbiochem.2015.02.01525753569) ; Jacob, S. M., Raimond, K. & Kanmani, D. Associated machine learning techniques based on diabetes based predictions, in 2019 International Conference on Intelligent Computing and Control Systems, ICCS 2019 1445–1450 (2019) https://doi.org/10.1109/ICCS45141.2019.9065411 . ; Early Classification of Diabetes \| Kaggle. https://www.kaggle.com/datasets/andrewmvd/early-diabetes-classification . ; Paleczek, A., Grochala, D. & Rydosz, A. Artificial breath classification using xgboost algorithm for diabetes detection. Sensors 21, 745 (2021). (PMID: 10.3390/s21124187) ; Zeng, H. et al. Metabolic Biomarkers for Prognostic Prediction of Pre-diabetes: Results from a longitudinal cohort study. Sci. Rep. 7, 1–12 (2017). (PMID: 10.1038/s41598-017-14856-1) ; Lim, H., Kim, G. & Choi, J. H. Advancing diabetes prediction with a progressive self-transfer learning framework for discrete time series data. Sci. Rep. 13 (2023). ; Fregoso-Aparicio, L., Noguez, J., Montesinos, L. & García-García, J. A. Machine learning and deep learning predictive models for type 2 diabetes: a systematic review. Diabetol Metab. Syndr. 13 (2021). ; Wee, B. F., Sivakumar, S., Lim, K. H., Wong, W. K. & Juwono, F. H. Diabetes detection based on machine learning and deep learning approaches. Multimed. Tools Appl. https://doi.org/10.1007/s11042-023-16407-5 (2023). (PMID: 10.1007/s11042-023-16407-5) ; Oikonomou, E. K. & Khera, R. Machine learning in precision diabetes care and cardiovascular risk prediction. Cardiovasc. Diabetol. https://doi.org/10.1186/s12933-023-01985-3 (2023). (PMID: 10.1186/s12933-023-01985-33774957910521578) ; Elshawi, R., Al-Mallah, M. H. & Sakr, S. On the interpretability of machine learning-based model for predicting hypertension. BMC Med. Inform. Decis. Mak. 19 (2019). ; Khan, M. A. B. et al. Epidemiology of Type 2 diabetes: Global burden of disease and forecasted trends. J. Epidemiol. Glob Health 10, 107–111 (2020). (PMID: 10.2991/jegh.k.191028.001321757177310804) ; Sadeghi, S., Khalili, D., Ramezankhani, A., Mansournia, M. A. & Parsaeian, M. Diabetes mellitus risk prediction in the presence of class imbalance using flexible machine learning methods. BMC Med. Inform. Decis. Mak. 22, 1–13 (2022). (PMID: 10.1186/s12911-022-01775-z) ; Liu, L. et al. Solving the class imbalance problem using ensemble algorithm: application of screening for aortic dissection. BMC Med. Inform. Decis. Mak. 22 (2022). ; Elseddawy, A. I., Karim, F. K., Hussein, A. M. & Khafaga, D. S. Predictive analysis of diabetes-risk with class imbalance. Comput. Intell. Neurosci. 2022 (2022). ; Rezvani, S. & Wang, X. A broad review on class imbalance learning techniques. Appl. Soft Comput. https://doi.org/10.1016/j.asoc.2023.110415 (2023). (PMID: 10.1016/j.asoc.2023.110415) ; Barmparis, G. D., Marketou, M. E., Tsironis, G. P., Dritsas, E. & Trigka, M. Data-driven machine-learning methods for diabetes risk prediction. Sensors 22, 5304 (2022). (PMID: 10.3390/s22145304) ; Azad, C. et al. Prediction model using SMOTE, genetic algorithm and decision tree (PMSGD) for classification of diabetes mellitus. Multimed. Syst. 28, 1289–1307 (2022). (PMID: 10.1007/s00530-021-00817-2) ; Roy, K. et al. An enhanced machine learning framework for type 2 diabetes classification using imbalanced data with missing values. Complexity 2021 (2021). ; Feng, X., Cai, Y. & Xin, R. Optimizing diabetes classification with a machine learning-based framework. BMC Bioinform. 24 (2023). ; Tasin, I., Nabil, T. U., Islam, S. & Khan, R. Diabetes prediction using machine learning and explainable AI techniques. Healthc. Technol. Lett. 10, 1–10 (2023). (PMID: 10.1049/htl2.1203937077883) ; Bellinger, C., Sharma, S. & Japkowicz, N. One-class versus binary classification: Which and when? in Proceedings - 2012 11th International Conference on Machine Learning and Applications, ICMLA 2012 vol. 2 102–106 (2012). ; Perera, P., Oza, P. & Patel, V. M. One-class classification: A survey. (2021). ; Kang, S. Using binary classifiers for one-class classification. Expert Syst. Appl. 187 (2022). ; Seliya, N., Abdollah Zadeh, A. & Khoshgoftaar, T. M. A Literature Review on One-Class Classification and Its Potential Applications in Big Data. Journal of Big Data vol. 8 (Springer, 2021). ; López-De-Ipiña, K., Faundez-Zanuy, M., Sole, J., Zelarin, F. & Calvo, P. Multi-Class versus One-Class Classifier in Spontaneous Speech Analysis Oriented to Alzheimer Disease Diagnosis. ; Vasighizaker, A., Sharma, A. & Dehzangi, A. A novel one-class classification approach to accurately predict disease-gene association in acute myeloid leukemia cancer. PLoS ONE 14 (2019). ; Liu, X., Ouellette, S., Jamgochian, M., Liu, Y. & Rao, B. One-class machine learning classification of skin tissue based on manually scanned optical coherence tomography imaging. Sci. Rep. 13 (2023). ; Argaw, P. N., Kushner, J. A., Kohane, I. S. & Paulson, H. J. A. Unsupervised Anomaly Detection to Characterize Heterogeneity in Type 2 Diabetes. in AMIA Jt Summits Transl Sci Proc 32–41 (2023). ; Fang, J. et al. Anomaly detection of diabetes data based on hierarchical clustering and CNN. in Procedia Computer Science vol. 199 71–78 (Elsevier B.V., 2021). ; Fitriyani, N. L. et al. Prediction Model for Type 2 Diabetes using Stacked Ensemble Classifiers. in 2020 International Conference on Decision Aid Sciences and Application, DASA 2020 399–402 (Institute of Electrical and Electronics Engineers Inc., 2020). https://doi.org/10.1109/DASA51403.2020.9317090 . ; Dharmarathne, G., Jayasinghe, T. N., Bogahawaththa, M., Meddage, D. P. P. & Rathnayake, U. A novel machine learning approach for diagnosing diabetes with a self-explainable interface. Healthc. Analyt. 5 (2024). ; Hendawi, R., Li, J. & Roy, S. A mobile app that addresses interpretability challenges in machine learning–based diabetes predictions: survey-based user study. JMIR Form Res 7 (2023). ; Jakka, A. & Vakula Rani, J. An Explainable AI Approach for Diabetes Prediction. in Lecture Notes in Networks and Systems vol. 565 LNNS 15–25 (Springer Science and Business Media Deutschland GmbH, 2023). ; Jia, W. Standardising HbA1c-based diabetes diagnosis: Opportunities and challenges. Expert Rev. Mol. Diagn. 16, 343–355 (2016). (PMID: 10.1586/14737159.2016.113329926680319) ; Dorcely, B. et al. Novel biomarkers for prediabetes, diabetes, and associated complications. Diabetes Metab. Syndr. Obes. 10, 345–361 (2017). (PMID: 10.2147/DMSO.S100074288608335565252) ; Wong, C. W. Vitamin B12 deficiency in the elderly: Is it worth screening?. Hong Kong Med. J. 21, 155–164 (2015). (PMID: 25756278) ; Australian Institute of Health and Welfare. Diabetes: Australian Facts, Summary. Diabetes https://www.aihw.gov.au/reports/diabetes/diabetes/contents/summary (2023). ; Pouvreau, C., Dayre, A., Butkowski, E. G., De Jong, B. & Jelinek, H. F. Inflammation and oxidative stress markers in diabetes and hypertension. J. Inflamm. Res. 11, 61–68 (2018). (PMID: 10.2147/JIR.S148911294973245822844) ; Venkatraman, S., Yatsko, A., Stranieri, A. & Jelinek, H. F. Missing data imputation for individualised CVD diagnostic and treatment. Comput. Cardiol. 2010(43), 349–352 (2016). ; Nwose, E. U., Jelinek, H. F., Richards, R. S. & Kerr, P. G. Changes in the erythrocyte glutathione concentration in the course of diabetes mellitus. Redox Rep. 11, 99–104 (2006). (PMID: 10.1179/135100006X11658316805963) ; Zhao, J. et al. Triglyceride is an independent predictor of type 2 diabetes among middle-aged and older adults: A prospective study with 8-year follow-ups in two cohorts. J. Transl. Med. 17 (2019). ; Abdul-Ghani, M. A. & DeFronzo, R. A. Plasma glucose concentration and prediction of future risk of type 2 diabetes. Diabetes care vol. 32 Suppl 2. https://doi.org/10.2337/dc09-s309 (2009). ; Ganz, M. L. et al. The association of body mass index with the risk of type 2 diabetes: A case-control study nested in an electronic health records system in the United States. Diabetol. Metab. Syndr. 6 (2014). ; Tony Liu, F., Ming Ting, K. & Zhou, Z.-H. Isolation forest ICDM08. ICDM (2008). ; Carletti, M., Terzi, M. & Susto, G. A. Interpretable anomaly detection with DIFFI: Depth-based feature importance of isolation forest. Eng. Appl. Artif. Intell. 119 (2023). ; Butkowski, E. G. & Jelinek, H. F. Hyperglycaemia, oxidative stress and inflammatory markers. Redox Rep. 22, 257–264 (2017). (PMID: 10.1080/13510002.2016.121564328277069) ; Lagman, M. et al. Investigating the causes for decreased levels of glutathione in individuals with type II diabetes. PLoS ONE 10, 1–19 (2015). (PMID: 10.1371/journal.pone.0118436) ; Al-Goblan, A. S., Al-Alfi, M. A. & Khan, M. Z. Mechanism linking diabetes mellitus and obesity. Diabetes Metab. Syndr. Obes. 7, 587–591 (2014). (PMID: 10.2147/DMSO.S67400255062344259868) ; Leitner, D. R. et al. Obesity and type 2 diabetes: Two diseases with a need for combined treatment strategies - EASO can lead the way. Obes. Facts 10, 483–492 (2017). (PMID: 10.1159/000480525290206745741209) ; Akbari, M. & Hassan-Zadeh, V. IL-6 signalling pathways and the development of type 2 diabetes. Inflammopharmacology 26, 685–698. https://doi.org/10.1007/s10787-018-0458-0 (2018). (PMID: 10.1007/s10787-018-0458-029508109) ; Ene, C. V., Nicolae, I., Geavlete, B., Geavlete, P. & Ene, C. D. IL-6 Signaling link between inflammatory tumor microenvironment and prostatic tumorigenesis. Analyt. Cell. Pathol. https://doi.org/10.1155/2022/5980387 (2022). (PMID: 10.1155/2022/5980387) ; Mirmira, R. G. et al. Interleukin-6 reduces B-cell oxidative stress by linking autophagy with the antioxidant response. in Diabetes vol. 67 1576–1588 (American Diabetes Association Inc., 2018). ; Halimi, A. et al. The relation between serum levels of interleukin 10 and interferon-gamma with oral candidiasis in type 2 diabetes mellitus patients. BMC Endocr. Disord. 22 (2022). ; Ayelign, B. et al. Association of IL-10 (− 1082 A/G) and IL-6 (− 174 G/C) gene polymorphism with type 2 diabetes mellitus in Ethiopia population. BMC Endocr. Disord. 21 (2021). ; Abhilasha et al. Downregulation of interleukin-10 receptor (IL-10R) along with low serum IL-10 levels in newly diagnosed type 2 diabetes mellitus patients. Gene Rep. 24 (2021). ; Carlini, V. et al. The multifaceted nature of IL-10: regulation, role in immunological homeostasis and its relevance to cancer, COVID-19 and post-COVID conditions. Front. Immunol. https://doi.org/10.3389/fimmu.2023.1161067 (2023). (PMID: 10.3389/fimmu.2023.11610673735954910287165) ; Jelinek, H., Jamil, D. & Al-Aubaidy, H. Impaired fasting glucose & 8-iso-prostaglandin F2α in diabetes disease progression. Br. J. Med. Med. Res. 4, 5229–5237 (2014). (PMID: 10.9734/BJMMR/2014/11147) ; Schöttker, B., Xuan, Y., Gào, X., Anusruti, A. & Brenner, H. Oxidatively damaged DNA/RNA and 8-isoprostane levels are associated with the development of type 2 diabetes at older age: Results from a large cohort study. Diabetes Care 43, 130–136 (2020). (PMID: 10.2337/dc19-137931653645) ; Butkowski, E. G., Brix, L. M., Kiat, H., Al-Aubaidy, H. & Jelinek, H. F. Diabetes, oxidative stress and cardiovascular risk. Basic Res. J. Med. Clin. Sci. (2016). ; Boutari, C., Pappas, P. D., Theodoridis, T. D. & Vavilis, D. Humanin and diabetes mellitus: A review of in vitro and in vivo studies. World J. Diabetes 13, 213–223 (2022). (PMID: 10.4239/wjd.v13.i3.213354327588984571) ; Coradduzza, D. et al. Humanin and its pathophysiological roles in aging: A systematic review. Biology https://doi.org/10.3390/biology12040558 (2023). (PMID: 10.3390/biology120405583710675810135985) ; Wu, Y., Sun, L., Zhuang, Z., Hu, X. & Dong, D. Mitochondrial-derived peptides in diabetes and its complications. Front. Endocrinol. https://doi.org/10.3389/fendo.2021.808120 (2022). (PMID: 10.3389/fendo.2021.808120) ; Biondi, G. et al. The p66Shc redox protein and the emerging complications of diabetes. Int. J. Mol. Sci. https://doi.org/10.3390/ijms25010108 (2024). (PMID: 10.3390/ijms250101083889184111171768) ; Mousavi, S. et al. The role of p66Shc in diabetes: A comprehensive review from bench to bedside. Journal of Diabetes Research 20, 22. https://doi.org/10.1155/2022/7703520 (2022). (PMID: 10.1155/2022/7703520) Contributed Indexing: Keywords: Diabetes; Inflammation; Isolation forest; Mitochondrial dysfunction; Oxidative stress; Predictive modelling Substance Nomenclature: 0 (Biomarkers) ; 0 (Blood Glucose) Entry Date(s): Date Created: 20240622 Date Completed: 20240622 Latest Revision: 20240625 Update Code: 20240626 PubMed Central ID: PMC11193708

Klicken Sie ein Format an und speichern Sie dann die Daten oder geben Sie eine Empfänger-Adresse ein und lassen Sie sich per Email zusenden.

BibTeX Citavi, JabRef, u.a.
(Literaturverwaltung)

PDF kein Volltext!
(Merkzettel, Notizen)

RIS Endnote, Citavi u.a.
(Literaturverwaltung)

MODS
(XML zur Weiterverarbeitung)

oder

Wählen Sie das für Sie passende Zitationsformat und kopieren Sie es dann in die Zwischenablage, lassen es sich per Mail zusenden oder speichern es als PDF-Datei.

Gewünschter Zitations-Stil:

oder

Bitte prüfen Sie, ob die Zitation formal korrekt ist, bevor Sie sie in einer Arbeit verwenden. Benutzen Sie gegebenenfalls den "Exportieren"-Dialog, wenn Sie ein Literaturverwaltungsprogramm verwenden und die Zitat-Angaben selbst formatieren wollen.

Exploratory risk prediction of type II diabetes with isolation forests and novel biomarkers.