1- Pasteur Institute of Iran, Tehran, Iran
2- Artificial Intelligence in Health Research Center, Biomedicine Technologies Institute, Baqiyatallah University of Medical Sciences, Tehran, Iran ,arabfard@gmail.com
2- Artificial Intelligence in Health Research Center, Biomedicine Technologies Institute, Baqiyatallah University of Medical Sciences, Tehran, Iran ,
Abstract: (71 Views)
Background: Stroke is a leading cause of disability and mortality worldwide, with ischemic strokes comprising the majority of cases. Despite advances in neuroimaging, there is a pressing need for supplementary diagnostic tools to enhance accuracy. This study explores the application of machine learning (ML) techniques to predict ischemic stroke using RNA-seq data from the GEO database (GSE22255).
Methods: We developed and evaluated various machine learning models, including Random Forest, K-Nearest Neighbors (KNN), and CHAID (Chi-squared Automatic Interaction Detection), based on their accuracy, precision, specificity, and sensitivity. The analysis utilized a dataset comprising 54,676 genes across 40 samples (20 cases and 20 controls). All modeling was conducted using IBM SPSS Modeler version 18.
Results: The models were assessed based on their classification accuracy, performance evaluation scores, and AUC/Gini AUC metrics. The Random Forest model achieved the highest accuracy (96.67% in training, 80% in testing), while the CHAID algorithm provided interpretable results with key variables (TP53, CYP1A1, and CYP2D6) identified. The KNN model exhibited strong performance with notable confidence in its predictions.
Conclusion: This study demonstrates the potential of ML techniques, particularly Random Forest, to enhance stroke diagnosis and provide insights into stroke pathology, offering a novel approach to improving clinical decision-making. However, the study is limited by the small sample size, and future work should focus on validation with larger datasets and integration with other omics data for clinical application.
Methods: We developed and evaluated various machine learning models, including Random Forest, K-Nearest Neighbors (KNN), and CHAID (Chi-squared Automatic Interaction Detection), based on their accuracy, precision, specificity, and sensitivity. The analysis utilized a dataset comprising 54,676 genes across 40 samples (20 cases and 20 controls). All modeling was conducted using IBM SPSS Modeler version 18.
Results: The models were assessed based on their classification accuracy, performance evaluation scores, and AUC/Gini AUC metrics. The Random Forest model achieved the highest accuracy (96.67% in training, 80% in testing), while the CHAID algorithm provided interpretable results with key variables (TP53, CYP1A1, and CYP2D6) identified. The KNN model exhibited strong performance with notable confidence in its predictions.
Conclusion: This study demonstrates the potential of ML techniques, particularly Random Forest, to enhance stroke diagnosis and provide insights into stroke pathology, offering a novel approach to improving clinical decision-making. However, the study is limited by the small sample size, and future work should focus on validation with larger datasets and integration with other omics data for clinical application.
Keywords: Ischemic Stroke, Machine Learning, Random Forest, CHAID, K-Nearest Neighbors, Predictive Modeling (Precision Medicine)
Type of Article: Original article |
Subject:
Basic Medical Sciences
Received: 2024/11/13 | Accepted: 2025/09/1
Received: 2024/11/13 | Accepted: 2025/09/1
References
2. Putaala J. Ischemic Stroke in Young Adults. Continuum (Minneapolis, Minn). 2020;26(2):386-414. [View at Publisher] [DOI] [PMID] [Google Scholar]
3. Lim H, Park Y, Hong JH, Yoo K-B, Seo K-D. Use of machine learning techniques for identifying ischemic stroke instead of the rule-based methods: a nationwide population-based study. Eur J Med Res. 2024;29(1):6. [View at Publisher] [DOI] [PMID] [Google Scholar]
4. Rahmati M, Ferns GA, Mobarra N. The lower expression of circulating miR-210 and elevated serum levels of HIF-1α in ischemic stroke; Possible markers for diagnosis and disease prediction. J Clin Lab Anal. 2021;35(12):e24073. [View at Publisher] [DOI] [PMID] [Google Scholar]
5. Li W, Shao C, Zhou H, Du H, Chen H, Wan H, et al. Multi-omics research strategies in ischemic stroke: A multidimensional perspective. Ageing Res Rev. 2022;81:101730. [View at Publisher] [DOI] [PMID] [Google Scholar]
6. Patil S, Rossi R, Jabrah D, Doyle K. Detection, diagnosis and treatment of acute ischemic stroke: current and future perspectives. Front Med Technol. 2022:4:748949.
2022;4:748949. [View at Publisher] [DOI] [PMID] [Google Scholar]
7. Wardlaw JM, Mair G, Von Kummer R, Williams MC, Li W, Storkey AJ, et al. Accuracy of automated computer-aided diagnosis for stroke imaging: a critical evaluation of current evidence. Stroke. 2022;53(7):2393-403. [View at Publisher] [DOI] [PMID] [Google Scholar]
8. Ruksakulpiwat S, Phianhasin L, Benjasirisan C, Schiltz NK. Using Neural Networks Algorithm in Ischemic Stroke Diagnosis: A Systematic Review. J Multidiscip Healthc. 2023;16:2593-602. [View at Publisher] [DOI] [PMID] [Google Scholar]
9. Daidone M, Ferrantelli S, Tuttolomondo A. Machine learning applications in stroke medicine: advancements, challenges, and future prospectives. Neural Regen Res. 2024;19(4):769-73. [View at Publisher] [DOI] [PMID] [Google Scholar]
10. Wang J, Gong X, Chen H, Zhong W, Chen Y, Zhou Y, et al. Causative Classification of Ischemic Stroke by the Machine Learning Algorithm Random Forests. Front Aging Neurosci. 2022;14:788637. [View at Publisher] [DOI] [PMID] [Google Scholar]
11. Jabal MS, Joly O, Kallmes D, Harston G, Rabinstein A, Huynh T, et al. Interpretable Machine Learning Modeling for Ischemic Stroke Outcome Prediction. Front Neurol. 2022;13:884693. [View at Publisher] [DOI] [PMID] [Google Scholar]
12. Krug T, Gabriel JP, Taipa R, Fonseca BV, Domingues-Montanari S, Fernandez-Cadenas I, et al. TTC7B emerges as a novel risk factor for ischemic stroke through the convergence of several genome-wide approaches. J Cereb Blood Flow Metab. 2012;32(6):1061-72.
. [View at Publisher] [DOI] [PMID] [Google Scholar]
13. Yahiya Adam S, Yousif A, Bashir MB. Classification of Ischemic Stroke using Machine Learning Algorithms. International Journal of Computer Applications. 2016;149(10):26-31. [View at Publisher] [DOI] [Google Scholar]
14. Hong S, Kim H-W, Walton B, Kaboi M. The Intersectionality of Factors Predicting Co-occurring Disorders: A Decision Tree Model. Int J Ment Health Addict. 2024;22(6):1-24. [View at Publisher] [DOI] [Google Scholar]
15. Althuwaynee OF, Pradhan B, Park H-J, Lee JH. A novel ensemble decision tree-based CHi-squared Automatic Interaction Detection (CHAID) and multivariate logistic regression models in landslide susceptibility mapping. Landslides .2014;11:1063–78. [View at Publisher] [DOI] [Google Scholar]
16. Zhang Z. Introduction to machine learning: k-nearest neighbors. Ann Transl Med. 2016;4(11):218. [View at Publisher] [DOI] [PMID] [Google Scholar]
17. Halder RK, Uddin MN, Uddin MA, Aryal S, Khraisat A. Enhancing K-nearest neighbor algorithm: a comprehensive review and performance analysis of modifications. J Big Data. 2024;11(1):113. [View at Publisher] [DOI] [Google Scholar]
18. Arabfard M, Najafi A, Rezaei E. Predicting COVID-19 Models for Death with Three Different Decision Algorithms: Analysis of 600 Hospitalized Patients. Applied Biotechnology Reports. 2023;10(2):1018-24. [View at Publisher] [DOI] [Google Scholar]
19. Pandian JD, Gall SL, Kate MP, Silva GS, Akinyemi RO, Ovbiagele BI, et al. Prevention of stroke: a global perspective. Lancet. 2018;392(10154):1269-78. [View at Publisher] [DOI] [PMID] [Google Scholar]
20. Montaner J, Ramiro L, Simats A, Tiedt S, Makris K, Jickling GC, et al. Multilevel omics for the discovery of biomarkers and therapeutic targets for stroke. Nat Rev Neurol. 2020;16(5):247-64. [View at Publisher] [DOI] [PMID] [Google Scholar]
21. Zou R, Zhang D, Lv L, Shi W, Song Z, Yi B, et al. Bioinformatic gene analysis for potential biomarkers and therapeutic targets of atrial fibrillation-related stroke. J Transl Med. 2019;17(1):45. [View at Publisher] [DOI] [PMID] [Google Scholar]
22. Daidone M, Ferrantelli S, Tuttolomondo A. Machine learning applications in stroke medicine: advancements, challenges, and future prospectives. Neural Regen Res. 2024;19(4):769-73. [View at Publisher] [DOI] [PMID] [Google Scholar]
23. Shah YAR, Qureshi SM, Qureshi HA, Shah S, Shiwlani A, Ahmad A. Artificial Intelligence in Stroke Care: Enhancing Diagnostic Accuracy, Personalizing Treatment, and Addressing Implementation Challenges. IJARSS. 2024;2(10):855-86. [View at Publisher] [DOI] [Google Scholar]
24. Asif S, Wenhui Y, ur-Rehman S-, ul-ain Q-, Amjad K, Yueyang Y, et al. Advancements and Prospects of Machine Learning in Medical Diagnostics: Unveiling the Future of Diagnostic Precision. Arch Comput Methods Eng. 2024;32(2):853–83. [View at Publisher] [DOI] [Google Scholar]
25. Fernandes JN, Cardoso VE, Comesaña-Campos A, Pinheira A. Comprehensive Review: Machine and Deep Learning in Brain Stroke Diagnosis. Sensors (Basel). 2024;24(13):4355. [View at Publisher] [DOI] [PMID] [Google Scholar]
26. Deshpande D, Chhugani K, Chang Y, Karlsberg A, Loeffler C, Zhang J, et al. RNA-seq data science: From raw data to effective interpretation. Front Genet. 2023;14:997383. [View at Publisher] [DOI] [PMID] [Google Scholar]
27. Zhou L, Pan S, Wang J, Vasilakos A. Machine learning on big data: Opportunities and challenges. Neurocomputing. 2017;237:350-61. [View at Publisher] [DOI] [Google Scholar]
28. Heo J, Yoon JG, Park H, Kim YD, Nam HS, Heo JH. Machine learning-based model for prediction of outcomes in acute stroke. Stroke.
2019;50(5):1263-5. [View at Publisher] [DOI] [PMID] [Google Scholar]
29. Diaz-Uriarte R, Gómez de Lope E, Giugno R, Fröhlich H, Nazarov PV, Nepomuceno-Chamorro IA, et al. Ten quick tips for biomarker discovery and validation analyses using machine learning. PLoS Comput Biol. 2022;18(8):e1010357. [View at Publisher] [DOI] [PMID] [Google Scholar]
30. Perakakis N, Yazdani A, Karniadakis GE, Mantzoros C. Omics, big data and machine learning as tools to propel understanding of biological mechanisms and to discover novel diagnostics and therapeutics. Metabolism. 2018:87:A1-A9. [View at Publisher] [DOI] [PMID] [Google Scholar]
31. Imran B, Wahyudi E, Subki A, Salman S, Yani A. Classification of stroke patients using data mining with adaboost, decision tree and random forest models. ilk. J. Ilm. 2022;14(3):218-28. [View at Publisher] [DOI] [Google Scholar]
32. Mu Q, Zhang Y, Gu L, Gerner ST, Qiu X, Tao Q, et al. Transcriptomic Profiling Reveals the Antiapoptosis and Antioxidant Stress Effects of Fos in Ischemic Stroke. Front Neurol. 2021;12:728984. [View at Publisher] [DOI] [PMID] [Google Scholar]
33. Kurushima H, Ohno M, Miura T, Nakamura TY, Horie H, Kadoya T, et al. Selective induction of DeltaFosB in the brain after transient forebrain ischemia accompanied by an increased expression of galectin-1, and the implication of DeltaFosB and galectin-1 in neuroprotection and neurogenesis. Cell Death Differ. 2005;12(8):1078-96. [View at Publisher] [DOI] [PMID] [Google Scholar]
34. Wang SK, Zhang H, Hu CY, Liu JF, Chadha S, Kim JW, et al. FAM83H and Autosomal Dominant Hypocalcified Amelogenesis Imperfecta. J Dent Res.
2021;100(3):293-301. [View at Publisher] [DOI] [PMID] [Google Scholar]
35. Aubrey BJ, Strasser A, Kelly GL. Tumor-Suppressor Functions of the TP53 Pathway. Cold Spring Harb Perspect Med. 2016;6(5):a026062. [View at Publisher] [DOI] [PMID] [Google Scholar]
36. Meng F-d, Ma P, Sui C-g, Tian X, Jiang Y-h. Association between cytochrome P450 1A1 (CYP1A1) gene polymorphisms and the risk of renal cell carcinoma: a meta-analysis. Sci Rep. 2015;5(1):8108. [View at Publisher] [DOI] [PMID] [Google Scholar]
37. Carnwath TP, Demel SL, Prestigiacomo CJ. Genetics of ischemic stroke functional outcome. J Neurol. 2024;271(5):2345-69. [View at Publisher] [DOI] [PMID] [Google Scholar]
38. Peng C, Ding Y, Yi X, Shen Y, Dong Z, Cao L, et al. Polymorphisms in CYP450 Genes and the Therapeutic Effect of Atorvastatin on Ischemic Stroke: A Retrospective Cohort Study in Chinese Population. Clin Ther. 2018;40(3):469-77.e2. [View at Publisher] [DOI:] [PMID] [Google Scholar]
39. Zhang S, Li X, Zong M, Zhu X, Wang R. Efficient kNN classification with different numbers of nearest neighbors. IEEE Trans Neural Netw Learn Syst.
2018;29(5):1774-85. [View at Publisher] [DOI] [PMID] [Google Scholar]
40. Wang X, Zhang XY, Liao N-Q, He Z-H, Chen Q-F. Identification of ribosome biogenesis genes and subgroups in ischaemic stroke. Front Immunol.
2024;15:1449158. [View at Publisher] [DOI] [PMID] [Google Scholar]
41. Zhang Y, Li N, Kobayashi S. Paxillin participates in the sphingosylphosphorylcholine-induced abnormal contraction of vascular smooth muscle by regulating Rho-kinase activation. Cell Commun Signal. 2024;22(1):58. [View at Publisher] [DOI] [Google Scholar]
42. Yi J-H, Park S-W, Kapadia R, Vemuganti R. Role of transcription factors in mediating post-ischemic cerebral inflammation and brain damage. Neurochem Int. 2007;50(7-8):1014-27. [View at Publisher] [DOI] [PMID] [Google Scholar]
43. German AE, Mammoto T, Jiang E, Ingber DE, Mammoto A. Paxillin controls endothelial cell migration and tumor angiogenesis by altering neuropilin 2 expression. J Cell Sci. 2014;127(Pt 8):1672-83. [View at Publisher] [DOI] [PMID] [Google Scholar]
44. Liang J, Feng J, Lin Z, Wei J, Luo X, Wang QM, et al. Research on prognostic risk assessment model for acute ischemic stroke based on imaging and multidimensional data. Front Neurol. 2023;14:1294723. [View at Publisher] [DOI] [PMID] [Google Scholar]
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
