1- Pasteur institute of Iran, Tehran, Iran
2- Clinical Research Development Center, Shahid Beheshti Hospital, Babol University of Medical Sciences, Babol, Iran
3- Artificial Intelligence in Health Research Center, Biomedicine Technologies Institute, Baqiyatallah University of Medical Sciences, Tehran, Iran ,arabfard@gmail.com
2- Clinical Research Development Center, Shahid Beheshti Hospital, Babol University of Medical Sciences, Babol, Iran
3- Artificial Intelligence in Health Research Center, Biomedicine Technologies Institute, Baqiyatallah University of Medical Sciences, Tehran, Iran ,
Abstract: (34 Views)
Background: Bladder cancer (BC) is a life-threatening malignancy that can be successfully treated if diagnosed in its early stages. Machine learning techniques, by using large biological databases, are suggested as important approaches for identifying accurate diagnostic biomarkers. The present study aimed to introduce a simple and accurate model for the diagnosis of BC.
Methods: RNA-sequencing information of 412 primary bladder tumors versus 19 normal bladder tissues from The Cancer Genome Atlas were analyzed using the TCGAbiolinks R package to identify differentially expressed genes (DEGs). Gene ontology properties and the corresponding pathways of DEGs were investigated using the online ShinyGO tools. To develop a diagnostic model for BC, two binary classifier machine learning algorithms, C5.0 and CHAID, were employed in three subgroups of train, test, and validation sets using SPSS Modeler version 18.1. Their efficacy was evaluated using performance measures for binary classification.
Results: Most of the identified DEGs were associated with microtubule organization, coagulation, and myelination. Based on the constructed models, four important RNAs (Tubulin Polymerization-Promoting Protein: ENSG00000171368, Proteolipid Protein-1: ENSG00000123560, RP11-473E2: ENSG00000228877, and Coagulation Factor X: ENSG00000126218) were identified as important classifiers for diagnosis in both C5.0 and CHAID models. The CHAID model demonstrated superior performance in the testing dataset, achieving an accuracy of 98.75%, an F1-score of 99.36%, and an AUC of 99.4%.
Conclusion: According to the results, machine learning algorithms are beneficial for the diagnosis of BC and potentially useful for improving personalized medicine in BC patients. The developed model may serve as a non-invasive, data-driven tool to support early diagnosis and personalized treatment planning in clinical settings. Further evaluation using laboratory tests is suggested to validate the obtained results.
Methods: RNA-sequencing information of 412 primary bladder tumors versus 19 normal bladder tissues from The Cancer Genome Atlas were analyzed using the TCGAbiolinks R package to identify differentially expressed genes (DEGs). Gene ontology properties and the corresponding pathways of DEGs were investigated using the online ShinyGO tools. To develop a diagnostic model for BC, two binary classifier machine learning algorithms, C5.0 and CHAID, were employed in three subgroups of train, test, and validation sets using SPSS Modeler version 18.1. Their efficacy was evaluated using performance measures for binary classification.
Results: Most of the identified DEGs were associated with microtubule organization, coagulation, and myelination. Based on the constructed models, four important RNAs (Tubulin Polymerization-Promoting Protein: ENSG00000171368, Proteolipid Protein-1: ENSG00000123560, RP11-473E2: ENSG00000228877, and Coagulation Factor X: ENSG00000126218) were identified as important classifiers for diagnosis in both C5.0 and CHAID models. The CHAID model demonstrated superior performance in the testing dataset, achieving an accuracy of 98.75%, an F1-score of 99.36%, and an AUC of 99.4%.
Conclusion: According to the results, machine learning algorithms are beneficial for the diagnosis of BC and potentially useful for improving personalized medicine in BC patients. The developed model may serve as a non-invasive, data-driven tool to support early diagnosis and personalized treatment planning in clinical settings. Further evaluation using laboratory tests is suggested to validate the obtained results.
Keywords: Bioinformatic (Computational Biology), Bladder cancer (Urinary Bladder Neoplasms), Machine learning, Precision Medicine
Type of Article: Original article |
Subject:
Bio-statistics
Received: 2025/03/7 | Accepted: 2025/06/20
Received: 2025/03/7 | Accepted: 2025/06/20
References
1. Koul B, Koul B. Types of Cancer. In: Herbs for Cancer Treatment. Singapore: Springer; 2019. p. 53‑150 [View at Publisher] [DOI] [Google Scholar]
2. Jubber I, Ong S, Bukavina L, Black PC, Compérat E, Kamat AM, et al. Epidemiology of bladder cancer in 2023: a systematic review of risk factors. Eur Urol. 2023;84(2):176-90. [View at Publisher] [DOI] [PMID] [Google Scholar]
3. Crabb SJ, Douglas J. The latest treatment options for bladder cancer. Br Med Bull. 2018;128(1):85-95. [View at Publisher] [DOI] [PMID] [Google Scholar]
4. Lopez-Beltran A, Cookson MS, Guercio BJ, Cheng L. Advances in diagnosis and treatment of bladder cancer. BMJ. 2024:384:e076743. [View at Publisher] [DOI] [PMID] [Google Scholar]
5. DeGEORGE KC, Holt HR, Hodges SC. Bladder cancer: diagnosis and treatment. Am Fam Physician. 2017;96(8):507-14. [View at Publisher] [PMID] [Google Scholar]
6. Ivanisevic T, Sewduth RN. Multi-omics integration for the design of novel therapies and the identification of novel biomarkers. Proteomes.
2023;11(4):34. [View at Publisher] [DOI] [PMID] [Google Scholar]
7. Kirk S, Lee Y, Lucchesi F, Aredes N, Gruszauskas N, Catto J, et al. The Cancer Genome Atlas Urothelial Bladder Carcinoma Collection (TCGA-BLCA)(Version 8)[Data set]. Cancer Imaging Arch. 2016;K9(10). [View at Publisher] [DOI]
8. Cortés-Ciriano I, Gulhan DC, Lee JJ-K, Melloni GE, Park PJ. Computational analysis of cancer genome sequencing data. Nat Rev Genet.
2022;23(5):298-314. [View at Publisher] [DOI] [PMID] [Google Scholar]
9. Shen J, Shi J, Luo J, Zhai H, Liu X, Wu Z, et al. Deep learning approach for cancer subtype classification using high-dimensional gene expression data. BMC bioinformatics. 2022;23(1):430. [View at Publisher] [DOI] [PMID] [Google Scholar]
10. Robertson AG, Kim J, Al-Ahmadie H, Bellmunt J, Guo G, Cherniack AD, et al. Comprehensive molecular characterization of muscle-invasive bladder cancer. Cell. 2017;171(3):540-56.e25. [View at Publisher] [PMID] [Google Scholar]
11. Glaab E, Rauschenberger A, Banzi R, Gerardi C, Garcia P, Demotes J. Biomarker discovery studies for patient stratification using machine learning analysis of omics data: a scoping review. BMJ Open. 2021;11(12):e053674. [View at Publisher] [DOI] [PMID] [Google Scholar]
12. Al-Tashi Q, Saad MB, Muneer A, Qureshi R, Mirjalili S, Sheshadri A, et al. Machine learning models for the identification of prognostic and predictive cancer biomarkers: a systematic review. Int J Mol Sci. 2023;24(9):7781. [View at Publisher] [DOI] [PMID] [Google Scholar]
13. Mazlan AU, binti Sahabudin NA, Remli MA, Ismail NSN, Mohamad MS, Abd Warif NB, editors. Supervised and unsupervised machine learning for cancer classification: recent development. 2021 IEEE International Conference on Automatic Control & Intelligent Systems (I2CACIS); 2021: IEEE. [View at Publisher] [DOI]
14. Li J, Wang Z, Wang T. Machine-learning prediction of a novel diagnostic model using mitochondria-related genes for patients with bladder cancer. Sci Rep. 2024;14(1):9282. [View at Publisher] [DOI] [PMID] [Google Scholar]
15. Liosis KC. Utilizing Machine Learning Methods for Genomic Biomarker Discovery in Prostate and Bladder Cancer. 2021. [View at Publisher] [Google Scholar]
16. Liosis KC, Marouf AA, Rokne JG, Ghosh S, Bismar TA, Alhajj R. Genomic Biomarker Discovery in Disease Progression and Therapy Response in Bladder Cancer Utilizing Machine Learning. Cancers. 2023;15(19):4801. [View at Publisher] [DOI] [PMID] [Google Scholar]
17. Kolberg L, Raudvere U, Kuzmin I, Adler P, Vilo J, Peterson H. g: Profiler-interoperable web service for functional enrichment analysis and gene identifier mapping (2023 update). Nucleic Acids Res. 2023;51(W1):W207-W12. [View at Publisher] [DOI] [PMID] [Google Scholar]
18. Ge SX, Jung D, Yao R. ShinyGO: a graphical gene-set enrichment tool for animals and plants. Bioinformatics. 2020;36(8):2628-9. [View at Publisher] [DOI] [PMID] [Google Scholar]
19. Berrar D. Performance measures for binary classification. In: Encyclopedia of Bioinformatics and Computational Biology. Vol. 1. Amsterdam: Elsevier; 2019. p. 546-60. [View at Publisher] [DOI] [Google Scholar]
20. Chen Q, Yang C, Chen L, Zhang J-J, Ge W-L, Yuan H, et al. YY1 targets tubulin polymerisation-promoting protein to inhibit migration, invasion and angiogenesis in pancreatic cancer via p38/MAPK and PI3K/AKT pathways. Br J Cancer. 2019;121(11):912-21. [View at Publisher] [DOI] [PMID] [Google Scholar]
21. Li Y, Xu Y, Ye K, Wu N, Li J, Liu N, et al. Knockdown of tubulin polymerization promoting protein family member 3 suppresses proliferation and induces apoptosis in non-small-cell lung cancer. J Cancer. 2016;7(10):1189-96. [View at Publisher] [DOI] [PMID] [Google Scholar]
22. Xiao T, Lin F, Zhou J, Tang Z. The expression and role of tubulin polymerization-promoting protein 3 in oral squamous cell carcinoma. Arch Oral Biol.
2022;143:105519. [View at Publisher] [DOI] [PMID] [Google Scholar]
23. Alevizopoulos A, Tyritzis S, Leotsakos I, Anastasopoulou I, Pournaras C, Kotsis P, et al. Role of coagulation factors in urological malignancy: a prospective, controlled study on prostate, renal and bladder cancer. Int J Urol. 2017;24(2):130-6. [View at Publisher] [DOI] [PMID] [Google Scholar]
24. Xie F, Qu J, Lin D, Feng K, Tan M, Liao H, et al. Reduced Proteolipid Protein 2 promotes endoplasmic reticulum stress-related apoptosis and increases drug sensitivity in acute myeloid leukemia. Mol Biol Rep. 2023;51(1):10. [View at Publisher] [DOI] [PMID] [Google Scholar]
25. Wang H, Liu J, Lou Y, Liu Y, Chen J, Liao X, et al. Identification and preliminary analysis of hub genes associated with bladder cancer progression by comprehensive bioinformatics analysis. Sci Rep. 2024;14(1):2782. [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. |
