IDENTIFICATION AND GLOBAL INTERPRETATION OF POSSIBLE BIOMARKERS FOR THE DIAGNOSIS OF PANCREATIC CANCER USING EXPLAINABLE ARTIFICIAL INTELLIGENCE METHODS

Year 2025, Volume: 13 Issue: 1, 62 - 73

Şeyma Yaşar

https://doi.org/10.33715/inonusaglik.1571883

Abstract

Pancreatic cancer is a highly lethal malignancy with poor prognosis and limited early diagnosis methods. In this study, 60 serum samples (30 pancreatic cancer patients, 30 controls) were analyzed to identify potential biomarkers for early detection using machine learning. Proteomic data were obtained via glycoprotein enrichment and mass spectrometry, identifying 232 proteins. After preprocessing, 29 proteins were selected using the Elastic Net method. XGBoost, optimized with 10-fold cross-validation, classified pancreatic cancer with high performance (AUC=0.850, accuracy=0.833). The SHAP method identified P02750 (Leucine-rich alpha-2-glycoprotein), P02766 (Transthyretin), P01031 (Complement C5), and P02649 (Apolipoprotein E) as key proteins affecting cancer risk. These biomarkers may play a crucial role in early diagnosis and personalized treatment, but further validation in larger studies is required.

Keywords

Biomarker, Explainable artificial intelligence, Pancreatic cancer, XGBoost

Açıklanabilir Yapay Zekâ Yöntemleri Kullanılarak Pankreas Kanseri Tanısı için Olası Biyobelirteçlerin Belirlenmesi ve Global Olarak Yorumlanması

Abstract

Pankreas kanseri, kötü prognozu ve sınırlı erken tanı yöntemleri ile oldukça ölümcül bir malignitedir. Bu çalışmada, 60 serum örneği (30 pankreas kanseri hastası, 30 kontrol) makine öğrenimi kullanılarak erken teşhis için potansiyel biyobelirteçleri belirlemek üzere analiz edilmiştir. Proteomik veriler glikoprotein zenginleştirme ve kütle spektrometrisi yoluyla elde edilmiş ve 232 protein tanımlanmıştır. Ön işlemeden sonra, 29 protein Elastik Ağ yöntemi kullanılarak seçilmiştir. XGBoost, 10 kat çapraz doğrulama ile optimize edilmiş, pankreas kanserini yüksek performansla sınıflandırmıştır (AUC= 0.850, doğruluk = 0.833). SHAP yöntemi, P02750 (Lösinden zengin alfa-2-glikoprotein), P02766 (Transtiretin), P01031 (Complement C5) ve P02649'u (Apolipoprotein E) kanser riskini etkileyen anahtar proteinler olarak tanımlamıştır. Bu biyobelirteçler erken tanı ve kişiselleştirilmiş tedavide önemli bir rol oynayabilir, ancak daha büyük çalışmalarda daha fazla doğrulama yapılması gerekmektedir.

Keywords

Açıklanabilir yapay zekâ, Biyobelirteç, Pankreas kanseri, XGBoost

References

• Ansari, D., Torén, W., Zhou, Q., Hu, D. & Andersson, R. (2019). Proteomic and genomic profiling of pancreatic cancer. Cell biology and toxicology, 35, 333-343.
• Bascarán, J. B., Leal, Á. F., Mosqueira-Rey, E., Ríos, D. A., Hernández-Pereira, E. & Moret-Bonillo, V. (2023). Understanding Machine Learning Explainability Models in the context of Pancreatic Cancer Treatment. Paper presented at the VI Congreso XoveTIC: impulsando el talento científico.
• Chen, J., Chen, L.-J., Xia, Y.-L., Zhou, H.-C., Yang, R.-B., Wu, W., . . . Zhao, Y. (2013). Identification and verification of transthyretin as a potential biomarker for pancreatic ductal adenocarcinoma. Journal of Cancer Research and Clinical Oncology, 139, 1117-1127.
• Develi, I. & Sorgucu, U. (2015). Prediction of temperature distribution in human BEL exposed to 900 MHz mobile phone radiation using ANFIS. Applied Soft Computing, 37, 1029-1036.
• Emmanuel, T., Maupong, T., Mpoeleng, D., Semong, T., Mphago, B. & Tabona, O. (2021). A survey on missing data in machine learning. Journal of Big data, 8, 1-37.
• Halbrook, C. J., Lyssiotis, C. A., di Magliano, M. P. & Maitra, A. (2023). Pancreatic cancer: Advances and challenges. Cell, 186(8), 1729-1754.
• Hanna-Sawires, R. G., Schiphuis, J. H., Wuhrer, M., Vasen, H. F., van Leerdam, M. E., Bonsing, B. A., . . . Tollenaar, R. A. (2021). Clinical perspective on proteomic and glycomic biomarkers for diagnosis, prognosis, and prediction of pancreatic cancer. International journal of molecular sciences, 22(5), 2655.
• Huang, B., Huang, H., Zhang, S., Zhang, D., Shi, Q., Liu, J. & Guo, J. (2022). Artificial intelligence in pancreatic cancer. Theranostics, 12(16), 6931.
• Hussain, N., Das, D., Pramanik, A., Pandey, M. K., Joshi, V.,& Pramanik, K. C. (2022). Targeting the complement system in pancreatic cancer drug resistance: a novel therapeutic approach. Cancer Drug Resistance, 5(2), 317.
• Jenul, A., Schrunner, S., Huynh, B. N. & Tomic, O. (2021). RENT: A Python package for repeated elastic net feature selection. Journal of Open Source Software, 6(63), 3323.
• Kemp, S. B., Carpenter, E. S., Steele, N. G., Donahue, K. L., Nwosu, Z. C., Pacheco, A., . . . The, S. (2021). Apolipoprotein E promotes immune suppression in pancreatic cancer through NF-κB–mediated production of CXCL1. Cancer research, 81(16), 4305-4318.
• Kenner, B., Chari, S. T., Kelsen, D., Klimstra, D. S., Pandol, S. J., Rosenthal, M., . . . Abul-Husn, N. (2021). Artificial intelligence and early detection of pancreatic cancer: 2020 summative review. Pancreas, 50(3), 251-279.
• Kolbeinsson, H. M., Chandana, S., Wright, G. P. & Chung, M. (2023). Pancreatic cancer: a review of current treatment and novel therapies. Journal of Investigative Surgery, 36(1), 2129884.
• Lin, M., Liu, J., Zhang, F., Qi, G., Tao, S., Fan, W., . . . Zhou, F. (2022). The role of leucine-rich alpha-2-glycoprotein-1 in proliferation, migration, and invasion of tumors. Journal of Cancer Research and Clinical Oncology, 1-9.
• Mizrahi, J. D., Surana, R., Valle, J. W. & Shroff, R. T. (2020). Pancreatic cancer. The Lancet, 395(10242), 2008-2020.
• Nanno, Y., Toyama, H., Mizumoto, T., Ishida, J., Urade, T., Fukushima, K., . . . Asari, S. (2024). Preoperative level of serum transthyretin as a novel biomarker predicting survival in resected pancreatic ductal adenocarcinoma with neoadjuvant therapy. Pancreatology, 24(6), 917-924.
• Nie, S., Lo, A., Wu, J., Zhu, J., Tan, Z., Simeone, D. M., . . . Lubman, D. M. (2014). Glycoprotein biomarker panel for pancreatic cancer discovered by quantitative proteomics analysis. Journal of Proteome Research, 13(4), 1873-1884.
• Nsingwane, Z., Naicker, P., Omoshoro-Jones, J., Devar, J., Smith, M., Candy, G., . . . Nweke, E. E. (2023). Inhibition of the Complement Pathway Induces Cellular Proliferation and Migration in Pancreatic Ductal Adenocarcinoma. medRxiv, 2023.2008. 2008.23293417.
• Otsuru, T., Kobayashi, S., Wada, H., Takahashi, T., Gotoh, K., Iwagami, Y., . . . Serada, S. (2019). Epithelial‐mesenchymal transition via transforming growth factor beta in pancreatic cancer is potentiated by the inflammatory glycoprotein leucine‐rich alpha‐2 glycoprotein. Cancer science, 110(3), 985-996.
• Qureshi, T. A., Javed, S., Sarmadi, T., Pandol, S. J. & Li, D. (2022). Artificial intelligence and imaging for risk prediction of pancreatic cancer. Chinese clinical oncology, 11(1), 1.
• Shams, M. Y., Elshewey, A. M., El-Kenawy, E.-S. M., Ibrahim, A., Talaat, F. M. & Tarek, Z. (2024). Water quality prediction using machine learning models based on grid search method. Multimedia Tools and Applications, 83(12), 35307-35334.
• Sorgucu, U., Kabalcı, Y., Develi, İ. ve Bilim, M. (2011). Aşırı Düşük Frekanslı Elektromanyetik Alanın Derideki Hidroksiprolin Seviyesi Üzerine Olan Etkisinin ANFIS Kullanılarak Modellenmesi. Paper presented at the 6th International Advanced Technologies Symposium (IATS’11).
• Srinidhi, B. & Bhargavi, M. (2023). An XAI Approach to Predictive Analytics of Pancreatic Cancer. Paper presented at the 2023 International Conference on Information Technology (ICIT).
• Swathi, K. & Kodukula, S. (2022). XGBoost Classifier with Hyperband Optimization for Cancer Prediction Based on Geneselection by Using Machine Learning Techniques. Revue d'Intelligence Artificielle, 36(5).
• Venkatesh, B. & Anuradha, J. (2019). A review of feature selection and its methods. Cybernetics and information technologies, 19(1), 3-26.
• Wu, B., Yang, X., Chen, F., Song, Z., Ding, X. & Wang, X. (2024). Apolipoprotein E is a prognostic factor for pancreatic cancer and associates with immune infiltration. Cytokine, 179, 156628.
• Xia, J., Zhang, S., Cai, G., Li, L., Pan, Q., Yan, J. & Ning, G. (2017). Adjusted weight voting algorithm for random forests in handling missing values. Pattern Recognition, 69, 52-60.
• Yang, Z., LaRiviere, M. J., Ko, J., Till, J. E., Christensen, T., Yee, S. S., . . . Shen, H. (2020). A multianalyte panel consisting of extracellular vesicle miRNAs and mRNAs, cfDNA, and CA19-9 shows utility for diagnosis and staging of pancreatic ductal adenocarcinoma. Clinical Cancer Research, 26(13), 3248-3258.
• Yasar, S., Yagin, F. H., Melekoglu, R. & Ardigò, L. P. (2024). Integrating proteomics and explainable artificial intelligence: a comprehensive analysis of protein biomarkers for endometrial cancer diagnosis and prognosis. Frontiers in Molecular Biosciences, 11, 1389325.
• Zheng, H., Zhao, J., Wang, X., Yan, S., Chu, H., Gao, M. & Zhang, X. (2022). Integrated pipeline of rapid isolation and analysis of human plasma exosomes for cancer discrimination based on deep learning of MALDI-TOF MS fingerprints. Analytical Chemistry, 94(3), 1831-1839.