2025 Vol.8 Apr.N02

• Title: Ensemble feature selection for Tumor Immune System
• Name: Jiajia Lu, Meifang Li, Rui Li, Xiaofang Li
• Company: School of Computer Information Engineering,Shanxi Technology And Business University,Taiyuan 030062, China
• Abstract:

  In recent years, machine learning algorithms have become increasingly prevalent in medical diagnosis applications. To gain insights into the vital immune cells involved in antitumor processes, this paper introduces an ensemble feature selection approach tailored for modeling the tumor immune system,based on matrix method and blockedcross-validation. This methodology incorporates ensemble feature selection techniques and classification algorithms from the realm of machine learning into the investigation of the tumor immune system, utilizing accuracy rate as the primary metric for assessing classification performance. The aim is to develop an ensemble feature selection model that can identify key immune cells in tumor immunity. To validate the model, colorectal cancer data is employed as a case study. The results indicate that the ratios of natural killer (NK) cells, total B lymphocyte (BLB) count, and the ratio of helper T cells to cytotoxic T cells, as identified through the ensemble feature selection approach, are crucial factors in the immune cell landscape of colorectal cancer. Remarkably, this ensemble feature selection method improves the diagnostic accuracy of colorectal cancer. This methodology offers a theoretical framework for analyzing key  cellular components in tumor immunity and diagnosis, holding great potential for similar investigations into the immune systems of other tumors.

  
  

• Keyword: Ensemble Feature selection,Tumor Immune, colorectal cancer, blockedcross-validation
• DOI: 10.12250/jpciams2025090416
• Citation form: 名字.题目[J]. Computer Informatization and Mechanical System,2025,Vol.8,pp.

REFERENCES

[1] Y. Wang, J. Yu, T. Ju, Y. Chen, and Z. Wang, “Research progress of immune cells against tumor,” in 2023 IEEE International Conference on Manipulation, Manufacturing and Measurement on the Nanoscale (3M-NANO), 2023, pp. 358–361.

[2] E. A. Kuzina and N. A. Babushkina, “Mathematical modeling of anti- tumor vaccinotherapy: The interaction of immune  system with tumor cells,” in 2019 Twelfth International Conference ”Management of large- scale system development” (MLSD), 2019, pp. 1–5.

[3] S. Shafiekhani, S. Rahbar, F. Akbarian, and A. H. Jafari, “Fuzzy stochastic petri net with uncertain kinetic parameters for  modeling tumor-immune system,” in 2018 25th National and 3rd International Iranian Conference on Biomedical Engineering (ICBME), 2018, pp. 1– 5.

[4] C. I. Nwabugwu, K. Rakhra, D. W. Felsher, and D. S. Paik, “A tumor- immune mathematical model of cd4+ t helper cell  dependent tumor regression by oncogene inactivation,” in 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2013, pp. 4529–4532.

[5] A. Arabameri, D. Asemani, and J. Hajati, “Mathematical model of cancer immunotherapy by dendritic cells combined with tumor hypoxia treatment,” in 2018 25th National and 3rd International Iranian Con- ference on Biomedical Engineering (ICBME), 2018, pp. 1–6.

[6] B. A. D. Gopika, “An analysis on ensemble methods in classification tasks,”   International Journal  of Advanced Research in Computer and Communication Engineering, vol. 3, pp. 7423 – 7427, 2014. [Online]. Available: https://api.semanticscholar.org/CorpusID:7121676

[7] V. L. D. Peter, G. Matej, “Ensemble feature selection using election methods and ranker clustering,” Information Sciences, vol. 480, pp. 365– 380, 2019.

[8] I. Guyon and A. Elisseeff, “An introduction to variable and feature selection,” J. Mach. Learn. Res., vol. 3, no. null, p.  11571182, mar 2003.

[9] A.-B. V.Boln-Canedo, N.Snchez-Maroo, “An ensemble of fifilters and classififiers for microarray data classifification,” vol. 45, no. 1, 2012, p. 531539.

[10] X. Yang, Y. Wang, R. Wang, and J. Li, “Ensemble feature selection with block-regularized m × 2 cross-validation,” IEEE Transactions on Neural Networks and Learning Systems, vol. 34, no. 9, pp. 6628–6641, 2023.

[11] M. Shahhosseini, G. Hu, and H. Pham, “Optimizing ensemble weights and hyperparameters of machine learning models for regression prob- lems,” 2020.

[12] H.  J.  J.  L.  Y.  Wang,  R.B.  Wang,  “Blocked  3  × 2  cross-validated  t- test for comparing supervised classification learning algorithms,” Neural Computation, vol. 1, pp. 208–235, 2014.

[13] D. K. e. a. C. Century, K. Tianrui, “Research progress of immunotherapy based on nk cells in liver cancer,”  IJournal  of  Clinical Hepatobiliary Diseases, vol. 39, no. 06, pp. 1476–1781, 2023.

[14] W.  F.  Chen  Y,  Lu  Y,  “Predictive  value  of  cd4+/cd8+  after  treatment  on the curative effect of immune checkpoint inhibitor combined with  pingxiao capsule in the treatment of digestive system malignant tumor.” Cancer Foundation and Clinical, vol. 36, no. 02, pp. 137–142, 2023.

[15] L.  X.  Zhang  XD,  “Expression  and  significance  of  regulatory  t  cells, helper  t  cells   17  and  their  related  cytokines  in  peripheral  blood  of patients  with  acute  myeloid  leukemia.”  Journal  of  Xinxiang  Medical College, vol. 40, no. 04, pp. 339–342+352, 2023.

[16] A.  Santamaria-Pang,  R.  K.  Padmanabhan,  A.   Sood,  M.  J.   Gerdes, C.  Sevinsky,  Q.  Li,  N.  LaPlante,  and  F.  Ginty,  “Robust  single  cell quantification of immune cell subtypes in histological samples,” 2017, pp. 121–124.

[17] L. Hazanov, R. Mehr, Y.-C. B. Wu, and D. K. Dunn-Walters, “Lineage tree analysis of high throughput immunoglobulin sequencing clarifies b cell maturation pathways,” 2015, pp. 1–6.

[18] P. Han, yu De Chen, and F. Yang, “Identified and validated the characterization of the colorectal cancer tumor immune microenvironment,” 2020.

[19] M. A. Al-Mterin,  K. Murshed,  and E. Elkord, “Correlations between circulating and tumor-infiltrating cd4+ t cell  subsets with immune checkpoints in colorectal cancer,” vol. 10, pp. 538–538, 2022.

[20] H. Chen and X. Yao, “Multiobjective neural network ensembles based on regularized negative correlation learning,” IEEE Transactions on Knowledge and Data Engineering, vol. 22, no. 12, pp. 1738–1751, 2010.

[21] J.-R. Y. Brown, G.Wyatt, “Diversity creation methods:a survey and categorisation,” Information Fusion, vol. 6, no. 1, pp. 5–20, 2005.

[22] M. A. Ganaie, M. Hu, M. Tanveer,  and P. N.  Suganthan,  “Ensemble deep learning: A review,” CoRR, vol. abs/2104.02395, 2021.  [Online]. Available: https://arxiv.org/abs/2104.02395

[23] L. Hansen and P. Salamon, “Neural network ensembles,” IEEE Trans- actions on Pattern Analysis and Machine Intelligence, vol.  12, no.  10, pp. 993–1001, 1990.

[24] Z. Gu, X. Yang, Q. Zhang, W. Yu, and Z. Liu, “Terl: Two-stage ensemble reinforcement learning paradigm for large-scale decentralized decision making in transportation simulation,” IEEE Transactions on Knowledge and Data Engineering, vol. 35, no. 12, pp. 13 043–13 054, 2023.

[25] M.  Manonmani  and  S.  Balakrishnan,  “An  ensemble  feature  selection method  for  prediction  of  ckd,”  in  2020  International  Conference  on Computer Communication and Informatics (ICCCI), 2020, pp. 1–6.

[26] S.  S.  Kshatri,  D.   Singh,  and  D.   S.  Sisodia,  “Multiple  aggregation model using ensembles classifier for feature selection: A homogeneous approach,”  in   2021   IEEE  International   Conference   on   Technology, Research,  and Innovation for Betterment  of  Society  (TRIBES),  2021, pp. 1–6.

[27] M.  R.  Alhamidi,  D.  M.  S.  Arsa,  M.  F.  Rachmadi,  and  W.  Jatmiko,  “2-dimensional  homogeneous  distributed  ensemble  feature  selection,” in   2018 International Conference on Advanced Computer Science and  Information Systems (ICACSIS), 2018, pp. 367–372.

[28] R.  Wang,  Y.  Wang,  J.  Li,  X.  Yang,  and  J.  Yang,  “Block-regularized m × 2 cross-validated  estimator  of  the  generalization  error,”  Neural Computation, vol. 29, no. 2, pp. 519–554, 2017.

[29] N. Cheng, C. Bi, Y. Shi, M. Liu, A. Cao, M. Ren, J. Xia, and Z. Liang, “Effect predictor of driver synonymous mutations based on multi-feature fusion  and  iterative  feature representation  learning,” IEEE Journal  of Biomedical and Health Informatics, vol. 28, no. 2, pp. 1144–1151, 2024.