Prediction of postoperative recovery in patients with acoustic neuroma using machine learning and SMOTE-ENN techniques

Jianing Wang; Jianing Wang

doi:10.3934/mbe.2022487

Mathematical Biosciences and Engineering

2022, Volume 19, Issue 10: 10407-10423. doi: 10.3934/mbe.2022487

Previous Article Next Article

Research article Special Issues

Prediction of postoperative recovery in patients with acoustic neuroma using machine learning and SMOTE-ENN techniques

Jianing Wang ^,

School of Mathematics and Statistics, Central South University, Changsha 410083, China

Academic Editor: Soheila Borhani

Received: 22 April 2022 Revised: 23 June 2022 Accepted: 03 July 2022 Published: 22 July 2022

Acoustic neuroma is a common benign tumor that is frequently associated with postoperative complications such as facial nerve dysfunction, which greatly affects the physical and mental health of patients. In this paper, clinical data of patients with acoustic neuroma treated with microsurgery by the same operator at Xiangya Hospital of Central South University from June 2018 to March 2020 are used as the study object. Machine learning and SMOTE-ENN techniques are used to accurately predict postoperative facial nerve function recovery, thus filling a gap in auxiliary diagnosis within the field of facial nerve treatment in acoustic neuroma. First, raw clinical data are processed and dependent variables are identified based on clinical context and data characteristics. Secondly, data balancing is corrected using the SMOTE-ENN technique. Finally, XGBoost is selected to construct a prediction model for patients' postoperative recovery, and is also compared with a total of four machine learning models, LR, SVM, CART, and RF. We find that XGBoost can most accurately predict the postoperative facial nerve function recovery, with a prediction accuracy of 90.0$ \% $ and an AUC value of 0.90. CART, RF, and XGBoost can further select the more important preoperative indicators and provide therapeutic assistance to physicians, thereby improving the patient's postoperative recovery. The results show that machine learning and SMOTE-ENN techniques can handle complex clinical data and achieve accurate predictions.
- XGBoost,
- SMOTE-ENN,
- machine learning,
- acoustic neuroma,
- postoperative recovery
Citation: Jianing Wang. Prediction of postoperative recovery in patients with acoustic neuroma using machine learning and SMOTE-ENN techniques[J]. Mathematical Biosciences and Engineering, 2022, 19(10): 10407-10423. doi: 10.3934/mbe.2022487

Related Papers:

Abstract

Acoustic neuroma is a common benign tumor that is frequently associated with postoperative complications such as facial nerve dysfunction, which greatly affects the physical and mental health of patients. In this paper, clinical data of patients with acoustic neuroma treated with microsurgery by the same operator at Xiangya Hospital of Central South University from June 2018 to March 2020 are used as the study object. Machine learning and SMOTE-ENN techniques are used to accurately predict postoperative facial nerve function recovery, thus filling a gap in auxiliary diagnosis within the field of facial nerve treatment in acoustic neuroma. First, raw clinical data are processed and dependent variables are identified based on clinical context and data characteristics. Secondly, data balancing is corrected using the SMOTE-ENN technique. Finally, XGBoost is selected to construct a prediction model for patients' postoperative recovery, and is also compared with a total of four machine learning models, LR, SVM, CART, and RF. We find that XGBoost can most accurately predict the postoperative facial nerve function recovery, with a prediction accuracy of 90.0$ \% $ and an AUC value of 0.90. CART, RF, and XGBoost can further select the more important preoperative indicators and provide therapeutic assistance to physicians, thereby improving the patient's postoperative recovery. The results show that machine learning and SMOTE-ENN techniques can handle complex clinical data and achieve accurate predictions.

References

[1]	J. Halliday, S. A. Rutherford, M. G. McCabe, D. G. Evans, An update on the diagnosis and treatment of vestibular schwannoma, Expert Rev. Neurother., 18 (2018), 29–39. https://doi.org/10.1080/14737175.2018.1399795 doi: 10.1080/14737175.2018.1399795
[2]	D. Starnoni, R. T. Daniel, C. Tuleasca, M. George, M. Levivier, M. Messerer, Systematic review and meta-analysis of the technique of subtotal resection and stereotactic radiosurgery for large vestibular schwannomas: a "nerve-centered" approach, Neurosurg. Focus, 44 (2018), E4. https://doi.org/10.3171/2017.12.FOCUS17669 doi: 10.3171/2017.12.FOCUS17669
[3]	B. Acs, M. Rantalainen, J. Hartman, Artificial intelligence as the next step towards precision pathology, J. Intern. Med., 288 (2020), 62–81. https://doi.org/10.1111/joim.13030 doi: 10.1111/joim.13030
[4]	J. Goecks, V. Jalili, L. Heiser, J. Gray, How machine learning will transform biomedicine, Cell, 181 (2020), 92–101. https://doi.org/10.1016/j.cell.2020.03.022 doi: 10.1016/j.cell.2020.03.022
[5]	G. S. Handelman, H. K. Kok, R. V. Chandra, A. H. Razavi, M. J. Lee, H. Asadi, eDoctor: machine learning and the future of medicine, J. Intern. Med., 284 (2018), 603–609. https://doi.org/10.1111/joim.12822 doi: 10.1111/joim.12822
[6]	M. M. Hasan, M. A. Alam, W. Shoombuatong, H. W. Deng, B. Manavalan, H. Kurata, NeuroPred-FRL: an interpretable prediction model for identifying neuropeptide using feature representation learning, Briefings Bioinf., 22 (2021). https://doi.org/10.1093/bib/bbab167
[7]	A. Hoshino, H. S. Kim, L. Bojmar, K. E. Gyan, M. Cioffi, J. Hernandez, et al., Extracellular vesicle and particle biomarkers define multiple human cancers, Cell, 18 (2020), 1044–1061. https://doi.org/10.1016/j.cell.2020.07.009 doi: 10.1016/j.cell.2020.07.009
[8]	B. Koo, J. K. Rhee, Prediction of tumor purity from gene expression data using machine learning, Briefings Bioinf., 22 (2021). https://doi.org/10.1093/bib/bbab163
[9]	H. Luo, Q. Zhao, W. Wei, L. Zheng, S. Yi, G. Li, et al., Circulating tumor DNA methylation profiles enable early diagnosis, prognosis prediction, and screening for colorectal cancer, Sci. Transl. Med., 12 (2020). https://doi.org/10.1126/scitranslmed.aax7533
[10]	L. Huang, L. Wang, X. Hu, S. Chen, Y. Tao, H. Su, et al., Machine learning of serum metabolic patterns encodes early-stage lung adenocarcinoma, Nat. Commun., 11 (2020), 3556. https://doi.org/10.1038/s41467-020-17347-6 doi: 10.1038/s41467-020-17347-6
[11]	M. K. Abd Ghani, M. A. Mohammed, N. Arunkumar, S. A. Mostafa, D. A. Ibrahim, M. K. Abdullah, et al., Decision-level fusion scheme for nasopharyngeal carcinoma identification using machine learning techniques, Neural Comput. Appl., 32 (2020), 625–638. https://doi.org/10.1007/s00521-018-3882-6 doi: 10.1007/s00521-018-3882-6
[12]	P. Achilli, C. Magistro, M. A. A. E. Aziz, G. Calini, C. L. Bertoglio, G. Ferrari, et al., Modest agreement between magnetic resonance and pathological tumor regression after neoadjuvant therapy for rectal cancer in the real world, Int. J. Cancer, (2022), 1–8. https://doi.org/10.1002/ijc.33975
[13]	Z. M. Zhuang, Z. B. Yang, S. X. Zhuang, A. N. J. Raj, Y. Yuan, R. Nersisson, Multi-features-based automated breast tumor diagnosis using ultrasound image and support vector machine, Comput. Intell. Neurosci., 2021 (2021). https://doi.org/10.1155/2021/9980326
[14]	M. M. Ghiasi, S. Zendehboudi, Application of decision tree-based ensemble learning in the classification of breast cancer, Comput. Biol. Med., 128 (2021). https://doi.org/10.1016/j.compbiomed.2020.104089
[15]	A. Moncada-Torres, M. C. van Maaren, M. P. Hendriks, S. Siesling, G. Geleijnse, Explainable machine learning can outperform Cox regression predictions and provide insights in breast cancer survival, Sci. Rep., 11 (2021). https://doi.org/10.1038/s41598-021-86327-7
[16]	C. Yang, X. W. Huang, Y. Li, J. F. Chen, Y. Y. Lv, S. X. Dai, et al., Prognosis and personalized treatment prediction in TP53-mutant hepatocellular carcinoma: an in silico strategy towards precision oncology, Briefings Bioinf., 22 (2021). https://doi.org/10.1093/bib/bbaa164
[17]	Y. Q. Wu, N. Jiao, R. X. Zhu, Y. D. Zhang, D. F. Wu, A. J. Wang, et al., Identification of microbial markers across populations in early detection of colorectal cancer, Nat. Commun., 12 (2021). https://doi.org/10.1038/s41467-021-23265-y
[18]	L. Zhang, H. X. Ai, W. Chen, Z. M. Yin, H. Hu, J. F. Zhu, et al., CarcinoPred-EL: Novel models for predicting the carcinogenicity of chemicals using molecular fingerprints and ensemble learning methods, Sci. Rep., 7 (2017). https://doi.org/10.1038/s41598-017-02365-0
[19]	A. Tahmassebi, G. J. Wengert, T. H. Helbich, Z. Bago-Horvath, S. Alaei, R. Bartsch, et al., Impact of machine learning with multiparametric magnetic resonance imaging of the breast for early prediction of response to neoadjuvant chemotherapy and survival outcomes in breast cancer patients, Invest. Radiol., 54 (2019), 110–117. https://doi.org/10.1097/RLI.0000000000000518 doi: 10.1097/RLI.0000000000000518
[20]	J. Li, Z. Shi, F. Liu, X. Fang, K. Cao, Y. H. Meng, et al., XGBoost classifier based on computed tomography radiomics for prediction of tumor-infiltrating CD8+T-Cells in patients with pancreatic ductal adenocarcinoma, Front. Oncol., 11 (2021). https://doi.org/10.3389/fonc.2021.671333
[21]	K. Thedinga, R. Herwig, A gradient tree boosting and network propagation derived pan-cancer survival network of the tumor microenvironment, iScience, 25 (2021), 103617. https://doi.org/10.1016/j.isci.2021.103617 doi: 10.1016/j.isci.2021.103617
[22]	W. Tang, H. Zhou, T. H. Quan, X. Y. Chen, H. N. Zhang, Y. Lin, et al., XGboost prediction model based on 3.0T diffusion kurtosis imaging improves the diagnostic accuracy of MRI BiRADS 4 masses, Front. Oncol., 12 (2022), 833680. https://doi.org/10.3389/fonc.2022.833680 doi: 10.3389/fonc.2022.833680
[23]	B. Fu, P. Liu, J. Lin, L. Deng, K. Hu, H. Zheng, Predicting invasive disease-free survival for early stage breast cancer patients using follow-up clinical data, IEEE Trans. Biomed. Eng., 66 (2019), 2053–2064. https://doi.org/10.1109/TBME.2018.2882867 doi: 10.1109/TBME.2018.2882867
[24]	S. L. Li, X. J. Zhang, Research on orthopedic auxiliary classification and prediction model based on XGBoost algorithm, Neural Comput. Appl., 32 (2020), 1971–1979. https://doi.org/10.1007/s00521-019-04378-4 doi: 10.1007/s00521-019-04378-4
[25]	Y. M. Hsiao, C. L. Tao, E. Y. Chuang, T. P. Lu, A risk prediction model of gene signatures in ovarian cancer through bagging of GA-XGBoost models, J. Adv. Res., 30 (2021), 113–122. https://doi.org/10.1016/j.jare.2020.11.006 doi: 10.1016/j.jare.2020.11.006
[26]	B. Krawczyk, Learning from imbalanced data: open challenges and future directions, Prog. Artif. Intell., 5 (2016), 221–232. https://doi.org/10.1007/s13748-016-0094-0 doi: 10.1007/s13748-016-0094-0
[27]	S. Fotouhi, S. Asadi, M. W. Kattan, A comprehensive data level analysis for cancer diagnosis on imbalanced data, J. Biomed. Inf., 90 (2019). https://doi.org/10.1016/j.jbi.2018.12.003
[28]	N. V. Chawla, K. W. Bowyer, L. O. Hall, W. P. Kegelmeyer, SMOTE: synthetic minority over-sampling technique, J. Artif. Intell. Res., 6 (2001), 321–357. https://doi.org/10.1613/jair.953 doi: 10.1613/jair.953
[29]	G. Batista, R. C. Prati, M. C. Monard, A study of the behavior of several methods for balancing machine learning training data, ACM SIGKDD Explor. Newsl., 6 (2004), 20–29. https://doi.org/10.1145/1007730.1007735 doi: 10.1145/1007730.1007735
[30]	S. Fotouhi, S. Asadi, M. W. Kattan, A comprehensive data level analysis for cancer diagnosis on imbalanced data, J. Biomed. Inf., 90 (2019). https://doi.org/10.1016/j.jbi.2018.12.003
[31]	X. Huang, T. Y. Cao, L. Z. Q. Chen, J. P. Li, Z. H. Tan, B. J. M. Xu, et al., Novel insights on establishing machine learning-based stroke prediction models among hypertensive adults, Front. Cardiovasc. Med., 9 (2022). https://doi.org/10.3389/fcvm.2022.901240
[32]	L. Breiman, Random forest, Mach. Learn., 45 (2001), 5–32. https://doi.org/10.1023/A:1010933404324
[33]	T. Q. Chen, C. Guestrin, XGBoost: a scalable tree boosting system, in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, (2016), 785–794. https://doi.org/10.1145/2939672.2939785
[34]	M. Sokolova, G. Lapalme, TA systematic analysis of performance measures for classification tasks, Inf. Process. Manage., 45 (2009), 427–437. https://doi.org/10.1016/j.ipm.2009.03.002 doi: 10.1016/j.ipm.2009.03.002
[35]	A. P. Bradley, The use of the area under the ROC curve in evaluation of machine learning algorithms, Pattern Recognit., 30 (1997), 1145–1159. https://doi.org/10.1016/S0031-3203(96)00142-2 doi: 10.1016/S0031-3203(96)00142-2

Reader Comments

Your name:*

Email:*
© 2022 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)