A Hybrid Optimized Machine Learning Model for Non-Invasive Procedures Based Early Diagnosis of Hepatocellular Carcinoma Using Novel Biomarker
Keywords:
Hepatocellular carcinoma, detection, machine learning, hybrid, PIVKA II, Lasso, PSO.Abstract
The primary liver cancer, Hepatocellular Carcinoma (HCC) is found mainly in the alcoholic and non-alcoholic patients. The detection of the disease in the early stage is having a vital role as it is having less or no symptoms till the final stage of the progress. In this paper, a hybrid machine learning model is presented for the detection of HCC in early stage. Here we use a novel biomarker PIVKA II (protein-induced by vitamin K absence). We can use it in combination with traditional routine biomarker Alphafeto protein as well as others. The paper proposes a metaheuristic optimization-based embedded method of feature selection using Least Absolute Shrinkage and Selection Operator (LASSO) blended with Particle Swarm Optimization (PSO). Classification done with three different algorithms called Support Vector Machine (SVM), Linear Discriminant Analysis (LDA), and K Nearest Neighbor (KNN) algorithms. First model emphasizes on the lasso regression and cross validation with the classifiers. Second model proposes PSO optimized LASSO with the classifiers. The proposed second model combines the advantages of both embedded LASSO and PSO algorithms to obtain the best classification results. Using the latter model, among three classification algorithms, LASSO and PSO optimized SVM showed much elevated level of classification results. The proposed LASSO and PSO based SVM showed an elevated accuracy rate of 88.1%, f1 score 91.2% and true positive rate 91.7%.
Downloads
References
1T. C. Yip et al., “Impact of age and gender on risk of hepatocellular carcinoma after hepatitis B surface antigen seroclearance,” J. Hepatol., vol. 67, no. 5, pp. 902-908, 2017.
K. A. McGlynn et al., “Epidemiology of hepatocellular carcinoma,” Hepatology, vol. 73 suppl. 1, pp. 4-13, 2021.
F. Özdemir and A. Baskiran, “The importance of AFP in liver transplantation for HCC,” J. Gastrointest. Cancer, vol. 51, no. 4, pp. 1127-1132, 2020
T. Inoue and Y. Tanaka, “Novel biomarkers for the management of chronic hepatitis B,” Clin. Mol. Hepatol., vol. 26, no. 3, p. 261-279, 2020.
H. Hadi et al., “Utility of Pivka-II and AFP in Differentiating Hepatocellular Carcinoma from Non-malignant High-risk patients,” Medicina (Kaunas), vol. 58, no. 8, p. 1015, 2022
G. N. Ioannou, “Epidemiology and risk-stratification of NAFLD-associated HCC,” J. Hepatol., vol. 75, no. 6, pp. 1476-1484, 2021
L. T. de Lima Franca, Daniel Broszczak, Xi, “Zhang, Kim Bridle,” Darrell Crawford, and Chamindie Punyadeera. "The use of minimally invasive biomarkers for the diagnosis and prognosis of hepatocellular carcinoma." Biochimica et Biophysica Acta (BBA)-Reviews on Cancer 1874, vol. 2, 2020, p. 188451.
T. H. Kim et al., “Comparison of international guidelines for noninvasive diagnosis of hepatocellular carcinoma: 2018 update,” Clin. Mol. Hepatol., vol. 25, no. 3, p. 245-263, 2019.
G. Marasco et al., “Non-invasive tests for the prediction of primary hepatocellular carcinoma,” World J. Gastroenterol., vol. 26, no. 24, p. 3326-3343, 2020.
T. H. Kim et al., “Comparison of international guidelines for noninvasive diagnosis of hepatocellular carcinoma: 2018 update,” Clin. Mol. Hepatol., vol. 25, no. 3, p. 245-263, 2019.
F. Qi et al., “The diagnostic value of Pivka‐II, AFP, AFP‐L3, CEA, and their combinations in primary and metastatic hepatocellular carcinoma,” J. Clin. Lab. Anal., vol. 34, no. 5, p. e23158, 2020.
M. Sato et al., “Machine-learning approach for the development of a novel predictive model for the diagnosis of hepatocellular carcinoma,” Sci. Rep., vol. 9, no. 1, p. 7704, 2019.
L. Ali et al., “LDA–GA–SVM: Improved hepatocellular carcinoma prediction through dimensionality reduction and genetically optimized support vector machine,” Neural Comput. Appl., vol. 33, no. 7, pp. 2783-2792, 2021.
C. C. Wu et al., “Prediction of fatty liver disease using machine learning algorithms,” Comput. Methods Programs Biomed., vol. 170, pp. 23-29, 2019.
V. Saraswathi et al., “Implementation of hyper parameter optimization in liver disease prediction” in International Conference on Power, Energy, Control and Transmission Systems (ICPECTS). IEEE, 2022, pp. 1-6.
M. Fathi et al., “A machine learning approach based on SVM for classification of liver diseases,” Biomed. Eng. Appl. Basis Commun., vol. 32, no. 3, p. 2050018, 2020.
R. K. Huda and H. Banka, “Efficient feature selection and classification algorithm based on PSO and rough sets,” Neural Comput. Appl., vol. 31, no. 8, pp. 4287-4303, 2019.
Y. Xiong et al., “An efficient gene selection method for microarray data based on lasso and BPSO,” BMC Bioinformatics, vol. 20 suppl. 22, pp. 715, 2019.
M. Amoozegar and B. Minaei-Bidgoli, “Optimizing multi-objective PSO based feature selection method using a feature elitism mechanism,” Expert Syst. Appl., vol. 113, pp. 499-514, 2018.
S. Binti et al. "Particle swarm optimization feature selection for breast cancer recurrence prediction.", “Sakri,” IEEE Access, vol. 6, pp. 29637-29647, 2018.
K. Wang et al., “Software defect prediction model based on lasso–SVM,” Neural Comput. Appl., vol. 33, no. 14, pp. 8249-8259, 2021.
S. Afrin et al., “Mst Fahmida Muntasim”, Md Shakil Moharram, M. M. Imran, and Md Abdulla. "Supervised machine learning based liver disease prediction approach with LASSO feature selection." Bulletin of Electrical Engineering and Informatics 10, vol. 6, 2021, pp. 3369-3376.
G. R. Nitta et al., “Lasso-based feature selection and naïve Bayes classifier for crime prediction and its type,” Serv. Oriented Comput. Appl., vol. 13, no. 3, pp. 187-197, 2019.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.