Improved prognostic prediction model for liver cancer based on biomarker data screened by combined methods

Zhiyue Su; Chengquan Li; Haitian Fu; Liyang Wang; Meilong Wu; Xiaobin Feng; Zhiyue Su; Chengquan Li; Haitian Fu; Liyang Wang; Meilong Wu; Xiaobin Feng

doi:10.3934/mbe.2023246

Mathematical Biosciences and Engineering

2023, Volume 20, Issue 3: 5316-5332. doi: 10.3934/mbe.2023246

Previous Article Next Article

Research article Special Issues

Improved prognostic prediction model for liver cancer based on biomarker data screened by combined methods

1.
Faculty of Mathematical and Physical Sciences, University College London, London, WC1E 6BT, UK
2.
School of Clinical Medicine, Tsinghua University, Beijing 100084, China
3.
Division of Hepatobiliary and Pancreas Surgery, Department of General Surgery, Shenzhen People's Hospital (The Second Clinical Medical College, Jinan University; The First Affiliated Hospital, Southern University of Science and Technology), Shenzhen 518020, Guangdong, China

Received: 20 October 2022 Revised: 01 January 2023 Accepted: 04 January 2023 Published: 11 January 2023

Liver cancer is a common cause of death from cancer in the population, with the 4th highest mortality rate from cancer worldwide. The high recurrence rate of hepatocellular carcinoma after surgery is an important cause of high mortality among patients. In this paper, based on eight scheduled core markers of liver cancer, an improved feature screening algorithm was proposed based on the analysis of the basic principles of the random forest algorithm, and the system was finally applied to liver cancer prognosis prediction to improve the prediction of biomarkers for liver cancer recurrence, and the impact of different algorithmic strategies on the prediction accuracy was compared and analyzed. The results showed that the improved feature screening algorithm was able to reduce the feature set by about 50% while ensuring that the prediction accuracy was reduced within 2%.
- gene sequencing data,
- liver cancer recurrence,
- predictive model,
- biomarkers,
- random forest
Citation: Zhiyue Su, Chengquan Li, Haitian Fu, Liyang Wang, Meilong Wu, Xiaobin Feng. Improved prognostic prediction model for liver cancer based on biomarker data screened by combined methods[J]. Mathematical Biosciences and Engineering, 2023, 20(3): 5316-5332. doi: 10.3934/mbe.2023246

Related Papers:

Abstract

Liver cancer is a common cause of death from cancer in the population, with the 4th highest mortality rate from cancer worldwide. The high recurrence rate of hepatocellular carcinoma after surgery is an important cause of high mortality among patients. In this paper, based on eight scheduled core markers of liver cancer, an improved feature screening algorithm was proposed based on the analysis of the basic principles of the random forest algorithm, and the system was finally applied to liver cancer prognosis prediction to improve the prediction of biomarkers for liver cancer recurrence, and the impact of different algorithmic strategies on the prediction accuracy was compared and analyzed. The results showed that the improved feature screening algorithm was able to reduce the feature set by about 50% while ensuring that the prediction accuracy was reduced within 2%.

References

[1]	Cancer International Agency for Research on Cancer, Cancer Today, 2020. Available from: https://gco.iarc.fr/today/home.
[2]	Z. Obermeyer, E. J. Emanuel, Predicting the future—Big data, machine learning, and clinical medicine, N. Engl. J. Med., 375 (2016), 1216. https://doi.org/10.1056/NEJMp1606181 doi: 10.1056/NEJMp1606181
[3]	V. K. Dhiman, M. J. Bolt, K. P. White, Nuclear receptors in cancer—Uncovering new and evolving roles through genomic analysis, Nat. Rev. Genet., 19 (2018), 160–174. https://doi.org/10.1038/nrg.2017.102 doi: 10.1038/nrg.2017.102
[4]	Z. Zhang, The role of big-data in clinical studies in laboratory medicine, J. Lab. Precis. Med., 2 (2017), 34. https://doi.org/10.21037/jlpm.2017.06.07 doi: 10.21037/jlpm.2017.06.07
[5]	P. Han, R. Chu, C. C. Zhang, X. Guo, Clinical value of AFP-L3 in the diagnosis of hepatocellular carcinoma, Chin. J. Mod. Med., 14 (2012), 26–27.
[6]	J. D. Yang, I. Nakamura, L. R. Roberts, The tumor microenvironment in hepatocellular carcinoma: Current status and therapeutic targets, Semin. Cancer Biol., 21 (2011), 35–43. https://doi.org/10.1016/j.semcancer.2010.10.007 doi: 10.1016/j.semcancer.2010.10.007
[7]	M. Hao, K. Liu, X. Guo, Y. Ouyang, D. Liu, D. Chen, et al., Effect of transforming growth factor-β on stem cell development and recurrence of hepatocellular carcinoma after radiofrequency ablation therapy, Beijing Med., 2016, 38 (2016), 1290–1294. https://doi.org/10.15932/j.0253-9713.2016.12.010 doi: 10.15932/j.0253-9713.2016.12.010
[8]	L. Jiang, Q. Yan, S. Fang, M. Liu, Y. Li, Y. F. Yuan, et al., Calcium-binding protein 39 promotes hepatocellular carcinoma growth and metastasis by activating extracellular signal-regulated kinase signaling pathway, Hepatology, 66 (2017), 1529–1545. https://doi.org/10.1002/hep.29312 doi: 10.1002/hep.29312
[9]	S. Umeda, M. Kanda, H. Sugimoto, H. Tanaka, M. Hayashi, S. Yamada, et al., Downregulation of GPR155 as a prognostic factor after curative resection of hepatocellular carcinoma, BMC Cancer, 17 (2017), 1–8. https://doi.org/10.1186/s12885-017-3629-2 doi: 10.1186/s12885-017-3629-2
[10]	S. Roessler, H. L. Jia, A. Budhu, M. Forgues, Q. H. Ye, J. S. Lee, et al., A unique metastasis gene signature enables prediction of tumor relapse in early-stage hepatocellular carcinoma patients, Cancer Res., 70 (2010), 10202–10212. https://doi.org/10.1158/0008-5472.CAN-10-2607 doi: 10.1158/0008-5472.CAN-10-2607
[11]	R. Genuer, J. M. Poggi, C. Tuleau-Malot, Variable selection using random forests, Pattern Recogn. Lett., 31 (2010), 2225–2236. https://doi.org/10.1016/j.patrec.2010.03.014 doi: 10.1016/j.patrec.2010.03.014
[12]	D. Yao, J. Yang, X. Zhan, Feature selection algorithm based on random forest, J. Jilin Univ., 44 (2014), 137–141.
[13]	Matplotlib Developers, Annotations 2.2.2, 2012. Available from: https://matplotlib.org/2.2.2/tutorials/text/annotations.html.

Reader Comments

Your name:*

Email:*
© 2023 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)