Application of machine learning in liver disease： improving diagnosis， treatment， and efficacy evaluation

doi:10.3760/cma.j.cn371439-20230227-00062

Abstract

Abstract:

Compared with traditional statistical models， machine learning in artificial intelligence has certain advantages in establishing predictive models. Currently， a large amount of research has been conducted on the application of machine learning in liver diseases. However， there is still no unified approach for selection of machine learning algorithms and steps of training different machine learning algorithms. As research progresses， predictive models based on machine learning combined with various omics have great potential in improving the diagnosis， treatment， and efficacy evaluation of liver diseases.

Key words: Machine learning, Liver disease

Chen Fengyang, Zhang Wei. Application of machine learning in liver disease： improving diagnosis， treatment， and efficacy evaluation[J]. Journal of International Oncology, 2023, 50(5): 310-314.

References 30

[1]	Mitchell TM. Machine learning[M]. New York: McGraw-Hill, 1997.
[2]	Ding H, Fawad M, Xu X, et al. A framework for identification and classification of liver diseases based on machine learning algorithms[J]. Front Oncol, 2022, 12: 1048348. DOI: 10.3389/fonc.2022.1048348. doi: 10.3389/fonc.2022.1048348
[3]	Wu Y, Yang X, Morris HL, et al. Noninvasive diagnosis of nonalcoholic steatohepatitis and advanced liver fibrosis using machine lear-ning methods: comparative study with existing quantitative risk scores[J]. JMIR Med Inform, 2022, 10(6): e36997. DOI: 10.2196/36997. doi: 10.2196/36997
[4]	Pei X, Deng Q, Liu Z, et al. Machine learning algorithms for predicting fatty liver disease[J]. Ann Nutr Metab, 2021, 77(1): 38-45. DOI: 10.1159/000513654. doi: 10.1159/000513654
[5]	Li J, Tao Y, Cong H, et al. Predicting liver cancers using skewed epidemiological data[J]. Artif Intell Med, 2022, 124: 102234. DOI: 10.1016/j.artmed.2021.102234. doi: 10.1016/j.artmed.2021.102234
[6]	Libbrecht MW, Noble WS. Machine learning applications in genetics and genomics[J]. Nat Rev Genet, 2015, 16(6): 321-332. DOI: 10.1038/nrg3920. doi: 10.1038/nrg3920 pmid: 25948244
[7]	Han N, He J, Shi L, et al. Identification of biomarkers in nonalcoholic fatty liver disease: a machine learning method and experimental study[J]. Front Genet, 2022, 13: 1020899. DOI: 10.3389/fgene.2022.1020899. doi: 10.3389/fgene.2022.1020899
[8]	Mann M, Kumar C, Zeng WF, et al. Artificial intelligence for proteomics and biomarker discovery[J]. Cell Syst, 2021, 12(8): 759-770. DOI: 10.1016/j.cels.2021.06.006. doi: 10.1016/j.cels.2021.06.006 pmid: 34411543
[9]	Zhang S, Liu Y, Chen J, et al. Autoantibody signature in hepatocellular carcinoma using seromics[J]. J Hematol Oncol, 2020, 13(1): 85. DOI: 10.1186/s13045-020-00918-x. doi: 10.1186/s13045-020-00918-x
[10]	Streba CT, Ionescu M, Gheonea DI, et al. Contrast-enhanced ultrasonography parameters in neural network diagnosis of liver tumors[J]. World J Gastroenterol, 2012, 18(32): 4427-4434. DOI: 10.3748/wjg.v18.i32.4427. doi: 10.3748/wjg.v18.i32.4427
[11]	Turco S, Tiyarattanachai T, Ebrahimkheil K, et al. Interpretable machine learning for characterization of focal liver lesions by contrast-enhanced ultrasound[J]. IEEE Trans Ultrason Ferroelectr Freq Control, 2022, 69(5): 1670-1681. DOI: 10.1109/TUFFC.2022.3161719. doi: 10.1109/TUFFC.2022.3161719 pmid: 35320099
[12]	Căleanu CD, Sîrbu CL, Simion G. Deep neural architectures for contrast enhanced ultrasound (CEUS) focal liver lesions automated diagnosis[J]. Sensors (Basel), 2021, 21(12): 4126. DOI: 10.3390/s21124126. doi: 10.3390/s21124126
[13]	Nebbia G, Zhang Q, Arefan D, et al. Pre-operative microvascular invasion prediction using multi-parametric liver MRI radiomics[J]. J Digit Imaging, 2020, 33(6): 1376-1386. DOI: 10.1007/s10278-020-00353-x. doi: 10.1007/s10278-020-00353-x
[14]	Nakaura T, Higaki T, Awai K, et al. A primer for understanding radiology articles about machine learning and deep learning[J]. Diagn Interv Imaging, 2020, 101(12): 765-770. DOI: 10.1016/j.diii.2020.10.001. doi: 10.1016/j.diii.2020.10.001
[15]	Sandfort V, Yan K, Pickhardt PJ, et al. Data augmentation using generative adversarial networks (CycleGAN) to improve generali-zability in CT segmentation tasks[J]. Sci Rep, 2019, 9(1): 16884. DOI: 10.1038/s41598-019-52737-x. doi: 10.1038/s41598-019-52737-x pmid: 31729403
[16]	Mulé S, Galletto Pregliasco A, Tenenhaus A, et al. Multiphase liver MRI for identifying the macrotrabecular-massive subtype of hepatocellular carcinoma[J]. Radiology, 2020, 295(3): 562-571. DOI: 10.1148/radiol.2020192230. doi: 10.1148/radiol.2020192230 pmid: 32228294
[17]	Mulé S, Lawrance L, Belkouchi Y, et al. Generative adversarial networks (GAN)-based data augmentation of rare liver cancers: the SFR 2021 artificial intelligence data challenge[J]. Diagn Interv Imaging, 2023, 104(1): 43-48. DOI: 10.1016/j.diii.2022.09.005. doi: 10.1016/j.diii.2022.09.005
[18]	Heusel M, Ramsauer H, Unterthiner T, et al. GANs trained by a two time-scale update rule converge to a local Nash equilibrium[C]// Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, California, USA: Curran Associates Inc., 2017: 6629-6640. DOI: 10.5555/3295222.3295408. doi: 10.5555/3295222.3295408
[19]	Xu Q, Huang G, Yuan Y, et al. An empirical study on evaluation metrics of generative adversarial networks[DB/OL]. [2018-08-17][2023-02-19]. https://arxiv.org/abs/1806.07755v1.
[20]	Teramoto T, Shinohara T, Takiyama A. Computer-aided classification of hepatocellular ballooning in liver biopsies from patients with NASH using persistent homology[J]. Comput Methods Programs Biomed, 2020, 195: 105614. DOI: 10.1016/j.cmpb.2020.105614. doi: 10.1016/j.cmpb.2020.105614
[21]	Matteoni CA, Younossi ZM, Gramlich T, et al. Nonalcoholic fatty liver disease: a spectrum of clinical and pathological severity[J]. Gastroenterology, 1999, 116(6): 1413-1419. DOI: 10.1016/S0016-5085(99)70506-8. doi: 10.1016/s0016-5085(99)70506-8 pmid: 10348825
[22]	Saillard C, Schmauch B, Laifa O, et al. Predicting survival after hepatocellular carcinoma resection using deep learning on histological slides[J]. Hepatology, 2020, 72(6): 2000-2013. DOI: 10.1002/hep.31207. doi: 10.1002/hep.31207
[23]	Minerali E, Foil DH, Zorn KM, et al. Comparing machine learning algorithms for predicting drug-induced liver injury (DILI)[J]. Mol Pharm, 2020, 17(7): 2628-2637. DOI: 10.1021/acs.molpharmaceut.0c00326. doi: 10.1021/acs.molpharmaceut.0c00326
[24]	Chen M, Suzuki A, Thakkar S, et al. DILIrank: the largest refe-rence drug list ranked by the risk for developing drug-induced liver injury in humans[J]. Drug Discov Today, 2016, 21(4): 648-653. DOI: 10.1016/j.drudis.2016.02.015. doi: 10.1016/j.drudis.2016.02.015
[25]	Williams DP, Lazic SE, Foster AJ, et al. Predicting drug-induced liver injury with Bayesian machine learning[J]. Chem Res Toxicol, 2020, 33(1): 239-248. DOI: 10.1021/acs.chemrestox.9b00264. doi: 10.1021/acs.chemrestox.9b00264 pmid: 31535850
[26]	Aleo MD, Shah F, Allen S, et al. Moving beyond binary predictions of human drug-induced liver injury (DILI) toward contrasting relative risk potential[J]. Chem Res Toxicol, 2020, 33(1): 223-238. DOI: 10.1021/acs.chemrestox.9b00262. doi: 10.1021/acs.chemrestox.9b00262 pmid: 31532188
[27]	Wu CY, Benet LZ. Predicting drug disposition via application of BCS: transport/absorption/elimination interplay and development of a biopharmaceutics drug disposition classification system[J]. Pharm Res, 2005, 22(1): 11-23. DOI: 10.1007/s11095-004-9004-4. doi: 10.1007/s11095-004-9004-4
[28]	Mazzaferro V, Llovet JM, Miceli R, et al. Predicting survival after liver transplantation in patients with hepatocellular carcinoma beyond the Milan criteria: a retrospective, exploratory analysis[J]. Lancet Oncol, 2009, 10(1): 35-43. DOI: 10.1016/S1470-2045(08)70284-5. doi: 10.1016/S1470-2045(08)70284-5 pmid: 19058754
[29]	Kim WR, Lake JR, Smith JM, et al. OPTN/SRTR 2017 annual data report: liver[J]. Am J Transplant, 2019, 19 Suppl 2: 184-283. DOI: 10.1111/ajt.15276. doi: 10.1111/ajt.15276 pmid: 30811890
[30]	He T, Fong JN, Moore LW, et al. An imageomics and multi-network based deep learning model for risk assessment of liver transplantation for hepatocellular cancer[J]. Comput Med Imaging Graph, 2021, 89: 101894. DOI: 10.1016/j.compmedimag.2021.101894. doi: 10.1016/j.compmedimag.2021.101894