Page 104 - AIH-2-2

Artificial Intelligence in Health Cirrhosis prediction in hepatitis C

Consent for publication models in predicting development of hepatocellular
carcinoma. Am J Gastroenterol. 2013;108(11):1723-1730.
Not applicable.
doi: 10.1038/ajg.2013.332
Availability of data 6. Chen YW, Luo J, Dong C, et al. Computer-aided diagnosis

These analyses were performed using data from the and quantification of cirrhotic livers based on morphological
Corporate Warehouse Domains that are available only analysis and machine learning. Comput Math Methods Med.
2013;2013:264809.
within the U.S. Department of Veterans Affairs firewall
in a secure research environment, the VA Informatics doi: 10.1155/2013/264809
and Computing Infrastructure (VINCI). To comply with 7. Konerman MA, Zhang Y, Zhu J, et al. Improvement of
VA privacy and data security policies and regulatory predictive models of risk of disease progression in chronic
constraints, only aggregate summary statistics and results hepatitis C by incorporating longitudinal data. Hepatology.
of our analyses are permitted to be removed from the data 2015;61:1832-1841.
warehouse for publication. The authors have provided doi: 10.1002/hep.27750
detailed results of the analyses in the paper. These
restrictions are in place to maintain veteran privacy and 8. Weerakody PB, Wong KW, Wang G, Ela W. A review of
confidentiality. Access to these data can be granted to irregular time series data handling with gated recurrent
neural networks. Neurocomputing. 2021;441:161-178.
persons who are not employees of the VA; however, there
is an official protocol that must be followed for doing so. doi: 10.1016/j.neucom.2021.02.046
The authors also confirm that VA policies are currently 9. Veterans Health Administration. Available from: https://
being developed that should allow an interested researcher www.va.gov/health [Last accessed on 2024 Dec 22].
to obtain a de-identified, raw dataset upon request with a 10. Corporate Data Warenouse (CDW): US Department of
data use agreement. Those wishing to access the data that Veterans Affairs. Available from: https://www.hsrd.research.
were used for this analysis may contact Jennifer Burns, va.gov/for_researchers/vinci/cdw.cfm [Last accessed on
MHSA, who is a senior data manager at the VA Center for 2014 Mar 28].
Clinical Management Research, to discuss the details of the
VA data access approval process. Her contact information 11. Oliveira AC, El-Bacha I, Vianna MV, Parise ER. Utility and
limitations of APRI and FIB4 to predict staging in a cohort
is as follows: Jennifer.Burns@va.gov; UM North Campus of nonselected outpatients with hepatitis C. Ann Hepatol.
Research Complex, Department of Veterans Affairs, 2800 2016;15(3):326-332.
Plymouth Road Bldg 16, Ann Arbor, MI.
doi: 10.5604/16652681.1198801
References 12. Lin ZH, Xin YN, Dong QJ, et al. Performance of the aspartate

1. Zeremski M, Dimova RB, Pillardy J, de Jong YP, aminotransferase-to-platelet ratio index for the staging
Jacobson IM, Talal AH. Fibrosis progression in patients of hepatitis C-related fibrosis: An updated meta-analysis.
with chronic hepatitis C virus infection. J Infect Dis. Hepatology. 2011;53(3):726-736.
2016;214(8):1164-1170. doi: 10.1002/hep.24105
doi: 10.1093/infdis/jiw332 13. Ioannou GN, Tang W, Beste LA, et al. Assessment of a
2. Freeman AJ, Law MG, Kadlor JM, Dore GJ. Predicting deep learning model to predict hepatocellular carcinoma
progression to cirrhosis in chronic hepatitis C virus in patients with hepatitis C cirrhosis. JAMA Netw Open.
infection. J Infect Dis. 2003;10(4):285-293. 2020;3(9):e2015626.
doi: 10.1046/j.1365-2893.2003.00436.x doi: 10.1001/jamanetworkopen.2020.15626
3. Waljee AK, Higgins PD. Machine learning in 14. Chung, J, Gulcehre, C, Cho KH, Bengio Y. Empirical
medicine: A primer for physicians. Am J Gastroenterol. evaluation of gated recurrent neural networks on sequence
2010;105(6):1224-1226. modeling. arXiv. Preprint posted online 2014.
doi: 10.1038/ajg.2010.173 doi: 10.48550/arXiv.1412.3555
4. Konerman MA, Beste LA, Van T, et al. Machine learning 15. Kingma DP, Ba J. Adam: A method for stochastic
models to predict disease progression among veterans with optimization. arXiv. Preprint posted online 2014.
hepatitis C virus. PLoS One. 2019;14(1):e0208141. doi: 10.48550/arXiv.1412.6980
doi: 10.1371/journal.pone.0208141
16. Srivastava N, Hinton G, Krizhevsky A, Sutskever I,
5. Singal AG, Mukherjee A, Elmunzer BJ, et al. Machine Salakhutdinov R. Dropout: A simple way to prevent
learning algorithms outperform conventional regression neural networks from overfitting. J Mach Learn Res.

Volume 2 Issue 2 (2025) 98 doi: 10.36922/aih.4671