Purpose: The objective of this study was to develop a model for predicting the positivity of hepatitis A antibody based on nationwide health information using a machine learning technique.
Methods: We used a data set that included the records of 4,626 samples. the data was randomly divided into a training set 80% (3,701) and validation set 20% (925). Customized sequential convolutional neural network (CNN) model was used to predict the positivity of hepatitis A antibody. The loss and accuracy of this model was calculated.
Results: This model has 12-input and 2-concatenate and 3-dense layers. The total parameters of this model were 1,779. The accuracy quickly reached to over 85% validation accuracy in 50 epochs. The train loss, train accuracy, validation loss and validation accuracy of this model were 25.4%, 89.5%, 29.0%, and 87.2%, respectively.
Conclusion: The model derived from the sequential CNN model exhibited a high level of accuracy. This model is a useful tool for predicting the positivity of hepatitis A antibody.
Article
Original Article
머신러닝 알고리즘을 이용한 A형 간염 항체 여부 판별의 정확도
Diagnostic Accuracy of Machine Learning Algorithms for Hepatitis A Antibody
서울대학교병원 국제진료센터
Juwon Lim 
, M.D., Ph.D.
, M.D., Ph.D.International Healthcare Center, Seoul National University Hospital, Seoul, Korea
Correspondence to:Received: April 3, 2022; Accepted: April 7, 2022
This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License, which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
Korean J Aerosp Environ Med 2022; 32(1): 16-21
Published April 30, 2022 https://doi.org/10.46246/KJAsEM.220005
Copyright © Aerospace Medical Association of Korea.
Abstract
Keywords
Hepatitis A virus, Antibodies, Machine learning, Algorithms
References
- Lim J, Kim K, Choi S, Park SM. The effectiveness and limitation of the national childhood hepatitis A vaccination program in the Republic of Korea: findings from the Korean National Health and Nutrition Examination Survey (KNHANES), 2015. PLoS One 2017;12:e0189210. https://doi.org/10.1371/journal.pone.0189210
- Jang JS, Lee MJ, Lee TR. Development of T2DM prediction model using RNN. J Digit Converg 2019;17:249-255. https://doi.org/10.14400/JDC.2019.17.8.249
- Lim YS, Shin WG, Kim HH. A prediction model of gastric cancer in patients with chronic gastritis based on RNN using clinical big data. Proc KCC 2020;47:1289-1291.
- Kang NG, Suh YJ, Han K, Kim YJ, Choi BW. Performance of prediction models for diagnosing severe aortic stenosis based on aortic valve calcium on cardiac computed tomography: incorporation of radiomics and machine learning. Korean J Radiol 2021;22:334-343. https://doi.org/10.3348/kjr.2020.0099
- Passera R, De Luca S, Fiori C, Bollito E, Porpiglia F. Machine learning techniques in prostate cancer diagnosis according to prostate-specific antigen levels and prostate cancer gene 3 score. Korean J Urol Oncol 2021;19:164-173. https://doi.org/10.22465/kjuo.2021.19.3.164
- Kim J, Lim H, Ahn JH, Lee KH, Lee KS, Koo KC. Optimal triage for COVID-19 patients under limited health care resources with a parsimonious machine learning prediction model and threshold optimization using discreteevent simulation: development study. JMIR Med Inform 2021;9:e32726. https://doi.org/10.2196/32726
Related articles in KJASEM
