APPLICATION OF ARTIFICIAL INTELLIGENCE IN MONITORING AND PROGNOSIS OF HAND, FOOT, AND MOUTH DISEASE IN CHILDREN AT CAN THO CHILDREN'S HOSPITAL
Main Article Content
Abstract
Background: Hand, Foot, and Mouth Disease is a common pediatric infectious disease that can lead to serious neurological, cardiovascular, and respiratory complications if not detected early; however, early identification of severe progression remains challenging, and predictive models such as logistic regression and artificial intelligence may help support more objective risk assessment and monitoring. Objectives: 1. To develop an artificial intelligence model for monitoring the status of Hand, Foot, and Mouth Disease in children; 2. To apply the artificial intelligence model for early prediction of the likelihood of severe disease progression, assisting physicians with timely treatment. Materials and methods: A cross-sectional descriptive study was conducted on 302 pediatric patients diagnosed with Hand, Foot, and Mouth Disease treated as inpatients at Can Tho Children's Hospital from October 2024 to October 2025, who met the criteria set by the Ministry of Health in 2024. Data were processed using R 4.3.1 and Python 3.11 software; a logistic regression model was used to construct a Nomogram, and the Random Forest model was used to predict severe progression. Results: Statistically significant independent prognostic factors included CRP, glucose, white blood cell count, convulsions, and pulmonary crackles (p < 0.05). The Nomogram model achieved an AUC of 0.833, a sensitivity of 82.1%, and a specificity of 78.3%. The artificial intelligence - Random Forest model achieved an Accuracy of 70.9%, Precision of 0.69, Recall of 0.71, and an F1-score of 0.69. The most important features in the model included number of treatment days (0.345), severity upon admission (0.157), and duration of fever (0.130). Conclusion: The combination of logistic regression and an artificial intelligence model shows high efficacy in predicting and monitoring the progression of Hand, Foot, and Mouth Disease, contributing to supporting physicians in early identification of high-risk pediatric patients, thereby improving the quality of treatment and clinical prognosis.
Keywords
Hand foot mouth disease, artificial intelligence, nomogram, Random Forest
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
References
2. World Health Organization. Hand, Foot and Mouth Disease: Clinical Management and Prevention. Geneva: WHO Press. 2022.
3. Qiu J., Yan H., Chen X. Epidemiology and clinical features of hand, foot, and mouth disease in Asia. Journal of Infection and Public Health. 2023. 16(4), 512-519.
4. Nguyen Thi Ngoc Lan, Tran Van Trung, Nguyen Van Dat. Clinical characteristics and treatment outcomes of Hand, Foot, and Mouth Disease at Children's Hospital 1. Vietnam Journal of Medicine. 2021. 506(2), 43-49.
5. Lee K.Y., Lee M.S., Kim D.B. Clinical significance of laboratory parameters in severe enterovirus 71 infection. Pediatrics International. 2020. 62(7), 753-760.
6. Wang S.M., Liu C.C. Update on hand, foot, and mouth disease. Current Opinion in Infectious Diseases. 2022. 35(3), 254-262, https://doi.org/10.1097/QCO.0000000000000835.
7. Peiqing Li, Yuge Huang, Danping Zhu, Sida Yang, Dandan Hu. Risk Factors for Severe HandFoot-and-Mouth Disease in China: A Systematic Review and Meta-Analysis. Frontiers in Pediatrics. 2021. 9, 716039, https://doi.org/10.3389/fped.2021.716039.
8. Nguyen Huu Tri, Le Thi Kim Phung. Some prognostic factors for severe Hand, Foot, and Mouth Disease in children at Can Tho Children's Hospital. Can Tho Journal of Medicine and Pharmacy. 2022. 54, 79-85.
9. Pham Thanh Binh. Application of logistic regression model in prognosticating severe Hand, Foot, and Mouth Disease in children. Journal of Practical Medicine. 2022. 1178(6), 35-40.
10. Chen L., Zhang H., Zhou W., Li X., Huang Y., et al. Machine learning models for predicting severe cases of hand, foot, and mouth disease: a multicenter study. Frontiers in Cellular and Infection Microbiology. 2023. 13, 1198452, https://doi.org/10.3389/fcimb.2023.1198452.
11. Nguyen M.H., Tran L.K., Vo P.T., Pham T.T., Le Q.H., et al. Application of artificial intelligence in early prediction of infectious diseases in children: a Vietnamese experience. BMC Medical Informatics and Decision Making. 2024. 24(1), 271, https://doi.org/10.1186/s12911-024-02345-1.