Article Sidebar

PDF
Date Published: 01/06/2023
Abstract Views: 614
Views PDF: 334
DOI: https://doi.org/10.51298/vmj.v526i2.5590
Issue
Vol. 526 No. 2 (2023)
Section
Các bài báo
How to Cite
Nguyễn, B. T. ., Trần, D. C. ., Nguyễn, T. T. ., Nguyễn, T. H. ., Trần, H. T. ., Đỗ, Q. H. ., Nguyễn, X. Đại ., Nguyễn, P. N. ., Đỗ, N. K. ., Lê, T. M. P. ., Đào , T. H. T. ., & Công , T. K. T. . (2023). RESEARCH ON THE APPLICATION OF ARTIFICIAL INTELLIGENCE IN PRENATAL SCREENING FOR THALASSEMIA. Vietnam Medical Journal, 526(2). https://doi.org/10.51298/vmj.v526i2.5590

RESEARCH ON THE APPLICATION OF ARTIFICIAL INTELLIGENCE IN PRENATAL SCREENING FOR THALASSEMIA

Bá Tùng Nguyễn1, Danh Cường Trần2,3, Thị Trang Nguyễn3,4, Tuấn Hưng Nguyễn5, Hồng Thái Trần3, Quang Huy Đỗ3, Xuân Đại Nguyễn3, Phương Ngọc Nguyễn3, Nguyễn Khánh Đỗ6, Thị Minh Phương Lê7, Thị Huyền Trang Đào 3, Thị Kim Thu Công 8,
1 Vietnam Military Medical Academy
2 National hospital of obstetrics and gynecology
3 HMU
4 HMU hospital
5 Ministry of Health
6 HNUE High School, in Vietnamese
7 VNU Hanoi-University of Medicine and Pharmacy
8 Dong Da hospital

Main Article Content

Abstract

Objective: Evaluate the test results of the artificial intelligence software system designed to support thalassemia antenatal screening at the National Hospital of Obstetrics and Gynecology and the Hanoi Obstetrics and Gynecology Hospital. Subjects and methods: 244 medical records including history of thalassemia, laboratory results including Complete blood count (at least 4 indices of HGB, MCV, MCH, RDW); serum iron, ferritin; Hb electrophoresis results (if any) of pregnant couples visiting the National Hospital of Obstetrics and Gynecology and Hanoi Hospital of Obstetrics and Gynecology, analyzed by an artificial intelligence software system (machine learning software and expert knowledge system software). Results were compared with the results of genetic testing for thalassemia using Stripassay method. Results: The artificial intelligence software system in antenatal thalassemia screening achieved high accuracy, with a sensitivity over 95% and specificity ranging from 94.29% to 100%. Conclusion: The AI software system for prenatal screening of thalassemia is a useful and highly effective tool in predicting the risk of carrying the disease gene of pregnant couples. It is expected to become an important supporting tool to help clinicians in thalassemia screening in the future.

Article Details

Keywords

Thalassemia, prenatal screening, artificial intelligence, machine learning software, expert knowledge system software

References

1. Nguyễn Anh Trí, Bạch Quốc Khánh và cs (2020). Nghiên cứu đặc điểm dịch tễ gen bệnh thalassemia/huyết sắc tố tại Việt Nam. Đề tài cơ sở Viện Huyết học - Truyền máu TW.
2. Amendolia SR, Cossu G, Ganadu ML, Golosio B, Masala GL, Mura GM. A comparative study of K-Nearest Neighbour, Support Vector Machine and Multi-Layer Perceptron for Thalassemia screening. Chemometrics and Intelligent Laboratory Systems. 2003/11/28/ 2003;69(1):13-20. doi:https://doi.org/10.1016/S0169-7439(03)00094-7
3. Egejuru N, Olusanya O, Asinobi A, Omotayo Joseph A, Adebayo V, Idowu P. Using Data Mining Algorithms for Thalassemia Risk Prediction. Journal of Biomedical Science and Engineering. 09/06 2019;7:33-44. doi:10.11648/ j.ijbse. 20190702.12
3. Fu YK, Liu HM, Lee LH, et al. The TVGH-NYCU Thal-Classifier: Development of a Machine-Learning Classifier for Differentiating Thalassemia and Non-Thalassemia Patients. Diagnostics (Basel, Switzerland). Sep 20 2021; 11(9)doi:10.3390/ diagnostics11091725