Effectiveness of artificial intelligence application in automated synchronization and interpretation of bone densitometry results at Hanoi Medical University Hospital
Main Article Content
Abstract
The objective of this cross-sectional study was to evaluate the application of optical character recognition combined with deep learning (OCR-DL) in automating, standardizing, and synchronizing bone density data by dual-energy X-ray absorptiometry (DEXA) at Hanoi Medical University Hospital. 6,960 DEXA scans were included in the study, comparing four levels of technological integration: manual operation, Hospital Information System (HIS), HIS with an automated system, and HIS with an automated system integrated with AI. The results showed that the OCR-DL-integrated system increased the total number of structured data points to 20.49 million (10 times higher than the automated system and over 100 times higher than the basic HIS), while reducing the average processing time per case from 36.1 ± 1.9 minutes to 0.79 ± 0.1 minutes, saving over 8,000 labor hours per year equivalent >600 million VND annually with an overall accuracy of 100%. A qualitative survey among 28 users indicated that 100% reported high satisfaction and acceptance, confirming that the system is user-friendly, easy to operate, and clinically valuable. The system not only enhances professional efficiency but also contributes to promoting green, circular, and shared economies in digital healthcare, advancing toward a smart and sustainable hospital model.
Article Details
Keywords
Bone density measurement, artificial intelligence, OCR, Optical Character Recognition, deep learning
References
2. Zhu Z, Yu P, Wu Y, et al. Sex Specific Global Burden of Osteoporosis in 204 Countries and Territories, from 1990 to 2030: An Age-Period-Cohort Modeling Study. The journal of nutrition, health & aging. 2023; 27(9): 767-774. doi:10.1007/s12603-023-1971-4.
3. Cosman F dBS, LeBoff et al. National Osteoporosis Foundation. Clinician’s Guide to Prevention and Treatment of Osteoporosis. Osteoporosis international: a journal established as result of cooperation between the European Foundation for Osteoporosis and the National Osteoporosis Foundation of the USA. 2014 25(10): 2359-81. doi: 10.1007/s00198-014-2794-2.
4. Bùi Mỹ Hạnh, Vương Thị Ngân. Kết quả giải pháp tự động hoá phân tích kết quả đo mật độ xương bằng tia X năng lượng kép tại Bệnh viện Đại học Y Hà Nội. Tạp chí Nghiên cứu Y học. 2023; 171(10): 79-86.
5. Osagie E, Ayo-Ogbor S. Challenges in the Design of Optical Character Recognitionfor Medical Image Modalities. International Journal of Multidisciplinary Research Configuration. 07/15 2022; 4: 109-112.
6. Bui HM, Ha MH, Pham HG, et al. Predicting the risk of osteoporosis in older Vietnamese women using machine learning approaches. Sci Rep. Nov 23 2022; 12(1): 20160. doi:10.1038/s41598-022-24181-x.
7. Quốc hội. Luật số 93/2025/QH15: Luật Khoa học, công nghệ và đổi mới sáng tạo 2025.
8. Bộ Khoa học và công nghệ. Thông tư số 04/2023/TT-BKHCN: Sửa đổi, bổ sung một số điều của các Thông tư quy định quản lý nhiệm vụ khoa học và công nghệ cấp quốc gia. 2023;
9. Kukhareva PV, Weir C, Del Fiol G, et al. Evaluation in Life Cycle of Information Technology (ELICIT) framework: Supporting the innovation life cycle from business case assessment to summative evaluation. Journal of biomedical informatics. Mar 2022; 127: 104014. doi:10.1016/j.jbi.2022.104014.
10. Ma MW, Gao XS, Zhang ZY, et al. Extracting laboratory test information from paper-based reports. BMC medical informatics and decision making. Nov 6 2023; 23(1): 251. doi:10.1186/s12911-023-02346-6.
11. Akheel S. Automating PHI Extraction with Optical Character Recognition: A Literature Review on Improving Efficiency in Healthcare Systems Using Tesseract. Progress in Medical Sciences. 06/30 2023; 7:1-4. doi:10.47363/PMS/2023(7)E125.
12. Giansanti D, Basilio F. The Artificial Intelligence in Digital Radiology: Part 1: The Challenges, Acceptance and Consensus. Healthcare. 03/10 2022; 10:509. doi:10.3390/healthcare10030509.
13. Bộ chính trị. Nghị quyết số 57-NQ/TW, ngày 22/12/2024 về đột phá phát triển khoa học, công nghệ, đổi mới sáng tạo và chuyển đổi số quốc gia. 2024;
14. Bộ Y tế. Quyết định số 5316/QĐ-BYT ngày 22/12/2020 phê duyệt Chương trình Chuyển đổi số y tế đến năm 2025, định hướng đến năm 2030.