Article Sidebar

PDF (Tiếng Việt)
Published: 2023-12-15
Abstract Views: 157
Views PDF (Tiếng Việt): 161
DOI: https://doi.org/10.52852/tcncyh.v171i10.2005
Issue
Vol. 171 No. 10 (2023)
Section
Các bài báo
How to Cite
Hạnh, B. M. ., Ngân, V. T. ., & Trang, N. T. T. . (2023). 11. Effectiveness of artificial intelligence for convey non-dicom to dicom signal and automation in electroencephalogram interpretation. Journal of Medical Research, 171(10), 95-105. https://doi.org/10.52852/tcncyh.v171i10.2005

11. Effectiveness of artificial intelligence for convey non-dicom to dicom signal and automation in electroencephalogram interpretation

Bui My Hanh, Vuong Thi Ngan, Nguyen Thi Thuy Trang

Main Article Content

Abstract

EEG analysis faces many difficulties, especially for non-specialist doctors because this is a complex type of non-dicom data that has not been converted synchronously on the HIS system. Our study evaluates the results of artificial intelligence applications that convert data to the HIS system in dicom form and automatically identify and extract results. The research applies artificial intelligence to 900 records of normal people and people with neurological diseases from January 2021 to June 2023 in Hanoi Medical University Hospital. Our results show that c AI converted and synchronized 100% of data directly from specialized recorders to the HIS system as well as identified, analyzed, and displayed brain waves based on the characteristics of frequency, amplitude, and localization according to recorded milestones with an accuracy of up to 98% and automatically extracted 100% accurate results into answer sheets. Component time and total time are shortened by 8.75 times, saving 465 working hours with nearly 4.6 billion data points stored compared to the manual process. This is an effective support tool for doctors to access results easily, quickly, and accurately, especially for medical facilities lacking specialists and equipment.

Article Details

Keywords

Electroencephalogram, EEG, automation, artificial intelligence, machine learning, deep learning, efficiency, accuracy

References

1. Britton JW, Frey LC, Hopp JL, et al. Electroencephalography (EEG): An Introductory Text and Atlas of Normal and Abnormal Findings in Adults, Children, and Infants. In: American Epilepsy Society, Chicago; 2016.
2. Lê Quang Cường, Pierre Jallon, Bùi Mỹ Hạnh. Điện não đồ lâm sàng. Nhà xuất bản Y học; 2023.
3. Feyissa AM, Tatum WO. Adult EEG. Handbook of clinical neurology. 2019;160:103-124.
4. Nakamura M, Sugi T, Ikeda A, et al. Automatic EEG interpretation adaptable to individual electroencephalographer using artificial neural network. International Journal of Adaptive Control and Signal Processing. 2002;16(1):25-37.
5. Subasi A, Ismail Gursoy M. EEG signal classification using PCA, ICA, LDA and support vector machines. Expert Systems with Applications. 2010;37(12):8659-8666.
6. Craik A, He Y, Contreras-Vidal JL. Deep learning for electroencephalogram (EEG) classification tasks: a review. Journal of Neural Engineering. 2019;16(3):031001.
7. Thủ tướng chính phủ. Quyết định số 749/QĐ-TTg ngày 03/6/2020 phê duyệt Chương trình Chuyển đổi số quốc gia.
8. Bộ Y tế. Quyết định số 5316/QĐ-BYT ngày 22/12/2020 phê duyệt Chương trình Chuyển đổi số y tế.
9. Baltatzis V, Bintsi K-M, Apostolidis GK, et al. Bullying incidences identification within an immersive environment using HD EEG-based analysis: A Swarm Decomposition and Deep Learning approach. Scientific Reports. 2017;7(1):17292.
10. Birjandtalab J, Heydarzadeh M, Nourani M. Automated EEG-Based Epileptic Seizure Detection Using Deep Neural Networks. International Conference on Healthcare Informatics. 2017;552-555.