• English
    • Tiếng Việt
  • English 
    • English
    • Tiếng Việt
  • Login
View Item 
  •   VinSpace Home
  • The College of Engineering and Computer Science
  • Pham Huy Hieu, PhD.
  • View Item
  •   VinSpace Home
  • The College of Engineering and Computer Science
  • Pham Huy Hieu, PhD.
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Deployment and validation of an AI system for detecting abnormal chest radiographs in clinical settings

Thumbnail
View/Open
Deployment-and-validation-of-an-AI-system-for-detecting-abnormal-chest-radiographs-in-clinical-settingsFrontiers-in-Digital-Health.pdf (2.257Mb)
Date
2022-07-27
Author
Nguyen, Ngoc Huy
Nguyen, Ha Quy
Nguyen, Nghia Trung
Nguyen, Thang Viet
Pham, Hieu Huy
Nguyen, Tuan Ngoc-Minh
Metadata
Show full item record
Abstract
Background: The purpose of this paper is to demonstrate a mechanism for deploying and validating an AI-based system for detecting abnormalities on chest X-ray scans at the Phu Tho General Hospital, Vietnam. We aim to investigate the performance of the system in real-world clinical settings and compare its effectiveness to the in-lab performance. Method: The AI system was directly integrated into the Hospital's Picture Archiving and Communication System (PACS) after being trained on a fixed annotated dataset from other sources. The system's performance was prospectively measured by matching and comparing the AI results with the radiology reports of 6,285 chest X-ray examinations extracted from the Hospital Information System (HIS) over the last 2 months of 2020. The normal/abnormal status of a radiology report was determined by a set of rules and served as the ground truth. Results: Our system achieves an F1 score—the harmonic average of the recall and the precision—of 0.653 (95% CI 0.635, 0.671) for detecting any abnormalities on chest X-rays. This corresponds to an accuracy of 79.6%, a sensitivity of 68.6%, and a specificity of 83.9%. Conclusions: Computer-Aided Diagnosis (CAD) systems for chest radiographs using artificial intelligence (AI) have recently shown great potential as a second opinion for radiologists. However, the performances of such systems were mostly evaluated on a fixed dataset in a retrospective manner and, thus, far from the real performances in clinical practice. Despite a significant drop from the in-lab performance, our result establishes a reasonable level of confidence in applying such a system in real-life situations.
URI
https://vinspace.edu.vn/handle/VIN/523
Collections
  • Pham Huy Hieu, PhD. [36]

Related items

Showing items related by title, author, creator and subject.

  • Thumbnail

    Awareness and preparedness of healthcare workers against the first wave of the COVID-19 pandemic: A cross-sectional survey across 57 countries 

    Nguyen, Tien Huy; Chico, R. Matthew; Vuong, Thanh Huan; Shaikhkhalil, Hosam Waleed; Vuong, Ngoc Thao Uyen; Qarawi, Ahmad Taysir Atieh; Alhady, Shamael Thabit Mohammed; Nguyen, Lam Vuong; Le, Van Truong; Luu, Mai Ngoc; Dumre, Shyam Prakash; Imoto, Atsuko; Lee, Peter N.; Dao, Ngoc Hien Tam; Ng, Sze Jia; Hashan, Mohammad Rashidul; Matsui, Mitsuaki; Nguyen, Tran Minh Duc; Karimzadeh, Sedighe; Koonrungsesomboon, Nut; Smith, Chris; Cox, Sharon; Moji, Kazuhiko; Hirayama, Kenji; Abbas, Kirellos Said; Le, Khac Linh; Tran, Nu Thuy Dung; AL-Ahdal, Tareq Mohammed Ali; Balogun, Emmanuel Oluwadare; Nguyen, The Duy; Eltaras, Mennatullah Mohamed; Huynh, Trang; Nguyen, Thi Linh Hue; Bui, Diem Khue; Gad, Abdelrahman; Tawfik, Gehad Mohamed; Kubota, Kazumi; Nguyen, Hoang Minh; Pavlenko, Dmytro; Le; Vu, Thi Thu Trang; Le, Thuong Vu; Tran, Hai Yen; Nguyen, Thi Yen Xuan; Luong, Thi Trang; Vinh, Dong; Sharma, Akash; Vu, Quoc Dat; Soliman, Mohammed; Abdul Aziz, Jeza; Shah, Jaffer; Pham, Dinh Long Hung; Jee, Yap Siang; Dang, Thuy Ha Phuong; Tran, Thuy Huong Quynh; Hoang, Thi Nam Giang; Vy, Thi Nhat Huynh; Nguyen, Anh Thi; Truc, Phan; Nguyen, Hai Nam; Dhouibi, Nacir; Duru, Vincent; Ghozy, Sherief (2021-12-22)
    Since the COVID-19 pandemic began, there have been concerns related to the preparedness of healthcare workers (HCWs). This study aimed to describe the level of awareness and preparedness of hospital HCWs at the time of the ...
  • Thumbnail

    VinDr-CXR: An open dataset of chest X-rays with radiologist’s annotations 

    Nguyen, Ha Q.; Lam, Khanh; Le, Linh T.; Pham, Hieu H.; Tran, Dat Q.; Nguyen, Dung B.; Le, Dung D.; Pham, Chi M.; Tong, Hang T. T.; Dinh, Diep H.; Do, Cuong D.; Doan, Luu T.; Nguyen, Cuong N.; Nguyen, Binh T.; Nguyen, Que V.; Hoang, Au D.; Phan, Hien N.; Nguyen, Anh T.; Ho, Phuong H.; Ngo, Dat T.; Nguyen, Nghia T.; Nguyen, Nhan T.; Dao, Minh; Vu, Van (2022)
    Most of the existing chest X-ray datasets include labels from a list of findings without specifying their locations on the radiographs. This limits the development of machine learning algorithms for the detection and ...
  • Thumbnail

    VinDr-CXR: An open dataset of chest X-rays with radiologist’s annotations 

    Nguyen, Ha Q.; Lam, Khanh; Le, T. Linh; Pham, H. Hieu; Tran, Q. Dat; Nguyen, B. Dung; Le, D. Dung; Tong, T. T. Hang; Dinh, H. Hiep; Do, D. Cuong; Doan, T. Luu; Nguyen, N. Cuong; Nguyen, T. Binh; Nguyen, V. Que; Hoang, D. Au; Phan, N. Hien; Nguyen, T. Anh; Ho, H. Phuong; Ngo, T. Dat; Nguyen, T. Nghia; Nguyen, T. Nhan; Dao, Minh; Vu, Van (2022-03-20)
    Most of the existing chest X-ray datasets include labels from a list of findings without specifying their locations on the radiographs. This limits the development of machine learning algorithms for the detection and ...

Contact Us | Send Feedback
 

 

Browse

All of VinSpaceCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

My Account

LoginRegister

Contact Us | Send Feedback