Vai trò của trí tuệ nhân tạo Qure.AI phân tích hình ảnh X-quang ngực trong chẩn đoán sớm Lao phổi tại Bệnh viện Đại học Y Hà Nội năm 2022=The role of Qure.AI artificial intelligence in chest x-ray image analysis for early diagnosis of pulmonary tuberculosis at Hanoi Medical University Hospital in 2022

0 Người đánh giá. Xếp hạng trung bình 0

Tác giả: Thị Thu Thủy Nguyễn, Thị Thu Hằng Trương

Ngôn ngữ: vie

Ký hiệu phân loại:

Thông tin xuất bản: Y Dược Thái Bình (Đại học Y Dược Thái Bình), 2024

Mô tả vật lý: tr.96-100

Bộ sưu tập: Metadata

ID: 157164

Thêm vào giỏ

Nghiên cứu của chúng tôi nhằm đánh giá vai trò của trí tuệ nhân tạo Qure. AI phân tích hình ảnh X-quang ngực trong chẩn đoán sớm lao phổi. Phương pháp: Nghiên cứu mô tả với 126 bệnh nhân nghi lao phổi được Qure.AI phân tích hình ảnh X-quang ngực và làm các xét nghiệm vi sinh hoặc mô bệnh học để chẩn đoán lao phổi và so sánh giữa kết quả chẩn đoán cuối cùng với phân tích của Qure.AI. Kết quả: So sánh giữa kết quả chẩn đoán cuối cùng với phân tích của Qure.AI cho kết quả tính đồng thuận ở mức tốt giữa 2 phương pháp. Độ nhạy của Qure.AI là 88,8%, độ đặc hiệu là 48,8%, giá trị dự đoán âm tính 71%. Diện tích dưới đường cong ROC là 77,1% với p <
0,001, KTC 95%: 0,69-0,86. Như vậy hình ảnh X-quang ngực được đọc bởi Qure.AI có giá trị trong chẩn đoán lao phổi với độ chính xác ở mức độ khá tốt với điểm cut off là 0,503. Nghiên cứu của chúng tôi cho thấy rằng AI có tiềm năng trở thành một công cụ cần thiết trong việc hỗ trợ chẩn đoán sớm lao phổi, sàng lọc lao phổi cộng đồng. Kết luận: Trí tuệ nhân tạo Qure. AI có thể đóng vai trò quan trọng trong chẩn đoán sớm lao phổi và hỗ trợ cho kết quả vi sinh hoặc mô bệnh học.Our study aims to evaluate the role of Qure.AI artificial intelligence in analyzing chest X-ray images for the early diagnosis of pulmonary tuberculosis (TB). Method: This is a descriptive study involving 126 patients suspected of having pulmonary tuberculosis. Their chest X-ray images were analyzed by Qure.AI, and microbiological or histopathological tests were conducted for TB diagnosis. The final diagnostic results were compared with the Qure.AI analysis. Results: The comparison between the final diagnostic results and Qure.AI’s analysis showed a good level of agreement between the two methods. Qure.AI’s sensitivity was 88.8%, specificity was 48.8%, and negative predictive value was 71%. The area under the ROC curve was 77.1% with p <
0.001, 95% confidence interval: 0.69-0.86. Therefore, chest X-ray images interpreted by Qure.AI are valuable in diagnosing pulmonary tuberculosis, with a fairly good accuracy at a cut-off point of 0.503. Our study indicates that AI has the potential to become an essential tool in assisting with early TB diagnosis and community TB screening. Conclusion: Qure.AI artificial intelligence can play a significant role in the early diagnosis of pulmonary tuberculosis and support microbiological or histopathological results.

1. Đọc trực tuyến

1. Đọc trực tuyến

Tạo bộ sưu tập với mã QR