CLINICAL AND SUBCLINICAL FEATURES AND CHEST X-RAY RESULTS ANALYZED BY QURE ARTIFICIAL INTELLIGENCE.AI OF PATIENTS SUSPECTED OF PULMONARY TUBERCULOSIS AT HANOI MEDICAL UNIVERSITY HOSPITAL IN 2022
Main Article Content
Abstract
Objectives: Description of clinical features, subclinical and comment on chest X-ray results analyzed by artificial intelligence Qure.AI of patients suspected of pulmonary TB for examination and inpatient treatment at Hanoi Medical University Hospital in 2022. Subjects and methodology: Cross-sectional descriptive study of 126 patients with suspected pulmonary TB for inpatient examination and treatment at Hanoi Medical University. Results: The age of patients suspected of pulmonary TB is still mainly in the working age group of 30-60. Common systemic symptoms of the study group of patients were fatigue, fever, thinness, weight loss,weating.The most common symptom of the study group was sputum cough accounting for 91,3%. Sedimentation test results are still very valuable in diagnosing pulmonary TB. Study patients with chest X-ray lesions were hazy lesions accounting for the highest rate of 74.6%.The detection of TB bacteria by MGIT and Genxpert assays is higher than that of AFB tests using Ziehl-Neelsen staining. The area under the ROC curve is 77.1% with p< 0,001,95% Cl: 0.69- 0.86. Thus, the chest X-ray images read by Qure.AI are valuable in diagnosing pulmonary tuberculosis with a fairly good level of accuracy with a cut-off score of 0.503
Article Details
Keywords
Suspected pulmonary tuberculosis, clinical features, subclinical, Qure.AI, chest X-ray.
References
2. Quyết định 3126/QĐ-BYT hướng dẫn chẩn đoán, điều trị, dự phòng lao. Accessed June 23, 2022. https://vnras.com/quyet-dinh-3126-qd-byt/
3. Nghiên cứu giá trị của xét nghiệm Xpert MTB/RIF Ultra đờm ở người bệnh nghi lao có hai mẫu xét nghiệm soi đờm trực tiếp AFB (-). Accessed July 7, 2023. https://tapchinghiencuuyhoc.vn/index.php/tcncyh/article/view/571/269
4. Linguissi LSG, Vouvoungui CJ, Poulain P, Essassa GB, Kwedi S, Ntoumi F. Diagnosis of smear-negative pulmonary tuberculosis based on clinical signs in the Republic of Congo. BMC Res Notes. 2015;8:804. doi:10.1186/s13104-015-1774-8
5. Trịnh Việt Anh (2014), Đặc điểm lâm sàng, cận lâm sàng và xét nghiệm genxpert trong đờm ở những bệnh nhân nghi lao phổi tại trung tâm hô hấp BV Bạch Mai, Luận văn thạc sĩ y học, Trường Đại học Y Hà Nội
6. Qin ZZ, Sander MS, Rai B, et al. Using artificial intelligence to read chest radiographs for tuberculosis detection: A multi-site evaluation of the diagnostic accuracy of three deep learning systems. Sci Rep. 2019;9(1):15000. doi: 10.1038/s41598-019-51503-3