Ruby Maka Shrestha, Ram Chandra Paudel, Puspanjali Adhikari, Ram Hari Ghimire, Karma Gurung, Rajeev Shrestha
{"title":"基于人工智能的胸部x线透视筛查肺结核的诊断准确性。","authors":"Ruby Maka Shrestha, Ram Chandra Paudel, Puspanjali Adhikari, Ram Hari Ghimire, Karma Gurung, Rajeev Shrestha","doi":"10.33314/jnhrc.v22i03.4637","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Tuberculosis remains a public health challenge in Nepal and ranks as the seventh leading cause of death in the country. The END Tuberculosis strategy stresses - the screening for symptoms alone may not suffice; additional screening tools such as a chest radiograph may facilitate referral for diagnosis of tuberculosis. The study aims to evaluate the diagnostic accuracy of artificial intelligence (AI) based Chest X-ray and compare it with the human reading (radiologist), using GeneXpert-MTB RIF Assay for tuberculosis case detection.</p><p><strong>Methods: </strong>Tuberculosis-suspected patients with a history of cough were screened using chest X-rays at two study sites (Dhulikhel Hospital and Nobel Medical College). The reading of AI qXR software was compared with radiologists reading who were blinded of the results generated by the software.</p><p><strong>Results: </strong>The sensitivity of the test by qXR-based AI reading was 100%, (95% CI: 40 - 100%) and specificity 80% (95% CI: 73 - 87%), whereas the sensitivity of the test by the radiologist was 100%, (95% CI: 40 - 100%); and specificity 62% (95% CI: 53 - 70%).</p><p><strong>Conclusions: </strong>Higher sensitivity and specificity were observed for both qXR-based AI and Radiographer readings for the diagnosis of TB.</p>","PeriodicalId":16380,"journal":{"name":"Journal of Nepal Health Research Council","volume":"22 3","pages":"477-483"},"PeriodicalIF":0.0000,"publicationDate":"2024-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Diagnostic Accuracy of Artificial Intelligence-Based Chest X-Ray reading for screening of Tuberculosis.\",\"authors\":\"Ruby Maka Shrestha, Ram Chandra Paudel, Puspanjali Adhikari, Ram Hari Ghimire, Karma Gurung, Rajeev Shrestha\",\"doi\":\"10.33314/jnhrc.v22i03.4637\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Background: </strong>Tuberculosis remains a public health challenge in Nepal and ranks as the seventh leading cause of death in the country. The END Tuberculosis strategy stresses - the screening for symptoms alone may not suffice; additional screening tools such as a chest radiograph may facilitate referral for diagnosis of tuberculosis. The study aims to evaluate the diagnostic accuracy of artificial intelligence (AI) based Chest X-ray and compare it with the human reading (radiologist), using GeneXpert-MTB RIF Assay for tuberculosis case detection.</p><p><strong>Methods: </strong>Tuberculosis-suspected patients with a history of cough were screened using chest X-rays at two study sites (Dhulikhel Hospital and Nobel Medical College). The reading of AI qXR software was compared with radiologists reading who were blinded of the results generated by the software.</p><p><strong>Results: </strong>The sensitivity of the test by qXR-based AI reading was 100%, (95% CI: 40 - 100%) and specificity 80% (95% CI: 73 - 87%), whereas the sensitivity of the test by the radiologist was 100%, (95% CI: 40 - 100%); and specificity 62% (95% CI: 53 - 70%).</p><p><strong>Conclusions: </strong>Higher sensitivity and specificity were observed for both qXR-based AI and Radiographer readings for the diagnosis of TB.</p>\",\"PeriodicalId\":16380,\"journal\":{\"name\":\"Journal of Nepal Health Research Council\",\"volume\":\"22 3\",\"pages\":\"477-483\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-12-19\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Nepal Health Research Council\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.33314/jnhrc.v22i03.4637\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"Medicine\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Nepal Health Research Council","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.33314/jnhrc.v22i03.4637","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"Medicine","Score":null,"Total":0}
Diagnostic Accuracy of Artificial Intelligence-Based Chest X-Ray reading for screening of Tuberculosis.
Background: Tuberculosis remains a public health challenge in Nepal and ranks as the seventh leading cause of death in the country. The END Tuberculosis strategy stresses - the screening for symptoms alone may not suffice; additional screening tools such as a chest radiograph may facilitate referral for diagnosis of tuberculosis. The study aims to evaluate the diagnostic accuracy of artificial intelligence (AI) based Chest X-ray and compare it with the human reading (radiologist), using GeneXpert-MTB RIF Assay for tuberculosis case detection.
Methods: Tuberculosis-suspected patients with a history of cough were screened using chest X-rays at two study sites (Dhulikhel Hospital and Nobel Medical College). The reading of AI qXR software was compared with radiologists reading who were blinded of the results generated by the software.
Results: The sensitivity of the test by qXR-based AI reading was 100%, (95% CI: 40 - 100%) and specificity 80% (95% CI: 73 - 87%), whereas the sensitivity of the test by the radiologist was 100%, (95% CI: 40 - 100%); and specificity 62% (95% CI: 53 - 70%).
Conclusions: Higher sensitivity and specificity were observed for both qXR-based AI and Radiographer readings for the diagnosis of TB.
期刊介绍：
The journal publishes articles related to researches done in the field of biomedical sciences related to all the discipline of the medical sciences, medical education, public health, health care management, including ethical and social issues pertaining to health. The journal gives preference to clinically oriented studies over experimental and animal studies. The Journal would publish peer-reviewed original research papers, case reports, systematic reviews and meta-analysis. Editorial, Guest Editorial, Viewpoint and letter to the editor are solicited by the editorial board. Frequently Asked Questions (FAQ) regarding manuscript submission and processing at JNHRC.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
