Diagnostic accuracy of three computer-aided detection systems for detecting pulmonary tuberculosis on chest radiography when used for screening: analysis of an international, multicenter migrants screening study
Author/s: Sifrash Meseret Gelaw, Sandra V. Kik, Morten Ruhwald, Stefano Ongarello, Tesfa Semagne Egzertegegne, Olga Gorbacheva, Christopher Gilpin, Nina Marano, Scott Lee, Christina R. Phares, Victoria Medina, Bhaskar Amatya, Claudia M. Denkinger
The aim of this study was to independently evaluate the diagnostic accuracy of three artificial intelligence (AI)-based computer aided detection (CAD) systems for detecting pulmonary tuberculosis (TB) on global migrants screening chest x-ray (CXR) cases.
Retrospective clinical data and CXR images were collected from the International Organization for Migration (IOM) pre-migration health assessment TB screening global database for US-bound migrants. A total of 2,812 participants were…Read more
Diagnostic accuracy of chest X-ray interpretation for tuberculosis by three artificial intelligence-based software in a screening use-case: an individual patient meta-analysis of global data
Author/s: Sandra V. Kik, Sifrash M. Gelaw, Morten Ruhwald, Rinn Song, Faiz Ahmad Khan, Rob van Hest, Violet Chihota, Nguyen Viet Nhung, Aliasgar Esmail, Anna Marie Celina Garfin, Guy B. Marks, Olga Gorbacheva, Onno W. Akkerman, Kgaugelo Moropane, Le Thi Ngoc Anh, Keertan Dheda, Greg J. Fox, Nina Marano, Knut Lönnroth, Frank Cobelens, Andrea Benedetti, Puneet Dewan, Stefano Ongarello, Claudia M. Denkinger
Chest X-ray (CXR) screening is a useful diagnostic tool to test individuals at high risk of tuberculosis (TB), yet image interpretation requires trained human readers who are in short supply in many high TB burden countries. Therefore, CXR interpretation by computer-aided detection software (CAD) may overcome some of these challenges, but evidence of its accuracy is still limited.
We established a CXR library with images and metadata from…Read more
A new resource on artificial intelligence powered computer automated detection software products for tuberculosis programmes and implementers
Author/s: Zhi Zhen Qin, Tasneem Naheyan, Morten Ruhwald, Claudia M. Denkinger, Sifrash Gelaw, Madlen Nash, Jacob Creswell, Sandra Vivian Kik
Recently, the number of artificial intelligence-powered computer-aided detection (CAD) products that detect tuberculosis (TB)-related abnormalities from chest X-rays (CXR) available on the market has increased. Although CXR is a relatively effective and inexpensive method for TB screening and triaging, a shortage of skilled radiologists in many high TB-burden countries limits its use. CAD technology offers a solution to this problem. Before adopting a CAD product,…Read more
Author/s: A Ohkado, P Douglas, D Zenner, L Kawatsu
As the proportion of foreign-born persons among TB notifications continues to rise, Japan is preparing to introduce pre-migration TB screening for those coming from selected countries, who are intending to stay for more than 90 days. It has announced that the programme will commence in 2020. In this review, the authors examine the experiences from two countries which already have years of experience in operating pre-migration TB screening, namely the United Kingdom…Read more
Author/s: Arnold Bainomugisa, Christopher Gilpin, Christopher Coulter, Ben J. Marais
The spread of DR-TB strains threatens recent gains in global TB control, with evidence that the majority of patients with rifampicin-resistant (RR-TB) or multi-drug resistant (MDR-TB) TB acquire their infection through person-to-person transmission. Inadequate diagnostic and treatment options have hampered an effective global response. The use of Xpert MTB/RIF as a rapid and sensitive frontline TB detection test has been shown to improve patient outcomes and is cost-effective, but data for…Read more
Author/s: Gabriella Scandurra, Chris Degeling, Paul Douglas, Claudia C. Dobler, Ben Marais
Tuberculosis (TB) is the leading infectious cause of human mortality and is responsible for nearly 2 million deaths every year. It is often regarded as a ‘silent killer’ because it predominantly affects the poor and marginalized, and disease outbreaks occur in ‘slow motion’ compared to Ebola or coronavirus 2 (COVID-19). In low incidence countries, TB is predominantly an imported disease and TB control in migrants is pivotal for countries to progress towards TB elimination in accordance with…Read more
Health profile of adult special immigrant visa holders arriving from Iraq and Afghanistan to the United States, 2009–2017: A cross-sectional analysis
Author/s: Gayathri S. Kumar, Simone S. Wien, Christina R. Phares, Walid Slim, Heather M. Burke, Emily S. Jentes
Between 2,000 and 19,000 Special Immigrant Visa (SIV) holders (SIVH) from Iraq and Afghanistan resettle in the United States annually. Despite the increase in SIV admissions to the US over recent years, little is known about the health conditions in SIV populations. We assessed the burden of select communicable and noncommunicable diseases (NCDs) in SIV adults to guide recommendations to clinicians in the US.
Methods and…Read more
Tools to implement the WHO End TB Strategy: Addressing common challenges in high and low endemic countries
Author/s: Seif Al Abri, Thereza Kasaeva, Giovanni-Batista Migliori, Delia Goletti, Dominik Zenner, Justin Denholm, Amal Al Maani, Daniela Maria Cirillo, Thomas Schön, Troels Lillebæk, Amina Al-Jardani, Un-Yeong GO, Hannah Monica Dias, Simon Tiberi, Fatma Al Yaquobi, Faryal Ali Khamis, Padmamohan Kurup, Michael Wilson, Ziad Memish, Ali Al Maqbali, Muhammad Akhtar, Christian Wejse, Eskild Petersen
The purpose of this viewpoint is to summarize the advantages and constraints of the tools and strategies available for reducing the annual incidence of TB by implementing the WHO End TB Strategy and the linked WHO TB Elimination Framework with special reference to Oman.
The case-study was built based on the presentations and discussions at an international workshop on TB elimination in low incidence countries organized by the Ministry of…
Author/s: Barbara Bardenheir, Meda Pavkov, Carla Winston, Alex Klosovsky, Catherine Yen, Stephen Benoit, Stefan Gravenstein, Drew Posey, Christina Phares
The association between chronic kidney disease (CKD) and tuberculosis disease (TB) has been recognized for decades. Recently CKD prevalence is increasing in low- to middle-income countries with high TB burden. Using data from the required overseas medical exam and the recommended US follow-up exam for 444,356 US-bound refugees aged ≥ 18 during 2009–2017, we ran Poisson regression to assess the prevalence of TB among refugees with and without CKD, controlling for sex, age,…Read more
Using artificial intelligence to read chest radiographs for tuberculosis detection: A multi-site evaluation of the diagnostic accuracy of three deep learning systems
Author/s: Zhi Zhen Qin, Melissa S. Sander, Bishwa Rai, Collins N. Titahong, Santat Sudrungrot, Sylvain N. Laah, Lal Mani Adhikari, E. Jane Carter, Lekha Puri, Andrew J. Codlin, & Jacob Creswell
Deep learning (DL) neural networks have only recently been employed to interpret chest radiography (CXR) to screen and triage people for pulmonary tuberculosis (TB). No published studies have compared multiple DL systems and populations. We conducted a retrospective evaluation of three DL systems (CAD4TB, Lunit INSIGHT, and qXR) for detecting TB-associated abnormalities in chest radiographs from outpatients in Nepal and Cameroon. All 1196 individuals received a Xpert MTB/RIF assay and a CXR…Read more