A Steiner1, C Mangu2, J van den Hombergh3, H van Deutekom4, B van Ginneken5, P Clowes6, F Mhimbira1, S Mfinanga7, A Rachow8, K Reither1, M Hoelscher9. 1. Swiss Tropical and Public Health Institute, Basel, Switzerland ; University of Basel, Basel, Switzerland. 2. National Institute of Medical Research, Mbeya Medical Research Center, Mbeya, Tanzania. 3. PharmAccess Foundation, Dar es Salaam, Tanzania. 4. Department of Tuberculosis Control, Municipal Health Service, Amsterdam, The Netherlands. 5. Radboud University Medical Center, Nijmegen, The Netherlands. 6. National Institute of Medical Research, Mbeya Medical Research Center, Mbeya, Tanzania ; Division of Infectious Disease and Tropical Medicine, Medical Center of the University of Munich, Munich, Germany. 7. Muhimbili Medical Research Centre, Dar es Salaam, Tanzania. 8. Division of Infectious Disease and Tropical Medicine, Medical Center of the University of Munich, Munich, Germany ; German Centre for Infection Research, Munich, Germany. 9. National Institute of Medical Research, Mbeya Medical Research Center, Mbeya, Tanzania ; Division of Infectious Disease and Tropical Medicine, Medical Center of the University of Munich, Munich, Germany ; German Centre for Infection Research, Munich, Germany.
Abstract
SETTING: Tanzania is a high-burden country for tuberculosis (TB), and prisoners are a high-risk group that should be screened actively, as recommended by the World Health Organization. Screening algorithms, starting with chest X-rays (CXRs), can detect asymptomatic cases, but depend on experienced readers, who are scarce in the penitentiary setting. Recent studies with patients seeking health care for TB-related symptoms showed good diagnostic performance of the computer software CAD4TB. OBJECTIVE: To assess the potential of computer-assisted screening using CAD4TB in a predominantly asymptomatic prison population. DESIGN: Cross-sectional study. RESULTS: CAD4TB and seven health care professionals reading CXRs in local tuberculosis wards evaluated a set of 511 CXRs from the Ukonga prison in Dar es Salaam. Performance was compared using a radiological reference. Two readers performed significantly better than CAD4TB, three were comparable, and two performed significantly worse (area under the curve 0.75 in receiver operating characteristics analysis). On a superset of 1321 CXRs, CAD4TB successfully interpreted >99%, with a predictably short time to detection, while 160 (12.2%) reports were delayed by over 24 h with conventional CXR reading. CONCLUSION: CAD4TB reliably evaluates CXRs from a mostly asymptomatic prison population, with a diagnostic performance inferior to that of expert readers but comparable to local readers.
SETTING: Tanzania is a high-burden country for tuberculosis (TB), and prisoners are a high-risk group that should be screened actively, as recommended by the World Health Organization. Screening algorithms, starting with chest X-rays (CXRs), can detect asymptomatic cases, but depend on experienced readers, who are scarce in the penitentiary setting. Recent studies with patients seeking health care for TB-related symptoms showed good diagnostic performance of the computer software CAD4TB. OBJECTIVE: To assess the potential of computer-assisted screening using CAD4TB in a predominantly asymptomatic prison population. DESIGN: Cross-sectional study. RESULTS: CAD4TB and seven health care professionals reading CXRs in local tuberculosis wards evaluated a set of 511 CXRs from the Ukonga prison in Dar es Salaam. Performance was compared using a radiological reference. Two readers performed significantly better than CAD4TB, three were comparable, and two performed significantly worse (area under the curve 0.75 in receiver operating characteristics analysis). On a superset of 1321 CXRs, CAD4TB successfully interpreted >99%, with a predictably short time to detection, while 160 (12.2%) reports were delayed by over 24 h with conventional CXR reading. CONCLUSION: CAD4TB reliably evaluates CXRs from a mostly asymptomatic prison population, with a diagnostic performance inferior to that of expert readers but comparable to local readers.
Authors: S den Boon; N W White; S W P van Lill; M W Borgdorff; S Verver; C J Lombard; E D Bateman; E Irusen; D A Enarson; N Beyers Journal: Int J Tuberc Lung Dis Date: 2006-08 Impact factor: 2.373
Authors: Iacopo Baussano; Brian G Williams; Paul Nunn; Marta Beggiato; Ugo Fedeli; Fabio Scano Journal: PLoS Med Date: 2010-12-21 Impact factor: 11.069
Authors: Katie R Maggard; Sisa Hatwiinda; Jennifer B Harris; Winifreda Phiri; Annika Krüüner; Kaunda Kaunda; Stephanie M Topp; Nathan Kapata; Helen Ayles; Chisela Chileshe; German Henostroza; Stewart E Reid Journal: Bull World Health Organ Date: 2015-02-01 Impact factor: 9.408
Authors: Natalie V S Vinkeles Melchers; Sabine L van Elsland; Joep M A Lange; Martien W Borgdorff; Jan van den Hombergh Journal: PLoS One Date: 2013-01-25 Impact factor: 3.240
Authors: Marianne Breuninger; Bram van Ginneken; Rick H H M Philipsen; Francis Mhimbira; Jerry J Hella; Fred Lwilla; Jan van den Hombergh; Amanda Ross; Levan Jugheli; Dirk Wagner; Klaus Reither Journal: PLoS One Date: 2014-09-05 Impact factor: 3.240
Authors: Miriam Harris; Amy Qi; Luke Jeagal; Nazi Torabi; Dick Menzies; Alexei Korobitsyn; Madhukar Pai; Ruvandhi R Nathavitharana; Faiz Ahmad Khan Journal: PLoS One Date: 2019-09-03 Impact factor: 3.240
Authors: Eui Jin Hwang; Sunggyun Park; Kwang-Nam Jin; Jung Im Kim; So Young Choi; Jong Hyuk Lee; Jin Mo Goo; Jaehong Aum; Jae-Joon Yim; Chang Min Park Journal: Clin Infect Dis Date: 2019-08-16 Impact factor: 9.079