Performance of a Novel Algorithm Using Automated Digital Microscopy for Diagnosing Tuberculosis

Abstract

Abstract:Rationale: TBDx automated microscopy is a novel technology that processes digital microscope images to identify acid-fast bacilli (AFB). TBDx as part of a diagnostic algorithm could improve the diagnosis of tuberculosis (TB), but its performance characteristics have not been formally tested.Objective: To evaluate the performance of the TBDx automated microscopy system in algorithms for diagnosis of TB. Methods: Prospective samples from patients with presumed TB were processed in parallel with conventional smear microscopy, TBDx microscopy, and liquid culture. AllTBDx positive specimens were also tested with Xpert MTB/RIF (GXP). We evaluated the sensitivity and specificity of two algorithms: 1) TBDX-GXP (TBDx, with positive specimens tested by Xpert MTB/RIF) and 2) TBDx alone, against the gold standard liquid-media culture. as having 1-9 putative AFB (low positive). An algorithm in which "low positive" results on TBDx were confirmed by GXP had 78% sensitivity (85/109) and 99.8% specificity (889/900), requiring 21% (207/1009) specimens to be processed by GXP. As a standalone test, a "high positive" result on TBDx had 62% sensitivity and 99.7% specificity.Conclusions: TBDx used in diagnostic algorithms with GXP provided reasonable sensitivity and high specificity for active TB while dramatically reducing the number GXP tests performed. As a stand-alone microscopy system, performance was equivalent to a highly experienced TB microscopist.

Update in Tuberculosis/Pulmonary Infections 2015

“…In this study, Ismail and colleagues found that the TBDx System (Signature Mapping Medical Sciences Inc., Herndon, VA) performed as well as an experienced TB microscopist, with 62% sensitivity and 99.7% specificity (13). Although this tool may offer some diagnostic options in areas where there are limited human resources, its inability to detect resistance and its low sensitivity may limit its utility in the field.…”

New technologies for the diagnosis of drug-resistant tuberculosis

“…Для окрашивания мазков перед внесением в систему могут быть использованы автоматизированные высокопроизводительные окрашивающие платформы, например RAL Stainer (RAL Diagnostics, Франция) или Aerospray TB Series 2 (ELITechGroup, Франция). Изучение целесообразности применения TBDx для диагностики туберкулеза, проведенное в Южной Африке, продемонстрировало, что результаты, полученные с использованием автономной системы, оказались сопоставимы с результатами, получаемыми опытными микроскопистами, поэтому TBDx является идеальным диагностическим решением в ситуации отсутствия квалифицированных специалистов [9,10].…”

Update in Mycobacterium tuberculosis Lung Disease 2014

“…Ismail and colleagues evaluated performance of an automated digital microscopy platform with digital image processing, using more than 1,000 samples (21). They found performance to be equivalent to that of an experienced TB microscopist, and that it provided acceptable sensitivity and a high specificity for active TB.…”