Computer aided detection of tuberculosis on chest radiographs: An evaluation of the CAD4TB v6 system.

There is a growing interest in the automated analysis of chest X-Ray (CXR) as a sensitive and inexpensive means of screening susceptible populations for pulmonary tuberculosis. In this work we evaluate the latest version of CAD4TB, a commercial software platform designed for this purpose. Version 6 of CAD4TB was released in 2018 and is here tested on a fully independent dataset of 5565 CXR images with GeneXpert (Xpert) sputum test results available (854 Xpert positive subjects). A subset of 500 subjects (50% Xpert positive) was reviewed and annotated by 5 expert observers independently to obtain a radiological reference standard. The latest version of CAD4TB is found to outperform all previous versions in terms of area under receiver operating curve (ROC) with respect to both Xpert and radiological reference standards. Improvements with respect to Xpert are most apparent at high sensitivity levels with a specificity of 76% obtained at a fixed 90% sensitivity. When compared with the radiological reference standard, CAD4TB v6 also outperformed previous versions by a considerable margin and achieved 98% specificity at the 90% sensitivity setting. No substantial difference was found between the performance of CAD4TB v6 and any of the various expert observers against the Xpert reference standard. A cost and efficiency analysis on this dataset demonstrates that in a standard clinical situation, operating at 90% sensitivity, users of CAD4TB v6 can process 132 subjects per day at an average cost per screen of $5.95 per subject, while users of version 3 process only 85 subjects per day at a cost of $8.38 per subject. At all tested operating points version 6 is shown to be more efficient and cost effective than any other version.

Risk of developing tuberculosis disease among persons diagnosed with latent tuberculosis infection in the Netherlands.

Diagnosis and preventive treatment of latent tuberculosis infection (LTBI) among high-risk groups is recommended to achieve tuberculosis (TB) elimination in low-incidence countries.We studied TB incidence rates among those notified with LTBI in the Netherlands from 2005 to 2013 and analysed associated risk factors. We stratified analyses by target group for screening, and by initiation and completion of preventive treatment.The incidence for those completing, stopping and not receiving preventive treatment was 187, 436 and 355 per 100 000 person-years for contacts of TB patients, respectively, and 63, 96 and 110 per 100 000 person-years for other target groups. The rate ratio for TB development among contacts compared to other target groups was 3.1 (95% CI 2.0-4.9). In both groups, incidence was highest in the first year after diagnosis. Independent factors associated with progression to TB among contacts were age <5 years and stopping preventive treatment within 28 days compared to those not receiving preventive treatment. Among other target groups, being foreign born was the only risk factor associated with the risk of developing TB.We conclude that the epidemiological impact of preventive treatment is highest in contacts of TB patients and limited in other target groups for LTBI management in the Netherlands.

Monitoring latent tuberculosis infection diagnosis and management in the Netherlands.

Targeted diagnosis and treatment of latent tuberculosis (TB) infection (LTBI) among persons with a high risk of exposure to TB or of developing TB when infected has been performed and monitored routinely in the Netherlands since 1993. We describe trends in target groups, diagnostic methods and treatment regimens, and explore determinants for treatment initiation, treatment completion and adverse events.In total, 37 729 persons were registered with LTBI from 1993 to 2013, of whom 28 931 (77%) started preventive treatment; 82% of those completed preventive treatment and 8% stopped preventive treatment due to adverse events. Two-thirds of the notified cases were detected through contact investigation.Increasing numbers of persons with immunosuppressive disorders, elderly persons and foreign-born persons were notified in recent years, due to policy changes and the introduction of the interferon-γ release assay. Children (96%) and the immunosuppressed (95%) were more likely to start preventive treatment. Children (93%) were also more likely to complete preventive treatment, as were persons treated with rifampicin or rifampicin/isoniazid regimens (91% and 92%, respectively). The latter groups were also 40% less likely to stop preventive treatment due to adverse events.Under these operational conditions, the estimated risk reduction on incident TB in the target population for LTBI management is 40-60%.

TB-HIV co-infection in the Netherlands: estimating prevalence and under-reporting in national registration databases using a capture-recapture analysis.

BACKGROUND: Knowledge of the HIV status in patients with tuberculosis (TB) and vice versa is crucial for proper individual patient management, while knowledge of the prevalence of co-infection guides preventive and therapeutic strategies. The aim of the study was to assess if national disease databases on TB and HIV are adequate sources to provide this information. METHODS: A two way capture-recapture analysis to assess the completeness of the registers, and to obtain the prevalence of TB-HIV co-infection in the Netherlands in the years 2002-2012. RESULTS: HIV testing was performed in less than 50% of the patients with TB. Of the 932 TB-HIV infected patients, just 293 (31.4%) were registered in both registers. Under-reporting of TB-HIV co-infection ranged from 50% to 70% in the national TB register, and from 31% to 37% in the HIV database. Prevalence of TB-HIV co-infection in the Netherlands in 2012 was 7.1% (95% CI 6.0% to 8.3%), which was more than double of the prevalence estimated from the national TB database. CONCLUSIONS: TB-HIV co-infection is markedly under-reported in national disease databases. There is an urgent need for improved registration and preferably a routine data exchange between the two surveillance systems.