The sensitivity and specificity of using a computer aided diagnosis program for automatically scoring chest X-rays of presumptive TB patients compared with Xpert MTB/RIF in Lusaka Zambia

Computer-aided detection of tuberculosis from chest radiographs in a tuberculosis prevalence survey in South Africa: external validation and modelled impacts of commercially available artificial intelligence software

BACKGROUND

Computer-aided detection (CAD) can help identify people with active tuberculosis left undetected. However, few studies have compared the performance of commercially available CAD products for screening in high tuberculosis and high HIV settings, and there is poor understanding of threshold selection across products in different populations. We aimed to compare CAD products' performance, with further analyses on subgroup performance and threshold selection.

METHODS

We evaluated 12 CAD products on a case-control sample of participants from a South African tuberculosis prevalence survey. Only those with microbiological test results were eligible. The primary outcome was comparing products' accuracy using the area under the receiver operating characteristic curve (AUC) against microbiological evidence. Threshold analyses were performed based on pre-defined criteria and across all thresholds. We conducted subgroup analyses including age, gender, HIV status, previous tuberculosis history, symptoms presence, and current smoking status.

FINDINGS

Of the 774 people included, 516 were bacteriologically negative and 258 were bacteriologically positive. Diverse accuracy was noted: Lunit and Nexus had AUCs near 0·9, followed by qXR, JF CXR-2, InferRead, Xvision, and ChestEye (AUCs 0·8-0·9). XrayAME, RADIFY, and TiSepX-TB had AUC under 0·8. Thresholds varied notably across these products and different versions of the same products. Certain products (Lunit, Nexus, JF CXR-2, and qXR) maintained high sensitivity (>90%) across a wide threshold range while reducing the number of individuals requiring confirmatory diagnostic testing. All products generally performed worst in older individuals, people with previous tuberculosis, and people with HIV. Variations in thresholds, sensitivity, and specificity existed across groups and settings.

INTERPRETATION

Several previously unevaluated products performed similarly to those evaluated by WHO. Thresholds differed across products and demographic subgroups. The rapid emergence of products and versions necessitates a global strategy to validate new versions and software to support CAD product and threshold selections.

FUNDING

Government of Canada.

Accuracy of digital chest x-ray analysis with artificial intelligence software as a triage and screening tool in hospitalized patients being evaluated for tuberculosis in Lima, Peru

Tuberculosis (TB) transmission in healthcare facilities is common in high-incidence countries. Yet, the optimal approach for identifying inpatients who may have TB is unclear. We evaluated the diagnostic accuracy of qXR (Qure.ai, India) computer-aided detection (CAD) software versions 3.0 and 4.0 (v3 and v4) as a triage and screening tool within the FAST (Find cases Actively, Separate safely, and Treat effectively) transmission control strategy. We prospectively enrolled two cohorts of patients admitted to a tertiary hospital in Lima, Peru: one group had cough or TB risk factors (triage) and the other did not report cough or TB risk factors (screening). We evaluated the sensitivity and specificity of qXR for the diagnosis of pulmonary TB using culture and Xpert as primary and secondary reference standards, including stratified analyses based on risk factors. In the triage cohort (n = 387), qXR v4 sensitivity was 0.91 (59/65, 95% CI 0.81-0.97) and specificity was 0.32 (103/322, 95% CI 0.27-0.37) using culture as reference standard. There was no difference in the area under the receiver-operating-characteristic curve (AUC) between qXR v3 and qXR v4 with either a culture or Xpert reference standard. In the screening cohort (n = 191), only one patient had a positive Xpert result, but specificity in this cohort was high (>90%). A high prevalence of radiographic lung abnormalities, most notably opacities (81%), consolidation (62%), or nodules (58%), was detected by qXR on digital CXR images from the triage cohort. qXR had high sensitivity but low specificity as a triage in hospitalized patients with cough or TB risk factors. Screening patients without cough or risk factors in this setting had a low diagnostic yield. These findings further support the need for population and setting-specific thresholds for CAD programs.

Standardised Measurements for Monitoring and Comparing Multiphoton Microscope Systems

The goal of this protocol is to enable better characterisation of multiphoton microscopy hardware across a large user base. The scope of this protocol is purposefully limited to focus on hardware, touching on software and data analysis routines only where relevant. The intended audiences are scientists using and building multiphoton microscopes in their laboratories. The goal is that any scientist, not only those with optical expertise, can test whether their multiphoton microscope is performing well and producing consistent data over the lifetime of their system.

Computer-aided detection thresholds for digital chest radiography interpretation in tuberculosis diagnostic algorithms

Objectives

Use of computer-aided detection (CAD) software is recommended to improve tuberculosis screening and triage, but threshold determination is challenging if reference testing has not been performed in all individuals. We aimed to determine such thresholds through secondary analysis of the 2019 Lesotho national tuberculosis prevalence survey.

Methods

Symptom screening and chest radiographs were performed in participants aged ≥15 years; those symptomatic or with abnormal chest radiographs provided samples for Xpert MTB/RIF and culture testing. Chest radiographs were processed using CAD4TB version 7. We used six methodological approaches to deal with participants who did not have bacteriological test results to estimate pulmonary tuberculosis prevalence and assess diagnostic accuracy.

Results

Among 17 070 participants, 5214 (31%) had their tuberculosis status determined; 142 had tuberculosis. Prevalence estimates varied between methodological approaches (0.83-2.72%). Using multiple imputation to estimate tuberculosis status for those eligible but not tested, and assuming those not eligible for testing were negative, a CAD4TBv7 threshold of 13 had a sensitivity of 89.7% (95% CI 84.6-94.8) and a specificity of 74.2% (73.6-74.9), close to World Health Organization (WHO) target product profile criteria. Assuming all those not tested were negative produced similar results.

Conclusions

This is the first study to evaluate CAD4TB in a community screening context employing a range of approaches to account for unknown tuberculosis status. The assumption that those not tested are negative - regardless of testing eligibility status - was robust. As threshold determination must be context specific, our analytically straightforward approach should be adopted to leverage prevalence surveys for CAD threshold determination in other settings with a comparable proportion of eligible but not tested participants.

Accuracy of digital chest x-ray analysis with artificial intelligence software as a triage and screening tool in hospitalized patients being evaluated for tuberculosis in Lima, Peru

Introduction

Tuberculosis (TB) transmission in healthcare facilities is common in high-incidence countries. Yet, the optimal approach for identifying inpatients who may have TB is unclear. We evaluated the diagnostic accuracy of qXR (Qure.ai, India) computer-aided detection (CAD) software versions 3.0 and 4.0 (v3 and v4) as a triage and screening tool within the FAST (Find cases Actively, Separate safely, and Treat effectively) transmission control strategy.

Methods

We prospectively enrolled two cohorts of patients admitted to a tertiary hospital in Lima, Peru: one group had cough or TB risk factors (triage) and the other did not report cough or TB risk factors (screening). We evaluated the sensitivity and specificity of qXR for the diagnosis of pulmonary TB using culture and Xpert as primary and secondary reference standards, including stratified analyses based on risk factors.

Results

In the triage cohort (n=387), qXR v4 sensitivity was 0.91 (59/65, 95% CI 0.81-0.97) and specificity was 0.32 (103/322, 95% CI 0.27-0.37) using culture as reference standard. There was no difference in the area under the receiver-operating-characteristic curve (AUC) between qXR v3 and qXR v4 with either a culture or Xpert reference standard. In the screening cohort (n=191), only one patient had a positive Xpert result, but specificity in this cohort was high (>90%). A high prevalence of radiographic lung abnormalities, most notably opacities (81%), consolidation (62%), or nodules (58%), was detected by qXR on digital CXR images from the triage cohort.

Conclusions

qXR had high sensitivity but low specificity as a triage in hospitalized patients with cough or TB risk factors. Screening patients without cough or risk factors in this setting had a low diagnostic yield. These findings further support the need for population and setting-specific thresholds for CAD programs.

Computer-Aided Detection for Chest Radiography to Improve the Quality of Tuberculosis Diagnosis in Vietnam's District Health Facilities: An Implementation Study

In Vietnam, chest radiography (CXR) is used to refer people for GeneXpert (Xpert) testing to diagnose tuberculosis (TB), demonstrating high yield for TB but a wide range of CXR abnormality rates. In a multi-center implementation study, computer-aided detection (CAD) was integrated into facility-based TB case finding to standardize CXR interpretation. CAD integration was guided by a programmatic framework developed for routine implementation. From April through December 2022, 24,945 CXRs from TB-vulnerable populations presenting to district health facilities were evaluated. Physicians interpreted all CXRs in parallel with CAD (qXR 3.0) software, for which the selected TB threshold score was ≥0.60. At three months, there was 47.3% concordance between physician and CAD TB-presumptive CXR results, 7.8% of individuals who received CXRs were referred for Xpert testing, and 858 people diagnosed with Xpert-confirmed TB per 100,000 CXRs. This increased at nine months to 76.1% concordant physician and CAD TB-presumptive CXRs, 9.6% referred for Xpert testing, and 2112 people with Xpert-confirmed TB per 100,000 CXRs. Our programmatic CAD-CXR framework effectively supported physicians in district facilities to improve the quality of referral for diagnostic testing and increase TB detection yield. Concordance between physician and CAD CXR results improved with training and was important to optimize Xpert testing.

Benchmarking the diagnostic test accuracy of certified AI products for screening pulmonary tuberculosis in digital chest radiographs: Preliminary evidence from a rapid review and meta-analysis

BACKGROUND AND OBJECTIVE

The global market for AI systems used in lung tuberculosis (TB) detection has expanded significantly in recent years. Verifying their performance across diverse settings is crucial before medical organisations can invest in them and pursue safe, wide-scale deployment. The goal of this research was to synthesise the clinical evidence for the diagnostic accuracy of certified AI products designed for screening TB in chest X-rays (CXRs) compared to a microbiological reference standard.

METHODS

Four databases were searched between June to September 2022. Data concerning study methodology, system characteristics, and diagnostic accuracy metrics was extracted and summarised. Study bias was evaluated using QUADAS-2 and by examining sources of funding. Forest plots for diagnostic odds ratio (DOR) and summary receiver operating characteristic (SROC) curves were constructed for the AI products individually and collectively.

RESULTS

10 out of 3642 studies satisfied the review criteria however only 8 were subject to meta-analysis following bias assessment. Three AI products were evaluated with a 95 % confidence interval producing the following pooled estimates for accuracy rankings: qXR v2 (sensitivity of 0.944 [0.887-0.973], specificity of 0.692 [0.549-0.805], DOR of 3.63 [3.17-4.09], Lunit INSIGHT CXR v3.1 (sensitivity of 0.853 [0.787-0.901], specificity of 0.646 [0.627-0.665], DOR of 2.37 [1.96-2.78]), and CAD4TB v3.07 (sensitivity of 0.917 [0.848-0.956], specificity of 0.371 [0.336-0.408], DOR of 1.91 [1.4-2.47]). Overall, the products had a sensitivity of 0.903 (0.859-0.934), specificity of 0.526 (0.409-0.641), and DOR of 2.31 (1.78-2.84).

CONCLUSION

Current publicly available evidence indicates considerable variability in the diagnostic accuracy of available AI products although overall they have high sensitivity and modest specificity which is improving with time. These preliminary results are limited by the small number of studies and poor coverage for low TB burden settings. More research is needed to expand the clinical evidence base for the performance of AI products.

Assessment of non-tuberculosis abnormalities on digital chest x-rays with high CAD4TB scores from a tuberculosis prevalence survey in Zambia and South Africa

BACKGROUND

Chest X-rays (CXRs) have traditionally been used to aid the diagnosis of TB-suggestive abnormalities. Using Computer-Aided Detection (CAD) algorithms, TB risk is quantified to assist with diagnostics. However, CXRs capture all other structural abnormalities. Identification of non-TB abnormalities in individuals with CXRs that have high CAD scores but don't have bacteriologically confirmed TB is unknown. This presents a missed opportunity of extending novel CAD systems' potential to simultaneously provide information on other non-TB abnormalities alongside TB. This study aimed to characterize and estimate the prevalence of non-TB abnormalities on digital CXRs with high CAD4TB scores from a TB prevalence survey in Zambia and South Africa.

METHODOLOGY

This was a cross-sectional analysis of clinical data of participants from the TREATS TB prevalence survey conducted in 21 communities in Zambia and South Africa. The study included individuals aged ≥ 15 years who had high CAD4TB scores (score ≥ 70), but had no bacteriologically confirmed TB in any of the samples submitted, were not on TB treatment, and had no history of TB. Two consultant radiologists reviewed the images for non-TB abnormalities.

RESULTS

Of the 525 CXRs reviewed, 46.7% (245/525) images were reported to have non-TB abnormalities. About 11.43% (28/245) images had multiple non-TB abnormalities, while 88.67% (217/245) had a single non-TB abnormality. The readers had a fair inter-rater agreement (r = 0.40). Based on anatomical location, non-TB abnormalities in the lung parenchyma (19%) were the most prevalent, followed by Pleura (15.4%), then heart & great vessels (6.1%) abnormalities. Pleural effusion/thickening/calcification (8.8%) and cardiomegaly (5%) were the most prevalent non-TB abnormalities. Prevalence of (2.7%) for pneumonia not typical of pulmonary TB and (2.1%) mass/nodules (benign/ malignant) were also reported.

CONCLUSION

A wide range of non-TB abnormalities can be identified on digital CXRs among individuals with high CAD4TB scores but don't have bacteriologically confirmed TB. Adaptation of AI systems like CAD4TB as a tool to simultaneously identify other causes of abnormal CXRs alongside TB can be interesting and useful in non-faculty-based screening programs to better link cases to appropriate care.

Utilization of artificial intelligence for tuberculosis screening in Nepal

BACKGROUNDS

Tuberculosis (TB) is an infectious disease that needs to be diagnosed and enrolled for treatment. Artificial intelligence for TB (AI4TB) software screens TB suspected cases at the point of care and helps in quick diagnosis. This study aims to explore the significance and usefulness of AI4TB by comparing its performance with different diagnostic test results.

METHODS

A cross-sectional study was conducted among 197 participants who had symptoms suggestive to TB. The chest X-ray images were analyzed by AI4TB software and human expert readers. The bacteriological test results were obtained, and Kappa test was applied to calculate the inter-reader reliability. The sensitivity, specificity, positive predictive value and negative predictive value was calculated and ROC curve was generated.

RESULTS

Among 85 sputum smear microscopy, about 21% of the had sputum positivity rate. At 0.4 threshold: 62.4%, at 0.5 threshold: 58.4% and at 0.6 threshold: 50.3% symptoms suggestive cases were identified having abnormal X-ray images. Reader-I identified 28.4% and Reader-II identified 37.1% of the symptoms suggestive cases of TB as positive cases. There was a significant substantial agreement between two human expert readers (k-0.783, p-value: <0.001). The ROC curve explored the fair sensitivity accuracy of the AI4TB test results at 0.5 threshold level (AUC = 0.72) and at 0.6 threshold level (AUC = 0.77).

CONCLUSION

The sensitivity of the AI4TB was higher compared to different human readers. AI4TB can be the relevant screening tool for the TB symptoms suggestive cases prior to the laboratory test in the countries like Nepal with deficient health manpower.

Diagnostic Accuracy of the Artificial Intelligence Methods in Medical Imaging for Pulmonary Tuberculosis: A Systematic Review and Meta-Analysis

Tuberculosis (TB) remains one of the leading causes of death among infectious diseases worldwide. Early screening and diagnosis of pulmonary tuberculosis (PTB) is crucial in TB control, and tend to benefit from artificial intelligence. Here, we aimed to evaluate the diagnostic efficacy of a variety of artificial intelligence methods in medical imaging for PTB. We searched MEDLINE and Embase with the OVID platform to identify trials published update to November 2022 that evaluated the effectiveness of artificial-intelligence-based software in medical imaging of patients with PTB. After data extraction, the quality of studies was assessed using quality assessment of diagnostic accuracy studies 2 (QUADAS-2). Pooled sensitivity and specificity were estimated using a bivariate random-effects model. In total, 3987 references were initially identified and 61 studies were finally included, covering a wide range of 124,959 individuals. The pooled sensitivity and the specificity were 91% (95% confidence interval (CI), 89-93%) and 65% (54-75%), respectively, in clinical trials, and 94% (89-96%) and 95% (91-97%), respectively, in model-development studies. These findings have demonstrated that artificial-intelligence-based software could serve as an accurate tool to diagnose PTB in medical imaging. However, standardized reporting guidance regarding AI-specific trials and multicenter clinical trials is urgently needed to truly transform this cutting-edge technology into clinical practice.

Clinical and radiographic characteristics of presumptive tuberculosis patients previously treated for tuberculosis in Zambia

Background

Persistent respiratory symptoms and radiographic abnormalities are common among individuals previously treated for tuberculosis (TB) and may contribute to misdiagnosis and incorrect treatment when they seek care. We sought to determine if clinical and radiographic characteristics differed among previously treated, presumptive TB patients according to their current TB disease status.

Methods

Adults (>18 years of age) seeking care at a public health facility in Lusaka, Zambia were systematically evaluated for active TB using symptom screening and chest X-ray. All patients with presumptive TB submitted a sputum sample for microbiological TB testing. Patients who reported a prior history of TB treatment were included in the present analysis. ‘Confirmed TB’ was defined by the detection of TB using Xpert Ultra and/or liquid culture, while ‘possible TB’ was defined by the receipt of TB treatment without a positive Xpert Ultra or culture result. We evaluated the positive predictive value (PPV) of clinical symptoms and radiographic features for active TB alone and in combination.

Results

Of 740 presumptive TB patients, 144 (19%) had been previously treated for active TB. Of these, 19 (13%) patients had confirmed TB, 14 (10%) had possible TB, and 111 (77%) had no pulmonary TB. Overall, 119 (83%) patients had ≥1 current respiratory symptom—this did not differ according to current TB disease classification (95%, 93%, 79%; p = 0.23). Sixty-one patients (56%) had radiographic abnormalities suggestive of active TB and such findings were more common among patients with confirmed or possible TB compared to those without TB (93%, 71%, vs. 47%; p = 0.002). Most patients (n = 91, 83%) had at least one radiographic abnormality—no difference by current TB classification was observed (93%, 100%, 79%; p = 0.08). The PPV of any current respiratory symptom, active TB radiographic finding, or any radiographic abnormality for TB was 13% (95%CI: 7–21%), 21% (95%CI: 12–34) and 14% (95%CI: 9–23), respectively; combining clinical and radiographic characteristics did not significantly improve the PPV for active TB.

Conclusions

Among presumptive TB patients previously treated for TB, respiratory symptoms and radiographic abnormalities were common and poorly differentiated those with current active TB from those without current active TB. Reliance on clinical and radiographic characteristics alone in this patient population may result in substantial overtreatment and therefore, microbiological investigations should be used to inform TB treatment decisions whenever possible.

Accuracy of computer-aided chest X-ray in community-based tuberculosis screening: Lessons from the 2016 Kenya National Tuberculosis Prevalence Survey

Community-based screening for tuberculosis (TB) could improve detection but is resource intensive. We set out to evaluate the accuracy of computer-aided TB screening using digital chest X-ray (CXR) to determine if this approach met target product profiles (TPP) for community-based screening. CXR images from participants in the 2016 Kenya National TB Prevalence Survey were evaluated using CAD4TBv6 (Delft Imaging), giving a probabilistic score for pulmonary TB ranging from 0 (low probability) to 99 (high probability). We constructed a Bayesian latent class model to estimate the accuracy of CAD4TBv6 screening compared to bacteriologically-confirmed TB across CAD4TBv6 threshold cut-offs, incorporating data on Clinical Officer CXR interpretation, participant demographics (age, sex, TB symptoms, previous TB history), and sputum results. We compared model-estimated sensitivity and specificity of CAD4TBv6 to optimum and minimum TPPs. Of 63,050 prevalence survey participants, 61,848 (98%) had analysable CXR images, and 8,966 (14.5%) underwent sputum bacteriological testing; 298 had bacteriologically-confirmed pulmonary TB. Median CAD4TBv6 scores for participants with bacteriologically-confirmed TB were significantly higher (72, IQR: 58-82.75) compared to participants with bacteriologically-negative sputum results (49, IQR: 44-57, p<0.0001). CAD4TBv6 met the optimum TPP; with the threshold set to achieve a mean sensitivity of 95% (optimum TPP), specificity was 83.3%, (95% credible interval [CrI]: 83.0%-83.7%, CAD4TBv6 threshold: 55). There was considerable variation in accuracy by participant characteristics, with older individuals and those with previous TB having lowest specificity. CAD4TBv6 met the optimal TPP for TB community screening. To optimise screening accuracy and efficiency of confirmatory sputum testing, we recommend that an adaptive approach to threshold setting is adopted based on participant characteristics.

Diagnostic accuracy of computer aided reading of chest x-ray in screening for pulmonary tuberculosis in comparison with Gene-Xpert

Background & Objectives:

Pakistan ranked fifth amongst 22 high-burden Tuberculosis countries, and it is an epidemic in Pakistan, hence screening is performed nationally, as part of the ambitious ZERO TB drive. Our objective was to assess the diagnostic accuracy of Computer Aided Detection (CAD4TB) software on chest Xray in screening for pulmonary tuberculosis in comparison with gene-Xpert.

Methods:

The study was conducted by Radiology Department Lady Reading Hospital Peshawar in affiliation with Indus Hospital network over a period of one year. Screening was done by using mobile Xray unit equipped with CAD4TB software with scoring system. All of those having score of more than 70 and few selected cases with strong clinical suspicion but score of less than 70 were referred to dedicated TB clinic for Gene-Xpert analysis.

Results:

Among 26,997 individuals screened, 2617 (9.7%) individuals were found presumptive for pulmonary TB. Sputum samples for Gene-Xpert were obtained in 2100 (80.24%) individuals, out of which 1825 (86.9%) were presumptive for pulmonary TB on CAD4TB only. Gene-Xpert was positive in 159 (8.7%) patients and negative in 1,666(91.3%). Sensitivity and specificity of CAD4TB and symptomatology with threshold score of ≥70 was 83.2% and 12.7% respectively keeping Gene-Xpert as gold standard.

Conclusion:

Combination of chest X-ray analysis by CAD4TB and symptomatology is of immense value to screen a large population at risk in a developing high burden country. It is significantly a more effective tool for screening and early diagnosis of TB in individuals, who would otherwise go undiagnosed.

Triage of Persons With Tuberculosis Symptoms Using Artificial Intelligence-Based Chest Radiograph Interpretation: A Cost-Effectiveness Analysis

BACKGROUND

In settings without access to rapid expert radiographic interpretation, artificial intelligence (AI)-based chest radiograph (CXR) analysis can triage persons presenting with possible tuberculosis (TB) symptoms, to identify those who require additional microbiological testing. However, there is limited evidence of the cost-effectiveness of this technology as a triage tool.

METHODS

A decision analysis model was developed to evaluate the cost-effectiveness of triage strategies with AI-based CXR analysis for patients presenting with symptoms suggestive of pulmonary TB in Karachi, Pakistan. These strategies were compared to the current standard of care using microbiological testing with smear microscopy or GeneXpert, without prior triage. Positive triage CXRs were considered to improve referral success for microbiologic testing, from 91% to 100% for eligible persons. Software diagnostic accuracy was based on a prospective field study in Karachi. Other inputs were obtained from the Pakistan TB Program. The analysis was conducted from the healthcare provider perspective, and costs were expressed in 2020 US dollars.

RESULTS

Compared to upfront smear microscopy for all persons with presumptive TB, triage strategies with AI-based CXR analysis were projected to lower costs by 19%, from $23233 per 1000 persons, and avert 3%-4% disability-adjusted life-years (DALYs), from 372 DALYs. Compared to upfront GeneXpert, AI-based triage strategies lowered projected costs by 37%, from $34346 and averted 4% additional DALYs, from 369 DALYs. Reinforced follow-up for persons with positive triage CXRs but negative microbiologic tests was particularly cost-effective.

CONCLUSIONS

In lower-resource settings, the addition of AI-based CXR triage before microbiologic testing for persons with possible TB symptoms can reduce costs, avert additional DALYs, and improve TB detection.

Chest X-ray analysis with deep learning-based software as a triage test for pulmonary tuberculosis: an individual patient data meta-analysis of diagnostic accuracy

BACKGROUND

Automated radiologic analysis using computer-aided detection software (CAD) could facilitate chest X-ray (CXR) use in tuberculosis diagnosis. There is little to no evidence on the accuracy of commercially-available deep learning-based CAD in different populations, including patients with smear-negative tuberculosis and people living with HIV (PLWH).

METHODS

We collected CXRs and individual patient data (IPD) from studies evaluating CAD in patients self-referring for tuberculosis symptoms with culture or nucleic acid amplification testing as the reference. We re-analyzed CXRs with three CAD (CAD4TB version (v) 6, Lunit v3.1.0.0, and qXR v2). We estimated sensitivity and specificity within each study and pooled using IPD meta-analysis. We used multivariable meta-regression to identify characteristics modifying accuracy.

RESULTS

We included CXRs and IPD of 3727/3967 participants from 4/7 eligible studies. 17% (621/3727) were PLWH. 17% (645/3727) had microbiologically-confirmed tuberculosis. Despite using the same threshold score for classifying CXR in every study, sensitivity and specificity varied from study to study. The software had similar unadjusted accuracy (at 90% pooled sensitivity, pooled specificities were: CAD4TBv6, 56.9% [95%CI:51.7-61.9]; Lunit, 54.1% [44.6-63.3]; qXRv2, 60.5% [51.7-68.6]). Adjusted absolute differences in pooled sensitivity between PLWH and HIV-uninfected participants was: CAD4TBv6, -13.4% [-21.1, -6.9]; Lunit, +2.2% [-3.6, +6.3]; qXRv2: -13.4% [-21.5, -6.6]); between smear-negative and smear-positive tuberculosis was: CAD4TBv6, -12.3% [-19.5, -6.1]; Lunit, -17.2% [-24.6, -10.5]; qXRv2, -16.6% [-24.4, -9.9]. Accuracy was similar to human readers.

CONCLUSIONS

For CAD CXR analysis to be implemented as a high-sensitivity tuberculosis rule-out test, users will need threshold scores identified from their own patient populations, and stratified by HIV- and smear-status.

ESAT-6 and Ag85A Synthetic Peptides as Candidates for an Immunodiagnostic Test in Children with a Clinical Suspicion of Tuberculosis

Background

Tuberculosis (TB) is being underdetected in children as most are smear-negative. This work was aimed at evaluating ESAT-6 and Ag85A synthetic peptides' serodiagnostic potential for diagnosing children having a clinical suspicion of TB.

Methods

The study involved 438 children: 77 Creole nonindigenous (13 suspected of having TB and 64 healthy ones) and 361 Warao indigenous children (39 suspected of TB and 322 healthy children). The approach's diagnostic information was compared using operational characteristics and receiver-operating characteristic (ROC) curves.

Results

Ag85A P-29879 had 94.6% sensitivity (AUC = 0.741: 0.651 to 0.819 95% CI) in indigenous children. ESAT-6 P-12036 and P-12037 had 100% and 92.3% of sensitivity (AUC = 0.929: 0.929: 0.846 to 0.975 95% CI and 0.791: 63.9 to 98.7 95% CI, respectively) in Creole children. ESAT-6 peptides also allowed a differentiation between children with TB and healthy ones.

Conclusions

Further validation of this approach could lead to developing a complementary tool for rapid TB diagnosis in children.

Computer-aided interpretation of chest radiography reveals the spectrum of tuberculosis in rural South Africa

Computer-aided digital chest radiograph interpretation (CAD) can facilitate high-throughput screening for tuberculosis (TB), but its use in population-based active case-finding programs has been limited. In an HIV-endemic area in rural South Africa, we used a CAD algorithm (CAD4TBv5) to interpret digital chest x-rays (CXR) as part of a mobile health screening effort. Participants with TB symptoms or CAD4TBv5 score above the triaging threshold were referred for microbiological sputum assessment. During an initial pilot phase, a low CAD4TBv5 triaging threshold of 25 was selected to maximize TB case finding. We report the performance of CAD4TBv5 in screening 9,914 participants, 99 (1.0%) of whom were found to have microbiologically proven TB. CAD4TBv5 was able to identify TB cases at the same sensitivity but lower specificity as a blinded radiologist, whereas the next generation of the algorithm (CAD4TBv6) achieved comparable sensitivity and specificity to the radiologist. The CXRs of people with microbiologically confirmed TB spanned a range of lung field abnormality, including 19 (19.2%) cases deemed normal by the radiologist. HIV serostatus did not impact CAD4TB's performance. Notably, 78.8% of the TB cases identified during this population-based survey were asymptomatic and therefore triaged for sputum collection on the basis of CAD4TBv5 score alone. While CAD4TBv6 has the potential to replace radiologists for triaging CXRs in TB prevalence surveys, population-specific piloting is necessary to set the appropriate triaging thresholds. Further work on image analysis strategies is needed to identify radiologically subtle active TB.

A new resource on artificial intelligence powered computer automated detection software products for tuberculosis programmes and implementers

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, TB programmes need to consider not only the diagnostic accuracy but also implementation-relevant features including operational characteristics, deployment mechanism, input and machine compatibility, output format, options for integration into the legacy system, costs, data sharing and privacy aspects, and certification. A landscaping analysis was conducted to collect this information among CAD developers known to have or soon to have a TB product. The responses were reviewed and finalized with the developers, and are published on an open-access website: www.ai4hlth.org. CAD products are constantly being improved and the site will continuously be updated to account for updates and new products. This unique online resource aims to inform the TB community about available CAD tools, their features and set-up procedures, to enable TB programmes to identify the most suitable product to incorporate in interventions.

An Evaluation of Programmatic Community-Based Chest X-ray Screening for Tuberculosis in Ho Chi Minh City, Vietnam

Across Asia, a large proportion of people with tuberculosis (TB) do not report symptoms, have mild symptoms or only experience symptoms for a short duration. These individuals may not seek care at health facilities or may be missed by symptom screening, resulting in sustained TB transmission in the community. We evaluated the yields of TB from 114 days of community-based, mobile chest X-ray (CXR) screening. The yields at each step of the TB screening cascade were tabulated and we compared cohorts of participants who reported having a prolonged cough and those reporting no cough or one of short duration. We estimated the marginal yields of TB using different diagnostic algorithms and calculated the relative diagnostic costs and cost per case for each algorithm. A total of 34,529 participants were screened by CXR, detecting 256 people with Xpert-positive TB. Only 50% of those diagnosed with TB were detected among participants reporting a prolonged cough. The study’s screening algorithm detected almost 4 times as much TB as the National TB Program’s standard diagnostic algorithm. Community-based, mobile chest X-ray screening can be a high yielding strategy which is able to identify people with TB who would likely otherwise have been missed by existing health services.

The TB REACH Initiative: Supporting TB Elimination Efforts in the Asia-Pacific

After many years of TB 'control' and incremental progress, the TB community is talking about ending the disease, yet this will only be possible with a shift in the way we approach the TB response. While the Asia-Pacific region has the highest TB burden worldwide, it also has the opportunity to lead the quest to end TB by embracing the four areas laid out in this series: using data to target hotspots, initiating active case finding, provisioning preventive TB treatment, and employing a biosocial approach. The Stop TB Partnership's TB REACH initiative provides a platform to support partners in the development, evaluation and scale-up of new and innovative technologies and approaches to advance TB programs. We present several approaches TB REACH is taking to support its partners in the Asia-Pacific and globally to advance our collective response to end TB.

CheXaid: deep learning assistance for physician diagnosis of tuberculosis using chest x-rays in patients with HIV

Tuberculosis (TB) is the leading cause of preventable death in HIV-positive patients, and yet often remains undiagnosed and untreated. Chest x-ray is often used to assist in diagnosis, yet this presents additional challenges due to atypical radiographic presentation and radiologist shortages in regions where co-infection is most common. We developed a deep learning algorithm to diagnose TB using clinical information and chest x-ray images from 677 HIV-positive patients with suspected TB from two hospitals in South Africa. We then sought to determine whether the algorithm could assist clinicians in the diagnosis of TB in HIV-positive patients as a web-based diagnostic assistant. Use of the algorithm resulted in a modest but statistically significant improvement in clinician accuracy (p = 0.002), increasing the mean clinician accuracy from 0.60 (95% CI 0.57, 0.63) without assistance to 0.65 (95% CI 0.60, 0.70) with assistance. However, the accuracy of assisted clinicians was significantly lower (p < 0.001) than that of the stand-alone algorithm, which had an accuracy of 0.79 (95% CI 0.77, 0.82) on the same unseen test cases. These results suggest that deep learning assistance may improve clinician accuracy in TB diagnosis using chest x-rays, which would be valuable in settings with a high burden of HIV/TB co-infection. Moreover, the high accuracy of the stand-alone algorithm suggests a potential value particularly in settings with a scarcity of radiological expertise.

Analysis and predication of tuberculosis registration rates in Henan Province, China: an exponential smoothing model study

Background

The World Health Organization End TB Strategy meant that compared with 2015 baseline, the reduction in pulmonary tuberculosis (PTB) incidence should be 20 and 50% in 2020 and 2025, respectively. The case number of PTB in China accounted for 9% of the global total in 2018, which ranked the second high in the world. From 2007 to 2019, 854 672 active PTB cases were registered and treated in Henan Province, China. This study was to assess whether the WHO milestones could be achieved in Henan Province.

Methods

The active PTB numbers in Henan Province from 2007 to 2019, registered in Chinese Tuberculosis Information Management System were analyzed to predict the active PTB registration rates in 2020 and 2025, which is conductive to early response measures to ensure the achievement of the WHO milestones. The time series model was created by monthly active PTB registration rates from 2007 to 2016, and the optimal model was verified by data from 2017 to 2019. The Ljung-Box Q statistic was used to evaluate the model. The statistically significant level is α = 0.05. Monthly active PTB registration rates and 95% confidence interval (CI) from 2020 to 2025 were predicted.

Results

High active PTB registration rates in March, April, May and June showed the seasonal variations. The exponential smoothing winter’s multiplication model was selected as the best-fitting model. The predicted values were approximately consistent with the observed ones from 2017 to 2019. The annual active PTB registration rates were predicted as 49.1 (95% CI: 36.2–62.0) per 100 000 population and 34.4 (95% CI: 18.6–50.2) per 100 000 population in 2020 and 2025, respectively. Compared with the active PTB registration rate in 2015, the reduction will reach 23.7% (95% CI, 3.2–44.1%) and 46.8% (95% CI, 21.4–72.1%) in 2020 and 2025, respectively.

Conclusions

The high active PTB registration rates in spring and early summer indicate that high risk of tuberculosis infection in late autumn and winter in Henan Province. Without regard to the CI, the first milestone of WHO End TB Strategy in 2020 will be achieved. However, the second milestone in 2025 will not be easily achieved unless there are early response measures in Henan Province, China.

Deep learning for automated classification of tuberculosis-related chest X-Ray: dataset distribution shift limits diagnostic performance generalizability

Background

Machine learning has been an emerging tool for various aspects of infectious diseases including tuberculosis surveillance and detection. However, the World Health Organization (WHO) provided no recommendations on using computer-aided tuberculosis detection software because of a small number of studies, methodological limitations, and limited generalizability of the findings.

Methods

To quantify the generalizability of the machine-learning model, we developed a Deep Convolutional Neural Network (DCNN) model using a Tuberculosis (TB)-specific chest x-ray (CXR) dataset of one population (National Library of Medicine Shenzhen No.3 Hospital) and tested it with non-TB-specific CXR dataset of another population (National Institute of Health Clinical Centers).

Results

In the training and intramural test sets using the Shenzhen hospital database, the DCCN model exhibited an AUC of 0.9845 and 0.8502 for detecting TB, respectively. However, the AUC of the supervised DCNN model in the ChestX-ray8 dataset was dramatically dropped to 0.7054. Using the cut points at 0.90, which suggested 72% sensitivity and 82% specificity in the Shenzhen dataset, the final DCNN model estimated that 36.51% of abnormal radiographs in the ChestX-ray8 dataset were related to TB.

Conclusion

A supervised deep learning model developed by using the training dataset from one population may not have the same diagnostic performance in another population. Conclusion: Technical specification of CXR images, disease severity distribution, dataset distribution shift, and overdiagnosis should be examined before implementation in other settings.

Evaluation of computer aided detection of tuberculosis on chest radiography among people with diabetes in Karachi Pakistan

Pakistan ranks fifth among high tuberculosis (TB) burden countries and also has seventh highest burden for diabetes mellitus (DM). DM increases the risk of developing TB and contributes to adverse TB treatment outcomes hence screening and integrated management for both diseases in high burden countries is suggested. Computer-Aided Detection for TB (CAD4TB) can potentially be used as triage tool in low resource settings to pre-screen individuals for Xpert MTB/RIF testing. The aim of this study was to evaluate the diagnostic accuracy and performance of CAD4TB software in people with diabetes (PWD) enrolled in a TB screening program in Karachi, Pakistan. A total of 694 individuals with a diagnosis of DM (of whom 31.1% were newly diagnosed) were screened with CAD4TB and simultaneously provided sputum for Xpert MTB/RIF testing. Of the 74 (10.7%) participants who had bacteriologically positive (MTB+) results on Xpert testing, 54 (73%) had a CAD4TB score >70; and 155 (25%) participants who tested MTB-negative had scores >70. The area under the receiver operator curve was 0.78 (95% CI: 0.77-0.80). Our study findings indicate that CAD4TB offers good diagnostic accuracy as a triage test for TB screening among PWD using Xpert MTB/RIF as the reference standard.

Computer-aided diagnosis for World Health Organization-defined chest radiograph primary-endpoint pneumonia in children

BACKGROUND

The chest radiograph is the most common imaging modality to assess childhood pneumonia. It has been used in epidemiological and vaccine efficacy/effectiveness studies on childhood pneumonia.

OBJECTIVE

To develop computer-aided diagnosis (CAD4Kids) for chest radiography in children and to evaluate its accuracy in identifying World Health Organization (WHO)-defined chest radiograph primary-endpoint pneumonia compared to a consensus interpretation.

MATERIALS AND METHODS

Chest radiographs were independently evaluated by three radiologists based on WHO criteria. Automatic lung field segmentation was followed by manual inspection and correction, training, feature extraction and classification. Radiographs were filtered with Gaussian derivatives on multiple scales, extracting texture features to classify each pixel in the lung region. To obtain an image score, the 95^th percentile score of the pixels was used. Training and testing were done in 10-fold cross validation.

RESULTS

The radiologist majority consensus reading of 858 interpretable chest radiographs included 333 (39%) categorised as primary-endpoint pneumonia, 208 (24%) as other infiltrate only and 317 (37%) as no primary-endpoint pneumonia or other infiltrate. Compared to the reference radiologist consensus reading, CAD4Kids had an area under the receiver operator characteristic (ROC) curve of 0.850 (95% confidence interval [CI] 0.823-0.876), with a sensitivity of 76% and specificity of 80% for identifying primary-endpoint pneumonia on chest radiograph. Furthermore, the ROC curve was 0.810 (95% CI 0.772-0.846) for CAD4Kids identifying primary-endpoint pneumonia compared to other infiltrate only.

CONCLUSION

Further development of the CAD4Kids software and validation in multicentre studies are important for future research on computer-aided diagnosis and artificial intelligence in paediatric radiology.

Early chest X-ray in persons with presumptive tuberculosis increases Xpert® MTB/RIF diagnostic yield and efficiency

Adult presumptive tuberculosis (TB) patients (n = 1690) were screened for TB using a questionnaire, chest X-ray (CXR) and sputum microscopy for acid-fast bacilli (AFB); Mycobacterium tuberculosis culture was performed for 74% of the patients and Xpert^® MTB/RIF was done for 17.2%. Among patients recruited, 943 (55.8%) were diagnosed with TB, of whom 870 (92.3%) were bacteriologically confirmed and 73 (7.7%) were clinically diagnosed on the basis of CXR. Using CXR prior to culture or Xpert testing reduces the number needed to screen from 7.6 to 5.0. Using CXR to triage for culture or Xpert testing reduces the number of missed cases and increases the efficiency of culture and Xpert testing.

Prevalence and risk factors of tuberculosis disease in South African correctional facilities in 2015

SETTING: Sixteen South African correctional facilities.OBJECTIVE: To determine the prevalence of and risk factors for tuberculosis (TB) in South African correctional facilities using data collected during a TB screening program in South African correctional facilities in 2015.DESIGN: Inmates in 16 South African correctional facilities were screened for TB from January to December 2015. Inmates reporting ≥1 TB symptom or having an abnormal computer-assisted digital chest X-ray (CXR) provided sputum. Abnormal CXRs were interpreted by a radiologist. Sputum was tested for Mycobacterium tuberculosis using Xpert® MTB/RIF. Data from 16 South African correctional facilities were used in regression analysis, and prevalence estimates calculated for 12 South African correctional facilities with >30% screening coverage.RESULTS: In 12 South African correctional facilities included in the prevalence estimates, 837 inmates had TB disease (2653/100 000) as indicated by current TB treatment or screening-identified TB by radiologist or Xpert. Previous TB was associated with increased odds of screening-identified TB in HIV-positive inmates (OR 4.3, 95%CI 2.5-7.3). For HIV-negative inmates, previous TB (adjusted OR [aOR] 4.9, 95%CI 1.7-14.1) and self-reported symptoms vs. none (1 symptom, aOR 8.8, 95%CI 1.2-67.7; >2 symptoms, aOR 21.7, 95%CI 3.0-158.8) were independently associated with increased odds of screening-identified TB.CONCLUSIONS: Routine TB screening, including CXR, is needed in South African correctional facilities to identify and refer inmates with active TB.

Using artificial intelligence to read chest radiographs for tuberculosis detection: A multi-site evaluation of the diagnostic accuracy of three deep learning systems

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 by two groups of radiologists and the DL systems. Xpert was used as the reference standard. The area under the curve of the three systems was similar: Lunit (0.94, 95% CI: 0.93-0.96), qXR (0.94, 95% CI: 0.92-0.97) and CAD4TB (0.92, 95% CI: 0.90-0.95). When matching the sensitivity of the radiologists, the specificities of the DL systems were significantly higher except for one. Using DL systems to read CXRs could reduce the number of Xpert MTB/RIF tests needed by 66% while maintaining sensitivity at 95% or better. Using a universal cutoff score resulted different performance in each site, highlighting the need to select scores based on the population screened. These DL systems should be considered by TB programs where human resources are constrained, and automated technology is available.

A systematic review of the diagnostic accuracy of artificial intelligence-based computer programs to analyze chest x-rays for pulmonary tuberculosis

We undertook a systematic review of the diagnostic accuracy of artificial intelligence-based software for identification of radiologic abnormalities (computer-aided detection, or CAD) compatible with pulmonary tuberculosis on chest x-rays (CXRs). We searched four databases for articles published between January 2005-February 2019. We summarized data on CAD type, study design, and diagnostic accuracy. We assessed risk of bias with QUADAS-2. We included 53 of the 4712 articles reviewed: 40 focused on CAD design methods (“Development” studies) and 13 focused on evaluation of CAD (“Clinical” studies). Meta-analyses were not performed due to methodological differences. Development studies were more likely to use CXR databases with greater potential for bias as compared to Clinical studies. Areas under the receiver operating characteristic curve (median AUC [IQR]) were significantly higher: in Development studies AUC: 0.88 [0.82–0.90]) versus Clinical studies (0.75 [0.66–0.87]; p-value 0.004); and with deep-learning (0.91 [0.88–0.99]) versus machine-learning (0.82 [0.75–0.89]; p = 0.001). We conclude that CAD programs are promising, but the majority of work thus far has been on development rather than clinical evaluation. We provide concrete suggestions on what study design elements should be improved.

Prostate cancer detection from multi-institution multiparametric MRIs using deep convolutional neural networks

Multiparametric magnetic resonance imaging (mpMRI) of the prostate aids in early diagnosis of prostate cancer, but is difficult to interpret and subject to interreader variability. Our objective is to generate probability maps, overlaid on original mpMRI images to help radiologists identify where a cancer is suspected as a computer-aided diagnostic (CAD). We optimized the holistically nested edge detection (HED) deep convolutional neural network. Our dataset contains T2, apparent diffusion coefficient, and high b -value images from 186 patients across six institutions worldwide: 92 with an endorectal coil (ERC) and 94 without. Ground-truth was based on tumor segmentations manually drawn by expert radiologists based on histologic evidence of cancer. The training set consisted of 120 patients and the validation set and test set included 19 and 47, respectively. Slice-level probability maps are evaluated at the lesion level of analysis. The best model: HED using 5 × 5 convolutional kernels, batch normalization, and optimized using Adam. This CAD performed significantly better ( p < 0.001 ) in the peripheral zone ( AUC = 0.94 ± 0.01 ) than the transition zone. It outperforms a previous CAD from our group in a head-to-head comparison on the same ERC-only test cases ( AUC = 0.97 ± 0.01 ; p < 0.001 ). Our CAD establishes a state-of-the-art performance for predicting prostate cancer lesions on mpMRIs.

Coordinating the prevention, treatment, and care continuum for HIV-associated tuberculosis in prisons: a health systems strengthening approach

PURPOSE OF REVIEW

To advance a re-conceptualized prevention, treatment, and care continuum (PTCC) for HIV-associated tuberculosis (TB) in prisons, and to make recommendations for strengthening prison health systems and reducing HIV-associated TB morbidity and mortality throughout the cycle of pretrial detention, incarceration, and release.

RECENT FINDINGS

Despite evidence of increased HIV-associated TB burden in prisons compared to the general population, prisoners face entrenched barriers to accessing anti-TB therapy, antiretroviral therapy, and evidence-based HIV and TB prevention. New approaches, suitable for the complexities of healthcare delivery in prisons, have emerged that may address these barriers, and include: novel TB diagnostics, universal test and treat for HIV, medication-assisted treatment for opioid dependence, comprehensive transitional case management, and peer navigation, among others.

SUMMARY

Realizing ambitious international HIV and TB targets in prisons will only be possible by first addressing the root causes of the TB/HIV syndemic, which are deeply intertwined with human rights violations and weaknesses in prison health systems, and, second, fundamentally re-organizing HIV and TB services around a coordinated PTCC. Taking these steps can help ensure universal access to comprehensive, good-quality, free and voluntary TB/HIV prevention, treatment, and care, and advance efforts to strengthen health resourcing, staffing, information management, and primary care access within prisons.

Nationwide surveillance algorithms for tuberculosis among immigrant workers from highly endemic countries following pre-entry screening in Taiwan

Background

This cross-sectional study was retrospectively performed to assess the trend of tuberculosis (TB) among Taiwan’s immigrant workers from highly TB-endemic countries under an intervention of conducting a 4-round follow-up (at 0–3 days and 6, 18, and 30 months post-migration) screening program with initial chest X-ray (CXR) following an overseas, pre-entry normal CXR.

Methods

The immigrant workers with TB disease enrolled in the Taiwan TB registry database in 2011–2014 were analyzed and linked to an immigrant worker physical exam database to stratify TB case categories of actively screened or not for comparison.

Results

Following pre-entry screening for the admission of CXR-normal immigrant workers from highly endemic countries, the overall TB incidence of 70.6–128.6/100,000 person-years resulted either from a subsequent series of 4-round post-entry active screenings or misalliance algorithms, including passive diagnostics for the illness. Overall, the TB relative risk based on incidence in the immigrant working population was 2.2- to 5.5-fold greater than that among corresponding age Taiwanese, with 14.3% (15.5/100,000 person-years) sputum-smear-positive pulmonary TB (SS+ PTB), 74.2% (80.8/100,000 person-years) sputum-smear-negative (SS-) PTB, and 7.8% (8.5/100,000 person-years) only extra-pulmonary TB (EPTB). Regarding the clinical characteristics, 55.5% TB cases – identified through passive illness diagnostics vs. 44.5% TB cases actively identified through mandatory screenings, were higher in SS+ PTB (adjusted odds Ratio (aOR): 1.5, 95% CI: 1.1–2.0, P = 0.008), higher in SC+ PTB (aOR: 1.4, 95% CI: 1.1–1.7, P = 0.004), higher in concurrent extra-pulmonary TB (aOR: 8.9, CI: 4.5–7.4, P < 0.001), and higher in normal CXR TB (aOR: > 100, CI: 0- > 100, P = 0.908). The TB yields of 3rd- to 4th-round screenings were higher than those of 1st- and 2nd-round screenings and ranged from 52.6–65.3 cases per 100,000 screenings in 2013–2014.

Conclusions

The multiple post-entry TB screenings with initial CXR for high-risk immigrants could actively reduce TB transmission by finding SS- TB cases at early stages. The TB yields at post-entry 3rd- to 4th-round screenings might imply a persistent reactivation of latent TB. Adding more sensitive, economical screenings and preventive treatments for latent TB infection is a comprehensive approach for accelerating TB elimination.

Evaluation of the diagnostic accuracy of Computer-Aided Detection of tuberculosis on Chest radiography among private sector patients in Pakistan

The introduction of digital CXR with automated computer-aided interpretation, has given impetus to the role of CXR in TB screening, particularly in low resource, high-burden settings. The aim of this study was to evaluate the diagnostic accuracy of CAD4TB as a screening tool, implemented in the private sector in Karachi, Pakistan. This study analyzed retrospective data from CAD4TB and Xpert MTB/RIF testing carried out at two private TB treatment and diagnostic centers in Karachi. Sensitivity, specificity, potential Xperts saved, were computed and the receiver operator characteristic curves were constructed for four different models of CAD4TB. A total of 6,845 individuals with presumptive TB were enrolled in the study, 15.2% of which had MTB + ve result on Xpert. A high sensitivity (range 65.8-97.3%) and NPV (range 93.1-98.4%) were recorded for CAD4TB. The Area under the ROC curve (AUC) for CAD4TB was 0.79. CAD4TB with patient demographics (age and gender) gave an AUC of 0.83. CAD4TB offered high diagnostic accuracy. In low resource settings, CAD4TB, as a triage tool could minimize use of Xpert. Using CAD4TB in combination with age and gender data enhanced the performance of the software. Variations in demographic information generate different individual risk probabilities for the same CAD4TB scores.

Screening for tuberculosis in migrants and visitors from high-incidence settings: present and future perspectives

In most settings with a low incidence of tuberculosis (TB), foreign-born people make up the majority of TB cases, but the distribution of the TB risk among different migrant populations is often poorly quantified. In addition, screening practices for TB disease and latent TB infection (LTBI) vary widely. Addressing the risk of TB in international migrants is an essential component of TB prevention and care efforts in low-incidence countries, and strategies to systematically screen for, diagnose, treat and prevent TB among this group contribute to national and global TB elimination goals.This review provides an overview and critical assessment of TB screening practices that are focused on migrants and visitors from high to low TB incidence countries, including pre-migration screening and post-migration follow-up of those deemed to be at an increased risk of developing TB. We focus mainly on migrants who enter the destination country via application for a long-stay visa, as well as asylum seekers and refugees, but briefly consider issues related to short-term visitors and those with long-duration multiple-entry visas. Issues related to the screening of children and screening for LTBI are also explored.

Empiric tuberculosis treatment in South African primary health care facilities - for whom, where, when and why: Implications for the development of tuberculosis diagnostic tests

Background

The extent and circumstances under which empiric tuberculosis (TB) treatment (treatment without microbiological confirmation at treatment initiation) is administered in primary health care settings in South Africa are not well described.

Methods

We used data from a pragmatic evaluation of Xpert MTB/RIF in which persons undergoing TB investigations by PHC nurses were followed for six months. Following Xpert or smear-microscopy at enrolment, investigations for tuberculosis were undertaken at the discretion of health care workers. We identified persons whose TB treatment was initiated empirically (no microbiological confirmation at time of treatment initiation at a primary health care facility) and describe pathways to treatment initiation.

Results

Of 4665 evaluable participants, 541 persons were initiated on treatment of whom 167 (31%) had negative sputum tests at enrolment. Amongst these 167, the median number of participant visits to health care providers prior to treatment initiation was 3 (interquartile range [IQR] 2–4). Chest radiography, sputum culture or hospital referral was done in 106/167 (63%). Reasons for TB treatment start were: 1) empiric (n = 82, 49%); 2) a positive laboratory test (n = 49, 29%); 3) referral and treatment start at a higher level of care (n = 28, 17%); and 4) indeterminable (n = 8, 5%). Empiric treatment accounted for 15% (82/541) of all TB treatment initiations and 1.7% (82/4665) of all persons undergoing TB investigations. Chest radiography findings compatible with TB (63/82 [77%]) were the basis for treatment initiation amongst the majority of empirically treated participants. Microbiological confirmation of TB was subsequently obtained for 11/82 (13%) empirically-treated participants. Median time to empiric treatment start was 3.9 weeks (IQR 1.4–11 weeks) after enrolment.

Conclusion

Uncommon prescription of empiric TB treatment with reliance on chest radiography in a nurse-managed programme underscores the need for highly sensitive TB diagnostics suitable for point-of-care, and strong health systems to support TB diagnosis in this setting.

An evaluation of automated chest radiography reading software for tuberculosis screening among public- and private-sector patients

Computer-aided reading (CAR) of medical images is becoming increasingly common, but few studies exist for CAR in tuberculosis (TB). We designed a prospective study evaluating CAR for chest radiography (CXR) as a triage tool before Xpert MTB/RIF (Xpert).Consecutively enrolled adults in Dhaka, Bangladesh, with TB symptoms received CXR and Xpert. Each image was scored by CAR and graded by a radiologist. We compared CAR with the radiologist for sensitivity and specificity, area under the receiver operating characteristic curve (AUC), and calculated the potential Xpert tests saved.A total of 18 036 individuals were enrolled. TB prevalence by Xpert was 15%. The radiologist graded 49% of CXRs as abnormal, resulting in 91% sensitivity and 58% specificity. At a similar sensitivity, CAR had a lower specificity (41%), saving fewer (36%) Xpert tests. The AUC for CAR was 0.74 (95% CI 0.73-0.75). CAR performance declined with increasing age. The radiologist grading was superior across all sub-analyses.Using CAR can save Xpert tests, but the radiologist's specificity was superior. Differentiated CAR thresholds may be required for different populations. Access to, and costs of, human readers must be considered when deciding to use CAR software. More studies are needed to evaluate CAR using different screening approaches.

Digital CXR with computer aided diagnosis versus symptom screen to define presumptive tuberculosis among household contacts and impact on tuberculosis diagnosis

BACKGROUND

Household (HH) contact tracing is a strategy that targets high risk groups for TB. Symptom based screening is the standard used to identify HH contacts at risk for TB during HH contact tracing for TB. However, this strategy may be limited due to poor performance in predicting TB. The objective of this study was to compare CXR with Computer Aided Diagnosis (CAD) against symptom screen for defining presumptive TB and how TB detection changes with each method.

METHODS

Household contacts of consecutive index bacteriologically confirmed TB cases were visited by study teams and given TB/HIV education to raise awareness of the risk of TB following close contact with a TB patient. Contacts were encouraged to visit the health facility for screening; where symptoms history was obtained and opt out HIV testing was provided as part of the screening process. CXR was offered to all regardless of symptoms, followed by definitive sputum test with either Xpert MTB RIF or smear microscopy.

RESULTS

Among 919 HH contacts that presented for screening, 865 were screened with CXR and 464 (53.6%) had an abnormal CXR and the rest had a normal CXR. Among 444 HH contacts with valid sputum results, 274 (61.7%) were symptom screen positive and 255 (57.4%) had an abnormal CXR. Overall, TB was diagnosed in 32/444 (7.2%); 13 bacteriologically unconfirmed and 19 bacteriologically confirmed. Of 19 bacteriologically confirmed TB 8 (42.1%) were symptom screen negative contacts with an abnormal CXR and these 6/8 (75.0%) were HIV positive. Among the 13 bacteriologically unconfirmed TB cases, 7 (53.8%) were HIV positive and all had an abnormal CXR.

CONCLUSION

Symptom screen if used alone with follow on definitive TB testing only for symptom screen positive individuals would have missed eight of the 19 confirmed TB cases detected in this study. There is need to consider use of other screening strategies apart from symptom screen alone for optimal rule out of TB especially in HIV positive individuals that are at greatest risk of TB and present atypically.

Parameter set for computer-assisted texture analysis of fetal brain

BACKGROUND

Magnetic resonance data were collected from a diverse population of gravid women to objectively compare the quality of 1.5-tesla (1.5 T) versus 3-T magnetic resonance imaging of the developing human brain. MaZda and B11 computational-visual cognition tools were used to process 2D images. We proposed a wavelet-based parameter and two novel histogram-based parameters for Fisher texture analysis in three-dimensional space.

RESULTS

Wavenhl, focus index, and dispersion index revealed better quality for 3 T. Though both 1.5 and 3 T images were 16-bit DICOM encoded, nearly 16 and 12 usable bits were measured in 3 and 1.5 T images, respectively. The four-bit padding observed in 1.5 T K-space encoding mimics noise by adding illusionistic details, which are not really part of the image. In contrast, zero-bit padding in 3 T provides space for storing more details and increases the likelihood of noise but as well as edges, which in turn are very crucial for differentiation of closely related anatomical structures.

CONCLUSIONS

Both encoding modes are possible with both units, but higher 3 T resolution is the main difference. It contributes to higher perceived and available dynamic range. Apart from surprisingly larger Fisher coefficient, no significant difference was observed when testing was conducted with down-converted 8-bit BMP images.

An Evaluation of Passive and Active Approaches to Improve Tuberculosis Notifications in Afghanistan

Background

In Afghanistan, improving TB case detection remains challenging. In 2014, only half of the estimated incident TB cases were notified, and notifications have decreased since peaking in 2007. Active case finding has been increasingly considered to improve TB case notifications. While access to health services has improved in Afghanistan, it remains poor and many people seeking health services won’t receive proper care.

Methods

From October 2011 through December 2012 we conducted three separate case finding strategies in six provinces of Afghanistan and measured impact on TB case notification. Systematically screening cough among attendees at 47 health facilities, active household contact investigation of smear-positive index TB patients, and active screening at 15 camps for internally displaced people were conducted. We collected both intervention yield and official quarterly notification data. Additional TB notifications were calculated by comparing numbers of cases notified during the intervention with those notified before the intervention, then adjusting for secular trends in notification.

Results

We screened 2,022,127 people for TB symptoms during the intervention, tested 59,838 with smear microscopy and detected 5,046 people with smear-positive TB. Most cases (81.7%, 4,125) were identified in health facilities while nearly 20% were found through active case finding. A 56% increase in smear-positive TB notifications was observed between the baseline and intervention periods among the 47 health facilities, where cases detected by all three strategies were notified.

Discussion

While most people with TB are likely to be identified through health facility screening, there are many people who remain without a proper diagnosis if outreach is not attempted. This is especially true in places like Afghanistan where access to general services is poor. Targeted active case finding can improve the number of people who are detected and treated for TB and can push towards the targets of the Stop TB Global Plan and End TB Strategy.

Perspectives on Advances in Tuberculosis Diagnostics, Drugs, and Vaccines

Despite concerted efforts over the past 2 decades at developing new diagnostics, drugs, and vaccines with expanding pipelines, tuberculosis remains a global emergency. Several novel diagnostic technologies show promise of better point-of-care rapid tests for tuberculosis including nucleic acid-based amplification tests, imaging, and breath analysis of volatile organic compounds. Advances in new and repurposed drugs for use in multidrug-resistant (MDR) or extensively drug-resistant (XDR) tuberculosis have focused on development of several new drug regimens and their evaluation in clinical trials and now influence World Health Organization guidelines. Since the failure of the MVA85A vaccine 2 years ago, there have been no new tuberculosis vaccine candidates entering clinical testing. The current status quo of the lengthy treatment duration and poor treatment outcomes associated with MDR/XDR tuberculosis and with comorbidity of tuberculosis with human immunodeficiency virus and noncommunicable diseases is unacceptable. New innovations and political and funder commitment for early rapid diagnosis, shortening duration of therapy, improving treatment outcomes, and prevention are urgently required.

An automated tuberculosis screening strategy combining X-ray-based computer-aided detection and clinical information

Lack of human resources and radiological interpretation expertise impair tuberculosis (TB) screening programmes in TB-endemic countries. Computer-aided detection (CAD) constitutes a viable alternative for chest radiograph (CXR) reading. However, no automated techniques that exploit the additional clinical information typically available during screening exist. To address this issue and optimally exploit this information, a machine learning-based combination framework is introduced. We have evaluated this framework on a database containing 392 patient records from suspected TB subjects prospectively recruited in Cape Town, South Africa. Each record comprised a CAD score, automatically computed from a CXR, and 12 clinical features. Comparisons with strategies relying on either CAD scores or clinical information alone were performed. Our results indicate that the combination framework outperforms the individual strategies in terms of the area under the receiving operating characteristic curve (0.84 versus 0.78 and 0.72), specificity at 95% sensitivity (49% versus 24% and 31%) and negative predictive value (98% versus 95% and 96%). Thus, it is believed that combining CAD and clinical information to estimate the risk of active disease is a promising tool for TB screening.

Tuberculosis in Older Adults

Tuberculosis (TB) remains one of the world's most lethal infectious diseases. Preventive and control strategies among other high-risk groups, such as the elderly population, continues to be a challenge. Clinical features of TB in older adults may be atypical and confused with age-related diseases. Diagnosis and management of TB in the elderly person can be difficult; treatment can be associated with adverse drug reactions. This article reviews the current global epidemiology, pathogenesis, clinical characteristics, diagnosis, management, and prevention of Mycobacterium tuberculosis infection in community-dwelling and institutionalized aging adults.

On Combining Multiple-Instance Learning and Active Learning for Computer-Aided Detection of Tuberculosis

The major advantage of multiple-instance learning (MIL) applied to a computer-aided detection (CAD) system is that it allows optimizing the latter with case-level labels instead of accurate lesion outlines as traditionally required for a supervised approach. As shown in previous work, a MIL-based CAD system can perform comparably to its supervised counterpart considering complex tasks such as chest radiograph scoring in tuberculosis (TB) detection. However, despite this remarkable achievement, the uncertainty inherent to MIL can lead to a less satisfactory outcome if analysis at lower levels (e.g., regions or pixels) is needed. This issue may seriously compromise the applicability of MIL to tasks related to quantification or grading, or detection of highly localized lesions. In this paper, we propose to reduce uncertainty by embedding a MIL classifier within an active learning (AL) framework. To minimize the labeling effort, we develop a novel instance selection mechanism that exploits the MIL problem definition through one-class classification. We adapt this mechanism to provide meaningful regions instead of individual instances for expert labeling, which is a more appropriate strategy given the application domain. In addition, and contrary to usual AL methods, a single iteration is performed. To show the effectiveness of our approach, we compare the output of a MIL-based CAD system trained with and without the proposed AL framework. The task is to detect textural abnormalities related to TB. Both quantitative and qualitative evaluations at the pixel level are carried out. Our method significantly improves the MIL-based classification.

Screening for pulmonary tuberculosis in a Tanzanian prison and computer-aided interpretation of chest X-rays

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.

Automatic detection of pleural effusion in chest radiographs

Automated detection of Tuberculosis (TB) using chest radiographs (CXRs) is gaining popularity due to the lack of trained human readers in resource limited countries with a high TB burden. The majority of the computer-aided detection (CAD) systems for TB focus on detection of parenchymal abnormalities and ignore other important manifestations such as pleural effusion (PE). The costophrenic angle is a commonly used measure for detecting PE, but has limitations. In this work, an automatic method to detect PE in the left and right hemithoraces is proposed and evaluated on a database of 638 CXRs. We introduce a robust way to localize the costophrenic region using the chest wall contour as a landmark structure, in addition to the lung segmentation. Region descriptors are proposed based on intensity and morphology information in the region around the costophrenic recess. Random forest classifiers are trained to classify left and right hemithoraces. Performance of the PE detection system is evaluated in terms of recess localization accuracy and area under the receiver operating characteristic curve (AUC). The proposed method shows significant improvement in the AUC values as compared to systems which use lung segmentation and the costophrenic angle measurement alone.

Tuberculosis in pregnancy: an estimate of the global burden of disease

BACKGROUND

The estimated number of maternal deaths in 2013 worldwide was 289 000, a 45% reduction from 1990. Non-obstetric causes such as infectious diseases including tuberculosis now account for 28% of maternal deaths. In 2013, 3·3 million cases of tuberculosis were estimated to occur in women globally. During pregnancy, tuberculosis is associated with poor outcomes, including increased mortality in both the neonate and the pregnant woman. The aim of our study was to estimate the burden of tuberculosis disease among pregnant women, and to describe how maternal care services could be used as a platform to improve case detection.

METHODS

We used publicly accessible country-level estimates of the total population, distribution of the total population by age and sex, crude birth rate, estimated prevalence of active tuberculosis, and case notification data by age and sex to estimate the number of pregnant women with active tuberculosis for 217 countries. We then used indicators of health system access and tuberculosis diagnostic test performance obtained from published literature to determine how many of these cases could ultimately be detected.

FINDINGS

We estimated that 216 500 (95% uncertainty range 192 100-247 000) active tuberculosis cases existed in pregnant women globally in 2011. The greatest burdens were in the WHO African region with 89 400 cases and the WHO South East Asian region with 67 500 cases in pregnant women. Chest radiography or Xpert RIF/MTB, delivered through maternal care services, were estimated to detect as many as 114 100 and 120 300 tuberculosis cases, respectively.