Automated chest-radiography as a triage for Xpert testing in resource-constrained settings: a prospective study of diagnostic accuracy and costs

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.

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.

Computer-aided diagnostic accuracy of pulmonary tuberculosis on chest radiography among lower respiratory tract symptoms patients

Even though the Gaza Strip is a low pulmonary tuberculosis (TB) burden region, it is well-known that TB is primarily a socioeconomic problem associated with overcrowding, poor hygiene, a lack of fresh water, and limited access to healthcare, which is the typical case in the Gaza Strip. Therefore, this study aimed at assessing the accuracy of the automatic software computer-aided detection for tuberculosis (CAD4TB) in diagnosing pulmonary TB on chest radiography and compare the CAD4TB software reading with the results of geneXpert. Using a census sampling method, the study was conducted in radiology departments in the Gaza Strip hospitals between 1 December 2022 and 31 March 2023. A digital X-ray, printer, and online X-ray system backed by CAD4TBv6 software were used to screen patients with lower respiratory tract symptoms. GeneXpert analysis was performed for all patients having a score > 40. A total of 1,237 patients presenting with lower respiratory tract symptoms participated in this current study. Chest X-ray readings showed that 7.8% (n = 96) were presumptive for TB. The CAD4TBv6 scores showed that 11.8% (n = 146) of recruited patients were presumptive for TB. GeneXpert testing on sputum samples showed that 6.2% (n = 77) of those with a score > 40 on CAD4TB were positive for pulmonary TB. Significant differences were found in chest X-ray readings, CAD4TBv6 scores, and GeneXpert results among sociodemographic and health status variables (P-value < 0.05). The study showed that the incidence rate of TB in the Gaza Strip is 3.5 per 100,000 population in the Gaza strip. The sensitivity of the CAD4TBv6 score and the symptomatic review for tuberculosis with a threshold score of >40 is 80.2%, and the specificity is 94.0%. The positive Likelihood Ratio is 13.3%, Negative Likelihood Ratio is 0.2 with 7.8% prevalence. Positive Predictive Value is 52.7%, Negative Predictive Value is 98.3%, and accuracy is 92.9%. In a resource-limited country with a high burden of neglected disease, combining chest X-ray readings by CAD4TB and symptomatology is extremely valuable for screening a population at risk. CAD4TB is noticeably more efficient than other methods for TB screening and early diagnosis in people who would otherwise go undetected.

Artificial Intelligence in Paediatric Tuberculosis

Tuberculosis (TB) continues to be a leading cause of death in children despite global efforts focused on early diagnosis and interventions to limit the spread of the disease. This challenge has been made more complex in the context of the coronavirus pandemic, which has disrupted the "End TB Strategy" and framework set out by the World Health Organization (WHO). Since the inception of artificial intelligence (AI) more than 60 years ago, the interest in AI has risen and more recently we have seen the emergence of multiple real-world applications, many of which relate to medical imaging. Nonetheless, real-world AI applications and clinical studies are limited in the niche area of paediatric imaging. This review article will focus on how AI, or more specifically deep learning, can be applied to TB diagnosis and management in children. We describe how deep learning can be utilised in chest imaging to provide computer-assisted diagnosis to augment workflow and screening efforts. We also review examples of recent AI applications for TB screening in resource constrained environments and we explore some of the challenges and the future directions of AI in paediatric TB.

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.

Artificial Intelligence-Based Software with CE Mark for Chest X-ray Interpretation: Opportunities and Challenges

Chest X-ray (CXR) is the most important technique for performing chest imaging, despite its well-known limitations in terms of scope and sensitivity. These intrinsic limitations of CXR have prompted the development of several artificial intelligence (AI)-based software packages dedicated to CXR interpretation. The online database "AI for radiology" was queried to identify CE-marked AI-based software available for CXR interpretation. The returned studies were divided according to the targeted disease. AI-powered computer-aided detection software is already widely adopted in screening and triage for pulmonary tuberculosis, especially in countries with few resources and suffering from high a burden of this disease. AI-based software has also been demonstrated to be valuable for the detection of lung nodules detection, automated flagging of positive cases, and post-processing through the development of digital bone suppression software able to produce digital bone suppressed images. Finally, the majority of available CE-marked software packages for CXR are designed to recognize several findings, with potential differences in sensitivity and specificity for each of the recognized findings.

Point-of-care test for tuberculosis: a boon in diagnosis

Rapid diagnosis of tuberculosis (TB) is an effective measure to eradicate this infectious disease worldwide. Traditional methods for screening TB patients do not provide an immediate diagnosis and thus delay treatment. There is an urgent need for the early detection of TB through point-of-care tests (POCTs). Several POCTs are widely available at primary healthcare facilities that assist in TB screening. In addition to the currently used POCTs, advancements in technology have led to the discovery of newer methods that provide accurate and fast information independent of access to laboratory facilities. In the present article, the authors tried to include and describe the potential POCTs for screening TB in patients. Several molecular diagnostic tests, such as nucleic acid amplification tests, including GeneXpert and TB-loop-mediated isothermal amplification, are currently being used as POCTs. Besides these methods, the pathogenic component of Mycobacterium tuberculosis can also be utilized as a biomarker for screening purposes through immunological assays. Similarly, the host immune response to infection has also been utilized as a marker for the diagnosis of TB. These novel biomarkers might include Mtb85, interferon-γ inducible protein-10, volatile organic compounds, acute-phase proteins, etc. Radiological tests have also been observed as POCTs in the TB screening POCT panel. Various POCTs are performed on samples other than sputum, which further eases the screening process. These POCTs should not require large-scale manpower and infrastructure. Hence, POCT should be able to identify patients with M. tuberculosis infection at the primary healthcare level only. There are several other advanced techniques that have been proposed as future POCTs and have been discussed in the present article.

Utility of Xpert MTB/RIF Ultra and digital chest radiography for the diagnosis and treatment of TB in people living with HIV: a randomised controlled trial (XACT-TB)

BACKGROUND

TB is a leading cause of morbidity among HIV positive individuals. Accurate algorithms are needed to achieve early TB diagnosis and treatment. We investigated the use of Xpert MTB/RIF Ultra in combination with chest radiography for TB diagnosis in ambulatory HIV positive individuals.

METHODS

This was a randomised controlled trial with a 2-by-2 factorial design. Outpatient HIV clinic attendees with cough were randomised to four arms: Arm 1-Standard Xpert/no chest radiography (CXR); Arm 2-Standard Xpert/CXR; Arm 3-Xpert Ultra/no CXR; and Arm 4-Xpert Ultra/CXR. Participants were followed up at days 28 and 56 to assess for TB treatment initiation.

RESULTS

We randomised 640 participants. Bacteriologically confirmed TB treatment initiation at day 28 were: Arm 1 (8.4% [14/162]), Arm 2 (6.9% [11/159]), Arm 3 (8.2% [13/159]) and Arm 4 (5.6% [9/160]) and between Xpert Ultra group (Arms 3 and 4) (6.9% [22/319]) vs Standard Xpert group (Arms 1 and 2) (7.8% [25/321]), risk ratio 0.89 (95% CI 0.51 to 1.54). By day 56, there were also similar all-TB treatment initiations in the x-ray group (Arms 2 and 4) (16.0% [51/319]) compared with the no x-ray group (Arms 1 and 3) (13.1% [42/321]), risk ratio 1.22 (95% CI 0.84 to 1.78); however, the contribution of clinically diagnosed treatment initiations were higher in x-ray groups (50.9% vs 19.0%).

CONCLUSIONS

Xpert Ultra performed similarly to Xpert MTB/RIF. X-rays are useful for TB screening but further research should investigate how to mitigate false-positive treatment initiations.

Economic analysis of different throughput scenarios and implementation strategies of computer-aided detection software as a screening and triage test for pulmonary TB

BACKGROUND

Artificial Intelligence (AI) systems have demonstrated potential in detecting tuberculosis (TB) associated abnormalities from chest X-ray (CXR) images. Thus, they might provide a solution to radiologist shortages in high TB burden countries. However, the cost of implementing computer-aided detection (CAD) software has thus far been understudied. In this study, we performed a costing analysis of CAD software when used as a screening or triage test for pulmonary TB, estimated the incremental cost compared to a radiologist reading of different throughput scenarios, and predicted the cost for the national scale-up plan in Pakistan.

METHODS

For the study, we focused on CAD software reviewed by the World Health Organization (CAD4TB, Lunit INSIGHT CXR, qXR) or listed in the Global Drug Facility diagnostics catalogue (CAD4TB, InferRead). Costing information was obtained from the CAD software developers. CAD4TB and InferRead use a perpetual license pricing model, while Lunit and qXR are priced per license for restricted number of scans. A major implementer in Pakistan provided costing information for human resource and software training. The per-screen cost was estimated for each CAD software and for radiologist for 1) active case finding, and 2) facility based CXR testing scenarios with throughputs ranging from 50,000-100,000 scans. Moreover, we estimated the scale-up cost for CAD or radiologist CXR reading in Pakistan based on the National Strategic Plan, considering that to reach 80% diagnostic coverage, 50% of TB patients would need to be found through facility-based triage and 30% through active case finding (ACF).

RESULTS

The per-screen cost for CAD4TB (0.25 USD- 2.33 USD) and InferRead (0.19 USD- 2.78 USD) was lower than that of a radiologist (0.70 USD- 0.93 USD) for high throughput scenarios studied. In comparison, the per-screen cost for Lunit (0.94 USD- 1.69 USD) and qXR (0.95 USD-1.9 USD) were only comparable with that of the radiologists in the highest throughput scenario in ACF. To achieve 80 percent diagnostic coverage at scale in Pakistan, the projected additional cost of deploying CAD software to complement the current infrastructure over a four-year period were estimated at 2.65-19.23 million USD, whereas Human readers, would cost an additional 23.97 million USD.

CONCLUSIONS

Our findings suggest that using CAD software could enable large-scale screening programs in high TB-burden countries and be less costly than radiologist. To achieve minimum cost, the target number of screens in a specific screening strategy should be carefully considered when selecting CAD software, along with the offered pricing structure and other aspects such as performance and operational features. Integrating CAD software in implementation strategies for case finding could be an economical way to attain the intended programmatic goals.

Diagnosing Tuberculosis: What Do New Technologies Allow Us to (Not) Do?

New tuberculosis (TB) diagnostics are at a crossroads: their development, evaluation, and implementation is severely damaged by resource diversion due to COVID-19. Yet several technologies, especially those with potential for non-invasive non-sputum-based testing, hold promise for efficiently triaging and rapidly confirming TB near point-of-care. Such tests are, however, progressing through the pipeline slowly and will take years to reach patients and health workers. Compellingly, such tests will create new opportunities for difficult-to-diagnose populations, including primary care attendees (all-comers in high burden settings irrespective of reason for presentation) and community members (with early stage disease or risk factors like HIV), many of whom cannot easily produce sputum. Critically, all upcoming technologies have limitations that implementers and health workers need to be cognizant of to ensure optimal deployment without undermining confidence in a technology that still offers improvements over the status quo. In this state-of-the-art review, we critically appraise such technologies for active pulmonary TB diagnosis. We highlight strengths, limitations, outstanding research questions, and how current and future tests could be used in the presence of these limitations and uncertainties. Among triage tests, CRP (for which commercial near point-of-care devices exist) and computer-aided detection software with digital chest X-ray hold promise, together with late-stage blood-based assays that detect host and/or microbial biomarkers; however, aside from a handful of prototypes, the latter category has a shortage of promising late-stage alternatives. Furthermore, positive results from new triage tests may have utility in people without TB; however, their utility for informing diagnostic pathways for other diseases is under-researched (most sick people tested for TB do not have TB). For confirmatory tests, few true point-of-care options will be available soon; however, combining novel approaches like tongue swabs with established tests like Ultra have short-term promise but first require optimizations to specimen collection and processing procedures. Concerningly, no technologies yet have compelling evidence of meeting the World Health Organization optimal target product profile performance criteria, especially for important operational criteria crucial for field deployment. This is alarming as the target product profile criteria are themselves almost a decade old and require urgent revision, especially to cater for technologies made prominent by the COVID-19 diagnostic response (e.g., at-home testing and connectivity solutions). Throughout the review, we underscore the importance of how target populations and settings affect test performance and how the criteria by which these tests should be judged vary by use case, including in active case finding. Lastly, we advocate for health workers and researchers to themselves be vocal proponents of the uptake of both new tests and those - already available tests that remain suboptimally utilized.

Cost and affordability of scaling up tuberculosis diagnosis using Xpert MTB/RIF testing in West Java, Indonesia

In Indonesia, a significant number of tuberculosis (TB) cases may be missed, due to the low sensitivity and specificity of the currently used diagnostic algorithm. In this regard, the rapid molecular test using Xpert MTB/RIF, which has recently been introduced in Indonesia, can improve case detection. Thus, this study determined the cost and affordability of incorporating Xpert MTB/RIF testing for TB diagnosis. For this purpose, we estimated the costs (from the health system and societal perspectives) of reaching the TB detection target in Depok municipality, and applied the findings to the West Java province of Indonesia. The resources available for the health and TB program were also analyzed to support the decision to scale up the TB diagnosis using Xpert MTB/RIF testing. According to the results, the unit cost for TB diagnosis per person was USD 27.22 and USD 70.16 from the health system and societal perspectives, respectively. To reach the target of 109,843 TB cases for the 2020–2024 time period, Depok municipality would need USD 2,989,927 and USD 2,549,455 from the health system viewpoint, assuming the machine’s lifespan of five and 10 years, respectively. Extrapolating these results to the West Java province, USD 56,353,833 would be necessary to test 2,076,413 cases from 2019 to 2024. However, in order to accelerate the case detection target up to 2024, West Java requires additional funds. The implication of the findings is that the central government must consider local capacity to accelerate TB case detection and ensure that the installation of Xpert MTB/RIF machines is included in the overall costs.

Spatially targeted digital chest radiography to reduce tuberculosis in high-burden settings: a study of adaptive decision making

Background:

Spatially-targeted approaches to screen for tuberculosis (TB) could accelerate TB control in high-burden populations. We aimed to estimate gains in case-finding yield under an adaptive decision-making approach for spatially-targeted, mobile digital chest radiography (dCXR)-based screening in communities with varying levels of TB prevalence.

Methods:

We used a Monte-Carlo simulation model to simulate a spatially-targeted screening intervention in 24 communities with TB prevalence estimates derived from a large community-randomized trial. We implemented a Thompson sampling algorithm to allocate screening units based on Bayesian probabilities of local TB prevalence that are continuously updated during weekly screening rounds. Four mobile units for dCXR-based screening and subsequent Xpert Ultra-based testing were allocated among the communities during a 52-week period. We estimated the yield of bacteriologically-confirmed TB per 1000 screenings comparing scenarios of spatially-targeted and untargeted resource allocation.

Results:

We estimated that under the untargeted scenario, an expected 666 (95% uncertainty interval 522–825) TB cases would be detected over one year, equivalent to 8.9 (7.5–10.3) per 1000 individuals screened. Allocating the screening units to the communities with the highest (prior-year) cases notification rates resulted in an expected 760 (617–926) TB cases detected, 10.1 (8.6–11.8) per 1000 screened. Adaptive, spatially-targeted screening resulted in an expected 1241 (995–1502) TB cases detected, 16.5 (14.5–18.7) per 1000 screened. Numbers of dCXR-based screenings needed to detect one additional TB case declined during the first 12–14 weeks as a result of Bayesian learning.

Conclusion:

We introduce a spatially-targeted screening strategy that could reduce the number of screenings necessary to detect additional TB in high-burden settings and thus improve the efficiency of screening interventions. Empirical trials are needed to determine whether this approach could be successfully implemented.

How does artificial intelligence in radiology improve efficiency and health outcomes?

Since the introduction of artificial intelligence (AI) in radiology, the promise has been that it will improve health care and reduce costs. Has AI been able to fulfill that promise? We describe six clinical objectives that can be supported by AI: a more efficient workflow, shortened reading time, a reduction of dose and contrast agents, earlier detection of disease, improved diagnostic accuracy and more personalized diagnostics. We provide examples of use cases including the available scientific evidence for its impact based on a hierarchical model of efficacy. We conclude that the market is still maturing and little is known about the contribution of AI to clinical practice. More real-world monitoring of AI in clinical practice is expected to aid in determining the value of AI and making informed decisions on development, procurement and reimbursement.

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.

Independent evaluation of 12 artificial intelligence solutions for the detection of tuberculosis

There have been few independent evaluations of computer-aided detection (CAD) software for tuberculosis (TB) screening, despite the rapidly expanding array of available CAD solutions. We developed a test library of chest X-ray (CXR) images which was blindly re-read by two TB clinicians with different levels of experience and then processed by 12 CAD software solutions. Using Xpert MTB/RIF results as the reference standard, we compared the performance characteristics of each CAD software against both an Expert and Intermediate Reader, using cut-off thresholds which were selected to match the sensitivity of each human reader. Six CAD systems performed on par with the Expert Reader (Qure.ai, DeepTek, Delft Imaging, JF Healthcare, OXIPIT, and Lunit) and one additional software (Infervision) performed on par with the Intermediate Reader only. Qure.ai, Delft Imaging and Lunit were the only software to perform significantly better than the Intermediate Reader. The majority of these CAD software showed significantly lower performance among participants with a past history of TB. The radiography equipment used to capture the CXR image was also shown to affect performance for some CAD software. TB program implementers now have a wide selection of quality CAD software solutions to utilize in their CXR screening initiatives.

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.

Use of targeted mobile X-ray screening and computer-aided detection software to identify tuberculosis among high-risk groups in Romania: descriptive results of the E-DETECT TB active case-finding project

OBJECTIVE

To implement and assess the mobile X-ray unit (MXU) equipped with digital radiography, computer-aided detection (CAD) software and molecular point of care tests to improve early tuberculosis (TB) diagnosis in vulnerable populations in a TB outreach screening programme in Romania.

DESIGN

Descriptive study.

SETTINGS

Prisons in Bucharest and other cities in the southern part of Romania, homeless shelters and services for problem drug users in Bucharest, and Roma populations in Bucharest and Craiova.

PARTICIPANTS

5510 individuals attended the MXU service; 5003 persons were radiologically screened, 61% prisoners, 15% prison staff, 11% Roma population, 10% homeless persons and/or problem drug users and 3% other.

INTERVENTIONS

Radiological digital chest X-ray (CXR) screening of people at risk for TB, followed by CAD and human reading of the CXRs, and further TB diagnostics when the pulmonologist classified the CXR as suggestive for TB.

PRIMARY AND SECONDARY OUTCOME MEASURES

Ten bacteriologically confirmed TB cases were identified translating into an overall yield of 200 per 100 000 persons screened (95% CIs of 109 to 368 per 100 000). Prevalence rates among homeless persons and/or problem drug users (826/100 000; 95% CI 326 to 2105/100 000) and the Roma population (345/100 000; 95% CI 95 to 1251/100 000) were particularly high.

RESULTS

The human reader classified 6.4% (n=317) of the CXRs as suspect for TB (of which 32 were highly suggestive for TB); 16.3% of all CXRs had a CAD4TB version 6 score >50. All 10 diagnosed TB patients had a CAD4TB score >50; 9 had a CAD4TB score >60.

CONCLUSIONS

Given the high TB prevalence rates found among homeless persons and problem drug users and in the Roma population, targeted active case finding has the potential to deliver a major contribution to TB control in Romania.

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.

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.

Economic evaluations of big data analytics for clinical decision-making: a scoping review

OBJECTIVE

Much has been invested in big data analytics to improve health and reduce costs. However, it is unknown whether these investments have achieved the desired goals. We performed a scoping review to determine the health and economic impact of big data analytics for clinical decision-making.

MATERIALS AND METHODS

We searched Medline, Embase, Web of Science and the National Health Services Economic Evaluations Database for relevant articles. We included peer-reviewed papers that report the health economic impact of analytics that assist clinical decision-making. We extracted the economic methods and estimated impact and also assessed the quality of the methods used. In addition, we estimated how many studies assessed "big data analytics" based on a broad definition of this term.

RESULTS

The search yielded 12 133 papers but only 71 studies fulfilled all eligibility criteria. Only a few papers were full economic evaluations; many were performed during development. Papers frequently reported savings for healthcare payers but only 20% also included costs of analytics. Twenty studies examined "big data analytics" and only 7 reported both cost-savings and better outcomes.

DISCUSSION

The promised potential of big data is not yet reflected in the literature, partly since only a few full and properly performed economic evaluations have been published. This and the lack of a clear definition of "big data" limit policy makers and healthcare professionals from determining which big data initiatives are worth implementing.

Evaluating the yield of systematic screening for tuberculosis among three priority groups in Ho Chi Minh City, Viet Nam

BACKGROUND

In order to end tuberculosis (TB), it is necessary to expand coverage of TB care services, including systematic screening initiatives. However, more evidence is needed for groups among whom systematic screening is only conditionally recommended by the World Health Organization. This study evaluated concurrent screening in multiple target groups using community health workers (CHW).

METHODS

In our two-year intervention study lasting from October 2017 to September 2019, CHWs in six districts of Ho Chi Minh City, Viet Nam verbally screened three urban priority groups: (1) household TB contacts; (2) close TB contacts; and (3) residents of urban priority areas without clear documented exposure to TB including hotspots, boarding homes and urban slums. Eligible persons were referred for further screening with chest radiography and follow-on testing with the Xpert MTB/RIF assay. Symptomatic individuals with normal or without radiography results were tested on smear microscopy. We described the TB care cascade and characteristics for each priority group, and calculated yield and number needed to screen. Subsequently, we fitted a mixed-effect logistic regression to identify the association of these target groups and secondary patient covariates with TB treatment initiation.

RESULTS

We verbally screened 321 020 people including 24 232 household contacts, 3182 social and close contacts and 293 606 residents of urban priority areas. This resulted in 1138 persons treated for TB, of whom 85 were household contacts, 39 were close contacts and 1014 belonged to urban priority area residents. The yield of active TB in these groups was 351, 1226 and 345 per 100 000, respectively, corresponding to numbers needed to screen of 285, 82 and 290. The fitted model showed that close contacts [adjusted odds ratio (aOR) = 2.07; 95% CI: 1.38-3.11; P < 0.001] and urban priority area residents (aOR = 2.18; 95% CI: 1.69-2.79; P < 0.001) had a greater risk of active TB than household contacts.

CONCLUSIONS

The study detected a large number of unreached persons with TB, but most of them were not among persons in contact with an index patient. Therefore, while programs should continue to optimize screening in contacts, to close the detection gap in high TB burden settings such as Viet Nam, coverage must be expanded to persons without documented exposure such as residents in hotspots, boarding homes and urban slums.

Radiological Findings of COVID-19 Patients in Italy

CONTEXT

The emergence of COVID-19/SARS-CoV2 (COVID-19) was an outbreak that began in December 2019 and rose to pandemic levels in 2020. One of the largest problems with COVID-19 is the typical delay in testing and diagnosis that can lead to additional transmission of the disease. Under consultation with a board-certified radiologist, the study team evaluated the common radiological findings of COVID-19 on computed tomography (CT) and compared the efficacy of chest radiographs (i.e., x-rays) to CT in diagnosing COVID-19.

METHODS

In 2020, the authors completed a retrospective review of radiologic imaging data (i.e., the original imaging report notes) from Italy performed on 47 patients who had tested positive for COVID-19 in Italy during the national outbreak from February to March 2020. Radiologic images were obtained from Società Italiana di Radiologia Medica e Interventistica radiological database of COVID-19 patients. Each case was analyzed for whether they had positive findings on either chest radiograph or CT or both among patients who had positive COVID-19 test results.

RESULTS

The authors found significant radiological finding similarities among the 47 COVID-19 positive case studies from Italy during the February to March 2020 time period. Ground glass opacities and crazy paving were the most significant findings, resembling the findings in China and other Coronavirus strains. The authors' statistical analyses indicated that CT scans were more reliable by 30.7% than chest radiographs in identifying signs of COVID-19. In cases where either an initial negative swab for COVID-19 or providers lacked patient social histories, chest radiographs were used to show clinical findings consistent with COVID-19.

CONCLUSIONS

Based on these results, chest radiographs appear to be a consistent method to assist in the diagnosis of most COVID-19 cases. The authors discuss several scenarios in community-based and non-hospital US settings for COVID-19 diagnostic processes.

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.

Deep learning-based automated detection algorithm for active pulmonary tuberculosis on chest radiographs: diagnostic performance in systematic screening of asymptomatic individuals

OBJECTIVES

Performance of deep learning-based automated detection (DLAD) algorithms in systematic screening for active pulmonary tuberculosis is unknown. We aimed to validate DLAD algorithm for detection of active pulmonary tuberculosis and any radiologically identifiable relevant abnormality on chest radiographs (CRs) in this setting.

METHODS

We performed out-of-sample testing of a pre-trained DLAD algorithm, using CRs from 19.686 asymptomatic individuals (ages, 21.3 ± 1.9 years) as part of systematic screening for tuberculosis between January 2013 and July 2018. Area under the receiver operating characteristic curves (AUC) for diagnosis of tuberculosis and any relevant abnormalities were measured. Accuracy measures including sensitivities, specificities, positive predictive values (PPVs), and negative predictive values (NPVs) were calculated at pre-defined operating thresholds (high sensitivity threshold, 0.16; high specificity threshold, 0.46).

RESULTS

All five CRs from four individuals with active pulmonary tuberculosis were correctly classified as having abnormal findings by DLAD with specificities of 0.959 and 0.997, PPVs of 0.006 and 0.068, and NPVs of both 1.000 at high sensitivity and high specificity thresholds, respectively. With high specificity thresholds, DLAD showed comparable diagnostic measures with the pooled radiologists (p values > 0.05). For the radiologically identifiable relevant abnormality (n = 28), DLAD showed an AUC value of 0.967 (95% confidence interval, 0.938-0.996) with sensitivities of 0.821 and 0.679, specificities of 0.960 and 0.997, PPVs of 0.028 and 0.257, and NPVs of both 0.999 at high sensitivity and high specificity thresholds, respectively.

CONCLUSIONS

In systematic screening for tuberculosis in a low-prevalence setting, DLAD algorithm demonstrated excellent diagnostic performance, comparable with the radiologists in the detection of active pulmonary tuberculosis.

KEY POINTS

• Deep learning-based automated detection algorithm detected all chest radiographs with active pulmonary tuberculosis with high specificities and negative predictive values in systematic screening. • Deep learning-based automated detection algorithm had comparable diagnostic measures with the radiologists for detection of active pulmonary tuberculosis on chest radiographs. • For the detection of radiologically identifiable relevant abnormalities on chest radiographs, deep learning-based automated detection algorithm showed excellent diagnostic performance in systematic screening.

Deep learning detection and quantification of pneumothorax in heterogeneous routine chest computed tomography

BACKGROUND

Automatically detecting and quantifying pneumothorax on chest computed tomography (CT) may impact clinical decision-making. Machine learning methods published so far struggle with the heterogeneity of technical parameters and the presence of additional pathologies, highlighting the importance of stable algorithms.

METHODS

A deep residual UNet was developed and evaluated for automated, volume-level pneumothorax grading (i.e., labelling a volume whether a pneumothorax was present or not), and pixel-level classification (i.e., segmentation and quantification of pneumothorax), on a retrospective series of routine chest CT data. Ground truth annotations were provided by radiologists. The fully automated pixel-level pneumothorax segmentation method was trained using 43 chest CT scans and evaluated on 9 chest CT scans with pixel-level annotation basis and 567 chest CT scans on a volume-level basis.

RESULTS

This method achieved a receiver operating characteristic area under the curve (AUC) of 0.98, an average precision of 0.97, and a Dice similarity coefficient (DSC) of 0.94. This segmentation performance resulted to be similar to the inter-rater segmentation accuracy of two radiologists, who achieved a DSC of 0.92. The comparison of manual and automated pneumothorax quantification yielded a Pearson correlation coefficient of 0.996. The volume-level pneumothorax grading accuracy was evaluated on 567 chest CT scans and yielded an AUC of 0.98 and an average precision of 0.95.

CONCLUSIONS

We proposed a deep learning method for the detection and quantification of pneumothorax in heterogeneous routine clinical data that may facilitate the automated triage of urgent examinations and enable treatment decision support.

Guidance for Studies Evaluating the Accuracy of Tuberculosis Triage Tests

Approximately 3.6 million cases of active tuberculosis (TB) go potentially undiagnosed annually, partly due to limited access to confirmatory diagnostic tests, such as molecular assays or mycobacterial culture, in community and primary healthcare settings. This article provides guidance for TB triage test evaluations. A TB triage test is designed for use in people with TB symptoms and/or significant risk factors for TB. Triage tests are simple and low-cost tests aiming to improve ease of access and implementation (compared with confirmatory tests) and decrease the proportion of patients requiring more expensive confirmatory testing. Evaluation of triage tests should occur in settings of intended use, such as community and primary healthcare centers. Important considerations for triage test evaluation include study design, population, sample type, test throughput, use of thresholds, reference standard (ideally culture), and specimen flow. The impact of a triage test will depend heavily on issues beyond accuracy, primarily centered on implementation.

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.

The technological imperative in tuberculosis care and prevention in Vietnam

A monocausal bacteriological understanding of infectious disease orients tuberculosis control efforts towards antimicrobial interventions. A bias towards technological solutions can leave multistranded public health and social interventions largely neglected. In the context of globalising biomedical approaches to infectious disease control, this ethnography-inspired review article reflects upon the implementation of rapid diagnostic technology in low- and middle-income countries. Fieldwork observations in Vietnam provided a stimulus for a critical review of the global rollout of tuberculosis diagnostic technology. To address local needs in tuberculosis control, health managers in resource-poor settings are readily cooperating with international donors to deploy novel diagnostic technologies throughout national tuberculosis programme facilities. Increasing investment in new diagnostic technologies is predicated on the supposition that these interventions will ameliorate disease outcomes. However, suboptimal treatment control persists even when accurate diagnostic technologies are available, suggesting that promotion of singular technological solutions can distract from addressing systemic change, without which disease susceptibility, propagation of infection, detection gaps, diagnostic delays, and treatment shortfalls persist.

Accuracy of an automated system for tuberculosis detection on chest radiographs in high-risk screening

SETTING:

Tuberculosis (TB) screening programmes can be optimised by reducing the number of chest radiographs (CXRs) requiring interpretation by human experts.

OBJECTIVE:

To evaluate the performance of computerised detection software in triaging CXRs in a high-throughput digital mobile TB screening programme.

DESIGN:

A retrospective evaluation of the software was performed on a database of 38 961 postero-anterior CXRs from unique individuals seen between 2005 and 2010, 87 of whom were diagnosed with TB. The software generated a TB likelihood score for each CXR. This score was compared with a reference standard for notified active pulmonary TB using receiver operating characteristic (ROC) curve and localisation ROC (LROC) curve analyses.

RESULTS:

On ROC curve analysis, software specificity was 55.71% (95%CI 55.21–56.20) and negative predictive value was 99.98% (95%CI 99.95–99.99), at a sensitivity of 95%. The area under the ROC curve was 0.90 (95%CI 0.86–0.93). Results of the LROC curve analysis were similar.

CONCLUSION:

The software could identify more than half of the normal images in a TB screening setting while maintaining high sensitivity, and may therefore be used for triage.

Modelling the impact of chest X-ray and alternative triage approaches prior to seeking a tuberculosis diagnosis

Background

Tuberculosis is a major challenge to health in the developing world. Triage prior to diagnostic testing could potentially reduce the volume of tests and costs associated with using the more accurate, but costly, Xpert MTB/RIF assay. An effective methodology to predict the impact of introducing triage prior to tuberculosis diagnostic testing could be useful in helping to guide policy.

Methods

The development and use of operational modelling to project the impact on case detection and health system costs of alternative triage approaches for tuberculosis, with or without X-ray, based on data from Porto Alegre City, Brazil.

Results

Most of the triage approaches modelled without X-ray were predicted to provide no significant benefit. One approach based on an artificial neural network applied to patient and symptom characteristics was projected to increase case detection (82% vs. 75%) compared to microscopy, and reduce costs compared to Xpert without triage. In addition, use of X-ray before diagnostic testing for HIV-negative patients could maintain diagnostic yield of using Xpert without triage, and reduce costs.

Conclusion

A model for the impact assessment of alternative triage approaches has been tested. The results from using the approach demonstrate its usefulness in informing policy in a typical high burden setting for tuberculosis.

Electronic supplementary material

The online version of this article (10.1186/s12879-019-3684-1) contains supplementary material, which is available to authorized users.

Binomial Classification of Pediatric Elbow Fractures Using a Deep Learning Multiview Approach Emulating Radiologist Decision Making

PURPOSE

To determine the feasibility of using deep learning with a multiview approach, similar to how a human radiologist reviews multiple images, for binomial classification of acute pediatric elbow radiographic abnormalities.

MATERIALS AND METHODS

A total of 21 456 radiographic studies containing 58 817 images of the elbow and associated radiology reports over the course of a 4-year period from January 2014 through December 2017 at a dedicated children's hospital were retrospectively retrieved. Mean age was 7.2 years, and 43% were female patients. The studies were binomially classified, based on the reports, as either positive or negative for acute or subacute traumatic abnormality. The studies were randomly divided into a training set containing 20 350 studies and a validation set containing the remaining 1106 studies. A multiview approach was used for the model by combining both a convolutional neural network and recurrent neural network to interpret an entire series of three radiographs together. Sensitivity, specificity, positive predictive value, negative predictive value, area under the receiver operating characteristic curve (AUC), and their 95% confidence intervals were calculated.

RESULTS

AUC was 0.95, and accuracy was 88% for the model on the studied dataset. Sensitivity for the model was 91% (536 of 590), while the specificity for the model was 84% (434 of 516). Of 241 supracondylar fractures, one was missed. Of 88 lateral condylar fractures, one was missed. Of 77 elbow effusions without fracture, 15 were missed. Of 184 other abnormalities, 37 were missed.

CONCLUSION

Deep learning can effectively classify acute and nonacute pediatric elbow abnormalities on radiographs in the setting of trauma. A recurrent neural network was used to classify an entire radiographic series, arrive at a decision based on all views, and identify fractures in pediatric patients with variable skeletal immaturity.Supplemental material is available for this article.© RSNA, 2019.

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.

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.

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.

Texture analysis of the developing human brain using customization of a knowledge-based system

Background: Pattern recognition software originally designed for geospatial and other technical applications could be trained by physicians and used as texture-analysis tools for evidence-based practice, in order to improve diagnostic imaging examination during pregnancy.Methods: Various machine-learning techniques and customized datasets were assessed for training of an integrable knowledge-based system (KBS), to determine a hypothetical methodology for texture classification of closely-related anatomical structures in fetal brain magnetic resonance (MR) images. Samples were manually categorized according to the magnetic field of the MRI scanner (i.e. 1.5-tesla (1.5T), 3-tesla (3T)), rotational planes (i.e. coronal, sagittal and axial), and signal weighting (i.e. spin-lattice, spin-spin, relaxation, proton density). In the machine-learning sessions, the operator manually selected relevant regions of interest (ROI) in 1.5/3T MR images. Semi-automatic procedures in MaZda/B11 were performed to determine optimal parameter sets for ROI classification. Four classes were defined: ventricles, thalamus, grey matter, and white matter. Various textures analysis methods were tested. The KBS performed automatic data pre-processing and semi-automatic classification of ROIs.Results: After testing 3456 ROIs, statistical binary classification revealed that combination of reduction techniques with linear discriminant algorithms (LDA) or nonlinear discriminant algorithms (NDA) yielded the best scoring in terms of sensitivity (both 100%, 95% CI: 99.79-100), specificity (both 100%, 95% CI: 99.79-100) and Fisher coefficient (≈E+4, ≈E+5, respectively). Conclusions: LDA and NDA in MaZda can be useful data mining tools for screening a population of interest subjected to a clinical test.

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.

Cost-effectiveness of triage testing for facility-based systematic screening of tuberculosis among Ugandan adults

BACKGROUND

Systematic screening is often proposed as a way to improve case finding for tuberculosis (TB), but the cost-effectiveness of specific strategies for systematic screening remains poorly studied.

METHODS

We constructed a Markov-based decision analytic model to analyse the cost-effectiveness of triage testing for TB in Uganda, compared against passive case detection with Xpert MTB/RIF. We assumed a triage algorithm whereby all adults presenting to healthcare centres would be screened for cough, and those with cough of at least 2 weeks would receive the triage test, with positive triage results confirmed by Xpert MTB/RIF. We adopted the perspective of the TB control sector, using a primary outcome of the cost per year of life gained (YLG) over a lifetime time horizon.

RESULTS

Systematic screening in a population with a 5% underlying prevalence of TB was estimated to cost US$610 per YLG (95% uncertainty range US$200-US$1859) with chest X-ray (CXR) (US$5 per test, specificity 0.67), or US$588 (US$221-US$1746) with C reactive protein (CRP) (US$3 per test, specificity 0.59). In addition to the cost and specificity of the triage test, cost-effectiveness was most sensitive to the underlying prevalence of TB, monthly risk of mortality in people with untreated TB and the proportion of patients with TB who would be treated in the absence of systematic screening.

CONCLUSIONS

To optimise the cost-effectiveness of facility-based systematic screening of TB with a triage test, it must be carried out in a high-risk population, or use triage tests that are cheaper or more specific than CXR or CRP.