Delft supports Zambia’s Journey to Better Health

In 2020, the total population of Zambia totaled approximately 18.4 million people. That year, there were an estimated 59,000 people who developed TB. Among them 5,500 were children. Moreover, there were 19,000 missing people with TB, of which 2,776 were children.

In 2009, Delft Imaging already installed the first semi-mobile X-ray system at Kanyama clinic, Lusaka Zambia. Kanyama is one of the busiest HIV/TB clinics in Zambia and provides health services for around 200.000 people. The clinic provides the X-ray facilities free of charge to the mainly poor people.

In 2010, Delft Imaging delivered the first ‘OneStopTB’ mobile clinic for a TB Reach project executed by the Center of Infectious Disease and Research in Zambia (CIDRZ). In this WHO/TB Reach project the unit is used to screen prison inmates on TB in 4 different prisons located throughout Zambia. The container consists of a digital X-ray unit and a TB smear microscopy laboratory. The laboratory is equipped with a ventilated smear cabinet; LED fluorescent microscope, refrigerator and workbenches. The small lab has proven its capability and effectiveness with an average capacity of over 50 smear examinations a day. The X-ray and CAD4TB software were used to screen for TB suspects for molecular testing and DST making it a fast and cost effective TB intervention.

In 2011 the first version of the CAD4TB software was installed and used in a TB Reach funded project of Zambart. The software is used as a stand-alone tool to determine who is eligible for a more time-consuming and expensive confirmatory test. The first results of this project were very promising, showing a high correlation between a high (abnormal) score of the CAD4TB and a positive Xpert test. By using the X-ray as a first screening tool many more TB patients are found at a fraction of the cost.

In 2017, Delft Imaging leased one of its OneStopTB mobile TB screening clinics to CIDRZ in Zambia. The clinic was fitted with the multi-functional, digital EasyDR X-ray system and supported by the CAD4TB software.

In 2018, Delft Imaging supplied a containerized clinic, again fitted with the EasyDR X-ray system and the CAD4TB solution to FHI360, as part of the Challenge TB project.

In 2018, another lease project was implemented using a OneStopTB mobile TB screening clinic (with the EasyDR digital X-ray system and the CAD4TB software) for Zambart, as part of an EDCTP grant.

Later that same year, a OneStopTB mobile clinic was procured by PATH as part of the Eradicate TB Project (funded by USAID). The project included the EasyDR digital X-ray system, the CAD4B artificial intelligence software, and also included the necessary training and installation services.

In 2019, additional CAD4TB solutions were provided to CIDRZ to support their TB screening efforts across Zambia.

In 2020 and 2021, CAD4TB was further installed across different mobile TB screening clinics within the country.

Early 2021, 3 Delft Light portable backpack X-ray systems were also provided to CIDRZ, to complement their TB screening efforts in-country, which up to then had largely leveraged the utilization of mobile TB screening clinics.

In 2023, Delft Imaging provided 4 BabyChecker solutions to an in-country partner in Zambia, aimed to support the rapid detection of risky pregnancies using low-cost ultrasound and artificial intelligence-based insights.

Making a difference

Already back in 2013, a study was published on the detection of tuberculosis using automated reading (utilizing the CAD4TB artificial intelligence solution). The study should that the assessment of chest X-rays using CAD4TB and by clinical officers was comparable and that CAD4TB had the potential as a point-of-care test and for the automated identification of subjects who require further examinations. Note that in this study, a significantly older version of CAD4TB was used than what is currently available.

In 2014, another study was published looking at the utilization of CAD4TB in Lusaka, Zambia. It showed that the use of CAD with digital chest X-ray has the potential to increase the use and availability of chest radiography in screening for TB where trained human resources are scarce.

In 2017, a study looked at using digital chest X-ray with computer-aided diagnosis software (CAD4TB) versus symptom screening to define tuberculosis among household contacts and the impact on tuberculosis diagnosis. The study showed that symptom screen if used alone with follow-on definitive TB testing would have lead to missing eight of the 19^th confirmed TB cases and CAD software could support in TB screening efforts.

That same year, CAD4TB was reviewed as part of the Zambia National Tuberculosis Prevalence Survey. A study on this objective looked at the performance of the CAD4TB software against that of field- and central readers. The performance of CAD4TB was found to be similar to that of field and central readers and the study concluded that the performance of automatic chest X-ray readings is comparable to that of human experts in a TB prevalence survey setting using culture as reference.

Later, in 2021, one study published on the costs and cost-effectiveness of a comprehensive tuberculosis case finding strategy in Zambia, also considering CAD4TB.

That same year, a study looked at using CAD as a triage test for pulmonary tuberculosis and found that CAD-based chest X-ray analysis can be implemented as a high-sensitivity tuberculosis rule-out test.

In 2022, a study reviewed the performance of computer-aided detection digital chest X-ray reading technologies (CAD4TB) for the triage of active tuberculosis among persons with a history of previous tuberculosis. It showed that CAD4TB achieved a sensitivity and specificity of 89.3% and 24%, and 90.5% and 60.3% amongst those with and without previous TB, respectively.

In 2023, one study assessed non-tuberculosis abnormalities on digital chest X-rays with high CAD4TB scores using data from a tuberculosis prevalence survey in Zambia and South Africa. The study found that a wide range of non-TB abnormalities can be identified on digital chest X-rays among individuals with high CAD4TB scores, but that do not have bacteriologically confirmed TB. A tool like CAD4TB could simultaneously identify other causes of abnormal chest X-rays along side TB and this could be interesting for future research.