Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
| Name | Class |
|---|---|
| Mercy Corps Pakistan | OTHER |
Not provided
Not provided
Not provided
Not provided
The aim of this pragmatic, stepped wedge cluster-randomized trial is to measure the comparative yield (number of incident TB cases diagnosed during active case-finding camps) using a site selection approach based on predictions generated via an artificial intelligence software called MATCH-AI (intervention group) versus the conventional approach of camp site selection using field-staff knowledge and experience (control group). The trial will help inform whether a targeted approach towards screening for TB using artificial-intelligence can improve yields of TB cases detected through community-based active case-finding.
Despite significant progress over the past decades, an estimated 10.6 million individuals fell ill with tuberculosis (TB) in 2021 and the disease caused 1.6 million deaths globally. Pakistan is ranked as the 5th highest TB burden country in the world and TB causes 42,000 deaths annually in the country. A key challenge in the Pakistan's response to TB is ensuring diagnosis and treatment of all individuals with TB. In 2020, out of the 573,000 cases, a total of 276,736 (48%) were notified. Bridging this case-detection gap is a critical objective for the National TB Program (NTP). Active case-finding (ACF), is a potential strategy to increase case-detection by systematic screening of communities for TB. Recent evidence, indicates that ACF can also reduce population-level TB incidence and prevalence through early detection. While ACF interventions have demonstrated effectiveness in community-trials and are now being conducted at scale in Pakistan, concerns remain regarding their yields and cost-effectiveness in programmatic settings.
The primary aim of this study is to investigate whether a targeted approach towards community-based screening using MATCH-AI, an artificial intelligence software that models sub-district TB prevalence, can improve the yield of ACF interventions in Pakistan. In the intervention arm, field-team will conduct community-based ACF activities (called chest camps) primarily in locations predicted by MATCH-AI to have a higher prevalence of TB. In the control arm, field-teams will continue to utilize existing approaches towards camp site-selection. The trial will be conducted in 65 districts of Pakistan in collaboration with implementation partners of the NTP.
Not provided
Not provided
Not provided
Not provided
| Label | Type | Description | Intervention Names |
|---|---|---|---|
| Intervention | Experimental | Camps site selection for active case finding for TB using MATCH-AI |
|
| Control | No Intervention | Camps site selection for active case finding for TB using existing approaches. |
| Name | Type | Description | Arm Group Labels | Other Names |
|---|---|---|---|---|
| Camps site selection for active case finding for TB using MATCH-AI | Other | The primary intervention in this study is the roll-out of MATCH-AI, an artificial intelligence software that models sub-district TB prevalence, to guide site selection of ACF camps. The MATCH-AI tool uses a Bayesian modelling approach to predict TB prevalence to a resolution of 10,000 population that are mapped as polygons. The model integrates data from a range of sources including historical TB facility notification data, previous ACF data as well as contextual factors such as demographics, income, population density, health indicators such as vaccination coverage and climate related variables to predict localized TB prevalence. In the intervention arm, camps will be conducted primarily in locations guided by MATCH-AI. |
| Measure | Description | Time Frame |
|---|---|---|
| Camp positivity yield | Counts of bacteriologically confirmed TB (B+) cases diagnosed in each camp | 12 months |
| Measure | Description | Time Frame |
|---|---|---|
| Camp positivity rate | Bacteriologically confirmed TB (B+) cases per population screened | 12 months |
| Camp All-Forms yield | Counts of All-Forms TB (AF-TB) cases diagnosed in each camp |
Not provided
Inclusion Criteria:
Exclusion Criteria:
Not provided
Not provided
Not provided
Not provided
Not provided
| Name | Role | Phone | Extension | |
|---|---|---|---|---|
| Amna Mahfooz, MS(PH) | Contact | +923438101441 | amna.mahfooz@cgph.org.pk | |
| Faheem Baig | Contact | +923345379004 | faheem@cgph.org.pk |
| Name | Affiliation | Role |
|---|---|---|
| Faran Emmanuel | Centre for Global Public Health Pakistan | Principal Investigator |
| Facility | Status | City | State | ZIP | Country | Contacts |
|---|---|---|---|---|---|---|
| Mercy Corps Pakistan | Recruiting | Islamabad | Pakistan |
| PubMed Identifier | Type | Citation | Retractions |
|---|---|---|---|
| 38991950 | Derived | Zaidi SMA, Mahfooz A, Latif A, Nawaz N, Fatima R, Rehman FU, Reza TE, Emmanuel F. Geographical targeting of active case finding for tuberculosis in Pakistan using hotspots identified by artificial intelligence software (SPOT-TB): study protocol for a pragmatic stepped wedge cluster randomised control trial. BMJ Open Respir Res. 2024 Jul 11;11(1):e002079. doi: 10.1136/bmjresp-2023-002079. |
Not provided
Not provided
At the conclusion of the trial, aggregate, summary data used for the final analysis will be stored on a public repository for archiving.
Not provided
Not provided
Not provided
Not provided
Not provided
| ID | Term |
|---|---|
| D014376 | Tuberculosis |
| ID | Term |
|---|---|
| D009164 | Mycobacterium Infections |
| D000193 | Actinomycetales Infections |
| D016908 | Gram-Positive Bacterial Infections |
| D001424 | Bacterial Infections |
Not provided
Not provided
The MATCH-AI evaluation is designed as a stepped-wedge cluster randomized trial. In this study, clusters (mobile X-ray van teams) will successively switch over in groups of 3 to the intervention in a randomly assigned order until all clusters are eventually exposed to the intervention.
In the intervention arm, TB active case finding camps will be conducted primarily in locations guided by MATCH-AI a modelling software that predicts TB hotspots. In the control sites, field-teams will continue to utilize existing approaches such as local knowledge, historical data etc towards camp site-selection.
Not provided
Not provided
Individuals visiting camps will be masked to the intervention status.
|
| 12 months |
| Camp All-Forms TB rate | All-Forms TB (AF-TB) cases per population screened | 12 months |
| D001423 | Bacterial Infections and Mycoses |
| D007239 | Infections |