Pan African Clinical Trials Registry
South African Medical Research Council, South African Cochrane Centre
PO Box 19070, Tygerberg, 7505, South Africa
Telephone: +27 21 938 0835 or +27 21 938 0967
Email: pactradmin@mrc.ac.za Website: pactr.samrc.ac.za
Trial no.: PACTR202607649868973 Date of Registration: 28/07/2026
Trial Status: Registered in accordance with WHO and ICMJE standards
TRIAL DESCRIPTION
Public title Building Respiratory Evidence for AI Tools and Health Equity (BREATHE)
Official scientific title Building Respiratory Evidence for AI Tools and Health Equity (BREATHE)
Brief summary describing the background and objectives of the trial Respiratory diseases, including tuberculosis (TB) and community acquired pneumonia, are major global health problems that affect both adults and children. The 2024 Global TB report from the WHO has documented TB as the number one killer among all infectious pathogens globally in 2023, contributing to approximately 1.25 million deaths worldwide. Although Chest X-rays (CXR) and WHO-recommended molecular tests (mWRD) are available, access to these diagnostics in remote and rural settings remains limited. Moreover, diagnosis is more challenging in children owing to the paucibacillary nature of TB, difficulty in obtaining adequate samples for testing, and non-specific symptoms, especially in the under 5 age group. Community acquired pneumonia (lower respiratory infections) cause 2.5 million deaths each year, including 610,000 in children under 5 years of age. These illnesses predominantly affect populations in low- and middle-income countries (LMICs). Point Of Care Ultrasound (POCUS) -based thoracic ultrasound (TUS) has been increasingly used to detect lung abnormalities in respiratory infections, and its use has been expanded to screen and detect pneumonia and other diseases. Evidence also suggests that TUS can differentiate between viral and bacterial pneumonias, thus triaging the need for antibiotics. Artificial Intelligence (AI) based Computer Aided Detection (CAD) has emerged as a tool for standardized interpretation of CXRs and has been extensively studied and deployed globally for detecting radiological signs of TB in the absence of human readers, following the WHO recommendation in 2021. The multi-site, multi-country prospective arm of the study will be recruiting approximately 15,000 to 18,000 subjects including children and adults with presumptive TB or pneumonia, targeting 1,500 children and 2,000 adults with confirmed diagnosis.
Type of trial Observational
Acronym (If the trial has an acronym then please provide)
Disease(s) or condition(s) being studied Infections and Infestations,Paediatrics,Respiratory
Sub-Disease(s) or condition(s) being studied Tuberculosis
Purpose of the trial Early detection /Screening
Anticipated trial start date 01/08/2026
Actual trial start date
Anticipated date of last follow up 31/05/2028
Actual Last follow-up date
Anticipated target sample size (number of participants) 18000
Actual target sample size (number of participants)
Recruitment status Not yet recruiting
Publication URL
Secondary Ids Issuing authority/Trial register
STUDY DESIGN
Intervention assignment Allocation to intervention If randomised, describe how the allocation sequence was generated Describe how the allocation sequence/code was concealed from the person allocating the participants to the intervention arms Masking If masking / blinding was used
Single Group Non-randomised Allocation Sequence/Code was not concealed Open-label(Masking Not Used)
INTERVENTIONS
Intervention type Intervention name Dose Duration Intervention description Group size Nature of control
Experimental Group Microbiological Clinical and Radiological Data Collection from Adults and Children Not applicable 18 Months of recruitment; 3 months of follow-up The study aims to recruit approximately 15,000 to 18,000 participants to achieve the total number of 3500 cases of tuberculosis (n=1000 adults, n=500 children) or pneumonia (n=1000 adults, n=1000 children) across over 20 study recruitment sites in South Africa, India, and Nigeria. Cases are defined as subjects who present with symptoms of a lower respiratory illness, presumably TB or community-acquired pneumonia, and undergo microbiological, serological, and radiological tests subsequently to establish the final diagnosis of TB or pneumonia through a composite reference standard encompassing microbiological, clinical, or clinico-radiological diagnosis to initiate appropriate treatment. Asymptomatic subjects who are contacts of active TB disease and children or adults living with HIV, who are under evaluation for active TB disease or for TB Preventive Therapy (TPT) eligibility with or without symptoms, will also be recruited to represent about 10-15% of the prospective cohort. The clinical data, TUS, digital auscultation, cough sound recordings, and CXR image acquisition will be performed at that point, along with additional tests at the clinician’s discretion by the trained Research Assistant (RA). Mandatory additional data variables, including blood biomarkers, and the pneumonia panel will only be performed if the diagnosis of TB or pneumonia has been confirmed and for a predefined proportion of controls. Thus, there will be a larger database of TUS+ CXR from all presumptive participants. 18000
ELIGIBILITY CRITERIA
List inclusion criteria List exclusion criteria Age Category Minimum age Maximum age Gender
Adult TB: • Age ≥ 18 years • Symptoms suggestive of TB (e.g., cough >2 weeks, weight loss, fever, night sweats) OR Known TB contact in the past 12 months with or without symptoms OR Person living with HIV (PLHIV) under TB evaluation with or without symptoms with available chest radiograph Adult Pneumonia: • Age ≥ 18 years • Acute respiratory symptoms and signs (new or increased) (e.g., cough +/- fever +/- dyspnoea +/- pleuritic chest pain + tachypnoea or respiratory distress) suggestive of pneumonia Paediatric TB: • Age < 18 years • Symptoms suggestive of TB (e.g., persistent cough, fever >2 weeks, weight loss/ failure to thrive) OR Known TB contact in the past 12 months with or without symptoms OR Child living with HIV (CLHIV) under TB evaluation with or without symptoms Paediatric Pneumonia: • Age < 18 years • Acute respiratory symptoms (e.g., cough or difficulty breathing AND chest indrawing AND/ OR tachypnoea) Chest radiographs must be available for all participant categories. Adult TB: • Medical instability per treating clinician’s discretion (e.g., requiring immediate resuscitation or airway support) • Physical barriers to ultrasound (e.g bandages, chest tube, skin infection, open wound etc.) • Patients who have been on Anti-TB treatment (ATT) during the past 6 months • Patients on ATT for >1 week* Adult Pneumonia: • Nosocomial pneumonia (onset >48 hours after admission) • Medical instability per treating clinician’s discretion (e.g., requiring immediate resuscitation or airway support) • Physical barriers to ultrasound (e.g bandages, chest tube, skin infection, open wound etc.) • >24 hours since antibiotic initiation for pneumonia • Aspiration pneumonia due to any reason. The inability to consent is an exclusion criteria for all adult participants. Paediatric TB: • Patients who have been on ATT during the past 6 months • Patients on ATT for >2 weeks* • Medical instability per treating clinician’s discretion (e.g., requiring immediate resuscitation or airway support) • Physical barriers to ultrasound (e.g bandages, chest tube, skin infection, open wound etc.) Paediatric Pneumonia: • >24 hours since antibiotic initiation for pneumonia • Medical instability per treating clinician’s discretion (e.g., requiring immediate resuscitation or airway support) • Physical barriers to ultrasound (e.g bandages, chest tube, skin infection, open wound etc.) Lack of parental or guardian consent is an exclusion for both paediatric participant categories. 80 and over: 80+ Year,Adolescent: 13 Year(s)-17 Year(s),Adult: 18 Year(s)-44 Year(s),Aged: 65 Year(s)-79 Year(s),Child: 6 Year-12 Year,Infant: 1 Month(s)-12 Month(s),Infant: 13 Month(s)-24 Month(s),Middle Aged: 45 Year(s)-64 Year(s),New born: 0 Day-1 Month,Preschool Child: 2 Year-5 Year 0 Week(s) 100 Year(s) Both
ETHICS APPROVAL
Has the study received appropriate ethics committee approval Date the study will be submitted for approval Date of approval Name of the ethics committee
No 16/01/2026 University of Cape Town Faculty of Health Sciences Human Research Ethics Committee
Ethics Committee Address
Street address City Postal code Country
Groote Schuur Hospital Observatory Cape Town 7925 South Africa
Has the study received appropriate ethics committee approval Date the study will be submitted for approval Date of approval Name of the ethics committee
Yes 06/01/2026 University of Ibadan College of Medicine
Ethics Committee Address
Street address City Postal code Country
P. O. Box 22133, UIPO Ibadan 200001 Nigeria
Has the study received appropriate ethics committee approval Date the study will be submitted for approval Date of approval Name of the ethics committee
Yes 31/12/2025 Ministry of Health Department of Planning
Ethics Committee Address
Street address City Postal code Country
Power House Road Ibadan 200001 Nigeria
Has the study received appropriate ethics committee approval Date the study will be submitted for approval Date of approval Name of the ethics committee
Yes 12/03/2026 Christian Medical College Vellore
Ethics Committee Address
Street address City Postal code Country
Tamil Nadu Vellore 632-002 India
Has the study received appropriate ethics committee approval Date the study will be submitted for approval Date of approval Name of the ethics committee
Yes 25/05/2026 University of Cape Town Faculty of Health Sciences Human Research Ethics Committee Department of Paediatrics and Child Health
Ethics Committee Address
Street address City Postal code Country
Groote Schuur Hospital Observatory Cape Town 7925 South Africa
OUTCOMES
Type of outcome Outcome Timepoint(s) at which outcome measured
Primary Outcome • To create an open-source, geographically diverse database comprising TUS images and cine clips, paired with digital CXR and HRCT (in adults), along with annotations, reports, clinical information, respiratory sounds captured through digital stethoscopes, demographics, lab results, and supporting evidence toward final diagnoses of TB and community acquired pneumonia. End of the trial
Secondary Outcome • To develop and test the feasibility of prototype AI-enabled CAD models for the automated interpretation of POCUS-based TUS images for the triage and detection of radiological signs of TB and community acquired pneumonia in adults and children. End of the trial
RECRUITMENT CENTRES
Name of recruitment centre Street address City Postal code Country
MRC Unit on Child and Adolescent Health Red Cross Childrens Hospital Rondebosch Cape Town 7700 South Africa
Dora Nginza Hospital Zwide Street, Spondo Gqeberha South Africa
Christian Medical College Paediatrics and Community Health Department Ida Scudder Road Vellore India
Ibadan University College of Medicine Oyo Nigeria
Langa Clinic Corner Washington Street and King Langalibalele Drive Langa Cape Town South Africa
Gugulethu Clinic NY3 Gugulethu Cape Town South Africa
Groote Schuur Hospital Main Road Observatory Cape Town 7925 South Africa
FUNDING SOURCES
Name of source Street address City Postal code Country
Gates Foundation 500 5th Ave North Seattle 98109 United States of America
SPONSORS
Sponsor level Name Street address City Postal code Country Nature of sponsor
Primary Sponsor Gates Foundation 500 5th Ave North Seattle 98109 United States of America Funding Agency
COLLABORATORS
Name Street address City Postal code Country
Qure.ai Technologies 200 Vesey Street, 24th Floor New York City 10281 United States of America
CONTACT PEOPLE
Role Name Email Phone Street address
Principal Investigator Heather Zar heather.zar@uct.ac.za +27216505173 Red Cross Childrens Hospital
City Postal code Country Position/Affiliation
Rondebosch Cape Town 7700 South Africa Professor
Role Name Email Phone Street address
Public Enquiries Cynthia Baard cynthia.baard@uct.ac.za +27216505173 Red Cross Childrens Hospital
City Postal code Country Position/Affiliation
Rondebosch Cape Town 7700 South Africa Project Manager
Role Name Email Phone Street address
Scientific Enquiries Justy Antony justy.antony@qure.ai +12065329375 200 Vesey Street, 24th Floor
City Postal code Country Position/Affiliation
New York 10281 United States of America Clinical Director Global Health
Role Name Email Phone Street address
Principal Investigator Adegoke Falade afalade33@hotmail.com +2349084625231 Oxygen for Life Initiative, Department of Paediatrics, University College Hospital
City Postal code Country Position/Affiliation
Ibadan Nigeria Professor
Role Name Email Phone Street address
Principal Investigator Ali Esmail ali.esmail@uct.ac.za +27832711444 NY3, Gugulethu
City Postal code Country Position/Affiliation
Cape Town South Africa Site Investigator
Role Name Email Phone Street address
Scientific Enquiries DJ Christopher djchris@cmcvellore.ac.in +919443306573 Department of Pulmonary Medicine, CMC Vellore Ranipet Campus, Kilminnal Village, Ranipet
City Postal code Country Position/Affiliation
Tamil Nadu 632517 India Site Pulmonologist
Role Name Email Phone Street address
Principal Investigator Philip Verghese Valsan valsan@cmcvellore.ac.in +917708303319 Child Health Unit III, CMCH Vellore, Town campus
City Postal code Country Position/Affiliation
Tamil Nadu 632004 India Paediatrics Site Investigator
REPORTING
Share IPD Description Additional Document Types Sharing Time Frame Key Access Criteria
Yes Informed consent will be obtained from a parent/legal guardian and assent from a child from 7 years of age. A qualified staff member will conduct the informed consent and assent process with the parent/legal guardian of the child and the child. The child will complete a separate assent form, when applicable. The informed consent and assent process will be conducted before enrolment in their preferred language by trained study staff according to a standardised SOP. The consent and assent process will detail the purpose of the study, study procedures, and the risks and benefits to children and caregivers during the study. Consent will include permissions to abstract clinical data prospectively as well as for data sharing. Signed and witnessed documentation of informed consent and assent will be done. Following IRB guidelines in this setting, parents/legal guardians and children who are illiterate and unable to provide their signature will be asked to provide a thumbprint, which will be independently witnessed. Data and confidentiality All participants' information will be kept strictly confidential. All clinical and radiological data will be de-linked from identifying information and encrypted to ensure confidentiality of participants. All personnel involved in data collection and management undergo specific training for the study in confidentiality and related patient protection issues. Anonymous participant identification numbers are used on all study documents and all electronic records are kept in password-protected files to reduce access by anyone outside of the study. Study Protocol 12 months following trial completion Dissemination will initially take place through the publication of study results in peer-reviewed journals following the study's completion. The study consortium (study team) reserves the rights (controlled access) to data collected as part of the study. Only anonymised data will be considered for sharing. The data wil then subsequently be shared on an open-source platform, Everwell. This platform possesses operational expertise in large-scale TB program data systems and has a proven track record of international partnerships. The comprehensive open-source database is expected to be hosted for a duration of 7-10 years, and potentially utilizing cold storage solutions beyond this period. This collaboration will facilitate the hosting of data collected through this study and multiple other projects. database will be open-source,
URL Results Available Results Summary Result Posting Date First Journal Publication Date
No
Result Upload 1: Result Upload 2: Result Upload 3: Result Upload 4: Result Upload 5:
Result URL Hyperlinks Link To Protocol
Result URL Hyperlinks
Changes to trial information
Section Name Field Name Date Reason Old Value Updated Value
Trial Information Trial description 20/07/2026 Updated per reviewer comments This will be a multi-country study, recruiting both adults and children with TB and Pneumonia. The sites selected for the study will ensure geographical representation, ethnic diversity, and variability in disease burden and comorbidities, which are key factors for building a robust and generalisable artificial intelligence (AI) algorithm for point-of-care ultrasound (POCUS). This study aims to collect data to build a comprehensive database of patient data that will include clinical picture including symptomatology, digital auscultation and cough sound recordings, paired radiological images, microbiological tests, and other blood tests required to establish a diagnosis, as well as the socio-demographic information of the participants. Data will be collected from similar retrospective and ongoing projects, as well as through targeted prospective data collection, as planned in this proposal. Respiratory diseases, including tuberculosis (TB) and community acquired pneumonia, are major global health problems that affect both adults and children. The 2024 Global TB report from the WHO has documented TB as the number one killer among all infectious pathogens globally in 2023, contributing to approximately 1.25 million deaths worldwide. Although Chest X-rays (CXR) and WHO-recommended molecular tests (mWRD) are available, access to these diagnostics in remote and rural settings remains limited. Moreover, diagnosis is more challenging in children owing to the paucibacillary nature of TB, difficulty in obtaining adequate samples for testing, and non-specific symptoms, especially in the under 5 age group. Community acquired pneumonia (lower respiratory infections) cause 2.5 million deaths each year, including 610,000 in children under 5 years of age. These illnesses predominantly affect populations in low- and middle-income countries (LMICs). Point Of Care Ultrasound (POCUS) -based thoracic ultrasound (TUS) has been increasingly used to detect lung abnormalities in respiratory infections, and its use has been expanded to screen and detect pneumonia and other diseases. Evidence also suggests that TUS can differentiate between viral and bacterial pneumonias, thus triaging the need for antibiotics. Artificial Intelligence (AI) based Computer Aided Detection (CAD) has emerged as a tool for standardized interpretation of CXRs and has been extensively studied and deployed globally for detecting radiological signs of TB in the absence of human readers, following the WHO recommendation in 2021. The multi-site, multi-country prospective arm of the study will be recruiting approximately 15,000 to 18,000 subjects including children and adults with presumptive TB or pneumonia, targeting 1,500 children and 2,000 adults with confirmed diagnosis.
Section Name Field Name Date Reason Old Value Updated Value
Intervention Intervention List 20/07/2026 Updated for clarity as per reviewer comments Experimental Group, Microbiological Clinical and Radiological Data Collection from Adults and Children , Not applicable, 18 Months of recruitment; 3 months of follow-up, The study aims to recruit approximately 15,000 to 18,000 participants to achieve the total number of 3500 cases of tuberculosis (n=1000 adults, n=500 children) or pneumonia (n=1000 adults, n=1000 children) across over 20 study recruitment sites in South Africa, India, and Nigeria. Cases are defined as subjects who present with symptoms of a lower respiratory illness, presumably TB or community-acquired pneumonia, and undergo microbiological, serological, and radiological tests subsequently to establish the final diagnosis of TB or pneumonia through a composite reference standard encompassing microbiological, clinical, or clinico-radiological diagnosis to initiate appropriate treatment. Asymptomatic subjects who are contacts of active TB disease and children or adults living with HIV, who are under evaluation for active TB disease or for TB Preventive Therapy (TPT) eligibility with or without symptoms, will also be recruited to represent about 10-15% of the prospective cohort. The clinical data, TUS, digital auscultation, cough sound recordings, and CXR image acquisition will be performed at that point, along with additional tests at the clinician’s discretion by the trained Research Assistant (RA). Mandatory additional data variables, including blood biomarkers, and the pneumonia panel will only be performed if the diagnosis of TB or pneumonia has been confirmed and for a predefined proportion of controls. Thus, there will be a larger database of TUS+ CXR from all presumptive participants., 18000,
Section Name Field Name Date Reason Old Value Updated Value
Contact People Contacs List 20/07/2026 Missing from original submission Principal Investigator, Adegoke, Falade, Prof., afalade33@hotmail.com, , 00000000000, Ibadan University, Box 4078, Oyo, , Nigeria, Professor
Section Name Field Name Date Reason Old Value Updated Value
Contact People Contacs List 21/07/2026 Missing from original submission Principal Investigator, Adegoke, Falade, Prof., afalade33@hotmail.com, , 00000000000, Ibadan University, Box 4078, Oyo, , Nigeria, Professor Principal Investigator, Adegoke, Falade, Prof., afalade33@hotmail.com, , +2349084625231, Oxygen for Life Initiative, Department of Paediatrics, University College Hospital, Ibadan, , Nigeria, Professor
Section Name Field Name Date Reason Old Value Updated Value
Contact People Contacs List 20/07/2026 Missing from initial submission Principal Investigator, Ali, Esmail, Dr., ali.esmail@uct.ac.za, , +27832711444, NY3, Gugulethu, Cape Town, , South Africa, Site Investigator
Section Name Field Name Date Reason Old Value Updated Value
Contact People Contacs List 21/07/2026 Missing from original submission Principal Investigator, DJ , Christopher, Dr., djchris@cmcvellore.ac.in, , +919443306573, Department of Pulmonary Medicine, CMC Vellore Ranipet Campus, Kilminnal Village, Ranipet, Tamil Nadu, 632517, India, Site Pulmonologist
Section Name Field Name Date Reason Old Value Updated Value
Contact People Contacs List 21/07/2026 Missing from original submission Principal Investigator, DJ , Christopher, Dr., djchris@cmcvellore.ac.in, , +919443306573, Department of Pulmonary Medicine, CMC Vellore Ranipet Campus, Kilminnal Village, Ranipet, Tamil Nadu, 632517, India, Site Pulmonologist Scientific Enquiries, DJ , Christopher, Dr., djchris@cmcvellore.ac.in, , +919443306573, Department of Pulmonary Medicine, CMC Vellore Ranipet Campus, Kilminnal Village, Ranipet, Tamil Nadu, 632517, India, Site Pulmonologist
Section Name Field Name Date Reason Old Value Updated Value
Contact People Contacs List 21/07/2026 Missing from original submission Principal Investigator, Philip Verghese, Valsan , Dr., valsan@cmcvellore.ac.in, , +917708303319, Child Health Unit III, CMCH Vellore, Town campus, Tamil Nadu, 632004, India, Paediatrics Site Investigator