
M42 study highlights positive performance of AI model for tuberculosis screening
Ella Day | August 6, 2025 | News story | Research and Development |Â Â AI, Infections and infestations, M42, X-ray, tuberculosisÂ
Healthcare tech company, M42, has published results from one of the largest real-world studies of an artificial intelligence (AI)-powered tuberculosis (TB) screening model to date, based on the analysis of over one million chest X-rays (CXR). The findings, published in npj Digital Medicine, reinforce the potential of M42’s AI model – AIRIS-TB – to support routine TB screening.
Conducted in partnership with Capital Health Screening Centre in Abu Dhabi, United Arab Emirates, the study reported an Area under the Receiver Operating Characteristic Curve – a widely used metric indicating high diagnostic accuracy – of 98.5%. Notably, the model achieved a 0% false-negative rate for TB-specific cases across the dataset, suggesting high reliability in identifying true TB cases.
The study also evaluated the model’s performance across a broad spectrum of demographic variables, including age, gender, HIV status, income level and geographic origin, reflecting populations from six World Health Organization (WHO) regions. Results demonstrated consistency across all groups, indicating generalisability and fairness of the model in diverse settings.
According to the WHO, TB remains a major global health challenge, with an estimated 10.8 million cases and 1.25 million deaths in 2023. The study implies that AIRIS-TB could safely automate up to 80% of routine CXR assessments, helping to reduce radiologist workload and increase screening capacity.
Ethical oversight was provided by Abu Dhabi’s Department of Health.
Ella Day
6/8/25
Related Content

Cellbyte raises $2.75m to fund pharma drug launch platform
Cellbyte has announced that it has raised $2.75m in seed funding for the streamlining of …

M42 and Olive Rock agree ownership of UAE health assets
Global health company M42 and private equity firm Olive Rock Partners (ORP) have signed an …

MultiOmic Health and BIO4 Campus sign collaborative Memorandum of Understanding
MultiOmic Health (MOH), an artificial intelligence (AI)-enabled precision medicine biotechnology company and BIO4 Campus (BIO4), …






