قوقل: ذكاء اصطناعي يفحص أشعة الصدر للسل في 45 ثانية، حتى لعمال منجم على عمق 4 كيلومترGoogle: AI screens chest X-rays for TB in 45 seconds, even for miners four kilometres underground

Google has described how it uses AI models for tuberculosis screening, a disease it says kills an estimated 1.23 million people a year. The bottleneck is that radiologists are scarce in many places, so many cases go undetected.

Pretoria-based Nexus AI turned Google's chest X-ray algorithms into a certified clinical tool (CE MDR class IIb) that screens X-rays in as little as 45 seconds. It now runs in about 40 healthcare facilities in South Africa, Sierra Leone and Côte d'Ivoire, with expansions underway in the Democratic Republic of the Congo, Zambia and Cameroon. More than 90 clinicians have used it to evaluate over 25,000 chest X-rays, cutting turnaround from weeks to under 45 seconds, with clinicians making the final decision.

The most striking example is a South African gold mine, four kilometres underground: portable X-ray kits with offline AI let miners be screened on site within seconds, and anyone flagged with presumptive TB can be referred straight away for confirmatory testing.

Google has also released open models such as MedGemma, which run on-device without internet access and have passed 10 million downloads, it says. Indonesia's Ministry of Health is fine-tuning MedGemma and MedSigLIP on local chest X-rays, with a goal of screening 50 million citizens a year, keeping patient data inside the country.