Dubai, UAE — CHIL AI Lab, an African-led health technology company, has announced a breakthrough in breast cancer care. Their new AI platform can detect signs that a patient’s treatment is not working, much earlier than ever before. Instead of giving a simple “yes” or “no,” the system gives a confidence score, so doctors always know how sure the AI is.
The project is led by Dr. Nabuuma Shamim Kaliisa, who designed the platform to solve a painful problem as many patients wait up to six months just to find out if their treatment is working.
Most medical AI works like a “black box” giving an answer but doesn’t explain why. CHIL AI Lab’s platform is different. It measures how confident it is with every scan, working more like a trusted specialist than a machine.
Here’s what makes it stand out:
- Honest Answers: When the AI is unsure about a scan, it says so — and immediately flags the case for a doctor to review, rather than guessing.
- Early Detection: The platform can spot warning signs that treatment may not be working as early as the first 21 days — instead of waiting months.
- Built for Doctors: It gives oncologists a range of possibilities, helping them decide sooner whether to change a patient’s treatment plan.
Tested and Proven
The study ran for 24 months and included 306 patients across multiple cancer centers in Africa. The results showed that the AI’s early confidence scores accurately predicted how patients would respond to treatment by the end of their care.
“In oncology, an ‘I don’t know’ from a tool can be just as life-saving as a ‘Yes,’” said Dr. Nabuuma Shamim Kaliisa. “By building a system that can quantify its own certainty, we are giving doctors a tool they can actually trust. We are moving away from guessing and toward a future where we can pivot treatment the moment the math shows a high probability of failure.”
A Global Platform
The CHIL AI Lab team will present their findings at the upcoming World Health Assembly. Their work shows that advanced, life-saving technology can be built in Africa — and that it is urgently needed across emerging healthcare markets.
The team is now moving into the next phase, expanding the platform to cover more cancer types and improve its accuracy even further.
