A team at the University at Buffalo published a comprehensive meta-review in NPJ Digital Medicine. The researchers screened about 5,000 peer‑reviewed studies and selected 60 that examined the integration of AI and wearable technology in diabetes care. Wearables such as continuous glucose monitors provide frequent readings, and AI models can recognise patterns and predict glucose changes before they happen.
The review reports several benefits. AI-enhanced wearables can predict glucose changes up to one to two hours ahead, which may help people keep steadier glucose control and receive personalised guidance that reflects daily routines, activity and sleep. These systems can also reduce clinician workload by organising large data streams and flagging what needs attention. For people with prediabetes, early use of wearables plus AI could support lifestyle changes and perhaps delay progression to diabetes.
However, the review lists key limitations: research is uneven, many AI models act as "black boxes," sample sizes are limited and demographic coverage is narrow. The authors say larger studies, better validation and more transparent models are needed before AI-enabled wearables become routine in clinical care. The study was supported by the American Diabetes Association, the National Institute of Diabetes and Digestive Kidney Disease, and the National Institute for Minority Health and Health Disparities.
Difficult words
- integration — bringing parts together to work as one
- wearable — an electronic device worn on the bodywearables
- recognise — see or find patterns in information
- personalised — made to match a person's needs or life
- clinician — a health professional who treats patients
- prediabetes — a health condition before diabetes develops
- demographic — relating to groups of people by characteristics
- validation — testing to make sure results are accurate
Tip: hover, focus or tap highlighted words in the article to see quick definitions while you read or listen.
Discussion questions
- Would you consider using a wearable that predicts glucose changes? Why or why not?
- What concerns do you have about AI models that act like "black boxes" in medical care?
- How might organising large data streams with AI change the work of clinicians in your country?
Related articles
African leaders urged to fix health financing at UNGA80
At the 80th UN General Assembly in New York, Obinna Ebirim urges African countries to press for fairer donor partnerships and to increase domestic health funding. He highlights staff shortages, weak infrastructure and the National Health Fellows Programme.
Rising Temperatures and Arsenic in Rice
A study shows that climate change may increase arsenic levels in rice, impacting health risks for consumers.
Sensors and AI to Monitor People with ALS at Home
Researchers at the University of Missouri combine in-home sensors and artificial intelligence to track daily changes in people with ALS. The system aims to detect problems early and to alert clinicians for timely action.
Preserving Bangladesh's Multilingual Diversity Through Digital Platforms
The Multiling.cloud project aims to protect endangered languages in Bangladesh by digitizing them. This effort is vital for cultural preservation and education.
India’s Space Missions and the Debate on Science Funding
India has launched a new solar probe while considering the impact on science funding. Scientists express concern over prioritizing space missions over fundamental research.
Nigeria to Produce 147 Million Test Kits for HIV, TB, and Malaria
Codix Bio in Nigeria will produce test kits for HIV, TB, and malaria to fill gaps from US aid cuts.