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
Dementia rising in Africa as researchers seek answers
Dementia is increasing in Africa as populations age. Research and evidence in the region are limited, so scientists study genetics, new detection tools and community measures while working with traditional healers to reduce stigma.
Wearable 10‑Minute Antibody Sensors from University of Pittsburgh
Researchers at the University of Pittsburgh made a wearable biosensor that detects antibodies in interstitial fluid in 10 minutes without a blood draw. The tiny carbon nanotube sensors are highly sensitive and the work appears in Analytical Chemistry.
