image: Anderson Rocha, a professor at UNICAMP and coordinator of the ARC Viva Bem, gives his lecture at FAPESP Week London
Credit: Elton Alisson/Agência FAPESP
A wristwatch that can sense when the user is anxious, even before they realize it themselves. This concept, which sounds like science fiction, is becoming a reality in the laboratories of Viva Bem: Artificial Intelligence for Health and Well-Being. Viva Bem is an Applied Research Center (ARC) funded by FAPESP and Samsung at the State University of Campinas (UNICAMP) in the state of São Paulo, Brazil.
Researchers affiliated with the Viva Bem center have developed an artificial intelligence method that identifies states of anxiety with over 80% accuracy based on bodily signals captured by smartwatches.
The results of the study were presented by Anderson Rocha, a professor at UNICAMP and coordinator of the ARC, during FAPESP Week London, held June 2–4 in the British capital.
“We developed an initial technique, which has already been published, and now we’re refining a new one, which is currently being evaluated by Samsung,” Rocha told Agência FAPESP.
The technology integrates two types of data continuously collected by the watch: the electrocardiogram, which records the heart’s electrical activity, and accelerometry, which maps arm movements throughout the day. These signals form what the researchers call the user’s “data signature,” an individual pattern that the AI learns to recognize and monitor.
To teach the algorithms to distinguish between resting and anxious states, the team developed clinical protocols that induce stress in a controlled manner. In one test, participants are given the task of mentally calculating the result of multiplications such as 309 x 17 within 30 seconds while watching a countdown on the watch.
“Inevitably, people get anxious in this situation,” Rocha explains. “We measure how their bodies respond to this exercise and train the algorithms to identify it.”
The app is not intended to replace doctors or psychologists, the researcher emphasizes. The goal of the project is to provide a layer of proactive monitoring. If the watch detects recurring anxiety episodes, it will send an alert recommending that the user consult a specialist.
“The idea isn’t to make a diagnosis, but to serve as an alert tool,” Rocha emphasizes. The same logic applies to other conditions monitored by the project, such as hypertension, diabetes, Parkinson’s disease, and the risk of falls in older adults. The AI acts as a silent sentinel, leaving it up to the user to decide how to act on the information.
“The ultimate goal is that with the signals captured by smartwatches, we’ll be able to identify the early symptoms of different health conditions so that we can help people achieve a better quality of life,” Rocha stated.
The results of the project are still being evaluated and improved continuously. Once the results are deemed mature enough, authorization will be sought from relevant authorities, such as the Brazilian Health Regulatory Agency (ANVISA), to conduct tests with real users, said Rocha.
Synthetic realities
In the same lecture, Rocha presented the Horus project, which focuses on what the team calls “synthetic realities” – the universe of images, videos, and texts generated by artificial intelligence. The lab has developed tools that can detect deepfakes, as well as attacks via SMS and WhatsApp messages and falsifications in biomedical scientific publications. The lab can also track content linked to child trafficking and child pornography.
One of the solutions for identifying falsifications in biomedical publications is used by the U.S. government’s Office of Scientific Integrity and is available as open-source software. Another tool, designed for image verification, is used by Brazilian fact-checking agencies, such as Lupa, Aos Fatos, and G1. It has also been used to analyze visual records of recent conflicts in the Middle East, as reported by Reuters and Agence France-Presse.
For Rocha, health and the fight against misinformation converge around a single value: trust. “Human-centered AI is essential for strengthening resilience and well-being,” he said.
More information about FAPESP Week London is available at fapesp.br/week/2026/london.
About São Paulo Research Foundation (FAPESP)
The São Paulo Research Foundation (FAPESP) is a public institution with the mission of supporting scientific research in all fields of knowledge by awarding scholarships, fellowships and grants to investigators linked with higher education and research institutions in the State of São Paulo, Brazil. FAPESP is aware that the very best research can only be done by working with the best researchers internationally. Therefore, it has established partnerships with funding agencies, higher education, private companies, and research organizations in other countries known for the quality of their research and has been encouraging scientists funded by its grants to further develop their international collaboration. You can learn more about FAPESP at www.fapesp.br/en and visit FAPESP news agency at www.agencia.fapesp.br/en to keep updated with the latest scientific breakthroughs FAPESP helps achieve through its many programs, awards and research centers. You may also subscribe to FAPESP news agency at http://agencia.fapesp.br/subscribe