A new approach to dementia care

“A year after launching an ambitious research effort to support dementia patients and caregivers, UC Irvine nursing researchers have moved into real-world care settings, collecting data directly from patients and using AI-driven technology to better understand agitation, sleep disruption and fall risk. The interdisciplinary project – led by Adey Nyamathi, a Distinguished Professor in the Sue & Bill Gross School of Nursing, and supported by Amir Rahmani, professor of nursing and computer science, and the Susan and Henry Samueli Endowed Chair in Integrative Health – recently completed its initial pilot grant phase and is now preparing to submit a larger National Institutes of Health proposal to expand the work. Since this first story was published in 2025 , the researchers have partnered with two residential board-and-care facilities serving dementia patients to install a sophisticated multimodal monitoring system that includes cameras, microphones and physiological sensors. “We started collecting data in real dementia patients,” Rahmani said. “That’s been the biggest milestone.” The project focuses on detecting and easing agitation – one of the most common and dangerous behavioral symptoms associated with dementia. “Agitation is one of the major causes of falls and other complications,” Rahmani said. “If we can recognize when someone is becoming distressed and help calm them down, even temporarily, it can give caregivers time to intervene and potentially prevent catastrophic events.” To better understand those moments, the team equipped patient rooms with sensing technology to continuously monitor movement, speech patterns, sleep quality and physiological signals, such as heart rate and respiration. Researchers also analyze interactions between caregivers and patients to identify behavioral cues linked to emotional distress. The system’s artificial intelligence models evaluate more than just spoken words. They also examine vocal tone, speech frequency and communication patterns that may signal agitation or emotional changes. Early findings from the pilot study have revealed concerning trends around sleep quality. Researchers observed that many dementia patients experienced repeated sleep disruptions throughout the night, patterns that often appear connected to increased agitation and mood changes the following day. “We could see patterns emerge from both the camera data and the physiological data,” Rahmani said. “Sleep disturbances appear to affect mood, agitation and overall condition the next day.” Behind the scenes, researchers also spent months building secure infrastructure to protect patient privacy. Because the project collects highly sensitive audio, video and health data, the team developed its own internal server systems rather than relying on third-party cloud providers. “A lot of effort went into making sure everything is private and secure,” Rahmani said. “Only the research team can access the data.” Artificial intelligence remains central to the project’s long-term vision. Current AI models help researchers recognize emotional states, gait changes and behavioral patterns using audio and computer vision analysis. A future phase of the research will introduce generative AI capabilities to allow the robotic companion to engage patients in calming conversations modeled after successful caregiver interactions. The idea is for the system to eventually learn from real caregiving scenarios, including personal stories and conversational techniques to help reduce distress in dementia patients. That portion of the project is still in development, Rahmani said, because researchers need significantly larger datasets before training advanced generative AI models. The team is now seeking a multi-year NIH grant that would allow them to scale the project, validate the technology and continue developing intervention tools designed to support both patients and caregivers. While widespread use is still years away, Rahmani said the project is making important progress toward a future where AI-assisted technologies can help improve the quality of life for dementia patients and ease caregiver burden. “We’re now seeing how these systems can work in real environments with real patients,” Rahmani said. “That’s a critical step forward.”

Summary generated from the RSS feed of UC Irvine News. All article rights belong to the original publisher. Click through to read the full piece on news.uci.edu.