Imagine watching helplessly as a loved one's strength fades, their speech becomes slurred, and their independence slips away due to ALS. It's a devastating reality, but what if we could intervene before those critical moments, offering a better quality of life? Researchers are now harnessing the power of in-home sensor technology and artificial intelligence (AI) to revolutionize ALS care, paving the way for earlier interventions and improved well-being.
Bill Janes, a dedicated occupational therapist and researcher at the University of Missouri, is leading this crucial effort. Having witnessed firsthand the devastating impact of amyotrophic lateral sclerosis (ALS), he's determined to find a better way to manage the disease. ALS, a progressive neurodegenerative disease, attacks the nerve cells responsible for controlling muscle movement. This leads to a gradual loss of strength, difficulty speaking and swallowing, and ultimately, problems with breathing.
But here's where it gets controversial... ALS manifests differently in each individual. Some patients experience a rapid decline, while others progress more slowly. This variability makes it incredibly challenging to provide consistent and effective care. How can doctors personalize treatment plans when the disease's trajectory is so unpredictable? This is the challenge Janes and his team are tackling head-on.
To bridge these gaps in care, Janes is collaborating with experts from Mizzou's School of Medicine and Institute for Data Science and Informatics to develop a smarter system for tracking ALS progression in real-time. Their innovative solution combines unobtrusive in-home sensors with the analytical power of artificial intelligence.
"Right now, we’re essentially blind to what’s happening between clinic visits," explains Janes, an assistant professor in Mizzou’s College of Health Sciences. "With these sensors, we can detect subtle shifts in health sooner—sometimes even before a patient feels them—and act before a crisis occurs." Think of it like having a vigilant, always-on health monitor in the patient's home, capable of identifying potential problems before they escalate.
The sensor technology itself isn't entirely new. Professor Emerita Marjorie Skubic at Mizzou’s College of Engineering and Professor Emerita Marilyn Rantz at Mizzou’s Sinclair School of Nursing originally developed these sensors to monitor the well-being of older adults living independently. These devices are designed to detect changes in behavior and physical activity, such as alterations in walking and sleeping patterns. By identifying these changes, healthcare providers can intervene early, potentially delaying or preventing serious health events like falls or hospitalizations.
Now, Janes and his colleagues are adapting these proven sensors to meet the specific needs of ALS patients. While the functional decline in ALS often mirrors that of older adults, it tends to progress much more rapidly and unpredictably. This requires a more sensitive and responsive monitoring system.
Currently, the team is focused on validating the accuracy of the sensor data, ensuring that it reliably reflects real-world changes in a patient's daily functioning. This involves meticulously comparing the sensor readings with clinical assessments and patient reports. And this is the part most people miss... Without accurate data, even the most sophisticated AI algorithms are useless.
The next phase of the project involves using the collected data to build predictive models. The data flows wirelessly from two small boxes placed in the patient's home, then securely transmits to university systems for analysis. Using machine learning, a branch of AI, the researchers are developing models to estimate each patient's score on the ALS Functional Rating Scale Revised (ALSFRS-R). This clinical tool is used to assess how ALS is impacting a person's daily abilities over time, including walking, talking, swallowing, and breathing. It provides a standardized way to measure disease progression.
Noah Marchal, a research analyst in the School of Medicine and a PhD candidate in health informatics at Mizzou’s Institute for Data Science and Informatics, is leading the data science efforts. "Our goal is to not just track changes after they happen; we’re also trying to see them in advance," Marchal explains. "For example, we want to be able to detect a problem in gait or respiration before it causes a fall or hospitalization." Imagine the peace of mind this predictive capability could offer to patients and their families!
When Janes recognized the potential of these sensors to transform ALS care, Marchal, guided by his advisor, Xing Song, an assistant professor of biomedical informatics in the School of Medicine, helped bring that vision to life.
The final stage of the project involves integrating the system directly into clinical workflows. The vision is that if the model predicts a concerning decline in a patient's health, a clinician will receive an alert. This would prompt them to check in with the patient, adjust medication, recommend assistive devices, or suggest further treatment.
Early feedback from participating families has been overwhelmingly positive. Many appreciate the sense of connection and peace of mind that the system provides, knowing that they are being monitored and that potential problems can be addressed proactively.
"Our vision is that one day clinicians will have a secure portal where they can view a patient’s daily health trends the way ICU teams monitor telemetry," Janes says. "It’s about giving people living with ALS—and their care teams—the information they need, when they need it."
While the current project is specifically focused on ALS, the underlying technology could be adapted to monitor other chronic conditions, such as Parkinson’s disease or heart failure. The possibilities are vast.
The study detailing this groundbreaking research has been published in the journal Frontiers in Digital Health.
This raises a critical question: Should this type of technology be universally available to all ALS patients, regardless of their location or socioeconomic status? And what about the ethical implications of using AI to predict health outcomes? Could this lead to biases or unintended consequences? What are your thoughts on using sensor technology and AI to improve ALS care? Share your opinions in the comments below!
