Serious illnesses like ALS don’t just change test results—they quietly reshape a person’s entire daily life, moment by moment. And this is the part most people miss: tiny changes at home, often invisible to doctors between visits, could be the key to earlier help, fewer emergencies, and a better quality of life.
A new way to support ALS patients
Researchers are now blending smart in-home sensors with artificial intelligence to keep a closer eye on how people with amyotrophic lateral sclerosis (ALS) are really doing day to day. Instead of relying only on occasional clinic visits, this approach tracks subtle shifts in health and function at home, opening the door to earlier interventions and more personalized care.
Bill Janes, a licensed occupational therapist and researcher at the University of Missouri, has made it his mission to improve life for people living with ALS. In his work, he has watched how this condition can gradually strip away strength, speech, and independence—often faster than families and care teams can respond.
Understanding ALS and its challenges
ALS attacks the nerve cells that control voluntary muscle movement, leading to weakness and difficulties with speaking, swallowing, and breathing. But here’s where it gets controversial from a care-planning perspective: ALS does not follow a single predictable pattern—some people decline very quickly, while others lose function much more slowly.
That unpredictability creates large gaps in care, because traditional models depend heavily on periodic clinic checkups that may miss important changes happening at home. Janes and his colleagues want to shrink those gaps by using technology to see what’s happening between visits, not just on the day of the appointment.
Building smarter, real-time monitoring
To do that, Janes is collaborating with experts at Mizzou’s School of Medicine and the Institute for Data Science and Informatics to develop a smarter, real-time system for tracking ALS progression. Their solution combines discreet in-home sensors with AI tools that can interpret patterns in the data and highlight early warning signs.
As Janes explains, clinicians are largely “blind” to what patients experience in their own homes between appointments, especially when symptoms change gradually. The sensor system is designed to detect very subtle shifts in a person’s health—sometimes before the patient notices them—and give care teams a chance to act before a crisis, like a fall or a respiratory emergency, occurs.
How the sensor technology started
The sensor technology itself is not entirely new. Professor Emerita Marjorie Skubic from Mizzou’s College of Engineering and Professor Emerita Marilyn Rantz from the Sinclair School of Nursing originally created these in-home systems to monitor older adults who live independently.
These devices can pick up changes in daily behavior and physical activity, such as walking speed, movement patterns, and sleep quality. When something shifts in a concerning way, the system can prompt health care providers to step in sooner, sometimes delaying or even preventing serious events like falls or hospitalizations.
Adapting sensors specifically for ALS
Now, Janes and his team are tailoring this technology for people with ALS, whose decline can resemble that of older adults but tends to move faster and in more unpredictable ways. That makes responsive, data-driven monitoring especially valuable, because waiting for obvious symptoms can mean missing a critical window for intervention.
At the current stage, the researchers are focused on validating that what the sensors “see” truly reflects real-world changes in how patients function throughout the day. Once they are confident in that link, they plan to analyze the data with predictive modeling to forecast future changes more accurately.
What happens to the data?
In the home, the system uses two small boxes that wirelessly collect and transmit sensor data without disrupting the patient’s normal routine. That information is securely sent to university systems, where researchers analyze it while protecting patient privacy.
Using machine learning, a branch of artificial intelligence, the team builds predictive models to estimate each patient’s score on the ALS Functional Rating Scale Revised (ALSFRS-R). This widely used clinical tool tracks how ALS affects everyday abilities—such as walking, talking, swallowing, and breathing—over time, so estimating it continuously from home data could be a game changer.
The data science engine behind the project
Leading the data science side of the project is 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. His work focuses on turning raw sensor readings into meaningful, actionable information that clinicians can use.
Marchal emphasizes that the goal is not just to document changes after they occur, but to anticipate them. For instance, if the system detects early signs of a gait problem or subtle respiratory changes, it could flag them before they lead to a fall, a serious breathing issue, or a hospital stay.
From idea to implementation
When Janes recognized that the sensor system used with older adults could be adapted to transform ALS care, Marchal helped translate that vision into a working research project. He did so with guidance from his advisor, Xing Song, an assistant professor of biomedical informatics in the School of Medicine.
This collaboration blends clinical expertise, engineering, and data science—three areas that do not always communicate smoothly in traditional health care settings. And this is the part most people miss: truly innovative care often happens at the intersection of disciplines, not within a single specialty.
Bringing tech into everyday clinical workflows
The final goal is to integrate this system seamlessly into routine clinical practice, rather than keeping it as a separate research tool. In practical terms, that means building processes where clinicians can receive clear, timely alerts and use them to guide decisions.
If the predictive model signals a worrying decline, a clinician might be notified to check in with the patient sooner than planned. They could adjust medications, recommend assistive devices like walkers or communication tools, schedule respiratory evaluations, or refer the patient for additional therapies or support services.
How patients and families feel about it
Early feedback from families taking part in the project has been encouraging, with many saying the system gives them a stronger sense of connection to their care team. Instead of feeling alone between appointments, they know someone is virtually “keeping an eye” on how things are going.
That added peace of mind can make a big emotional difference for both patients and caregivers, who often worry about missing early signs of decline. A system that quietly tracks trends in the background may help them feel more supported and less anxious about what might happen between clinic visits.
A vision for ICU-level insight at home
Janes describes a future in which clinicians log into a secure portal to view daily health trends for their ALS patients, much like intensive care unit teams monitor telemetry data in real time. Imagine being able to see changes in mobility, sleep, or breathing patterns at a glance, rather than waiting for a patient to report them weeks later.
At its core, the project is about giving people with ALS—and the professionals who care for them—the right information at the right moment. That knowledge can inform smarter decisions, timelier support, and more personalized strategies to maintain independence for as long as possible.
Beyond ALS: a broader impact
Although this particular study centers on ALS, the underlying technology could be applied to many other chronic conditions, such as Parkinson’s disease or heart failure. These conditions also involve gradual changes in movement, sleep, and daily functioning that are often missed until they cause a serious event.
Using similar sensor-and-AI systems, health teams could monitor these patients remotely and respond earlier, potentially reducing hospitalizations and supporting safer independent living. That raises an important, and somewhat controversial, question: are we moving toward a future where continuous remote monitoring becomes a standard expectation for chronic care, and if so, how should privacy, autonomy, and consent be handled?
Where the research appears
The findings from this project are published in the journal Frontiers in Digital Health, highlighting the growing role of technology-driven solutions in modern medicine. The work is affiliated with the University of Missouri, which has been investing in cross-disciplinary efforts to engineer smarter, more responsive care models for complex conditions like ALS.
So what do you think: should continuous in-home monitoring powered by AI become a normal part of ALS and chronic disease care, or does it feel like a step too far toward surveillance in the home? Do you see this as empowering, intrusive, or something in between? Share where you stand—would you welcome this kind of system for yourself or a loved one, or would you draw the line somewhere else?
