Smartphones can monitor patients with neuromuscular diseases, suggests study

In a study published in the New England Journal of Medicine, Delp, a professor of bioengineering, and his collaborators showed that a smartphone could do the job as well or better. With two smartphone cameras and a free app, they were able to replicate results from standard movement tests for two neuromuscular diseases and capture more detail about patients’ physical abilities.

“Our goal was to bring the world’s most sophisticated biomechanical modeling and computer vision to bear in order to match what’s happening on the drug development side,” Delp said.

Delp is the senior author of the study. Parker Ruth, a doctoral student in computer science at Stanford University, is the lead author.

Clinicians typically use a stopwatch to capture how long it takes people with movement-related conditions to complete specific tasks, such as standing up from a chair or walking 10 meters. Known as a timed function test, this method is quick and inexpensive, but it can’t detect subtle changes in how patients move, especially in diseases that progress slowly.

For a more detailed view, patients need to visit a motion analysis lab, where hourslong biomechanical assessments require highly trained technicians and equipment that costs hundreds of thousands of dollars. “The status quo is that very few people can have their motion measured, and this is rarely used clinically — usually between zero and once in a person’s lifetime,” Delp said.

To test whether mobile phones could do the job, Delp and his collaborators used up to three smartphone cameras to record nearly 130 people as they performed nine movements, such as a 10-meter run and calf raise. Two-thirds of participants had a neuromuscular disease — facioscapulohumeral muscular dystrophy (FSHD) or myotonic dystrophy (DM) — while the rest had no diagnosed movement problems. At the same time, clinical evaluators performed four traditional timed function tests. The process took an average of just 16 minutes.

Researchers converted the videos into 3D models using OpenCap, an open-source tool that Delp and his team at Stanford released in 2023. The software automatically created a “digital twin” of each participant, allowing the team to measure range of motion, stride length, speed and other aspects of movement. Researchers then translated the data into 34 features of movement that are relevant to FSHD and DM, such as how high patients lift their ankles while walking.

Based on the smartphone data, researchers inferred nearly identical time scores to those measured with a stopwatch. When a subset of participants repeated the tests the next day, the smartphone system proved just as reliable. “With just a video, you can reproduce what an experienced and busy clinician would do in a clinic,” Delp said.

A better diagnostic tool

The videos also revealed disease-specific movement patterns that timed tests can’t capture. For example, people with FSHD took shorter strides and lifted their ankles higher while walking, while those with DM had more difficulty rising from a chair. Based on the footage, a computer model could identify the disease a person had with 82% accuracy, compared with 50% accuracy for the stopwatch method.

The findings suggest that analyses once confined to specialized labs can now be done quickly, anywhere and for free.

“It’s really encouraging,” Delp said. “By democratizing access with smartphone videos, we think we’ll be able to detect movement disorders for free in the community. We can detect diseases earlier so patients can seek treatment sooner or participate in drug trials earlier.”

Delp and his team have begun examining how tools like OpenCap can be incorporated into clinical trials. His hope is that this approach will make measurements of therapies for neuromuscular diseases more precise, accessible and easy to implement. “We’ll have more sophisticated measures to see if therapies are working,” he said.

In the meantime, thousands of labs around the world are already using OpenCap to assess conditions such as cerebral palsy and arthritis. Germany’s national volleyball team, for example, used the tool to evaluate sports injuries in 160 athletes. “It used to take them years to get that kind of data, and with OpenCap they did it in one season,” Delp said. “They’re gaining insight into how they can perform better, avoid injury and improve faster.”

Delp emphasizes that further research is needed to ensure the tool’s accuracy for each new application. Still, he believes the technology represents the future of how doctors diagnose and track movement disorders. “This method of accurately and rapidly assessing movement is on the verge of transforming multiple fields,” he said.

Scott Uhlrich, who earned a PhD at Stanford University and is now assistant professor at the University of Utah, is also a first author on the study. Stanford Medicine’s John Day, MD, PhD, professor of neurology, and research scientist Tina Duong, PhD, and their team also played a major role in the study.

Reference: Parker S. Ruth, B.S., Scott D. Uhlrich, Ph.D., Constance de Monts, D.P.T., Antoine Falisse, Ph.D., Julie Muccini, M.S., O.T.R./L., Sydney Covitz, M.S. , Shelby Vogt-Domke, B.S., John Day, M.D., Ph.D., Tina Duong, P.T., Ph.D., and Scott L. Delp, Ph.D., NEJM AI 2025;2(9),DOI: 10.1056/AIoa2401137.