GaitTrack app makes cellphone a medical monitor for heart and lung patients

May 9, 2014

(Credit: University of Illinois)

By simply carrying around their cellphones, patients who suffer from chronic disease could soon have an accurate health monitor that warns their doctors when their symptoms worsen.

GaitTrack, an app developed by researchers at the University of Illinois at Urbana-Champaign and the U. of I. at Chicago, doesn’t just count steps. It uses eight parameters to perform a detailed analysis of a person’s gait, or walking pattern, which can tell physicians much about a patient’s cardiopulmonary, muscular and neurological health.

Led by Bruce Schatz, the head of Medical Information Science and a professor of Computer Science at the U. of I., the team published its findings in the journal Telemedicine and e-Health.

“Fitness apps and devices are tuned for healthy people,” said Schatz. “They cannot accurately measure patients with chronic disease, who are the biggest medical market. A pedometer is not a medical device. But a cheap phone with GaitTrack software is.”

According to Schatz, gait is sometimes called the “sixth vital sign” — after temperature, blood pressure, heart rate, respiratory rate and blood oxygen level. Gait speed involves several systems of the body working together in coordination, so changes in gait can be a sign of trouble in one or more systems.

Doctors often use an assessment called the six-minute walk test for patients with heart and lung disease, such as congestive heart failure, chronic obstructive pulmonary disease (COPD) and asthma. Patients with chronic disease often cannot be measured with typical pedometers since they tend to walk with shorter, more careful strides, or to shuffle, so specialized medical accelerometers are used.

The Illinois team used GaitTrack to administer six-minute walk tests to 30 patients with chronic lung disease and found that it monitored more accurately — and more cheaply — than the medical accelerometers. In addition, they discovered that analysis of the gait data could predict lung function with 90 percent accuracy, within an age group.

Gait parameters used for gait model in the statistical machine learning algorithm, recorded from the spatiotermporal phone motion and transformed into body motion for gait analysis (credit: Joshua Juen et al., Telemedicine and e-Health)

“The original plan was just to validate the software against the standard medical walk test,” Schatz said, “but we looked at other data and found that it matched well with a pulmonary function test called FEV1.

“Predicting FEV1 is useful because that’s the standard number used to determine treatment. That’s worth a lot to a health system.”

Schatz envisions the GaitTrack app running constantly in the background as a patient carries a phone. The phone would periodically collect data, analyze it and keep tabs on the patient’s status, alerting the patient or patient’s doctor when it detects changes in gait that would indicate a decline in health so that treatment could be adjusted responsively.

The researchers now are testing GaitTrack in larger trials within health systems. Schatz hopes to have the app available for download within months.

The U.S. Department of Agriculture supported this work in part. Schatz will present this work at the annual meeting of the American Telemedicine Association this month.

Abstract of Telemedicine and e-Health paper

We have developed GaitTrack, a phone application to detect health status while the smartphone is carried normally. GaitTrack software monitors walking patterns, using only accelerometers embedded in phones to record spatiotemporal motion, without the need for sensors external to the phone. Our software transforms smartphones into health monitors, using eight parameters of phone motion transformed into body motion by the gait model. GaitTrack is designed to detect health status while the smartphone is carried during normal activities, namely, free-living walking. The current method for assessing free-living walking is medical accelerometers, so we present evidence that mobile phones running our software are more accurate. We then show our gait model is more accurate than medical pedometers for counting steps of patients with chronic disease. Our gait model was evaluated in a pilot study involving 30 patients with chronic lung disease. The six-minute walk test (6MWT) is a major assessment for chronic heart and lung disease, including congestive heart failure and especially chronic obstructive pulmonary disease (COPD), affecting millions of persons. The 6MWT consists of walking back and forth along a measured distance for 6 minutes. The gait model using linear regression performed with 94.13% accuracy in measuring walk distance, compared with the established standard of direct observation. We also evaluated a different statistical model using the same gait parameters to predict health status through lung function. This gait model has high accuracy when applied to demographic cohorts, for example, 89.22% accuracy testing the cohort of 12 female patients with ages 50–64 years.