Doctors can monitor the status cancer patients receiving chemotherapy using the sensors in smartphones and an algorithm that detects worsening symptoms based on objective changes in patient behavior, according to a new study.
The findings indicate that worsening symptoms during cancer treatments can be detected using smartphones that patients likely already own and use. Real-time estimation of symptoms and side effects could provide an opportunity for doctors to intervene earlier between clinic visits, preventing unnecessary physician or hospital visits and improving patient quality of life.
For the study, which appears in the Journal of Medical Internet Research, researchers enrolled 14 patients who were undergoing chemotherapy treatment for gastrointestinal cancer at the University of Pittsburgh Medical Center Hillman Cancer Center.
Researchers had patients carry a smartphone for four weeks as they went about their daily lives. Smartphone software the researchers developed passively and continuously collected data on behavior patterns, such as the number of calls or texts sent and received, smartphone apps used, and the movement and location of the phone.
“…on days when the patients reported worse-than-average symptoms, they tended to spend more time being sedentary, moved the phone more slowly, and spent more minutes using apps on the phone.”
Researchers asked the patients to rate the severity of 12 common symptoms, such as fatigue and nausea, at least once a day. They would classify each day as either a “higher-than-average burden,” “average burden,” or “low burden” day.
Researchers then used the data collected from the smartphone to develop an algorithm that could identify and correlate the patient’s “high-symptom,” “average-symptom,” and “low-symptom” days with 88 percent accuracy.
“We found that on days when the patients reported worse-than-average symptoms, they tended to spend more time being sedentary, moved the phone more slowly, and spent more minutes using apps on the phone,” says lead author of the study Carissa Low, assistant professor of medicine and psychology at the University of Pittsburgh.
“Collecting these objective behavioral measures from smartphone sensors requires no additional effort from patients, and they could prove beneficial for long-term monitoring of those undergoing arduous cancer treatments or those with other chronic illnesses,” Low says.
The researchers are conducting follow-up studies to determine whether the same passive sensing approach can be used to identify complications following cancer surgery. They are also are working with health care providers to understand how to integrate this data into the workflow of clinical care.
The National Cancer Institute and a Manners Faculty Development Award from the University of Pittsburgh Center for Social and Urban Research funded the work.
Source: University of Pittsburgh