Blood Pressure

BP and Wearables: Advancing At-Home Monitoring

For the first time using data from wearables, researchers were able to predict patients’ blood pressure (BP) and create personalized recommendations to lower it.1 This study confirms the increasing importance of wearable devices in continuous health monitoring.

 

“Our experimental results demonstrate that the proposed approach is robust to different individuals and has smaller prediction error than existing methods,” the researchers wrote. 

IF YOU LIKE THIS, READ MORE...

 

Wearable sensor collects, tests sweat for cystic fibrosis, glucose levels

 

Nutritional Pearls: How Accurate is Your Wearable Activity Tracker?

To conduct their study, the researchers collected data on sleep, exercise, and BP from 8 patients over 90 days using a FitBit and wireless BP monitor. With this data, the researchers created a personalized treatment plan for each patient instead of generalizing treatment across all 8 patients.

 

Their proposed algorithm used Random Forest with Feature Selection and other machine learning methods to help them create personalized recommendations.

 

For instance, the researchers found that exercise impacted BP for one particular patient. Therefore, that patient was instructed to increase exercise. The following week at check-up, the patient’s systolic BP and diastolic BP had decreased significantly.

 

“This research shows that using wireless wearables and other devices to collect and analyze personal data can help transition patients from reactive to continuous care,” said Sujit Dey, who is co-author of the study and Director of the Center for Wireless Communications at UC San Diego’s Jacobs School of Engineering.2

 

“Instead of saying ‘My blood pressure is high therefore I’ll go to the doctor to get medicine,’ giving patients and doctors access to this type of system can allow them to manage their symptoms on a continuous basis.”2

 

—Amanda Balbi

 

References:

  1. Chiang PH, Dey S. Personalized effect of health behavior on blood pressure: machine learning based prediction and recommendation. to appear in IEEE International Conference on E-health Networking, Application & Services. http://cwc.ucsd.edu/sites/cwc.ucsd.edu/files/u209/Po-Han_%20Chiang_best-paper-ieee.pdf.
  2. Using personal data to predict blood pressure [news release]. La Jolla, CA: University of California, San Diego; October 4, 2018. https://ucsdnews.ucsd.edu/pressrelease/using_personal_data_to_predict_blood_pressure. Accessed October 5, 2018.