Using Personal Data to Predict Blood Pressure – ScienceDaily

Their work received the title of Best Paper at IEEE Healthcom 2018. To the knowledge of the researchers, this is the first work of investigation on the daily forecast of blood pressure and its connection with health-related behavior data collected by wearable devices.

When doctors tell their patients to make a lot of important changes in their lifestyle – exercise more, sleep better, reduce their salt intake, and so on. – This can be overwhelming, and compliance is not very high, said Sujit Dey, co-author of the Paper and director of the Center for Wireless Communications of the Jacobs School of Engineering at the University from San Diego, San Francisco, where he is a professor in the Department of Electrical and Computer Engineering.

"And if we could identify the health behavior that has the most impact on an individual's blood pressure, and ask him to focus on that goal," Dey asked.

Dey and his co-author, Po-Han Chiang, a graduate student in the Mobile Systems Design Laboratory of the Department of Electrical and Computer Engineering at the Jacobs School of Engineering at the University of San Diego, collected data on sleep, exercise and blood pressure of eight patients for 90 days. using a FitBit Charge HR and Omron Evolv wireless blood pressure monitor. Using machine learning and this data from portable devices, they developed an algorithm to predict users' blood pressure and to indicate which specific health behaviors they have. affect the most.

This study confirmed the importance of personalized data over generalized information. While many health databases add large amounts of patient data in a single model, taking all patients into account for health-related suggestions, the personalized information in this study was more effective . For example, the blood pressure of a subject was most affected by the number of minutes he was sedentary throughout the day. Changing this factor had a significant impact, lowering their mean systolic blood pressure by 15.4% and their diastolic blood pressure by 14.2% in one week. For another subject, the time they went to bed was the most important factor in reducing their blood pressure based on their historical data. When the person went to bed 58 minutes earlier than the previous week, his systolic blood pressure dropped 3.6% and his mean diastolic blood pressure was 6.6% from the previous week.

"This research shows that the use of wireless handheld devices and other devices to collect and analyze personal data can help patients make the transition from responsive care to continuing care," he said. Dey. "Instead of saying," My blood pressure is high, so I'm going to get medicine from the doctor, "because giving patients and doctors access to this type of system can help them manage their symptoms on an ongoing basis."

Dey and Chiang have recently teamed up with UC San Diego Health clinicians and are working to test their predictive model on a larger sample, to plan a day in advance and study the study. Long-term effect of health behaviors on blood pressure.

This research was conducted as part of the Connected Health program of the Center for Wireless Communications, supported by industry partners including Kaiser Permanente, UC San Diego Health, Samsung Digital Health and Teradata.

Source of the story:

Material provided by University of California – San Diego. Original written by Katherine Connor. Note: Content can be changed for style and length.