Seed project: Development of an intelligent wearable – the DIWAH study

The overall goal of the research in this seeding project within the Linnaeus University Center for Data Intensive Sciences and Applications (DISA) is to combine the strengths of the commercial portable products with the products used in research and with the support of modern data processing methods to increase the knowledge of physical activity and health-related variables. The combination of information from the accelerometer (biomechanics) and heart rate from the optical sensor (physiological response) improves the predictions of intensity and related energy expenditure linked to physical activity at the individual level.

Project information

Development of an intelligent wearable to assess physical activity and health related variables – the DIWAH study
Patrick Bergman, Alisa Lincke, Welf LöweTobias Ohlsson, Fredrik Ahlgren, Cornelia Witthöft, Muhammed Hefni, och Haris Pojskic
Project period
February 2023 – May 2023
Final report
Linnaeus University Centre for Data Intensive Sciences and Applications (DISA)
Core research areas
E-health, Health Informatics, Computer Science
Research groups
E-health – Improved Data to and from Patients
Data Intensive Sciences and Applications (DISA)

More about the seed project

Physical activity is one of few behaviors that a human can change on its own to a low cost and that simultaneously confers health benefits.  One of the many diseases that physical activity has a positive influence on is high blood pressure. High blood pressure is the single largest risk factor for mortality and morbidity globally, hence there are several advantages to prevent high blood pressure and once it is manifested, to treat it.

Lifestyle treatment, including physical activity, is the first option to treat mild to moderate levels of high blood pressure. However, it is difficult for individuals to estimate how active they should be and it is even more difficult for health professionals to estimate the activity of a patient and evaluate their treatment. In part, this depends on that individuals in general do not know how active they are, and that blood pressure normally is measured at the clinic with long periods between the measurements.

During the last decade new methods to assess both physical activity and blood pressure have been developed, and a complete explosion of different wearables (Smart watches activity armbands etc) have emerged. Wearables are equipped with several sensors that can assess different aspects of physical activity such as steps and heart rate but also blood pressure, oxygen saturation and other health related variables. Thus, the wearables can be viewed as a Swiss army knife with a lot of tools in one device.

Today, wearables have several limitations that makes them unsuitable for use. Among the most important is their lack of validity, especially for a clinical population. Nor are they particularly ’’intelligent’’ in that they can’t provide a suitable dose of physical activity given the present health status of the individual. However, the technological evolution together with modern artificial intelligence creates a good foundation to do just that, i.e., model and learn from the real-time association between physical activity and blood pressure and based on that make suggestions to optimize the blood pressure of an individual. In this seed project we aim to take the first steps towards creating algorithms based on sensor data from wearables to in real time without human involvement suggest an individually tailored physical activity dose to optimize the blood pressure – an ePhysiotherapist. 

In this seed project we will, based on a maximal aerobic exercise test (from rest to maximal exertion), create a small training data set (n~10) from which we will sample and process sensor data and compare them against golden standard methods for physical activity, heart rate and blood pressure and thus being able to

  • Evaluate at least two open-source wearables in their ability to assess physical activity, heart rate, and blood pressure
  • Evaluate which AI methods are most accurate in assessing physical activity, heart rate, and blood pressure

In addition, we will develop the entire research protocol and apply for ethical permission. Together these steps will increase our ability to compete for research grants that can lay the foundation for the entire project.

The research in the seeding project is part of the research in the research groups E-health – Improved Data to and from Patients and Data Intensive Software Technologies and Applications (DISTA) and by Linnaeus University Center for Data Intensive Sciences and Applications (DISA).

What is a seed project?

A seed project is a minor project funded by a knowledge environment or a research group at the university. The aim is to launch and promote excellent research. Depending on the financier, a seed project may be to idenfify new or deepen existing collaborations, preferably cross-disciplinary ones, to explore possible research issues in a feasibility study, to collect empirical material, or to write an application for external funding.

DISA's seed projects

Learn more about the seed project concept and DISA's other seed projects.