BioMediTech Research Groups

Personal Health Informatics

Group Leader: Senior Reseach Fellow Hannu Nieminen


About Us

Personal Health Informatics Research Group studies and develops solutions, which help citizens to better follow up their health and wellness status, detect and predict changes, and identify and implement concrete lifestyle changes towards a healthier and happier life. Our mission is to help to prevent and manage especially chronic diseases. Our technical research areas include mobile health, health monitoring technologies, data analysis and interpretation and decision support systems. Team was founded in 2012.

Research interests and expertise

Our current research focus is on utilizing the tools and methods of data science for analyzing and visualizing the health and wellness status and its predicted evolution. We utilize the techniques of cognitive computing to build decision support solutions for the health and wellness domain. We also develop signal processing and analysis solutions for wearable health sensors. Our research is done in close collaboration with health care professionals, behavioral scientists and companies.


One of our research focuses has been to build models of people’s everyday health behaviors, predict the behaviors and to find new information on causal relations between health behaviors and outcomes. We have analyzed and combined several data sets from a variety of health data repositories owned by the Finnish and international organizations and companies, with whom we collaborate. We have published several articles e.g. from the areas of alcohol effects on sleep quality, long-term variation patterns of weight, stress-recovery patterns in the working population.

In the Digital Health Revolution project we have researched the human-centric personal health data management, data privacy and re-use. We have been developing and implementing a new architecture for health data management utilizing the MyData principles. Linked to the project, also a TUT spin-off company focusing on wellness data integration was created.

We have conducted research on wearable sensors, with special focus on improving the accuracy of wearable optical heart rate measurement systems.

We have also researched the area of technology-assisted health coaching and developed in TEKES and EU projects a web-based tool health and wellness coaching targeted for preventive health care. The results of the project have been commercialized through the PHI team spin-off company Movendos Oy.

Currently we are in a H2020 project conducting research on utilizing cognitive computing for sepsis prediction in intensive care.

Collaboration offer and requests

We carry out several projects collaboratively with domestic and international partners, both industrial and academic. We are searching for collaboration in the area of utilizing and developing big data analytics to build predictive models of health-related everyday behaviors based on extensively collected, digital personal data sets including digital footprint, health records, health sensor data and genetic data. Target is to utilize these models for personalized care and for disease prevention.


Team has in its use a laboratory facility for measuring various bioelectric signals (e.g. ECG, EEG, EMG, EOG, GSR). Laboratory is suitable for example for comparing health and wellness sensor devices against gold standard measurements, for sleep research, for sports and exercise research and for usability studies.

Major Publications

  1. Helander E, Wansink B, Chieh A. Weight Gain over the Holidays in Three Countries. N Engl J Med 2016; 375:1200-1202.
  2. Föhr T, Pietilä J, Helander E, Myllymäki T, Lindholm H, Rusko H, Kujala UM. Physical activity, body mass index and heart rate variability-based stress and recovery in 16 275 Finnish employees: a cross-sectional study. BMC Public Health. 2016 Aug 2;16:701.
  3. Helander E, Kaipainen K, Korhonen I, Wansink B. Factors related to sustained use of a free mobile app for dietary self-monitoring with photography and peer feedback: retrospective cohort study. J Med Internet Res 2014;16(4)/ e109: 1-13.
  4. Honko H, Andalibi V, Aaltonen T, Parak J, Saaranen M, Viik J, Korhonen I. W2E – Wellness Warehouse Engine for Semantic Interoperability of Consumer Health Data. IEEE J Biomed Health Inform. 2015 Aug 18.
  5. Ledesma A, Al-Musawi M, and Nieminen H. Health Figures: an open source JavaScript library for health data visualization. BMC Medical Informatics and Decision Making Journal. DOI: 10.1186/s12911-016-0275-6. 22 March, 2016.
© 2019 | BioMediTech Finland. All rights reserved.