Sign In

Health and wellness


Towards smarter healthcare through AI technologies

Ensuring high quality of care for the entire population with manageable costs requires that healthcare systems are completely re-invented and current processes are streamlined. We need to develop preventive health support with easy home diagnostics and self-monitoring solutions to affect a lasting behavioral change. A paradigm shift emphasizing participatory & preventive healthcare is needed. AI enabled technologies will help to optimise health care processes for ultimate resource efficiency. Smart usage of data will be in a decisive role in future health management. 

There’s no shortage of data in the modern healthcare setting. The problem is that we have had lots of data available, but it has been siloed in different databases, making it incredibly hard to combine for the purposes of making an objective diagnosis. Combining patient data with technologies like machine learning and artificial intelligence can quite easily produce a lot of personalized information, but it only becomes actionable if it is presented to healthcare professionals in a way they can quickly and easily understand.

What makes VTT unique is that we understand the needs of both healthcare professionals and medical device manufacturers alike. At the most basic level, a company or hospital may have a massive amount of data but lack the knowhow to process it with advanced methods. With secure access to their databases, we can transform the millions of data points into actionable information. Alternatively, a medical device manufacturer might want to cooperate in developing an algorithm to predict a certain disease or for provide disease management for a certain group of people. The toolbox of solutions VTT offers is designed to be applied in real life.

Preventive healthcare

The healthcare system of the future will have to be more proactive and health- (instead of disease-) oriented, involving citizens in a participatory role in health maintenance and risk assessment. 

Home diagnostics, data on e.g. nutrition, exercise, and the general status of health, can be used to create personalised profiles that function as the basis participatory lifestyle coaching. Together with genetics, this provides insights into the person’s health trends and risks while reducing healthcare costs and improving quality of living.

At VTT we have comprehensive experience e.g. in the following preventive healthcare areas:

  • Computerized memory tests and gait analysis methods for early detection of cognitive decline. Gait (walking style) analysis methods use wearable sensor data collected during walking.
  • Method for estimating fall risk. The method uses accelerometer signal and analyses the person’s gait. The method detects persons at risk of falling and allows prevention.
  • Web-based tool that combines data from various sources, and aggregates and analyses the data to provide wellbeing related profiles and visualizations. The users can transfer their data and profiles to other services. 

Methods for advancing personal health and empowering self-care

Digital services can be used for coaching behavior changes and supporting healthy lifestyles to improve personal health and empower self-care. Evidence-based methods of behavior change and user understanding are central in the design of these services, and automated personalized feedback and guidance based on sensor data and self-observations can be provided.


Predictive diagnostics and care

In Finland, the progressive Finnish Biobank Act and the forthcoming law on secondary use of health data form a firm basis for value creation. Kanta and Omakanta databases already form a digital link between the citizen and the patient.

Data lakes, collections of good quality patient data, are currently being developed by hospitals and private healthcare providers to enable clinical research using big data analytics. This will help gain knowledge on disease mechanisms, medication efficacy, treatment options and health risk profiling at individual level. This will provide better care quality, and new business opportunities for pharma and diagnostics industry, as well as software and service providers.

There is a need to predict health problems earlier and to improve disease management and rehabilitation as part of patient’s self-management and as part of clinical diagnosis and treatment. By improving the quality, analysis and use of patient-generated health data, a more complete view of patient status can be obtained. This will open new business opportunities, improve healthcare and its cost-effectiveness.

At VTT we have solutions and long experience in collecting and analyzing health data and its trends, detecting events etc. while dealing with practical issues such as, missing values, noise and artefacts etc. We are also specialized in:

  • Combining highly multi-modal data (images, time-series, lab values, text annotations)  in robust and understandable machine learning methods that help interpret complex patient data to support decision making 
  • Decision support systems for health data analysis, such as early diagnosis and differential diagnosis of complex diseases. VTT has applied these to e.g. neurological and cardiac diseases.
  • Biosignal analysis for next-generation patient monitoring systems.
  • Medical image analysis algorithms


Healthcare process optimisation

Today hospitals have trouble securing enough resources and capabilities. This increases the need for care journey optimisation. To maximize the efficiency of clinical resources, more timely decisions are needed in different clinical situations, together with increased home monitoring and providing hospital care at home (virtual hospitals). Patient profiling and categorisation of care needs require comprehensive medical histories and intelligent point-of-care tools. Effective decision-making requires extracting knowledge from vast amounts of different data sources.

However, health domain data is sparse and scattered. Efficient methods and service concepts are needed to realise the potential of data in the health policy making and allowing policy makers to make their decisions with a real knowledge instead of assumptions. This will enable better resource efficiency and improved clinical diagnosis with comprehensive, interoperable patient medical records and decision-support tools. Identifying not only current needs but predicting future needs and trends.

For the healthcare process optimization VTT offers:
  • Complete data integration system with a state of the art data virtualization system. A modern scalable analytics solution and an intelligent web interface with a visual analytics system
  • Interoperability with health care information systems
  • Systemic approach and tools for enabling data-driven decision making at policy level
  • Impact analysis


Wellness and wellbeing

Nowadays, wearable devices and smart phones come equipped with various sensors to enable people analyze their performance and track their progress towards personal goals. However, population-based physical activity detection is inaccurate and not personal. 

VTT has developed a deep activity algorithm, based on deep neural networks, that integrates general population data and machine learning to create a personalized movement model. The algorithm can be used to develop adaptive (personal) Health-on-the-Move applications and services. DeepActivity can also recognize activities that involve several different kinds of movements to recognize complex, composite activity patterns seen in sports such as soccer or basketball, where the player may be jumping, sprinting, and turning. 

Also the healthcare sector can benefit from this. In post-operative rehabilitation, for example, a device could accurately track the rate of improvement in a patient’s range of movements and alert doctors if things are progressing slower than expected. Insurance companies are also becoming more and more interested in personal activity trackers as an input to the risk assessment process for coverage. 


​​Interested? Find out more