Algorithms & Actionable Insights Project

Unique integrated approach for truly innovative health solutions

Algorithms are the driving force in translating clinical data into actionable insights that are useful and meaningful for the patient and physician. With this last building block, Holst Centre closes the loop, allowing us to not only diagnose patients but also offer them optimal treatment.

What if wearable or implantable devices could tell a hemodialysis patient how much water to drink? What if these devices could prevent exacerbations with chronic patients, or help optimize a patient’s rehabilitation program? For these applications to become reality, we need smart algorithms that translate health data (from medical devices, wearables and implantables) into actionable insights.

Detecting fiducials

When you are turning data into insights, the first step is often to detect characteristic points, so-called fiducial points, in the data, such as the R-peak in an electrocardiogram signal. After annotating important fiducials in the data stream, you need algorithms to identify digital biomarkers that give information on one or several physiological systems in the body. For example, heart rate is a biomarker, extracted from the ECG signal that gives information about the patient’s health and physical condition. Other important digital biomarkers are inspiratory time and volume, and respiratory frequency for patients with a chronic lung disease.

The development of novel digital biomarkers is something we focus on. Examples of ‘standard’ biomarkers are heart rate, heart rate variability, skin temperature etc. But what if we could devise biomarkers for more complex things such as inflammation, oxidative stress or endothelial function and measure this in an effortless way? These biomarkers are important in chronic conditions such as autoimmune diseases and cardiovascular diseases.

Quality of the data is key

As important as identifying fiducials, defining digital biomarkers, and gaining insights from the data, is the focus on the quality of all these findings. We develop algorithms that indicate the quality of all these levels, which is important information for the physician when devising a strategy for the patient. This quality indication is of uttermost importance for measurements in the home setting, outside the controlled environment of the hospital, as well as for autonomous devices.

Unique integrated approach

What’s truly unique about Holst Centre, is that we offer in-house expertise on the complete process. In our studies, we use our own chips and wearable monitoring devices for ECG, skin temperature, bio-impedance etc. Although Holst Centre is best known for its semiconductor technology, an enormous amount of expertise in algorithms, AI and machine learning is also present. We develop both the hard- and the software and it is this integrated approach that has led to a unique set of expertise, which is key to develop truly innovative health solutions. An intense collaboration between hard-, software and application experts is mandatory, especially when more intelligence will be added to future wearable, insertable and implantable devices. Our validation-focused quality assessment in close collaboration with hospitals, results in reliable insights that enable us to close the loop in patient care.