Master Data Science HSLU - Health_student projects
SUGAR-SWEET TECHNOLOGIES
Perfectly placed to shape the future with Data Science

Info-Events | Sign up now!

Data Science and Health How data helps you get well – and stay well

Whether someone struggles with diabetes, recovers from a stroke, or seeks to improve their emotional wellbeing as an older person, the effective use of data can boost not only treatment quality but also allow for simpler and more personalised care. Three groundbreaking projects from our Master's programme in Applied Information and Data Science explain how this works.

Info-Events | Sign up now!

Fastlinks:
Blood glucose testing | Stroke rehabilitation | Chatbot for elderly
Programme Information & Contact

Blood glucose testing

Could we do it without pricking?

Around half a million people in Switzerland have diabetes and have to measure their blood sugar regularly to avoid dangerous hypoglycemia. So far, this meant taking blood samples or relying on a device attached to the body, which naturally raises the question of whether smartwatches and similar devices that many people use day and night anyway can be programmed to warn them against hypoglycemia. Yasmine Mohamed, a graduate of the programme, used health data obtained from patients' Apple Watches, glucose meters and diary entries to train machine learning models. She then designed algorithms that could provide non-invasive warnings about hypoglycemia. When integrated into smartwatches, such algorithms could offer people with diabetes a further tool to help them best manage their health in daily life.

Yasmine Mohamed Portrait

«The ubiquitous use of smartwatches allows us to collect an enormous amount of health data, which we can use to train machine learning models to recognise the indications of hypoglycemia and warn the person then.» (Yasmine Mohamed)

 

Yasmine Mohamed Case Design

«Working with this type of data was challenging because hypoglycemia, fortunately, does not occur so often. This means that for every data point representing hypoglycemia, 100 other ones were irrelevant. This imbalance makes it hard to produce models.» (Yasmine Mohamed)

Do you want to know more about Yasmine's research project? Find the full interview here. 

Master Data Science HSLU - Info-Events - Register now

Stroke rehabilitation

Can sensor data shorten rehab after a stroke?

A stroke can turn our life upside down without any warning. That's why it's so important to provide comprehensive support to stroke victims to help them resume their everyday lives as quickly as possible. Daniele Buson, a graduate of the Master's programme in Data Science, is passionate about SmartVNS, a brain stimulator that stroke victims can wear in the ear during everyday activities to speed up their recovery. Daniele is developing a solution that digitally harnesses the vast amount of data from physical devices and makes it available on a treatment platform. This will enable stroke victims to benefit from state-of-the-art neuroscience rehab at home that is personalised, professionally supported, and available at a reasonable cost.

Daniele Buson_ Applied Data Science Masterabsolvent

Daniele, what steps did you take to come up with this digital solution?

«Creating a digital solution starts with understanding the problem, identifying the needs of everyone involved, and ensuring that we address patients as well as therapists. Once we clarified the requirements, we set out to develop the solution through iterative coding and discussions about the best way to align our solution with these needs.»

Master Data Science HSLU - Info-Events - Register now

Chatbot for elderly

How can a chatbot be used to support older people?

Older people who feel lonely and socially isolated cannot or do not always want to get help and may be reluctant to open up to others. Current AI language assistants are learning fast to understand people's emotions and address their needs. This is also the case with the chatbot Dr Guang Lu and several Applied Data Science students developed. The innovation of this system is its ability to combine rule-based, retrieval-based and generative responses and to select the best one in each case – all in a single chatbot. Depending on the nature of the conversation, the chatbot can then either automatically respond with pre-defined phrases that match the older person's context and emotional state or intelligently generate phrases and matching emotions by using the trained NLP models.

Dr Guang Lu, how did you come up with the idea for this chatbot?

quote
I came up with the idea during the pandemic when I saw how many people, especially older persons, were isolated at home and had to face major mental health problems alone. I then naturally thought of ways to develop a chatbot or digital companion to help them alleviate loneliness and social isolation.

To what extent were older persons involved?

quote
The organisations for older persons in the Lucerne area included Viva Luzern, Spitex Kriens, and Luzern60Plus, all of which were involved closely in the project and included in the workshops on designing the chatbot.

What's the next step?

quote
Our goal is to develop the chatbot into a digital companion with more comprehensive functions. However, for this we need additional resources, and we are thus applying for funding from the Velux Foundation and Innosuisse.

The project team

Programme Information | Contact | Info-Events

Interested in the MSc in Applied Data Science and AI? Visit our Info-Events. We look forward to meeting you!

Please contact us if you have any questions about your studies:
Tel.: +41 41 228 41 30
E-Mail: master.dai@hslu.ch 

Further links to the programme:
→ Generalist profile
→ Career profiles and study insights
→ Our Lecturers
→ Course structure and modules
→ Working and studying
→ Admission and registration
→ FAQ