AI is already being used for tasks such as image analysis, predictive analytics, patient monitoring and automated surgery. But in the near future, AI could also help doctors diagnose serious illnesses more easily and become an important tool for improving mental health care.

Fehmi Ben Abdesslem is a senior researcher in Artificial Intelligence at RISE. He has 20 years' experience as a data science researcher, working with many different types of data to generate new knowledge, particularly using machine learning.

"There are many potential benefits of using AI in medicine and healthcare, such as improving diagnostic accuracy and developing personalised treatment plans. AI can also be used as a tool for early detection of diseases and to improve efficiency in clinical settings," says Fehmi Ben Abdesslem.

Personalised care through AI

The development of AI has opened the door to new ways of conducting research studies. Image recognition, for example, has taken a giant leap forward in the last decade. Thanks to deep learning techniques, computers can now recognise objects with very high accuracy (see fact box).

Another area where AI can become a force for innovation – and perhaps ultimately help save lives – is mental health.

"For example, by allowing AI to sift through large amounts of data, doctors can get important clues about the type of medicine or therapy best suited to a patient, which could lead to a faster recovery. Because AI can be trained on huge amounts of data, we also hope that machine learning can be used to prevent suicide," says Fehmi.

A collaboration between Psykiatri Sydväst, Region Stockholm and RISE is investigating whether AI can improve cognitive behavioural therapy at the individual level. Using data from thousands of patients, AI will help a therapist assess the impact of therapy on the patient, with the aim of making it easier to individualise therapy early in the course of treatment. In addition, the team hopes that AI will be able to identify which patients may need more help after therapy.

Another example is a collaboration between RISE and the Faculty of Brain Sciences at UCL (University College London) in the UK, which used AI to compare the individual effects of different types of psychotropic drugs for bipolar disorder, using data from Sweden, the US, the UK, Taiwan and Hong Kong.

"At the moment, we don't know why one drug works better than another. By building machine learning models, we are investigating whether AI can recommend which drug is best for a person based on their specific condition."

We aim to build long-term relationships and collaborations that can make a difference to people's health and well-being.

Fighting suicide with AI

In the near future, machine learning will hopefully also become a tool for predicting suicide.

"800,000 people around the world take their own lives every year. What if data on their DNA could give us clues about risk factors and, in the long run, prevent suicide?," says Fehmi Ben Abdesslem.

The American Foundation for Suicide Prevention, Karolinska Institutet, the Department of Genetics at the University of North Carolina and RISE have launched a joint project to create the world's largest collection of data on suicide. The aim is to be able to identify genetic and environmental risk factors for suicide for prevention purposes.

The idea is to let AI sift through a huge amount of data, with instructions to look for all kinds of environmental variables and genetic variants and risks that can be linked to suicide.

"Previous studies have shown that our DNA may play a role in increasing the risk of suicide. Since we take a blood sample from all citizens when they are born in Sweden, we have a unique DNA database that can be used to advance suicide prevention research worldwide," says Fehmi Ben Abdesslem.

Addressing ethical issues

In order to develop a more digitalised, preventive and personalised healthcare system, many factors need to be ensured. There are several ethical challenges, such as how to obtain consent from individuals, how to counteract algorithmic bias, and how best to protect patient privacy.

Access to high-quality data is a crucial piece of the puzzle, but logistics in the form of continuous monitoring and updating of AI systems also need to be in place to scale up the safe use of AI.

Fehmi stresses the need for more use cases and more research. Interdisciplinary collaboration between different parties is crucial for the way forward.

"We are looking for long-term relationships and collaborations that can make a difference to people's health and well-being," says Fehmi Ben Abdesslem.

"We face a major demographic challenge in Europe. In Sweden, the municipality of Höganäs is experiencing a steeper curve than the rest of the country. We have fewer and fewer residents of working age and more and more who need our support. We talk about this and work on the issue all the time," says Viweca Thoresson, CEO of Höganäs Omsorg.

The Skåne municipal care company is one of 14 project partners in the North Sea region participating in a project that addresses precisely this issue – meeting the challenges facing the care sector. The aim is to enable more elderly people to continue living at home for as long as possible. The ACE project, Accelerating the Home Care Innovation Ecosystem, brings together the public sector, business, civil society and academia in the various countries.

"What we do is bring together all stakeholders so that they can be more successful in introducing digital solutions and services in elderly care," says Mona Jonsson, responsible for communication regarding ACE at RISE, which is the lead partner for the project.

“A great learning journey”

Höganäs Omsorg sees the international aspect of ACE as absolutely essential. The challenge they face is not an isolated Swedish problem, nor can it be solved by Swedish municipalities on their own.

“The ACE project is an opportunity for us to look beyond Sweden. What are others doing? What solutions are others working with that we can also use? What working methods can we adopt? This is a learning journey for us, but also an opportunity to establish contact with other municipalities and companies. Even researchers, who can help us work in an evidence-based way", says Linda Macke, investigation strategist and coordinator for the ACE project at Höganäs Omsorg, continuing:  

"We must change, work in different ways and think differently in order to keep up with developments. That is why it is very interesting to look at how other countries are tackling this issue, because it is challenging. Not least when it comes to making decisions about new ways of working."

The goal: scaling up smart solutions

Today, there are many digital solutions that can increase security and independence among older people that are not being utilised, according to Camilla Evensson, RISE's project manager for ACE. She explains that Swedish municipalities are good at testing innovations, but in many cases this does not result in upscaling and actual use in operations. The hope is that the ACE project's user-driven approach will change this.

By listening to staff, elderly people and their relatives, as well as pensioners' organisations, we can identify the most pressing needs. We then match these with companies that sell various types of digital solutions for home care and nursing. The technology must meet the needs that exist, says Camilla Evensson.

– Working methods and adaptation are also important aspects of this project. When implementing new technology, it will be necessary to change the working methods of care staff. It is also important to remember that seniors and their relatives need support and guidance in adapting to digital solutions, says Mona Jonsson.

It was the user-driven perspective and needs identification that attracted Höganäs Omsorg to participate in ACE. It felt important to take the opportunity to work with companies that can create solutions based on a real starting point.

"We want to base our decisions on the needs of our municipality. And we don't believe that the needs of our residents differ significantly from those of residents in Denmark or Germany," says Viweca Thoresson.

Solutions in the individual's living environment

So, what digital solutions could be rolled out in connection with the project? One example is so-called empathetic homes, which means that the home "takes over" some of the tasks of the care provider and supports older people in their everyday lives through aids such as light and sound signals. Project partners in the Netherlands are working on this.

“There is also an idea to better coordinate efforts from civil society. Today, actors such as pensioner organisations, family organisations and the Church of Sweden take on a great deal of responsibility for the elderly population. Technology could facilitate cooperation between these parties. Then, of course, it is a matter of matching existing digital solutions with actors such as Höganäs Omsorg", points out Mona Jonsson.

"Through this project, we can remove many obstacles and make it easier for companies to sell their solutions in more countries. At the same time, we are making it easier for municipalities and other care providers to access smart solutions that are available in countries other than their own," she says.

"What we have learned so far is that we need to collaborate. Working together with other organisations and companies is a necessity. We want to learn more and at the same time contribute with what we can," says Viweca Thoresson.

More partners welcome

The ACE project will run until June 2026, and Camilla Evensson would like to see more stakeholders join in to share their own experiences, but also to benefit from the knowledge and solutions developed and tested within the project.

"Healthcare and care providers, older people, researchers, civil society and suppliers of digital solutions – everyone is welcome to participate in events and online discussions to jointly develop the digital solutions of the future for healthcare and care in the home."

Artificial intelligence has the potential to revolutionise healthcare. Today already, algorithms are used to interpret X-ray and ultrasound images, for example. For these AI models to interpret the images as well as or better than an experienced doctor, they need to be trained on large volumes of high-quality data. This is easier said than done, since health data is sensitive information subject to various laws.  

“The laws exist to protect individuals’ privacy,” says Rickard Brännvall, senior researcher at RISE. “Perhaps they will need to be amended in the future, but for now we must comply with them. It’s important to work with the needs owners and those who know the law to understand how we can use various advanced privacy protection technologies to fully utilise the potential of the data collected.”  

Two effective tools 

According to Brännvall, there is a mixed toolbox available. One of the tools is federated learning. Simply put, it means that algorithms are trained on data held by different organisations without the data leaving their IT systems:  

“Using federated learning, healthcare providers can jointly build an AI model, without having to share their private datasets. Instead, they exchange model updates.”  

The process is repeated in many steps, with the end result being a better model than if everyone had trained separately. There is a risk however that the updates leak information that could be traced back to individuals.  

This is where the homomorphic encryption tool is especially useful. Homomorphic encryption allows encrypted data to be processed without first being decrypted. In the example of federated learning between healthcare providers, homomorphic encryption provides enhanced protection of healthcare provider data. The combination of these tools enables training of algorithms for use in healthcare, with a significantly reduced risk of sensitive data being compromised.  

“We have the opportunity to be involved in building an infrastructure and developing different types of models through federated learning and homomorphic encryption,” says Joakim Börjesson, a unit manager at RISE. “It will benefit the primary use of data, as well as secondary use for innovation and research.”  

Increased prevention with shared wellness data  

Börjesson highlights an example of the primary use of data made possible using privacy-protecting technologies. It involves utilising wellness data from our own mobile phones: 

“By correlating data collected during almost our entire waking hours with data generated when we visit healthcare, which may only be an hour a year, we can see behavioural changes and deviations. Based on the right type of data sources, you can predict a change. When you require healthcare, or perhaps even before seeking care, underlying problems can be identified based on collected wellness data.  

“When we visit a healthcare facility, new measurement values are taken, because doctors don’t have the right conditions to access our wellness data at present. Many, myself included, argue that the data we generate ourselves should be taken into account when making diagnoses.”  

If the providers of health apps could make their data available in a secure way, this data could be used to prevent ill health and reduce the burden on healthcare.  

“Good entry point for companies”  

RISE runs several projects in this area. In the Sjyst data! (Fair Data) project, RISE helps operators in the business sector to tackle challenges related to data protection and privacy. 

“We study the companies’ use cases and support the companies with expertise in how to use different privacy-protecting technologies,” says Brännvall. “This is an example of a meeting space where we discuss so-called close-to-market solutions, and it can serve as a good entry point for companies and industry organisations.” 

In another project, Brännvall and his research colleagues have developed a solution that enables secure sharing and analysis of sensitive data from diabetics, service providers, and healthcare.  

“By working together with healthcare providers and the business community, RISE can help define platforms with standardised interfaces, which allow you to work with health data and gain access to various tools for privacy protection,” explains Brännvall. “It’s very important to get all the pieces in the right place, including secure management of encryption keys. Otherwise, there is a risk of making sensitive data accessible. RISE can help with both the construction of platforms and by acting as a sounding board, such as through testing in Cyber Range, our testbed for cybersecurity.” 

One of the most difficult things seems to be building digital services for the elderly. The latest annual report on Swedes and the Internet (Svenskarna och internet) summarizes the situation as follows:

• Fewer than half of those born in the 1920s and 30s have used e-services in the past year.
• 6 out of 10 can't log in to online public health services without help.
• Among the oldest, only one in three thinks that e-services make things easier.

These kinds of issues are often mentioned. Digital exclusion in Sweden is primarily driven by age. No wonder, perhaps, because when the Internet had a broader impact in the mid-1990s, this group was already in their 60s and 70s. Factors such as level of education, income, disabilities and place of birth also have an impact. In short, things that deviate from the norm.

“If you look at who builds our digital solutions today, just over 80 percent of the world's developers are men,” says Melinda From at RISE “Of those, 75 percent are white with origins in Europe or North America. It is obvious that this group will be very homogeneous.

“We see signs of this in our digital products. For example, voice control that works better for men or facial recognition that works well with light faces but worse with other skin tones.”

Melinda From believes that our services sync better with the norm if they are also based on the norm, and therein the problem.

“Instead, we should develop for those who have the most difficulty using these services.”

Need to find alternative paths

As a service designer with an eye for what norms can do, Melinda From lists several examples of solutions that go wrong. Sometimes it is previously collected data that distorts the design, sometimes it is not a given that a digital service solves the whole problem but instead locks out people who lack the BankID service or sufficient computer skills.

“Somewhere there must be alternative paths. We sometimes digitalize in absurdum when we should instead start from people's needs.

This applies to both the private and public sectors, and as a resident and taxpayer, one might feel that the Swedish public sector should be there for the entire population,” says Melinda From. Her advice to developers is to take advantage of Sweden's anti-discrimination legislation, which lists seven different grounds for discrimination.

“A lot is gained if you consider parameters in the design phase such as gender, age, sexual orientation, disability, religion, ethnicity and transgender identity or expression. Then, of course, there are also the other perspectives that are not related to laws; urban or rural is an example,” says Melinda From.

Investment in inclusive system transition

RISE employs a number of service and interaction designers. There are also several norm-critical experts who can help in the early phases with reviews from a system perspective as well as assessing prototype solutions in ‘real life’

“We are also setting up a new unit for inclusive system transformation and innovation that will be up and running in the fall of 2022,” says Melinda From in conclusion.