In a short period of time, AI has gained a foothold in both business and the public sector. But it is perhaps in medicine and healthcare that AI's ability to interpret large amounts of data will have the most transformative impact – and could save lives.
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.
We strive for long-term relationships and partnerships 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.
AI FOR IMAGE ANALYSIS: HOW TO FIND ADRENAL CANCER
The adrenal gland is an important organ to examine for signs of lung cancer and melanoma, for example.
In a pilot project between RISE, Karolinska Institutet and Karolinska University Hospital, a machine learning AI model was used to determine the exact three-dimensional shape and size of adrenal glands in just a few minutes.
The results of the study showed that in many cases AI can make more accurate measurements than a doctor because it can store and interpret endless amounts of data – and compare it in a completely different way than a human can.
However, Fehmi Ben Abdesslem is quick to point out that AI should be seen as a complement to medical science, not a replacement for a doctor's knowledge.
– A doctor's experience and knowledge is still crucial to making diagnosis, but we can provide decision support tools to help radiologists identify changes in the gland and thus help fight cancer.
How RISE is working with AI in medicine
- Collaborative research: RISE partners with universities and pharmaceutical companies for collaborative research and clinical trials.
- Advanced analytics and AI: RISE is using AI and analytics to accelerate drug discovery and optimise drug design.
- Biotechnology and nanotechnology: RISE develops innovative drug delivery carriers and improves drug targeting.
- Regulatory expertise: RISE helps to navigate regulatory requirements and ensure compliance with safety and efficacy standards.
- Pilot and scale-up facilities: RISE provides facilities for the transition from laboratory experiments to commercial-scale drug production.
- Experience in coordinating large international (EU-funded) and national projects.
- Application partners with AI expertise.
