News archive

A newly published study involving researchers from Karolinska Institutet indicates that prostate cancer can be diagnosed at an early stage through a simple urine sample. With the aid of AI and extensive analyses of gene activity in tumours, they have identified new biomarkers of high diagnostic precision.

In a study on ovarian cancer cells, researchers from Karolinska Institutet demonstrate how the tumor environment influences how cancer cells respond to drugs by using AI. The study has been published in the journal Communications Biology.

In this episode of the KIB podcast we dig deeper into the academic perspective on AI: How do students use and reflect upon the use of AI in their studies – and how should they?
• How can I use AI to support me in my learning process?
• What’s happening to our brains? (Or to the intended learning outcome?)
• Is it cheating if I ask “my friend Bob” the AI to write my essay?

The aim of the newly established Centre for AI Innovation at Karolinska Institutet is to support and expedite the development of AI innovations in healthcare. “While AI has huge potential, there are many factors to take into account before AI solutions can become practicable,” says the centre’s director Johanna Furuhjelm.

The Trustworthy & Ethical AI Lab (TEA Lab) has been established at Center for Social Sustainability (CSS) as an interdisciplinary research initiative focused on promoting ethical, transparent, and sustainable AI applications in healthcare. The TEA Lab will align its work with the EU Guidelines for Trustworthy AI and combine expertise from fields including medicine, philosophy, psychology and social sciences.

The geroscience hypothesis focuses on extending the healthy lifespan by targeting aging mechanisms. Recent advances in biomarkers for biological aging give rise to tools for measuring aging and assessing treatments. Alzheimer’s disease, a major health issue, may benefit from common drugs and early interventions.

Histopathological evaluation of tumour specimens has long been essential in diagnosing breast cancer and guiding clinical decision-making. However, one of the key challenges in routine diagnostics include the inter-observer and inter-lab variabilities present in the assessment of prognostic markers that could lead to under- and over-treatment of patients.

A new international study led by researchers at Karolinska Institutet in Sweden shows that AI-based models can outperform human experts at identifying ovarian cancer in ultrasound images. The study is published in Nature Medicine.

Using an AI tool, researchers at Karolinska Institutet have analysed brain images from 70-year-olds and estimated their brains’ biological age. They found that factors detrimental to vascular health, such as inflammation and high glucose levels, are associated with an older-looking brain, while healthy lifestyles were linked to brains with a younger appearance. The results are presented in Alzheimer's & Dementia: The Journal of the Alzheimer's Association.

In this episode of the KIB podcast Alvin, bibliometric analyst, Lovisa, librarian, and Anna, writing instructor, discuss questions from colleagues and students at KI on LLMs (large language models).

Researchers at Karolinska Institutet and Royal Institute of Technology (KTH) have developed AI-driven warning technology capable of detecting infections up to 24 hours before symptoms appear.

Researchers at Karolinska Institutet have investigated how well different AI models can predict the prognosis of triple-negative breast cancer by analysing certain immune cells inside the tumour. The study, published in the journal eClinicalMedicine, is an important step towards using AI in cancer care to improve patient health.

The Royal Swedish Academy of Engineering Sciences (IVA) has published this year's 100 list of the most promising research projects from Sweden's colleges and universities. All applications to the list have been reviewed by IVA's expert group and the selected projects are considered to have great potential to benefit society. The list includes several projects involving researchers at Karolinska Institutet.

Mehdi Astaraki, a specialist in artificial intelligence (AI) for medical imaging, has achieved remarkable success in the MICCAI BraTS Challenges. He secured first place in the Pediatric Brain Tumor Segmentation and second place in the Meningioma RT Segmentation categories.

David Baker, USA, has succeeded in creating entirely new proteins – the building blocks of life that control all biological processes in the body. He shares the Nobel Prize in Chemistry 2024 with Demis Hassabis and John M. Jumper of Google DeepMind, UK, who have developed the AI tool AlphaFold2. “Now it can take minutes instead of years to get a good idea of what a protein looks like and how it may function,” says KI professor Luca Jovine, who intitiated a collaboration with DeepMind early on.

As the volume of clinical data increases, so does the amount and complexity of the work needed for a doctor to interpret them. Magnus Boman researches on how AI can be employed for healthcare-improving analyses. Meet one of Karolinska Institutet's new professors who will participate in this year's installation ceremony at Aula Medica on 3 October.

A new machine learning model can predict autism in young children from relatively limited information. This is shown in a new study from Karolinska Institutet published in JAMA Network Open. The model can facilitate early detection of autism, which is important to provide the right support.

AI, artificial intelligence, can be used to identify molecules with great potential to be developed into new drugs for mental illnesses, according to researchers from Karolinska Institutet, among others. The study, which has been presented in the journal Science Advances, and conducted on mice, shows that AI with high precision can contribute to more effective future treatments for conditions such as psychosis.

Cloud-based personal health records are on the rise globally. This article series introduces the concept of a GPOC of PHRs, consisting of five parts, with the current article focusing on systematic review and meta-analysis. It scrutinizes technical, computer scientific, and security-based prerequisites, analyzing twelve factors including data security, efficiency, cost, integrity, cryptography, and access.

The 2023 AI Swede of the Year feels no need to be at the center of research. Yet that is exactly where he is. The orthopaedic surgeon and researcher Max Gordon was an early adopter of artificial intelligence. Now everyone else wants to know how to do it.

AI is increasingly being used in healthcare, education and research. AI chats are part of the AI offering at KI and Copilot (previously called Bing Chat Enterprise) has recently been made available to all employees. The goal is for AI to become part of the everyday work of KI's researchers, staff and students.

For KI researcher Ylva Trolle Lagerros, AI and Microsoft Copilot (formerly Bing Chat Enterprise) offer time savings and texts with cited sources, but also future opportunities for research collaborations with several countries. She also sees valuable connections between the use of AI tools and the role of teacher and researcher on digital support in healthcare.

For KI doctoral student Eric Åhlberg, AI and Microsoft Copilot (formerly Bing Chat Enterprise) offer tools for statistical analysis work and for managing certain administration. His long-term goal is for AI to become a validated tool for high-quality research results.

For ICT educator Marcus Emas, Microsoft Copilot (formerly Bing Chat Enterprise) and AI offer new opportunities to streamline the work with reference management, reading lists and assessing assignments, among other things. He emphasizes that AI at KI should be an equal tool and welcomes the introduction of Microsoft Copilot.

Carl Henrik Ek has recently been appointed visiting professor of AI/machine learning at the Department of Clinical Science and Education, Södersjukhuset (KI SÖS), Karolinska Institutet. To take advantage of the new technology, development must take place in synergy between mathematics, computer science and medicine, says Carl Henrik Ek, who also leads a research group in machine learning at the University of Cambridge, UK.

The use of AI makes it possible for women with a high risk of breast cancer to be identified in mammography screening examinations so that the cancer can be caught earlier. An international research group led from Karolinska Institutet in Sweden can now show that the method is effective in different European countries. The study is published in The Lancet Regional Health – Europe.

Vinnova (the Swedish governmental agency for innovation systems) is to finance the project "For efficient and sustainable use of health data through the integration of the DIGITAL-projects and GMS in Sweden (DIGIfor1healthSE)" with a grant of SEK 12 million over a period of four years. The project, which is designed to gather Sweden’s expertise on health data, involves TEF-Health at Karolinska Institutet and has SciLifeLab as the national coordinator.

Researchers at Karolinska Institutet and SciLifeLab have combined artificial intelligence (AI) techniques used in satellite imaging and community ecology to interpret large amounts of data from tumour tissue. The method, presented in the journal Nature Communications, could contribute to more personalised treatment of cancer patients.

In recent years, there have been rapid advancements in the field of computational pathology, which refers to the application of computational methods in pathology workflows. Traditional pathology involves the study of diseases by examining tissues, organs, and bodily fluids. In computational pathology, digital pathology images are analyzed using computer algorithms to extract meaningful information.

Cardiovascular disease is one of the most common causes of death in Sweden and in the world. Researchers at Karolinska Institutet, among others, have now found that artificial intelligence seems to play a role in identifying the risk of cardiovascular disease. The study, published in Cardiovascular Research, may in the future lead to more accurate diagnostic methods.

Karolinska Institutet has decided to award Johan Hartman and Mattias Rantalainen the 2023 Prize for Innovation and Utilization. They are rewarded for improving cancer diagnostics with innovative research and inspiring working methods.

While there are currently a dozen approved AI systems for breast cancer screening, it has been difficult to evaluate their clinical performance objectively. Now, however, there is a Swedish validation platform ready to compare how well AI systems detect signs of breast cancer – and its development has been led by researchers at Karolinska Institutet.

Prostate cancer is a major global health concern and is the most common cancer-related cause of death in Sweden. Prostate cancer screening using PSA reduces prostate cancer mortality but also leads to significant overdiagnosis and overtreatment of low-risk cancers. The pathological evaluation of prostate biopsies determines the therapeutic course of treatment for prostate cancer patients.

Researchers at Karolinska Institutet, the Centre for Imaging Research (CIR), SciLifeLab, and RISE have together received a grant of over SEK 100 million from the European Commission's Digital Europe programme. The project, called TEF-Health, will, among other things, promote the rapid introduction of new artificial intelligence (AI) and robotics solutions in healthcare.

Two researchers at Karolinska Institutet have been awarded the Athena prize for an AI-based image analysis in precision medicine for risk classification of breast cancer patients. The Athena Prize is Sweden's largest prize for research and innovations that have been produced through collaboration between healthcare, academia and industry.

KI researchers have together with international collaborators completed a comprehensive international validation of artificial intelligence (AI) for diagnosing and grading prostate cancer. The study, published in Nature Medicine, shows that AI systems can identify and grade prostate cancer in tissue samples from different countries equally well as pathologists. The results suggest AI systems are ready to be responsibly introduced as a complementary tool in prostate cancer care, researchers say.

Can artificial intelligence (AI) overcome the challenges of precision medicine? We asked Magnus Boman, professor at KTH and affiliated to KI, whose research includes looking at how AI can be used in healthcare.

Researchers at Karolinska Institutet and Karolinska University Hospital in Sweden have compared the ability of three different artificial intelligence (AI) algorithms to identify breast cancer based on previously taken mammograms. The best algorithm proved to be as accurate as the average radiologist. The results, published in JAMA Oncology, may lead the way in reorganising breast cancer screening for the future.

A new digital tool that tailors specific questions based on a patient's medical history could improve the safety of diagnosis and effectiveness of care, according to a new study at Danderyd Hospital and Karolinska Institutet published in BMJ Open.

Many jobs, medical and otherwise, might one day be performed using artificial intelligence. According to a new study in Acta Orthopaedica by researchers at Karolinska Institutet in collaboration with the Royal Institute of Technology and Danderyd Hospital in Sweden, self-learning programmes can already find fractures with the same accuracy as orthopaedists.