ҳ

M4-HEALTH: a New Model for Health Using Digital Twins and AI

två personer ler och tittar på en dataskärm med en digital tvilling i ett gym, samt skärmar med massa kod på.
Gunnar Cedersund and Elin Nyman are two of nearly 40 researchers at ҳ involved in M4-HEALTH.

M4-HEALTH is a network that combines 16 Swedish universities together with over 100 companies and other organisations into a new ecosystem for health. This ecosystem is integrated using our revolutionary and flexible technology: physiologically based digital twins of individuals.

The heart of M4-HEALTH is physiologically based digital twins of individuals, in other words realistic computer models that describe what happens in the human body. The basis for these twins has been laid for example in a series of projects funded by Swedish Research Council and led by the coordinator Gunnar Cedersund. For example:M4-health: the basis for general AI in health care

In this new network, we are taking these twins to a new and distributed level, where scientists from all over Sweden, and all over the world, can contribute to the developments of the models, and where the twins are used in a new eco-system for health.

This ecosystem includes not only healthcare, but schools, defense industry, clothing and food industries, yoga studios and gyms, etc. M4-HEALTH is one of the most comprehensive, ambitious, and integrated networks focusing on health and healthcare ever assembled in Sweden. It attempts to create a new infrastructure for storage of all available knowledge and data about the human body and about each individual into the twin, and to use the twin to drive society in a more health-promoting, personalised and sound direction.

Why do we need a new model for health?

Our current, highly fragmented, healthcare systems are facing three simultaneous challenges:

  • The number of 80-year-olds in society is increasing with 50 percent in a 10-year period, which implies enormous increases in costs and need of personnel.
  • The health in our younger working force has decreased for several decades, and this keeps getting worse.
  • AI and data revolutions imply that knowledge and expertise is increasingly available for everybody, and not just to experts.

To be able to meet all these new changes, we need a new model for health – M4-HEALTH.

Revolutionary technology: hybrid digital twins of individuals

Over the last 25 years, we have incrementally and systematically assembled a new and unique technology: a physiologically based digital twin or computer model of the human body. What makes this twin technology special in the world is that it can simulate what happens when you do different things, like eat a meal, exercise or take a medication, along four crucial axes, described by four M:

  • Multi-level: From the whole-body to all organs and even inside cells.
  • Multi-timescale: From short responses over seconds to long-term disease progression over years.
  • Multi-species: Both in humans and in other animals for which we have key data.
  • Mechanistic: Using both data-driven and explainable physiologically based approaches.

These four axes makes up the basis for our unique M4-models, and we believe that the combination of these M4-models with machine learning (ML) and large language models (LLMs) will be the next big breakthrough in AI for health.

The solution: a new ecosystem for health

These hybrid digital twins look like an individual, can be used for a variety of different purposes, and can therefore be used as a binding kit for a new integrated ecosystem for health. This ecosystem can integrate all data and knowledge: your own data goes into your own personal data vault, all general data is coordinated into harmonized databases that can be used for federated learning, and all these data and knowledge is integrated into the digital twin, which describes an updated understanding of you as an individual.

This ecosystem can also be used along your entire health journey: ranging from schools and sports organisations, to the defense industry, gaming, food and clothing industry, to yoga studios, gyms and other preventive actors, all the way to traditional healthcare, eldercare and even forensics.

We integrate 16 universities in Sweden, and connect with many leading international networks and organisations. We have the explicit support and involvement of over 100 companies, governmental bodies, and other non-profit organizations.

Our ambition is that this new ecosystem will be able to create P4-medicine: predictive and therefore preventive actions that preventive diseases before, in a way that is personalized to each individual, and participatory, since that individual is active in his/her own health.

Why M4-HEALTH?

We are living longer

The number of 80-year olds is expected to increase with 50 percent in this ten year period. This will lead to enormous increases in healthcare costs and in need of personnel. 

We are more unhealthy

The young and working individuals who need to take care of all the elders are getting more unhealthy. This has been going on for decades and it keeps getting worse. 

We are asking AI for answers

AI, artificial intelligence, and new digital solutions, implies that knowledge and expertise is increasingly available for all – not only the employed experts in healthcare.   

We need someone to take a holistic approach to creating a new model for health, and we are doing this using something called digital twins.
Gunnar Cedersund, project coordinator, M4-HEALTH
Image not found
Gunnar Cedersund, project coordinator, M4-HEALTH is interviewed by his colleague Katja Woxell.

Why M4-HEALTH is needed

In this video, project coordinator Gunnar Cedersund talks about M4-HEALTH and explains why a new model for health is needed. He also shares his vision for the network and its future impact.

“Healthcare will have to change; status quo is not an option. That is why we need someone to take a holistic approach to creating a new model for health, and we are doing this using something called digital twins,” he say.

If no action is taken, the demand for healthcare is expected to increase significantly, partly because the Sweden have a growing numbers av elders and have an increasing unhealth in all ages.

Structure for a new ecosystem for health

En illustration med digital tvilling i mitten och allt som den fylls på med. Photographer: Love Wendel

Digital twins: the heart of M4-HEALTH

M4-HEALTH has four layers, where experts are integrating their data and knowledge in the bottom layers, and where impact on behaviors, health economy, and end-usage is examined in the upper layers.

Green and blue-gray layers

  • In the bottom green layer, we have experts on all main organs in the human body. They can use our new way of integrating their knowledge and data about these various aspects of the human body and mind into sub-models, which then are integrated into the overall digital twin.
  • In the second blue and gray layer, we have experts on data handling, new wearable sensors, and hybrid modelling. The create a pre-competitive technological platform, which allows an individual to store a copy of all of their data, from all available sources, into a personal data vault. This data can be used to update the twin, which is constructed using a hybrid technology combining M4-modelling, machine learning (ML), and large language models (LLMs). General data, stored in databases all over the world, are harmonized and structured to allow for distributed, federated learning.

Yellow and red layers

  • In the third yellow layer, we have experts on humanities, including ethics, behavioral science, and health economy. They use qualitative and quantitative methods to elucidate and bring clarity to all of the many impacts that this new technology has on humans and on society.
  • Finally, in the top red layer, we have end-users, companies and other organizations along the entire health journey, ranging from schools and food industry, to defense industry, gaming industry, and all the way to healthcare, eldercare and forensics. They all have their own eHealth apps, developed by a range of different companies, but all apps use the same digital twin. In this way, they are all coordinated and integrated into a single ecosystem, where you can continue your health journey in all of your activities during a day, and during your life. This is possible because of the unique flexible and reusable nature of our digital twins.

Want to get involved?

Join us as founder or partner

We are now seeking funding from various sources for this unique initiative, for instance to become an excellence cluster, with up to two billion SEK in funding over ten years in potential funding.

We are also looking for new partners, such as

  • individuals, who want to be involved as beta-testers or to participate in the new ecosystem.
  • scientists and experts on the body and mind.
  • experts on AI, modelling, and data infrastuctures.
  • visionaries, who want to help create a new model for health in Sweden and internationally.

Contact us by info@m4-health.se.

Upcoming and previous events 

New conference in November 2026

Are you curious about M4-HEALTH and the work towards a preventive health ecosystem?

In early November 2026, M4-HEALTH plan to hold another open network meeting at Linköping University in Linköping. The event will feature presentations, poster sessions, an exhibition area and panel discussions. Together, these activities will provide an opportunity to showcase all aspects of the network to the public.

Participants will gain insight into the different sub-projects, their objectives and planned activities, as well as the researchers and partners involved.

Like the previous event, this gathering is open to current members as well as to interested researchers, companies, public authorities, healthcare professionals and members of the public.

Further information and a registration link will follow.

Two-day workshop held on 25-26 May 2026

On 25–26 May 2026, the M4-HEALTH network organised an open two-day workshop in Linköping.

The workshop was held in conjunction with Linköping University’s annual conference in biomedical engineering, BME@LiU. The event brought together around 250 participants and 30 companies. Researchers, healthcare professionals, companies, students and interested members of the public gathered in Ljusgården and attended presentations in neighbouring venues at Linköping University Hospital.

The first day of the workshop coincided with the BME conference and included exhibitors, a poster exhibition and the full conference programme. The day featured nearly 30 presentations covering a broad range of topics in biomedical engineering, from e-health and clinical implementation to AI, data analysis and modelling. Several sessions highlighted the importance of collaboration between academia, healthcare and industry in translating research into practical benefits. Digital twins were a recurring theme throughout the programme.

The second day was an internal workshop dedicated to preparing the network’s application to become a cluster of excellence. Participants also continued work on the network’s shared goals, discussed strategies for the different sub-projects and planned future activities.

LiU-news about digital twins for medicine and health

Mycket folk står i och pratar i en utställningslokal.

17 July 2026

Successful BME day highlights collaboration

More exhibitors and an ideal mix of participants. Researchers, students, healthcare professionals and business representatives all took part in the seventh major conference in biomedical engineering, BME@LiU2026.

A man with glasses is looking at himself in the mirror.

29 April 2026

Digital twin could reveal alcohol consumption in crime cases

Using a digital twin, it is possible to predict with greater precision than at present how much alcohol a person has consumed and at what time. The study was conducted by researchers at LiU and the Swedish National Board of Forensic Medicine.

En person i labbrock som håller i en flaska.

24 February 2026

AI provides a more precise time of death

Artificial intelligence can be used to provide a more precise time of death, which can be crucial in e.g. murder investigations. The AI model is trained on so-called metabolites in thousands of blood samples from real deaths.

Research environment

Image showing the DNA steps, a brain and a human.

Biomedical Modeling and Informatics

We combine modeling, simulation, and data science to analyse biomedical data. Through advanced algorithms, we can interpret large datasets, understand complex processes, develop new treatments, and improve diagnostics.

Group of people standing outside.

Integrative Systems Biology -ISB

We aim towards being the world leading group in the unravelling of systems-level mechanistic insights, using inter-connected M4 models for decision support in pharma and P4 medicine – thereby making a positive change in society.

Two scientists are sitting infront of an MRI

Center for Medical Image Science and Visualization, CMIV

CMIV conducts focused front-line research providing solutions to tomorrow’s clinical issues. The CMIV mission is to develop future methods and tools for image analysis and visualization for applications within health care and medical research.

Research projects

Black background. You see several

M4-health: the basis for general AI in health care

In the VR funded project “M4-health: the basis for general AI in health care” we make way for a more general and flexible type of AI in health care.

Blurry illustration, silhouette of a head in blue monochrome tones.

STRATIF-AI – Digital twins for stroke

The STRATIF-AI project is about continuous stratification for improved prevention, treatment, and rehabilitation of stroke patients using digital twins and AI. It is a four-year research project funded by Horizon Europe.

Three screens of a game with a trophy.

The Heart-exergame study

In general, everybody is recommended to be physically active for at least 150 minutes a week to improve health. Physical activity helps us to participate in daily life activities, stay independent for a longer time and have a good quality of life.

Researchers from LiU in the network M4-HEALTH

Contact

Project publications about digital twins and our new model for health


  • Wickramasinghe N, Ulapane N, Zhang Y, Jansons P, Cedersund G, Maddison R. Sensors (Basel). 2025, 26(1):82

  • García-Rudolph A, Wright MA, Teixidó-Font C, Sanchez-Carrion R, Cedersund G, Opisso E. Top Stroke Rehabil. 2025, 7:1-15

  • Podéus, H., Simonsson, C., Jakobsson, G. et al. A digital twin framework for forensic reconstruction of alcohol intake via fast and slow metabolite kinetics. Sci Rep 16, 9336 (2026). https://doi.org/10.1038/s41598-026-44093-4

  • Henrik Podéus, Christian Simonsson, Patrik Nasr, Mattias Ekstedt, Stergios Kechagias, Peter Lundberg, William Lövfors, Gunnar Cedersund, (2024)."A physiologically-based digital twin for alcohol consumption-predicting real-life drinking responses and long-term plasma PEth".NPJ Digit Med.,7(1):112.

  • Kajsa Tunedal, Tino Ebbers, Gunnar Cedersund,(2025).“Uncertainty in cardiovascular digital twins despite non-normal errors in 4D flow MRI: Identifying reliable biomarkers such as ventricular relaxation rate”,Comput Biol Med,188:109878
  • Tilda Herrgårdh, Christian Simonsson, Mattias Ekstedt, Peter Lundberg, Karin G Stenkula, Elin Nyman, Peter Gennemark, Gunnar Cedersund (2023)."A multi-scale digital twin for adiposity-driven insulin resistance in humans: diet and drug effects".Diabetol Metab Syndr.15(1):250.

  • Oscar Silfvergren, Christian Simonsson, Mattias Ekstedt, Peter Lundberg, Peter Gennemark, Gunnar Cedersund (2022)."Digital twin predicting diet response before and after long-term fasting".PLoS Comput Biol.18(9):e1010469.

  • Tilda Herrgårdh, Elizabeth Hunter, Kajsa Tunedal, Håkan Örman, Julia Amann, Francisco Abad Navarro, Catalina Martinez-Costa, John D. Kelleher, Gunnar Cedersund (2022).Digital twins and hybrid modelling for simulation of physiological variables and stroke risk,bioRxiv, preprint.

  • Belén Casas, Jonas Lantz, Federica Viola, Gunnar Cedersund, Ann F Bolger, Carl-Johan Carlhäll, Matts Karlsson, Tino Ebbers (2017).“Bridging the gap between measurements and modelling: a cardiovascular functional avatar”,Sci Rep,7(1):6214.

Participating organisations at LiU

Studenthuset on Campus Valla in Linköping

About LiU

ҳ, LiU, offers innovative education and boundary-crossing research. The students are among the most desirable in the labour market and international rankings consistently place LiU as a leading global university.

Computer simulation of a person

Department of Biomedical Engineering (IMT)

A national centre for research, PhD studies and graduate studies within biomedical engineering, since 1972.

Other LiU departments involved

University park behind house I.

Department of Behavioural Sciences and Learning (IBL)

Human behaviour and learning is the focus for education and research at the department. We educate students and scientists that are well equipped to meet future challenges in society and working life.

Department of Biomedical and Clinical Sciences (BKV)

What characterizes the Department of Biomedical and Clinical Sciences (BKV) is the wide breadth of research and education. BKV is one of the largest departments at LiU with affiliation mainly to the Faculty of Medicine and Health Sciences.

Image of Building E, Campus Valla.

Department of Computer and Information Science (IDA)

The Department of Computer and Information Science is one of the largest departments in northern Europe in its field. Research activity covers artificial intelligence, human-computer interaction, software and computer systems, and data science.

More about research at LiU