Research at CAMES
Meet the research team - and find out why we are internationally recognised as part of the world's elite in this field.
Research in the international super league
The research carried out by CAMES is mainly application-oriented and is used to develop education and training activities at regional, national and international level.
CAMES is widely recognised as being part of the world's elite in healthcare research on how to most effectively use simulation and competency assessment in education contexts. In other words, it is researching innovative ways to develop and ensure medical competence.
On average, journals worldwide carry research publications from CAMES every three to four days
Do you have a project or idea that you want us to help with?
- Artificial Intelligence
- Robotic Surgery
- Orthopaedic Surgery
- Eye Surgery
- Patient safety
- Mental health
- Continuous training
- Simulation in the primary sector
CAMES AI is at the forefront internationally of research into AI applications that can support medical education and simulation training. It is fundamentally about using artificial intelligence to reduce medical and surgical errors while improving healthcare professionals' learning and clinical performance.
In this way, AI can help clinicians make better decisions in practice. Instead of using AI to replace tasks normally performed by clinicians, we are developing AI systems that support learning processes and clinical decision-making steps to make clinicians better at what they already do. We achieve this through close collaboration between data scientists, medical education researchers and clinicians
Robotic-assisted surgery has gradually gained ground in several areas of the hospital sector. And this trend will only accelerate. This is why CAMES has set up CAMES Robotics, a centre of excellence for robotic surgery training and educational research. The centre offers best practice training programmes for doctors and nurses in robotics on multiple systems. And we have a research-based approach in developing qualified training programs and new methods.
The centre designs industry-independent robotic surgical training targeted at clinicians in Denmark - and is a national focal point for training, development and introduction of new versions of robots and related technology. Through research, development and international collaboration, CAMES Robotics has entered the national and international map at record speed - and clinical trainees are flocking to train surgical skills.
Between 3000-4000 cases of rectal cancer are diagnosed annually among men and women. 1344 people died from the disease in 2019. Detection of colorectal cancer is mainly done by the technically difficult examination, colonoscopy. A procedure nurses and doctors nationwide perform over 100,000 times annually.
CAMES is among the leaders internationally in developing simulation-based colonoscopy tools that enhance the skills of colonoscopy professionals in a simulation-based forum. It is fundamentally about enhancing their skills before they see patients. For example, the "Automatic Assessment of Colonoscopy Performance" project has developed tools that allow doctors and nurses to upgrade their colonoscopy skills in an automated, objective and safe way.
Research, development and teaching in the orthopaedic surgery specialty at CAMES aims to ensure that junior surgeons are best trained outside the operating theatre before operating on patients. Optimal patient care has many facets that require care. Our goal is that patients with orthopaedic surgical conditions receive the best possible surgical care.
We are incorporating new technology extensively into this process in order to make learning and skills development for doctors as effective as possible in a health system with scarce resources. We work with both computer-aided simulator platforms with haptic feedback, virtual reality and AI. We do this with a focus on using and developing the technology that is most optimal for what needs to be mastered. The starting point for our work is based on needs surveys among clinical staff in Denmark, ensuring that CAMES' focus matches the needs of the Danish healthcare system.
We are currently working on the following projects:
- Learning and competency assessment in simulation-based training in osteosynthesis of hip fractures
- Development of AI algorithm using deep neural networks for automated competency assessment of surgical skills in simulation-based training in hip fracture surgery
- Development of a VR simulator for training in surgical treatment of fractures of the arms and legs
- ADD-SIMS: Development and implementation of simulation and competency-based courses according to current standards in the aeronautics industry
At CAMES, we are among the world leaders in simulation research in eye surgery.
The common goal of our projects is to optimise patient safety in eye surgery. Some of our previous studies have shown a significant effect of virtual-reality simulation training in terms of surgeon skills in the operating room when operating on patients for cataract. And the training has therefore been introduced as a mandatory element for ophthalmic surgeons in the Capital Region.
The research group works both to investigate how we can most optimally assess surgical skills in an evidence-based manner, as well as best practice in relation to training for advanced microsurgery; including intra-ocular procedures such as cataract and retinal surgery. These procedures are characterised by long learning curves, where one surgical error can result in vision loss for the patient.
Ultrasound has improved the treatment of patients in several medical and surgical specialties.
The use of ultrasound in the clinic is increasing and allows early diagnosis, treatment monitoring and guidance during procedures. Ultrasound has become an invaluable tool in everyday clinical practice and the only immediate disadvantage is that ultrasound is surgical dependent.
CAMES therefore has a research-based strategy that aims to develop the most effective training programmes in ultrasound. The research focuses on both diagnostic and interventional ultrasound in various specialties including:
- abdominal ultrasound
- head and neck ultrasound
- transesophageal ultrasound
- endobronchial ultrasound
- transvaginal ultrasound
- chest ultrasound
- point-of-care ultrasound
- contrast-enhanced ultrasound
- vascular ultrasound
- obstetric ultrasound
- musculoskeletal ultrasound
- ultrasound in general practice.
CAMES research projects involve the development and testing of various training technologies and interventions such as virtual reality, simulation-based training, e-learning platforms and the use of artificial intelligence.
In order to ensure physicians' competencies in ultrasound, CAMES is deeply engaged in the development and validation of competency assessment tools for several of the medical and surgical specialties.
Safety research, including patient safety research, is an essential element of effective and safe patient care. Our research addresses questions such as "what is patient safety and how do accidents and errors occur", "how can we analyze and prevent them?".
Based on questions like these, we focus on science and research in and about security. Specifically, we investigate and optimize daily practice and critical situations, new and already known analysis and intervention methods, both with and without simulation. Only in the interplay between people, technology and organization can we optimize patient safety. Our international publications shed light on the core of a healthy and safe healthcare system.
Health professionals are the most important resource in healthcare. Ensuring their mental health should be a priority from an ethical, patient safety, organizational and societal perspective.
The psychosocial work environment in healthcare is under increasing pressure and more and more healthcare professionals are experiencing emotional distress. When people are under stress, their ability to function optimally - both at home and at work - is affected. Prolonged stress leads to sick leave and resignations. There is a direct link between the psychosocial work environment and the ability to recruit and retain employees. Poor mental health also has negative consequences for the individual, the team, patient safety, the organization and the economy, and there is solid evidence for these links. We are conducting research on these links, consequences and solutions.
At CAMES, we conduct research on how to best and most effectively strengthen medical, social and cognitive competences in the pursuit of better care.
Our research findings help to ensure coherence between clinical education and training activities. The research contributes to the continuous revision of the learning outcomes for the seven medical roles and associated competence assessment tools used in clinical training.
Training is now a specific area of focus and our research supports, for example, the development of a portfolio toolkit.
Primary care covers care provided outside hospitals. This includes general practitioners, nursing homes and home care services. As the workflow in primary care differs from secondary care, simulation-based training should also take this difference into account.
At CAMES, we are focusing on this to strengthen the training of healthcare professionals in primary care, where they are often left alone with the task. We are therefore addressing the following questions: "Is simulation-based training as effective in a primary care context as in secondary care?", "Which simulation methods and learning objectives are suitable for simulation training in this context?". By exploring these questions, we can ensure that the citizen receives high quality care wherever it takes place.
Current research projects
VR-based training in surgical treatment of fractures
In Denmark, around 30,000 surgical procedures are performed each year for fractures. There is therefore an ongoing need for training of new, competent, orthopaedic surgeons to provide this treatment.
A 2019 national needs survey, including all of the country's orthopaedic surgery departments, showed that principles of surgical treatment of fractures is the orthopaedic surgery area where the need for simulation-based technical training is greatest.
The training of surgical competence traditionally consists of self-study and surgery under supervision. In other words, doctors actually train on patients. By having the earliest part of the training take place on a simulator, doctors can learn from their mistakes and achieve sufficient surgical competence before performing real operations. In this way, patients are not exposed to unnecessary risk.
The VR BOSS project (Virtual Reality Basic Osteosynthesis Surgery Simulation) is working on the development and implementation of a VR simulator for training and competence assessment in the surgical treatment of bone fractures.
The project has established a collaboration with the world-leading orthopaedic surgery organisation AO Foundation. Through this collaboration, orthopaedic surgical education experts from around the world have defined the parameters on which users of the simulator should be assessed, as well as how each parameter should be assessed. This novel approach to simulator development ensures that development is evidence-based, that the simulator meets the requirements and expectations of the target audience - and that the entire development process is transparent from the outset.
The development of the first of a total of seven orthopaedic surgical procedures is in its final phase, after which studies will begin to determine the validity of the simulator test and the impact of the simulation training.
Check out the VR simulator:
Here you can see how the VR simulator - developed by CAMES PhD student Mads Emil Jacobsen - works when surgeons train fracture surgery. The VR simulator has been developed in close collaboration with VR developers at VitaSim.
Cooperation and support
The VR-BOSS project is supported by grants from the Toyota Foundation and the Health Fund as well as Region Zealand's Research Fund and the Næstved- Slagelse- Ringsted Hospital Research Fund.
The project is anchored in the Department of Orthopaedic Surgery at Slagelse Hospital and CAMES as a PhD with Mads Emil Jacobsen, md, PhD student, in the lead.
Hip fracture surgery and artificial intelligence.
A project using image data to develop AI algorithms that can help orthopaedic surgeons choose the most optimal surgical methods for hip fractures and ensure the highest possible quality of surgery.
Artificial intelligence and automated skills assessments
Competence monitoring in the clinic is often resource-intensive - especially if it has to be carried out in a structured and continuous way.
CAMES has been running simulation-based courses in osteosynthesis of hip fractures based on validated competency scores for the last 7 years. The courses have provided several thousand simulated radiographs based on training and testing by both novices and experts.
This project seeks to uncover whether training an AI algorithm using deep neural network can automate competency assessment of performed surgery in the simulated context as well as on clinical per- and postoperative radiographs. Such a tool could monitor the quality of performed surgery at both the individual and organizational level and allow for earlier intervention in case of competence and quality gaps.
Automatic assessment of colonoscopy performance
The project started 09/02-2022 and will run for 18 months. Bispebjerg Hospital, Hillerød Hospital and Herlev Hospital are participating in the project. During this period, we will collect approximately 4500 microscopy studies and investigate whether ADR - the ratio of patients with at least one adenoma removed in the rectum or colon - is increased via autogenerated feedback. The Colonoscopy Retraction Score (CoRS) is an autogenerated competence measurement system based on artificial intelligence that is correlated with the detection of cancer precursors (polyps). We expect that by implementing feedback from CoRS we will increase detection due to a more thoroughly performed procedure.
Colorectal cancer is the second leading cause of cancer deaths in Denmark. Between 3000-4000 cases of colorectal cancer among men and women are diagnosed annually, while 1344 people died from the disease in 2019.
Colonoscopy is used to diagnose cancer of the rectum and colon. Early detection is essential to reduce mortality. The primary quality measure for the operator is how frequently precancerous lesions are detected and removed. It is therefore recommended to introduce quality targets and develop the skills of operators to increase detection.
Interventions and technological add-ons aimed at increasing this have an immediate effect, but common to them all is a limited retention (i.e. the effect ends when the focus/study is finished). This is why we are working with autogenerated feedback in the project.
Cooperation and support:
The project is supported by grants from the Danish Cancer Society and the Capital Region Research Fund. The funds are anchored in a post.doc. with Andreas Slot Vilmann and, with support from Ambu, a PhD by Kristoffer Mazanti Cold.
Colonoscopy: algorithm tool for calculating automatic cleansing score
Prior to a colonoscopy, the patient takes a laxative that acts as a cleanser. This is done to get the best possible view of the intestinal wall. Unfortunately, not all patients are cleansed equally well and it is estimated that 42% of polyps missed are due to a lack of cleansing.
Through the project - Copenhagen Automatic Bowel Preparation Score (CA-BoPS) - we collect video material on up to 2000 studies. These videos will be used to train an algorithm - based on artificial intelligence - to calculate an automatic bowel cleansing score. This score could be used to provide a risk analysis of the likelihood of missed polyps due to lack of cleansing.
The tool could be used to assess the clean-up, but also - together with other quality measures such as CoRS - whether the survey is satisfactorily conducted.
Cooperation and support:
The project is supported by grants from the Danish Cancer Society and the Capital Region Research Fund. The funds are anchored in a post.doc. with Andreas Slot Vilmann and, with support from Ambu, a PhD by Kristoffer Mazanti Cold.
AI-based training in the diagnosis of birthmark cancer
Through training using a mobile application, the project aims to make it more efficient for doctors to learn how to diagnose skin cancer. What we also call "Intelligent" learning in pattern recognition.
It currently takes more than 6 years to become proficient at telling the difference between benign and malignant skin tumours. This leads to delayed diagnosis of skin cancer and high costs for the healthcare sector due to unnecessary removal of benign tumours. The reason for the slow upskilling of doctors is probably that it is difficult for a young doctor to get visual feedback on a large number of skin tumours of different types.
We're working to improve this by giving doctors and nurses access to training in skin diagnostics via the learning app - Dermloop Learn. (See photos from the app store)
The app exposes the doctor to a huge library (20,000+ cases) of images of previous skin tumours and their diagnosis. Doctors are guided through a learning process optimised by artificial intelligence, which continuously measures the doctor's multi-dimensional competence and selects the optimal learning material based on this.
Results and effects:
As part of the research project, 76 medical students with no previous experience were trained in skin cancer diagnosis for 8 days. And they reached the same level as doctors with 3-4 years of experience. Combined with a tele-dermatology extension of the system, there is plenty of potential - in terms of economics, skills development and patient safety. For example, the research group behind the project has estimated that up to €800 million could be saved in healthcare. DKK 800 million a year if the technology were implemented nationally and used by all general practitioners, dermatologists, plastic surgeons and pathologists.
AI for improved diagnosis of pregnant women
In the SONAI (Sonography AI for pregnancy) project, we are working to develop AI models that support clinicians' performance when performing ultrasound scans. In Denmark, all women are offered an ultrasound scan at around 12 and 20 weeks of pregnancy as part of their routine antenatal care. Ultrasound is an important tool for examining pregnant women and their unborn children. We use ultrasound, among other things, to check for malformations in the unborn child around week 20.
Undetected congenital malformations of the heart, for example, can have serious and lifelong consequences. And although we're good at ultrasound scans in Denmark, we don't find all serious malformations and conditions - partly because it takes years of training to get good at these scans.
The aim of the SONAI project is to improve the diagnosis of pregnant women by providing AI-based feedback to clinicians performing ultrasound scans.
The project has been selected by the Danish Regions to be an AI Signature Project and has been awarded funding from the Danish Finance Act as well as a number of Danish foundations, including the Innovation Fund (DIREC), Aasa and Ejnar Danielsens Fond, Johannes Fogs Fond, Dagmar Marshalls Fond, RH-OUH forskningsfonden, and Region Hovedstaden Innovationspulje. The project is the result of a strong collaboration between CAMES and DTU Compute and the Department of Computer Science at the University of Copenhagen.
Acute caesarean section and AI
An emergency caesarean section is performed when the birth does not go as planned. Complications during labour can be life-threatening for mother or baby, and in these situations it is necessary to deliver the baby as soon as possible.
The quality of patient care in emergency caesarean section depends on many factors. For example, the indication for the caesarean section, the degree of danger to mother or baby, the mother's BMI, previous abdominal operations, psychological factors of the parents-to-be, the size of the baby and the type of anaesthesia can all have an impact on the quality of patient care. Furthermore, the individual, collective and relational competencies of the team will influence both professional quality and patient-perceived quality.
Using AI models, it is possible to identify patterns in large data sets where multiple diverse factors need to be investigated simultaneously. Furthermore, AI models are able to explore the relative importance of the factors. This knowledge is particularly important when planning future teaching and quality improvement initiatives.
Training of robot-assisted cardiac surgery
Robotic-assisted heart surgery performed through small holes in the chest using a robot is a more gentle surgical method than traditional "open" heart surgery. Despite its advantages, the method is slowly spreading around the world.
One of the reasons is the lack of training and competence assessment of cardiac surgeons in robotic surgery.
In the PhD project, the researchers want to validate a concrete competence assessment method for robot-assisted cardiac surgery. An international panel of robotic surgery experts has been assembled to help establish expert standards for competency assessment of new robotic surgeons. Next, the amount of training required to achieve expert level for new robotic surgeons in a simulated environment will be investigated.
Aims and objectives:
The results of the study will help establish competency-based training for cardiac surgeons, so that we can also implement this new and more gentle surgical method in Denmark. In addition, the study will generate new knowledge on how to design models that can be used for training without involving real patients.
The project is the result of a collaboration between European experts in robotic-assisted cardiac surgery (Belgium, the Netherlands, Spain, Czech Republic), cardiac surgery specialists (Denmark) and medical education researchers (Copenhagen Academy for Medical Education and Simulation and Western University, London Health Sciences Center, Canada). The project is carried out at Aalborg University Hospital.
The PhD students carrying out the project are: Gennady V. Atroshchenko, Specialist in Thoracic Surgery, Department of Cardiothoracic Surgery, Aalborg University Hospital.
PhD student at the Department of Clinical Sciences and Aalborg University.
Responsible for research and course management in robot-assisted cardiac surgery, ROCnord, Aalborg.
3D printed models for robot-assisted colorectal cancer
Colorectal cancer is a common disease, and in Denmark about 3,400 people are diagnosed with colorectal cancer each year. Surgical removal of the cancer is one of the cornerstones of treatment, and there is an increase in the number of robotic-assisted operations.
To meet a greater need for surgeon training and to develop training opportunities, we have developed a 3D printed phantom, based on patient scans, to train robotic surgical removal of the right part of the colon.
The PhD project investigates whether it is possible to perform reliable competence assessments of surgeons when performing an advanced robotic surgical procedure for colon cancer. Furthermore, it is investigated whether the competence assessment performed in the simulated environment is consistent with the surgeon's performance during real operations,
The researchers behind the project are also looking at the following
- What basic surgical skills a robotic surgeon should have
- What assessment tools are available to assess this, whether the assessment tools are reliable
- Whether the assessment tools can be used to identify a learning need in the individual surgeon
The PhD project is carried out as a collaboration between Kolding Hospital in the Southern Region and CAMES. The PhD student carrying out the project is: Peter Hertz, Reserve Physician, Organ Surgical Department, Lillebølt Hospital, Kolding Hospital. PhD student at the Department of Regional Health, University of Southern Denmark.
Example from the laboratory - setup for colon cancer study
Machine learning in robotic assisted prostate removal
Prostate cancer is one of the most common cancers worldwide, accounting for about 15% of cancer diagnoses in men.
For localised prostate cancer, many people have a robot-assisted radical prostatectomy. It aims to achieve cancer control while maintaining continence and potency. These patient outcomes are highly dependent on the surgeon's level of experience both in general, but also on the day itself.
The experience level of surgeons is generally described in terms of the number of operations performed to date, but this does not tell us anything about how the surgeon performs each operation. It may therefore be difficult at this stage to predict patient outcomes for individual patients.
Robotic surgery now makes it easier to follow the surgeon's movements and actions during the operation. These are automatically recorded by the robot, and new research suggests that this data can be used to predict patient outcomes.
The PhD project investigates. Whether we can predict both short-term and long-term patient outcomes in men who have undergone robot-assisted radical proctomy using the surgeon's movement patterns pg actions.
The project is carried out as a collaboration between the Urological Research Unit / Copenhagen Prostate Cancer Center and the Copenhagen Academy for Medical Education and Simulation.
Rikke Groth Olsen, PhD student at the University of Copenhagen and Copenhagen Prostate Cancer Center, Department of Urology, Copenhagen University Hospital - Rigshospitalet, Copenhagen, Denmark.
Team training in robotic surgery
The PhD project is about investigating the non-technical skills of the robotic surgical team.
The robotic surgical team differs from other health professional teams in that one of the team members - the surgeon - is physically separated from the rest of the team and the patient bed. This affects teamwork, including coordination. Among other things, the team does not have eye contact with the surgeon during the operation, who also cannot see the operating theatre, but only the video screen with the operating field.
We examine and compare how the experienced and inexperienced robotic surgical teams coordinate their work to optimize teamwork and patient safety. Team coordination has an impact on workflow and on the risk of errors during surgery. Training teamwork can reduce errors and increase patient safety
The project contributes to the development of the Capital Region's robotic surgery training, where teamwork is trained to increase patient safety in both routine and emergency situations.
The PhD students carrying out the project are: Doctor Jannie Lysgaard Poulsen, who is a PhD student at the University of Copenhagen and at the Copenhagen Academy for Medical Education and Simulation at Herlev Hospital.
Automated competence assessment of robotic surgeons using AI
Robotic surgery is increasingly used - both in Denmark and abroad. With the introduction of new technology also comes a need for training and continuous assessment to ensure safety in treatment.
So far, competence assessment has been based on expert surgeons' assessment of the skills of future surgeons. Artificial Intelligence (AI), on the other hand, represents a new way of assessing competence and may ensure that future surgeons acquire the necessary skills before operating independently.
In a national collaboration between Aalborg University Hospital and CAMES, a multidisciplinary team of doctors and engineers will use artificial intelligence to develop competence assessment tools for robotic surgeons. This could reduce errors and increase the quality of robot-assisted kidney surgery.
PhD student conducting the project is Nasseh Hashemi, MD
PhD student at the Department of Clinical Sciences, Aalborg University and Nordsim, Center for Skills Training and Simulation and ROCnord, Aalborg
How we work
The research in CAMES is oriented towards all the different professional groups, specialties and career levels that exist in health care. Some of the research is aimed at individual groups, but much of what we do is also about the interactions between groups - and about how healthcare working systems can be improved.
Research at CAMES has traditionally brought together actors who draw on very different experiences in terms of knowledge and practice: clinicians (from trainees to experts), innovative developers (from start-ups to international companies) and medical education researchers (from PhD students to professors).
We see this as a great strength, because we have learned that interdisciplinary project teams with different competences are part of the key to research that moves.
Meet the researchers
You can always find contact details and more information about the individual CAMES researcher by clicking through to our directory.
Researcher of the month
Find out more about selected research projects
Here we focus on the many projects and talented researchers associated with CAMES, who work hard every day to develop new knowledge, tools and technology in simulation-based education in healthcare.
Use the arrows to dive into selected research projects as described by the researchers themselves.
Check out the VR simulator in use
The VR BOSS project (Virtual Reality Basic Osteosynthesis Surgery Simulation) is an excellent example of how we at CAMES always work in an application-oriented way with our research. Mads Emil Jacobsen is working on his PhD to develop and implement a VR simulator for education, training and competence assessment in surgical treatment of bone fractures. Here you can see how the VR simulator works when surgeons are training in fracture surgery.