Find diseases earlier with the help of artificial intelligence

by time news

The sooner patients can start treatment, the better the chance of a cure

Lung cancer, chronic obstructive pulmonary disease (COPD) and cardiovascular disease are the main causes of death in the Netherlands and are therefore also referred to as the Big 3. Unfortunately, they are often only discovered when complaints arise, which usually indicates an advanced stage. There is increasing attention for the use of radiological images, such as CT and MRI scans, to detect diseases earlier. The sooner patients can start treatment, the better the chance of a cure.

Within the health care sector it has been known for several years that lung cancer can be detected at an earlier stage using a CT scan. What many people do not yet know is that radiologists can often use the same scans to detect early signs of COPD and cardiovascular disease. Researchers in the B3CARE project are investigating early risk indicators of these diseases on radiological images. In particular, they want to speed up the assessment of these images with the help of artificial intelligence.

Early detection and prevention is crucial
In the project, researchers bring together images from CT and MRI scans from large-scale studies such as ImaLife (Imaging in Lifelines). They then use this data to train computers to recognize early signs of Big-3 diseases. This is done using biomarkers. A biomarker is a measurable data with which you can identify (the chance of) a disease and predict its course. For example, a biomarker for lung cancer is an irregularity in the lung: a lung nodule. This bump may be visible on a low-dose CT scan. An early sign of cardiovascular disease risk is the presence and severity of coronary artery calcification.

‘Early detection and prevention of Big 3 diseases is crucial,’ says Rozemarijn Vliegenthart, project leader of B3CARE. Vliegenthart is a radiologist at the UMCG and an expert in cohort data at UMCG’s Data Science Center in Health (DASH). ‘Together, these diseases are expected to cause the most deaths in 2050. Unfortunately, most people are not diagnosed until the disease has reached an advanced stage and a cure is no longer possible. This is especially the case with lung cancer; at the time of diagnosis, the disease has already spread in most patients, and only 15% survive 5 years. If Big 3 diseases are detected at an early stage, timely treatment can take place and worse disease symptoms can be prevented in many patients.’

One screen for all Big-3 diseases
In the B3CARE project, researchers are preparing for combined screening for all three diseases. Analyzes by the project team show that adding COPD and cardiovascular disease to lung cancer screening greatly improves cost-effectiveness. This means that it is expected that more good life years can be gained at a lower cost. However, the screening will also yield many thousands of scans every year. Assessing this becomes a huge job for radiologists. ‘To support them in this, we train computers with software based on artificial intelligence,’ says Vliegenthart. ‘A large group of Lifelines participants had a scan of the heart and lungs. We used manual software to determine, among other things, the presence and size of lung nodules. Software based on artificial intelligence will probably be able to do this automatically in the future, without a radiologist having to find and measure it himself. We are now testing new, automatic software and comparing it with manual measurements. We work closely with academic and industrial partners who have developed automatic software.’

Pros and cons
But can Big 3 diseases actually always be preventively detected with such a CT screening? Not according to Vliegenthart: ‘If Big-3 screening is introduced, it will always involve weighing up the pros and cons. A CT scan involves a low dose of harmful X-rays and, in addition, early signs of Big-3 diseases at a younger age are rare. It is therefore to be expected that middle-aged or slightly older people in particular will be eligible for screening, probably in combination with risk factors such as smoking. You actually already miss the Big 3 diseases that occur at a younger age. Repeating lung cancer screening is also very important, every year or every other year. It is precisely then that the earlier stages of lung cancer can still be detected in time.’

It is expected that software based on artificial intelligence can help with the measurement of relevant biomarkers in the future. Vliegenthart: ‘Using that information, the computer can then make a proposal for a test result, after which the radiologist evaluates it. Based on this, the screening participant then receives personalized advice, for example about lifestyle, preventive medication, referral and repeat screening.’

Similar software is also under development for screening for other diseases, including breast cancer. Given the large number of radiological examinations that need to be assessed, artificial intelligence can help filter normal tests or put suspect tests at the front of the queue.

Visit the website B3care.nl for more information

Consult the source and/or provider for more information about this message. News may change, include errors or inaccuracies. Also read our disclaimer and please report messages, comments and/or images that go against our terms and conditions.

Click on the tags below for relevant posts, if any…

You may also like

Leave a Comment