Allergic diseases, such as asthma, eczema or hay fever, are very common childhood diseases worldwide that place a significant burden on patients' quality of life and healthcare systems. The prevalence of these diseases has been increasing rapidly for more than 50 years. Researchers expect half of the European population to suffer from an allergic disorder by 2030. Although genetic and environmental factors are known to play a major role in its development, the exact mechanisms are still unknown. As a result, it remains a chronic disease for which no permanent cure is currently available.
There is a need to predict the risk of allergic diseases, especially in young, pre-school children. In these children, allergy is difficult to diagnose. Prof. Gerard Koppelman, paediatric pulmonologist at UMCG and initiator of the project, explains: 'Young children often suffer from brief illnesses in which the symptoms may resemble an allergic condition, for example attacks of shortness of breath or frequent colds. It is then difficult to diagnose chronic allergic disease. After all, we should try to avoid prescribing medication for an allergic condition if it is not necessary. An algorithm provides additional insight to make a better diagnosis.'
Over the past decade, the amount of human DNA data has doubled every seven months. This data comes from different layers of the human genome, called multi-omics, and offers a new and unprecedented level of insight into diseases. The Groningen Research Institute for Asthma and COPD (GRIAC) has such unique DNA data from blood and nasal cells of participants in the national birth cohort 'Prevention and Incidence of Asthma and Mite Allergy' (PIAMA). In this cohort, participants are followed from birth in 1996/97. By analysing this DNA data on a large scale, the researchers found three DNA makers in nasal cells that were determinants of developing allergic disease. They were also able to show that these three DNA markers were associated with an inflammatory response in nasal cells. The developed algorithm can calculate a risk score for allergic disease based on these three DNA markers and use it to make a diagnosis.
To diagnose allergic disease in children, different methods are now often used. For asthma, a lung function test is usually done, but this is often not yet possible in younger children (up to 6 years old), so the doctor has to make the diagnosis based on certain symptoms, such as shortness of breath and a wheezing sound when breathing. To diagnose hay fever, a blood test or skin test is done in addition to looking at known symptoms such as cold symptoms and a runny nose. A blood test in particular is an invasive test that can be perceived as unpleasant for (young) children. To make diagnosing in children more gentle and effective, Koppelman wants to develop a non-invasive nasal swab based on the three DNA markers identified in the current study.
The algorithm also works well in children in other populations. The algorithm accurately diagnosed allergic diseases in an independent Puerto Rican cohort. This indicates that the algorithm indeed captures general biological signals present in other ethnic groups. This external testing is the golden standard in medical research to test whether the findings are reliable. However, the current algorithm was developed for 16-year-olds. As a result, the researchers found that the algorithm is less accurate two cohorts with 6-year-old children. Koppelman: 'Although this discovery is an important step forward in the application of artificial intelligence to diagnose allergy, we need to calibrate our algorithm for the younger age group in the future.'
In 2019, UMCG and MIcompany joined forces to conduct research by applying the latest techniques in artificial intelligence to complex, biomedical problems. Initiated by Gerard Koppelman and Marnix Bügel (founding partner MIcompany), the new algorithm was developed by a joint research team as part of this public-private partnership. The combination of expertise was key to the success of this study: artificial intelligence enables researchers to analyse large and complex data sets in a new way, and a deep understanding of such data and the underlying biology is crucial to reach meaningful conclusions.
Read the publication in Nature Communications here.
