Allergy in children identified by new algorithm

Allergic diseases, such as asthma, eczema or hay fever, are very common childhood diseases worldwide

A new algorithm can diagnose allergies in children using artificial intelligence. The algorithm does this on the basis of DNA from nasal cells taken with a nasal swab. By looking at just three spots in the DNA, the algorithm can determine whether a child has an allergy.

The algorithm appears to be able to detect allergies not only in European children, but also in other population groups. The algorithm was developed during research by UMCG, the Medical University of Hannover (MHH) and the artificial intelligence (AI) firm MIcompany. The research, recently published in Nature Communications, contributes to a better understanding of these complex diseases and provides opportunities for innovative diagnostics in the future.

Allergies burden the quality of life
Allergic diseases, such as asthma, eczema or hayfever, are very common childhood diseases worldwide, which significantly burden the quality of life of patients and the healthcare system. The number of patients with these diseases has increased rapidly over the past 50 years. Scientists expect that by 2030, half of the European population will suffer from an allergic disease. Although genetic and environmental factors are known to play a major role in its development, the precise mechanisms are still unknown. As a result, it remains a chronic disease for which there is currently no permanent cure.

Diagnosis in young children is complex
There is a need to predict the risk of allergic diseases, especially in young preschool children. In these children, allergies are difficult to diagnose. Prof. Dr. Gerard Koppelman, pediatric pulmonologist at UMCG and initiator of the project, explains: ‘Young children often suffer from short-term ailments where the symptoms can resemble an allergic condition, such as shortness of breath or frequent colds. It is therefore difficult to diagnose a chronic allergic disease. An algorithm provides additional insight to make a better diagnosis.’

Three DNA markers in nasal cells determine allergy
In the past decade, new techniques have doubled the amount of knowledge about human DNA every seven months. This knowledge provides many new insights into diseases. GRIAC (Groningen Research Institute for Asthma and COPD) has DNA data from blood and nasal cells from participants in the national birth cohort ‘Prevention and prevalence of asthma and mite allergy’ (PIAMA). In this cohort, the participants are followed from birth in 1996/97 and share their health data. By analyzing this DNA data on a large scale, the researchers found three DNA markers in nasal cells that were crucial for developing an allergic disease. They were also able to demonstrate that these three DNA markers are associated with an inflammatory response in nasal cells. Based on these three DNA markers, the developed algorithm can calculate a risk score for an allergic disorder and use it to make a diagnosis.

Blood test versus nasal swab
Different methods are now often used to diagnose an allergic disease in children. A pulmonary function test is usually performed in asthma, but it is often not yet possible in younger children (up to 6 years), so the doctor must make the diagnosis based on certain symptoms, such as shortness of breath and a wheezing sound when breathing. In order to determine hay fever, in addition to looking at known symptoms such as a cold and runny nose, a blood test or a skin test is also done. A blood test is especially a test that can be experienced as bothersome for (small) children. To make diagnosing children more friendly and efficient, Koppelman wants to develop a nasal swab test based on the three DNA markers identified in the current study.

Algorithm works well in different populations
The algorithm also works well for children from non-European populations. The algorithm accurately diagnosed allergic disease in an independent Puerto Rican cohort. This indicates that the algorithm is indeed capturing common biological signals present in other ethnic groups. This external review is the gold standard in medical research to test whether results are reliable. The current algorithm was developed for 16-year-olds. As a result, the researchers found that the algorithm is less accurate in two cohorts of children aged 6 years. Koppelman: “Although this discovery is an important step forward in the application of artificial intelligence to diagnose allergies, we will have to adapt our algorithm to the younger age group in the future.” In the future, Koppelman wants to use the algorithm to diagnose allergies in young children using a nasal swab.

Artificial intelligence for complex disorders
In 2019, UMCG and MIcompany joined forces to conduct research applying the latest artificial intelligence techniques to complex biomedical problems. At the initiative of Gerard Koppelman and Marnix Bügel (founding partner MIcompany), the new algorithm was developed by a joint research team as part of this collaboration. The combination of expertise was key to the success of this study: artificial intelligence enables researchers to analyze large and complex data sets in a new way, and a deep understanding of such data and the underlying biology is essential to reach meaningful conclusions .

Read the publication of the research in Nature Communications here.

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

Click on the tags below for any relevant posts…

Leave a Comment