European Rare Disease Specialists Ready to Embrace ML for Improved Diagnosis

Rare Daily Staff

Rare disease specialists in Europe don’t have a lot of experience with and limited knowledge of machine learning but recognized that the technology has the potential to revolutionize the diagnosis and treatment of rare diseases by reducing the diagnostic odyssey for people with a rare condition.

A study in the Orphanet Journal of Rare Diseases used a combination of an online survey and focus group discussion with medical professionals and others affiliated with members of the European Reference Networks, virtual healthcare provider networks that connect physicians with specialists with deep knowledge of rare and complex diseases.

The study sought to gauge the European Reference Networks for rare diseases readiness to embrace machine learning technologies. The online survey yielded 423 responses.

The respondents considered improved diagnostic accuracy the greatest potential benefit. The synthesis of clinical information was also seen as a major benefit.

The lack of training in these new technologies is seen as an obstacle to their adoption, and most respondents wanted to see the use of machine learning as an optional, but recommended part of the diagnostic process for rare diseases.

Participants in the focus group expect machine learning will have an important impact on healthcare and rare diseases specifically. But they said as most healthcare professionals lack competency with the technology, a close collaboration with developers will be necessary to ensure that results are valid and reliable.

Machine learning seems well suited for not only cutting the diagnostic odyssey for people with rare diseases by helping physicians reach an accurate diagnosis earlier by recognizing how symptoms may point to a condition a physician may not know enough about to recognize, but also help personalize treatment to individual patients and improve clinical decision making.