A machine learning approach to stratify patients with hypermobile Ehlers‐Danlos syndrome/hypermobility spectrum disorders according to disorders of gut brain interaction, comorbidities and quality of life
2025

Machine Learning to Classify Patients with Ehlers-Danlos Syndrome and Gut Disorders

Sample size: 1044 publication 10 minutes Evidence: high

Author Information

Author(s): Anisa Choudhary, Asma Fikree, James K. Ruffle, Kazuya Takahashi, Olafur S. Palsson, Imran Aziz, Qasim Aziz

Primary Institution: Queen Mary University of London

Hypothesis

We hypothesize that those with the largest number of DGBIs will have more non-GI comorbidities and lower quality of life in comparison with those with no DGBI overlap.

Conclusion

Subgroups of patients with hypermobile Ehlers-Danlos syndrome have a high prevalence of functional foregut disorders and irritable bowel syndrome, leading to poorer psychological health and quality of life.

Supporting Evidence

  • Patients with hEDS/HSD and functional foregut disorders have increased somatization and psychological disorders.
  • Cluster analysis revealed three distinct groups based on gut disorders.
  • Patients with overlapping DGBIs experience poorer quality of life compared to those with hEDS/HSD alone.

Takeaway

Some people with a condition called Ehlers-Danlos syndrome also have tummy problems, and those with more tummy issues feel worse overall.

Methodology

The study used machine learning techniques to analyze a cohort of 1044 individuals with hypermobile Ehlers-Danlos syndrome and stratified them into clusters based on their gut disorders and comorbidities.

Potential Biases

Differences in patient profiles between datasets may introduce selection bias.

Limitations

The study used retrospective datasets which may have led to the exclusion of valuable information and differences in assessment methods between cohorts.

Participant Demographics

The mean age of participants was 40 years, with 87.8% being female.

Statistical Information

P-Value

p<0.0001

Statistical Significance

p<0.0001

Digital Object Identifier (DOI)

10.1111/nmo.14957

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication