Machine learning analysis of the UK Biobank reveals prognostic and diagnostic immune biomarkers for polyneuropathy and neuropathic pain in diabetes
Authors' conclusion
Lifestyle factors and blood biomarkers predict the later development of DPN and may relate to DPN pathomechanisms. Our results are consistent with DPN as a disease involving systemic inflammation. We advocate for the use of these biomarkers clinically to predict future DPN risk and improve early diagnosis.
Study context
- Population
- People with diabetes in the UK Biobank
- Participants
- 11,047 people
- Outcome
- Ranking of 329 risk factors for DPN and DPN with chronic neuropathic pain
Methodological detailsUK Biobank, machine learning (Integrated Disease Explanation and Risk Scoring (IDEARS) platform), mean SHAP score risk ranking
- UK Biobank
- Machine learning (IDEARS platform)
- Mean SHAP score risk ranking
Main finding
As reported in the abstract
Risk factors for DPN
Discriminative performance of IDEARS models
AUC > 0.64
Observational data: associations, not effects.
Further findings
- C-reactive protein (CRP) significantly elevated in diabetic polyneuropathy (DPN) with chronic neuropathic pain vs DPN without pain
Original publication
Machine learning analysis of the UK Biobank reveals prognostic and diagnostic immune biomarkers for polyneuropathy and neuropathic pain in diabetes. Diabetes Res Clin Pract. Published 19 May 2023. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →