Clinical, genomic, and proteomic perspectives in the analysis of comorbid conditions in type 2 diabetes mellitus: a retrospective study

Angelina Thomas Villikudathil, Declan H. Mc Guigan, Andrew English

Research output: Contribution to journalArticlepeer-review

Abstract

Aim
Type-2 Diabetes Mellitus (T2DM) affects millions globally, with escalating rates. It often leads to undiagnosed complications and commonly coexists with other health conditions. This study investigates two types of prevalent comorbidities related to T2DM—the circulatory system (DCM1) and digestive system diseases (DCM2)—using clinical, genomic and proteomic datasets. The aim is to identify new biomarkers by applying existing machine learning (ML) based techniques for early detection, prognosis and diagnosis of these comorbidities.

Methods
Here, we report a cross-sectional retrospective analysis from a T2DM dataset of T2DM associated concordant comorbidities (diseases with shared pathophysiology and management) from the Diastrat cohort (a T2DM cohort) recruited at the Northern Ireland Centre for Stratified Medicine (NICSM), in Northern Ireland.

Results
In the clinical data analysis, we identified that lipidemia was shown to negatively correlate with depression in the DCM1 group while positively correlate with depression in the DCM2 group. In genomic analysis, we identified statistically significant variants rs9844730 in procollagen-lysine (PLOD2), rs73590361 in beta-1,4-N-acetyl- galactosaminyl-transferase (B4GALNT3) and rs964680 in A kinase (PRKA) anchor protein 14 (AKAP14) which appear to differentiate DCM1 and DCM2 groups. In proteomic analysis, we identified 4 statistically significant proteins: natriuretic peptides B (BNP), pro-adrenomedullin (ADM), natriuretic peptides B (NT-proBNP) and discoidin (DCBLD2) that can differentiate DCM1 and DCM2 groups and have built robust ML model using clinical, genomic, and proteomic markers (0.83 receiver operative characteristics curve area, 84% positive predictive value and 83% negative predictive value and a classification accuracy of 83%) for prediction of DCM1 and DCM2 groups.

Conclusion
Our study successfully identifies novel clinical, genomic, and proteomic biomarkers that differentiate between circulatory and digestive system comorbidities in Type-2 Diabetes Mellitus patients. The machine learning model we developed demonstrates strong predictive capabilities, providing a promising tool for the early detection, prognosis, and diagnosis of these T2DM-associated comorbidities. These findings have the potential to enhance personalized management strategies for patients with T2DM, ultimately improving clinical outcomes. Further research is needed to validate these biomarkers and integrate them into clinical practice.
Original languageEnglish
JournalActa Diabetologica
Volume(2024)
DOIs
Publication statusPublished - 7 Nov 2024

Fingerprint

Dive into the research topics of 'Clinical, genomic, and proteomic perspectives in the analysis of comorbid conditions in type 2 diabetes mellitus: a retrospective study'. Together they form a unique fingerprint.

Cite this