Identifying subtypes of chronic kidney disease with machine learning: development, internal validation and prognostic validation using linked electronic health records in 350,067 individuals

Identifying subtypes of type 2 diabetes mellitus with machine learning: development, internal validation, prognostic validation and medication burden in linked electronic health records in 420 448 individuals

INTRODUCTION

None of the studies of type 2 diabetes (T2D) subtyping to date have used linked population-level data for incident and prevalent T2D, incorporating a diverse set of variables, explainable methods for cluster characterization, or adhered to an established framework. We aimed to develop and validate machine learning (ML)-informed subtypes for type 2 diabetes mellitus (T2D) using nationally representative data.

RESEARCH DESIGN AND METHODS

In population-based electronic health records (2006-2020; Clinical Practice Research Datalink) in individuals ≥18 years with incident T2D (n=420 448), we included factors (n=3787), including demography, history, examination, biomarkers and medications. Using a published framework, we identified subtypes through nine unsupervised ML methods (K-means, K-means++, K-mode, K-prototype, mini-batch, agglomerative hierarchical clustering, Birch, Gaussian mixture models, and consensus clustering). We characterized clusters using intracluster distributions and explainable artificial intelligence (AI) techniques. We evaluated subtypes for (1) internal validity (within dataset; across methods); (2) prognostic validity (prediction for 5-year all-cause mortality, hospitalization and new chronic diseases); and (3) medication burden.

RESULTS

Development: We identified four T2D subtypes: metabolic, early onset, late onset and cardiometabolic. Internal validity: Subtypes were predicted with high accuracy (F1 score >0.98). Prognostic validity: 5-year all-cause mortality, hospitalization, new chronic disease incidence and medication burden differed across T2D subtypes. Compared with the metabolic subtype, 5-year risks of mortality and hospitalization in incident T2D were highest in late-onset subtype (HR 1.95, 1.85-2.05 and 1.66, 1.58-1.75) and lowest in early-onset subtype (1.18, 1.11-1.27 and 0.85, 0.80-0.90). Incidence of chronic diseases was highest in late-onset subtype and lowest in early-onset subtype. Medications: Compared with the metabolic subtype, after adjusting for age, sex, and pre-T2D medications, late-onset subtype (1.31, 1.28-1.35) and early-onset subtype (0.83, 0.81-0.85) were most and least likely, respectively, to be prescribed medications within 5 years following T2D onset.

CONCLUSIONS

In the largest study using ML to date in incident T2D, we identified four distinct subtypes, with potential future implications for etiology, therapeutics, and risk prediction.

Circulating miR-423-5p levels are associated with carotid atherosclerosis in patients with chronic kidney disease

BACKGROUND AND AIMS

Carotid atherosclerosis is associated with an elevated risk of stroke in patients with chronic kidney disease. However, the molecular basis for the incidence of carotid atherosclerosis in patients with CKD is poorly understood. Here, we investigated whether circulating miR-423-5p is a crucial link between CKD and carotid atherosclerosis.

METHODS AND RESULTS

We recruited 375 participants for a cross-sectional study to examine the occurrence of carotid plaque and plaque thicknesses. Levels of miR-423-5p were determined by qPCR analysis. We found that non-dialysis CKD patients had higher circulating exosomal and plasma miR-423-5p levels, and dialysis-dependent patients had lower miR-423-5p levels than non-dialysis CKD patients. After excluding for the influence of dialysis patients, linear regression analysis indicated that levels of circulating miR-423-5p are negatively correlated with eGFR (P < 0.001). Higher plasma miR-423-5p levels were associated with the incidence and severity of carotid plaques. In parallel, we constructed a murine model of CKD with a 5/6 nephrectomy protocol and performed RNA sequencing studies of aortic tissues. Consistent with these findings in CKD patients, circulating exosomal miR-423-5p levels in CKD mice were elevated. Furthermore, our RNA-seq studies indicated that the putative target genes of miR-423-5p were related to oxidative stress functions for aorta of CKD mice.

CONCLUSION

Levels of miR-423-5p are associated with the presence and severity of carotid plaque in CKD. Data from our mouse model suggests that miR-423-5p likely influences gene expression programs related to oxidative stress in aorta of CKD mice.