Dataset Information

Precision diagnostic approach to predict 5-year risk for microvascular complications in type 1 diabetes.

ABSTRACT:

Background

Individuals with long standing diabetes duration can experience damage to small microvascular blood vessels leading to diabetes complications (DCs) and increased mortality. Precision diagnostic tailors a diagnosis to an individual by using biomedical information. Blood small molecule profiling coupled with machine learning (ML) can facilitate the goals of precision diagnostics, including earlier diagnosis and individualized risk scoring.

Methods

Using data in a cohort of 537 adults with type 1 diabetes (T1D) we predicted five-year progression to DCs. Prediction models were computed first with clinical risk factors at baseline and then with clinical risk factors and blood-derived molecular data at baseline. Progression of diabetic kidney disease and diabetic retinopathy were predicted in two complication-specific models.

Findings

The model predicts the progression to diabetic kidney disease with accuracy: 0.96 ± 0.25 and 0.96 ± 0.06 area under curve, AUC, with clinical measurements and with small molecule predictors respectively and highlighted main predictors to be albuminuria, glomerular filtration rate, retinopathy status at baseline, sugar derivatives and ketones. For diabetic retinopathy, AUC 0.75 ± 0.14 and 0.79 ± 0.16 with clinical measurements and with small molecule predictors respectively and highlighted key predictors, albuminuria, glomerular filtration rate and retinopathy status at baseline. Individual risk scores were built to visualize results.

Interpretation

With further validation ML tools could facilitate the implementation of precision diagnosis in the clinic. It is envisaged that patients could be screened for complications, before these occur, thus preserving healthy life-years for persons with diabetes.

Funding

This study has been financially supported by Novo Nordisk Foundation grant NNF14OC0013659.

SUBMITTER: Al-Sari N

PROVIDER: S-EPMC9092516 | biostudies-literature | 2022 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Precision diagnostic approach to predict 5-year risk for microvascular complications in type 1 diabetes.

Al-Sari Naba N Kutuzova Svetlana S Suvitaival Tommi T Henriksen Peter P Pociot Flemming F Rossing Peter P McCloskey Douglas D Legido-Quigley Cristina C

EBioMedicine 20220506

<h4>Background</h4>Individuals with long standing diabetes duration can experience damage to small microvascular blood vessels leading to diabetes complications (DCs) and increased mortality. Precision diagnostic tailors a diagnosis to an individual by using biomedical information. Blood small molecule profiling coupled with machine learning (ML) can facilitate the goals of precision diagnostics, including earlier diagnosis and individualized risk scoring.<h4>Methods</h4>Using data in a cohort o ...[more]

PMID: 35533498

Similar Datasets

Project description:BackgroundCross-sectional studies found that frailty was associated with prevalent diabetic microvascular complications (DMC). Longitudinal evidence in this regard is inconclusive and insufficient. We aimed to prospectively evaluate the association of pre-frailty and frailty with DMC in patients with type 2 diabetes (T2D).MethodsWe included 18,062 adults (mean age 59.4 ± 7.2 years, 37.4% female) with T2D at baseline in the UK Biobank. Frailty was defined using the frailty phenotype according to five components (weight loss, exhaustion, low physical activity, slow gait speed, and low grip strength). DMC, defined as diabetic nephropathy, diabetic neuropathy, or diabetic retinopathy, was identified using hospital inpatient records and death registries. Cox proportional hazard regression models considering competing risks were used to evaluate the associations of frailty phenotype with overall DMC events and subtypes.ResultsAmong all participants, 6101 (33.8%) were classified as non-frail, 10,073 (55.8%) were classified as pre-frail, and 1888 (10.4%) were classified as frail. During a median follow-up of 12.0 years, 3678 DMC cases were documented, including 2213 diabetic nephropathy, 1520 diabetic retinopathy, and 673 diabetic neuropathy events. In the multivariable-adjusted model, compared with participants with non-frail, both pre-frailty and frailty were significantly associated with increased risk of overall DMC (HR 1.10, 95% CI: [1.02, 1.18] for pre-frailty and HR 1.52 [95% CI: 1.36, 1.69] for frailty). Similar results were observed in the subtypes of DMC. For each one-point increase in frailty phenotype score, the risk of overall DMC, diabetic nephropathy, diabetic retinopathy, and diabetic neuropathy event increased by 13%, 16%, 10%, and 20%, respectively.ConclusionsBoth pre-frailty and frailty were associated with an increased risk of DMC in patients with T2D. These findings have important implications for integrating early assessment and surveillance of frailty in diabetes and may favor the identification of at-risk patients.

Dataset Information

Precision diagnostic approach to predict 5-year risk for microvascular complications in type 1 diabetes.

Background

Methods

Findings

Interpretation

Funding

Publications

Precision diagnostic approach to predict 5-year risk for microvascular complications in type 1 diabetes.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets