JoVE - Journal of Visualized Experiments
JoVE Visualize
Contact Us

Development and external validation of an algorithm for self-identification of risk for microvascular complications in patients with type 1 diabetes

  • 0Department of Endocrinology and Metabolism, Peking University People's Hospital, Beijing, China.
Diabetes, Obesity & Metabolism +

|

November 25, 2024

|

November 25, 2024

View abstract on PubMed

Summary

This summary is machine-generated.

Machine learning models can help type 1 diabetes (T1D) patients identify microvascular complication risks using self-reported data. These tools empower patients for earlier healthcare engagement and improved outcomes.

Area Of Science

  • Biomedical informatics
  • Artificial intelligence in healthcare
  • Diabetes management

Background

  • Microvascular complications like diabetic retinopathy, nephropathy, and neuropathy are serious outcomes of poorly managed type 1 diabetes (T1D).
  • Early detection and intervention are critical for improving patient prognosis in T1D.
  • Developing accessible tools for risk assessment outside clinical settings is essential.

Purpose Of The Study

  • To develop and externally validate machine learning (ML) models for the self-identification of microvascular complication risks in individuals with T1D.
  • To assess the performance of ML models using self-reported patient data.
  • To provide a tool for T1D patients to proactively understand their health risks.

Main Methods

  • Utilized data from 911 T1D patients, including 15 self-reported variables.
  • Developed ML models using the XGBoost algorithm and cross-validation, selecting 5 key variables.
  • Externally validated models using an online survey of 157 T1D patients, evaluating performance with AUROC metrics.

Main Results

  • Internal validation showed high AUROC values: 0.889 for diabetic retinopathy (DR), 0.844 for diabetic nephropathy (DN), and 0.839 for diabetic peripheral neuropathy (DPN).
  • External validation achieved AUROC values of 0.762 for DR, 0.718 for DN, and 0.721 for DPN.
  • Prevalence rates for DR and DPN were significantly higher in the external validation set compared to the development set.

Conclusions

  • ML models based on self-reported data show promise as a self-identification tool for T1D microvascular complications.
  • These models can empower T1D patients to assess their risks independently.
  • The findings encourage earlier patient engagement with healthcare services for timely intervention.

Keywords:

Related Concept Videos

Diabetes: Symptoms, Diagnosis, and Complications 01:15

506

For most patients, experiencing several weeks of polyuria, polydipsia, fatigue, and significant weight loss may indicate the presence of diabetes. Furthermore, adults displaying the phenotypic appearance of type 2 diabetes (particularly those who are obese and not initially insulin-requiring), may have islet cell autoantibodies, suggesting autoimmune-mediated β cell destruction and a diagnosis of latent autoimmune diabetes of adults (LADA). The categorization of glucose homeostasis is...

Diabetes Mellitus: Overview and Type I Subtype 01:22

2.4K

Diabetes mellitus is a chronic metabolic disorder characterized by high blood glucose levels due to inadequate insulin production, insulin resistance, or both. The condition affects millions worldwide and can significantly impact their health and quality of life.
Type 1 diabetes is an autoimmune disease in which the immune system mistakenly attacks and destroys the insulin-producing beta cells in the pancreas. As a result, the body is unable to produce sufficient insulin, and individuals with...

Carbohydrate Metabolism 01:36

10.8K

Carbohydrates are polymers composed of molecules containing atoms of carbon, hydrogen and oxygen. One gram of carbohydrate can provide four kilo-calories of energy, which makes it the most efficient instant energy source.
Starch accounts for approximately 60% of the carbohydrates consumed by humans. Since amylase enzymes cannot function in the stomach's acidic environment, starch can only be digested in the mouth and small intestine. Simple sugars are found naturally in milk and fruits in...

Diabetes: Management and Pharmacotherapy 01:15

236

The therapy for diabetes aims to alleviate hyperglycemia-related symptoms, prevent acute metabolic decompensation, and reduce chronic end-organ complications. Glycemic control is evaluated through short-term (self-monitoring, continuous glucose monitoring) and long-term (A1c, fructosamine) metrics, enabling near real-time tracking of blood glucose levels and reflecting glycemic control over specific time frames.
Insulin remains the cornerstone of treatment for most patients with type 1 and many...