Machine learning-based risk predictive models for diabetic kidney disease in type 2 diabetes mellitus patients: a systematic review and meta-analysis
Contact us if these videos are not relevant.
Contact us if these videos are not relevant.
View abstract on PubMed
Summary
This summary is machine-generated.Machine learning models show strong performance in predicting diabetic kidney disease (DKD) risk for type 2 diabetes mellitus (T2DM) patients. Further research is needed to address data bias and improve model generalizability.
Area Of Science
- Nephrology
- Medical Informatics
- Data Science
Background
- Machine learning (ML) models are increasingly used to predict diabetic kidney disease (DKD) risk in type 2 diabetes mellitus (T2DM) patients.
- Variability in ML model performance hinders widespread clinical adoption.
- A systematic review and meta-analysis were conducted to evaluate ML model performance and applicability for DKD risk prediction.
Purpose Of The Study
- To systematically review and meta-analyze the performance of ML models for predicting DKD risk in T2DM patients.
- To assess the clinical applicability of these predictive models.
- To identify key research gaps in the field.
Main Methods
- A systematic literature search was performed on PubMed, Embase, Cochrane Library, and Web of Science.
- Studies published up to April 18, 2024, using ML algorithms for DKD risk prediction in T2DM were included.
- The primary performance metric was the area under the receiver operating characteristic curve (AUC); risk of bias was assessed using PROBAST.
Main Results
- 26 studies with 94 ML models were included; 25 studies used internal validation, and 8 used external validation.
- The pooled AUC was 0.839 (95% CI 0.787-0.890) for internal and 0.830 (95% CI 0.784-0.877) for external validation.
- Deep learning models achieved the highest pooled AUC (0.863), while random forest models showed the best performance among frequently used models (AUC 0.848).
Conclusions
- ML models demonstrate high performance in predicting DKD risk in T2DM patients.
- Challenges remain regarding data bias in model development and validation.
- Future research should prioritize data transparency, standardization, and multicenter validation for generalizability.
Contact us if these videos are not relevant.
Contact us if these videos are not relevant.
Related Concept Videos
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...
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...