Clinical Report: Creation and assessment of a nomogram for forecasting cardiac autonomic neuropathy in individuals with diabetes
Overview
This study developed and validated a nomogram for predicting diabetic cardiac autonomic neuropathy (DCAN) in diabetes patients using common clinical variables. The nomogram demonstrated high sensitivity and good calibration, offering a practical tool for early risk assessment.
Background
Diabetic cardiac autonomic neuropathy (DCAN) is a significant microvascular complication of diabetes, linked to increased mortality and severe cardiovascular outcomes. Traditional diagnostic methods are complex and underutilized, highlighting the need for simpler, accessible screening tools. This study addresses that gap by creating a predictive nomogram based on readily available clinical data.
Data Highlights
Predictor
Value
Prevalence of DCAN
45.0%
Optimal model AUC
0.838
Sensitivity of LR model
77.0%
Key Findings
The prevalence of DCAN among the study population was 45.0%.
Seven independent predictors for DCAN were identified: history of diabetic retinopathy or kidney disease, diabetes duration, age, heart rate, fasting plasma glucose, and HbA1c.
The logistic regression model provided the best performance with an AUC of 0.838.
The nomogram created from the logistic regression model showed good calibration and clinical utility.
This nomogram can facilitate early risk assessment and personalized management in diabetes patients.
Clinical Implications
Healthcare providers can utilize the developed nomogram to identify patients at high risk for DCAN, enabling earlier intervention and management strategies. The use of common clinical variables makes this tool practical for routine clinical settings.
Conclusion
The study successfully created a user-friendly nomogram for predicting DCAN in diabetes patients, which can enhance early detection and improve patient outcomes. This tool represents a significant advancement in the management of diabetic complications.
