To develop and validate a predictive nomogram for Diabetic Cardiac Autonomic Neuropathy (DCAN) using readily available clinical variables, enhancing early detection and management in clinical settings.
Key Findings:
The prevalence of DCAN in the study population was 45.0%.
Seven independent predictors for DCAN were identified: history of diabetic retinopathy or diabetic kidney disease, diabetes duration, age, heart rate, fasting plasma glucose, and HbA1c, which have significant implications for patient management.
The LR model showed the best performance in the validation cohort with an AUC of 0.838 and sensitivity of 77.0%, indicating its potential for clinical application.
Interpretation:
The developed nomogram and web calculator provide a user-friendly tool for early risk assessment of DCAN in diabetes patients, potentially improving patient outcomes.
Limitations:
The study was conducted in a single center, which may limit generalizability.
Retrospective design may introduce bias in data collection, affecting the reliability of the findings.
Conclusion:
A high-sensitivity prediction model for DCAN was developed and validated, offering a cost-effective tool for risk assessment in diabetes, emphasizing the importance of early detection and management.
"AI could help reduce the burden on ophthalmology services by triaging large numbers of patients with diabetes and allowing specialists to focus on those who most urgently need care."
