Heart Rate Variability measured during rest and after orthostatic challenge to detect autonomic dysfunction in Type 2...

Area of Science:

• Cardiology
• Endocrinology
• Biomedical Engineering

Background:

• Type 2 Diabetes Mellitus (T2DM) affects millions globally, with autonomic dysfunction being a common complication.
• Traditional assessment of autonomic dysfunction via Ewing's test and resting Heart Rate Variability (HRV) has limitations.

Purpose of the Study:

• To investigate the efficacy of a combined resting and orthostatic challenge HRV measurement approach.
• To utilize machine learning techniques for improved detection of autonomic dysfunction in T2DM.

Main Methods:

• Collected short-term ECG signals from 213 subjects (51 controls, 162 T2DM) during rest and after an orthostatic challenge.
• Extracted HRV indices according to HRV-Taskforce guidelines.
• Applied machine learning algorithms, including Classification and Regression Tree (CART), to analyze HRV patterns.

Main Results:

• Significant differences in resting HRV indices were observed between control and T2DM groups.
• T2DM patients exhibited a blunted autonomic response to orthostatic challenge.
• The CART model achieved 84.04% accuracy in differentiating autonomic dysfunction, outperforming resting HRV alone (75.12% accuracy).

Conclusions:

• A CART model effectively detects autonomic dysfunction in T2DM using combined resting and orthostatic HRV data.
• The percentage difference in HRV between resting and orthostatic states quantifies blunted autonomic response.
• This HRV monitoring approach offers a superior alternative for detecting T2DM-related autonomic dysfunction.