Frontal Cortex Entropy Derived From Resting-State fNIRS for Brain Age Prediction in Major Depressive Disorder.

Area of Science:

• Neuroscience
• Medical Imaging
• Psychiatry

Background:

• Major depressive disorder (MDD) is associated with complex neurobiological changes.
• Brain age prediction using neuroimaging is an emerging field for understanding brain health.
• Resting-state functional near-infrared spectroscopy (rs-fNIRS) offers a non-invasive method to assess brain activity.

Purpose of the Study:

• To investigate frontal brain entropy (BEN) metrics from rs-fNIRS as neurophysiological biomarkers.
• To predict brain age in patients with MDD.
• To evaluate the diagnostic potential of BEN and brain age gap (BAG) in distinguishing MDD from healthy controls (HC).

Main Methods:

• Acquired rs-fNIRS data from 35 MDD patients and 49 HC.
• Computed static and dynamic BEN using permutation entropy on hemodynamic signals (HbO, HbR, HbT).
• Used support vector regression (SVR) to predict brain age and receiver operating characteristic (ROC) analysis for diagnostic performance.

Main Results:

• Dynamic BEN from HbR best predicted brain age in HC (r=-0.62), while dynamic BEN from HbO was optimal for MDD (r=-0.78).
• MDD patients showed a significantly elevated brain age gap (BAG) compared to HC (p < 0.001).
• BEN and brain age metrics achieved excellent diagnostic performance, with some combinations reaching an area under the ROC curve of 1.00.

Conclusions:

• Frontal BEN derived from rs-fNIRS is a potential biomarker for accelerated brain aging in MDD.
• Brain age estimation from cerebrovascular complexity effectively identifies MDD.
• Frontal neurovascular complexity metrics may serve as diagnostic markers for MDD and indicators of pathological aging.