Predictive values of pre-treatment brain age models to rTMS effects in neurocognitive disorder with depression: Secondary analysis of a randomised sham-controlled clinical trial

Abstract

Introduction: One major challenge in developing personalised repetitive transcranial magnetic stimulation (rTMS) is that the treatment responses exhibited high inter-individual variations. Brain morphometry might contribute to these variations. This study sought to determine whether individual's brain morphometry could predict the rTMS responders and remitters.

Methods: This was a secondary analysis of data from a randomised clinical trial that included fifty-five patients over the age of 60 with both comorbid depression and neurocognitive disorder. Based on magnetic resonance imaging scans, estimated brain age was calculated with morphometric features using a support vector machine. Brain-predicted age difference (brain-PAD) was computed as the difference between brain age and chronological age.

Results: The rTMS responders and remitters had younger brain age. Every additional year of brain-PAD decreased the odds of relieving depressive symptoms by ∼25.7% in responders (Odd ratio [OR] = 0.743, p = .045) and by ∼39.5% in remitters (OR = 0.605, p = .022) in active rTMS group. Using brain-PAD score as a feature, responder-nonresponder classification accuracies of 85% (3^rd week) and 84% (12^th week), respectively were achieved.

Conclusion: In elderly patients, younger brain age appears to be associated with better treatment responses to active rTMS. Pre-treatment brain age models informed by morphometry might be used as an indicator to stratify suitable patients for rTMS treatment.

Trial registration: ClinicalTrials.gov Identifier: ChiCTR-IOR-16008191.

Keywords: MRI; brain age; cortical features; depression; neurocognitive disorder; neuroplasticity; prediction; rTMS.

Figure 1.

The logistics of current randomised clinical trial and neuroplastic measurements. For determining the cortical excitability at individual level, resting motor threshold (RMT) was measured at baseline (1^st time), after the 5^th session (2^nd time) and the 10^th session (3^rd time) of rTMS. The post-treatment outcomes were assessed at the 3^rd week, 6^th week and 12^th week.

Figure 2.

The pipeline of morphometric features mapping and brain age model calculation. Based on individual structural MRI data, the surface-based morphometry (SBM) analysis of morphometric features was performed to extract and quantify the morphometric features (A), including gray matter volume (GMV) and cortical thickness (CT) (B). (C) The estimated brain age and brain-PAD were calculated based on the quantified morphometric features using support vector machine (SVM) in the Cam-CAN dataset and our clinical samples.

Figure 3.

The differences of brain age models in responders and remitters in active rTMS group. At 3^rd week, the individual differences between chronological age and brain age were found in the responders (A) and remitters (C). Significant lower CT-based brain-PAD scores were found in the responders in active rTMS group at the 3^rd week (p = .013) and 12^th week (p = .039) (B). Significant lower CT-based brain-PAD scores were found in the remitters in active rTMS group at 3^rd week (p < .001).

Figure 4.

The correlation matrix of brain age model and the changes of cortical excitability. The lower scores of CT-based brain-PAD were related to enhanced cortical excitability. Abbreviations: CT: Cortical thickness; brain-PAD: Brain-predicted age difference.

Figure 5.

Receiver-operator characteristic (ROC) curves for the chronological age, estimated brain age and brain-PAD with differential values in the rTMS responders and remitters. The score of brain-PAD can differentiate the responders from the non-responders at the 3^rd week (A) and 12^th week (C). The chronological age and the score of CT-based brain-PAD can differentiate the remitters from the non-remitters at 3rd week (D), 6th week (E) and 12th week (F).