Correlations between patterns of activity and the response to treatment yield distinct signatures for different antidepressant treatments
Spulber, S.; Elberling, F.; Ceccatelli, S.; Garde, M.; Tiger, M.; Lundberg, J.
Show abstract
Alterations in circadian patterns of activity have been described in several psychiatric disorders, and in major depressive disorder (MDD) have been associated with symptom severity. The aim of this study was to investigate the correlations between activity patterns and the response to different antidepressive treatments. We used actigraphy recordings acquired in three independent clinical trials investigating the response to internet-delivered cognitive behavioral therapy (iCBT), escitalopram, or ketamine, where symptom severity was assessed on MADRS scale. Data processing procedure was designed to extract features describing individual circadian cycles, as well as the average circadian profile for each subject. The analysis of effects of antidepressive treatments on single features (independently from magnitude of response) showed alterations in treatment-specific subsets of features. Further analysis revealed distinct correlations between longitudinal changes in individual features and the response to iCBT, escitalopram, or ketamine. Linear regression ensembles modeling the response to treatment were trained on actigraphy recorded during the depressive episode, before intervention. The analysis of coefficients following Bayesian model averaging showed that better response to iCBT was associated with weaker circadian entrainment; better response to ketamine was associated with more robust circadian entrainment and higher fragmentation of activity patterns; while higher age and steeper propensity to sustain activity was associated with better response to either iCBT or ketamine. Our data suggest that the analysis of circadian patterns of activity can potentially be used for predicting the response to specific MDD treatments, however larger confirmatory studies are required. HighlightsO_LIDifferent antidepressant treatments alter specific subsets of features of activity patterns. C_LIO_LIThe magnitude of response to treatment correlate with changes in patterns of activity. C_LIO_LIPatterns of activity correlate with the response to specific antidepressive treatments. C_LI
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
- Individual pattens of activity predict the response to physical exercise as an intervention in mild to moderate depression 94%
- Individual Deviations from Normative Electroencephalographic Connectivity Predict Antidepressant Response 93%
- Enhanced network synchronization connectivity following transcranial direct current stimulation (tDCS) in bipolar depression: effects on EEG oscillations and deep learning-based predictors of clinical remission 92%
Similar papers in this journal
- Ketamine and attentional bias to threat: dynamic causal modeling of magnetoencephalographic connectivity in treatment-resistant depression 93%
- Targeted memory reactivation during REM sleep in patients with social anxiety disorder 90%
- Altered EEG resting-state large-scale brain network dynamics in euthymic bipolar disorder patients 90%
Similar papers in this journal
- A brain-enriched circRNA blood biomarker can predict response to SSRI antidepressants 92%
- The mPFC molecular clock mediates the effects of sleep deprivation on depression-like behavior and regulates sleep consolidation and homeostasis 92%
- Neural signatures of risk-taking adaptions across health, bipolar disorder, and lithium treatment 92%
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.