Classification of cocaine‐dependent participants with dynamic functional connectivity from functional magnetic resonance imaging data

Abstract

Static functional connectivity (FC) analyses based on functional magnetic resonance imaging (fMRI) data have been extensively explored for studying various psychiatric conditions in the brain, including cocaine addiction. A recently emerging, more powerful technique, dynamic functional connectivity (DFC), studies how the FC dynamics change during the course of the fMRI experiments. The aim in this paper was to develop a computational approach, using a machine learning framework, to determine if DFC features were more successful than FC features in the classification of cocaine-dependent patients and healthy controls. fMRI data were obtained from of 25 healthy and 58 cocaine-dependent participants while performing a motor response inhibition task, stop signal task. Group independent component analysis was carried out on all participant data to compute spatially independent components (ICs). Eight ICs were selected manually as relevant brain networks, which were used to classify healthy versus cocaine-dependent participants. FC and DFC measures of the chosen IC pairs were used as features for the classification algorithm. Support Vector Machines were used for both feature selection/reduction and participant classification. Based on DFC with only seven IC pairs, participants were successfully classified with 95% accuracy (and with 90% accuracy with three IC pairs), whereas static FC yielded only 81% accuracy. Visual, sensorimotor, default mode, and executive control networks, amygdala, and insula played the most significant role in the DFC-based classification. These findings support the use of DFC-based classification of fMRI data as a potential biomarker for the identification of cocaine dependence.

An interpretable connectivity-based decoding model for classification of chronic marijuana use

“…We used several different linear modeling approaches, all of which produced highly similar model weights, predictions, and regions with high mean predictive connectivity - suggesting they learned similar information. Our accuracies also compare favorably to previous fMRI decoding studies using functional connectivity to classify drug use, in both nicotine smoking 4,7,49 and cocaine use disorder 50 - even though most studies did not test out-of-sample or featured much smaller sample sizes (both of which can inflate prediction performance). Furthermore, this is one of the first fMRI study 51 , and the largest to date, to classify chronic MJ use (i.e., cannabis use disorder) - a relatively understudied drug use disorder.…”

Reconfiguration of Dynamic Functional Connectivity States in Patients With Lifelong Premature Ejaculation

“… Abrol et al (2019) introduced a multimodal (structural MRI and DFC) data fusion framework to predict Alzheimer’s disease progression and found a significant improvement in performance over unimodal prediction analyses. Sakoglu et al (2019) reported a higher accuracy of DFC-based classification (0.95) than that based on SFC (0.81) for the identification of cocaine dependence, suggesting the diagnostic value of DFC metrics. In the present study, we used the DFC state of each window as features to construct an optimal classifier to distinguish the LPE patients from the NCs.…”

Temporally Dynamic Interaction between Drug Cue Reactivity and Response Inhibition: An fMRI Study among People with Methamphetamine Use Disorder

“…This exploratory study is an investigation of temporally dynamic regional brain activation patterns underlying cue-reactivity, response-inhibition, and their interaction in individuals with MUD. While similar sliding window techniques are relatively common in dynamic functional connectivity analyses 54,55 and despite decades of evidence for temporal variation in regional sensitization and habituation in cognitive/affective neuroscience [31][32][33] , dynamic analyses of regional activation in addiction remain rare and this is the rst study which explored this dynamic interaction in response-inhibition in the context of cue-reactivity.…”