Functional connectome-based biomarkers predict chronic codeine-containing cough syrup dependent. (November 2020)

• Record Type: Journal Article
• Authors: Wu, Yunfan; Ma, Xiaofen; Zhou, Zhihua; Yan, Jianhao; Xu, Shoujun; Li, Meng; Fang, Jing; Li, Guoming; Zeng, Shaoqing; Lin, Chulan; Li, Chunlong; Huang, Shumei; Jiang, Guihua
• Is Part Of: Journal of psychiatric research. Volume 130(2020)
• Page Start: 333
• Page End: 341
• Publication Date: 2020-11
• Subjects: Cough -- Syrup -- Human connectome -- Impulsive behavior -- Machine learning; CCS codeine-containing cough syrup -- CCSD codeine-containing cough syrup dependent users -- HC healthy control -- LR Logistic Regression -- BIS the Barratt Impulsiveness Scale; Psychiatry -- Periodicals; Mental Disorders -- Periodicals; Maladies mentales -- Périodiques; Psychiatry; Electronic journals; Periodicals; 616.89005
• DOI: 10.1016/j.jpsychires.2020.08.001
• Languages: English
• ISSNs: 0022-3956

Abstract

Abstract: Purpose: Codeine-containing cough syrup (CCS) is considered among the most popular drugs of abuse in adolescents worldwide. Accurate prediction and identification of CCS dependent (CCSD) users are crucial. This study aimed to identify a brain-connectome-based predictor of CCSD using a machine learning model based on a ten-fold cross-validation logistic regression (LR) classifier. Methods: 40 CCSD users and 40 healthy control (HC) subjects underwent functional magnetic resonance imaging to construct weight functional networks. Partial correlation analysis was used to analyze relations between abnormal network metrics and clinical characteristics (BIS total scores, CCS abuse duration, and mean CCS dose) in CCSD. A ten-fold cross-validation LR classifier was used to classify CCSD users and HC subjects. Results: The CCSD group showed significantly abnormal nodes and connections in the right posterior cingulate, right middle insula, bilateral prefrontal cortex, parietal lobe, temporal lobe, occipital lobe, and cerebellum. Furthermore, higher characteristic path length and lower clustering coefficient (Cp), global efficiency, and local efficiency (Eloc) were observed in the global topologies in CCSD. The abnormal global properties (Cp and Eloc) and node properties of the prefrontal cortex were significantly correlated with clinical characteristics (BIS-11 scores, CCS abuse duration) in CCSD. The LR classifier models demonstrated accuracy, sensitivity, specificity, precision, and AUC of 82.5%, 82.5%, 82.5%, 76.8%, and 82.5%. Conclusions: These data demonstrate that abnormal functional connectome may be closely linked to clinical characteristics in CCSD. Functional connectome-based biomarkers can be a powerful tool for personalized diagnosis of CCSD in the future. Highlights: Brain functional connectome by rsfMRI is more comprehensive and compelling methods to explore the underlying neurobiological changes of various addictions. The abnormal global values (higher Lp and lower Cp, Eg, and Eloc) were detected. Cp and Eloc were negatively correlated with the CCS abuse duration, but positively correlated with BIS-11 score . The most important discovery that ten-fold cross-validation machine learning models (LR classifier) constructed from functional connectome metrics showed good discrimination between CCSD and HC groups. The abnormal nodal properties were primarily located in bilateral prefrontal cortex, bilateral parietal lobe, right posterior cingulate, and right occipital, which suggest changes in the characteristics of functional connectome in CCSD may be related to the neurological symptoms of CCS abuse. Moreover, there were positive correlations between the BIS-11 scores and the node properties of prefrontal cortex.