1
|
Huang Y, Zhang J, He K, Mo X, Yu R, Min J, Zhu T, Ma Y, He X, Lv F, Lei D, Liu M. Innovative Neuroimaging Biomarker Distinction of Major Depressive Disorder and Bipolar Disorder through Structural Connectome Analysis and Machine Learning Models. Diagnostics (Basel) 2024; 14:389. [PMID: 38396428 PMCID: PMC10888009 DOI: 10.3390/diagnostics14040389] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/10/2024] [Revised: 02/03/2024] [Accepted: 02/08/2024] [Indexed: 02/25/2024] Open
Abstract
Major depressive disorder (MDD) and bipolar disorder (BD) share clinical features, which complicates their differentiation in clinical settings. This study proposes an innovative approach that integrates structural connectome analysis with machine learning models to discern individuals with MDD from individuals with BD. High-resolution MRI images were obtained from individuals diagnosed with MDD or BD and from HCs. Structural connectomes were constructed to represent the complex interplay of brain regions using advanced graph theory techniques. Machine learning models were employed to discern unique connectivity patterns associated with MDD and BD. At the global level, both BD and MDD patients exhibited increased small-worldness compared to the HC group. At the nodal level, patients with BD and MDD showed common differences in nodal parameters primarily in the right amygdala and the right parahippocampal gyrus when compared with HCs. Distinctive differences were found mainly in prefrontal regions for BD, whereas MDD was characterized by abnormalities in the left thalamus and default mode network. Additionally, the BD group demonstrated altered nodal parameters predominantly in the fronto-limbic network when compared with the MDD group. Moreover, the application of machine learning models utilizing structural brain parameters demonstrated an impressive 90.3% accuracy in distinguishing individuals with BD from individuals with MDD. These findings demonstrate that combined structural connectome and machine learning enhance diagnostic accuracy and may contribute valuable insights to the understanding of the distinctive neurobiological signatures of these psychiatric disorders.
Collapse
Affiliation(s)
- Yang Huang
- Department of Radiology, The First Affiliated Hospital of Chongqing Medical University, Chongqing 400016, China
| | - Jingbo Zhang
- College of Medical Informatics, Chongqing Medical University, Chongqing 400016, China (J.M.)
| | - Kewei He
- College of Medical Informatics, Chongqing Medical University, Chongqing 400016, China (J.M.)
| | - Xue Mo
- Department of Radiology, The First Affiliated Hospital of Chongqing Medical University, Chongqing 400016, China
| | - Renqiang Yu
- Department of Radiology, The First Affiliated Hospital of Chongqing Medical University, Chongqing 400016, China
| | - Jing Min
- College of Medical Informatics, Chongqing Medical University, Chongqing 400016, China (J.M.)
| | - Tong Zhu
- College of Medical Informatics, Chongqing Medical University, Chongqing 400016, China (J.M.)
| | - Yunfeng Ma
- College of Medical Informatics, Chongqing Medical University, Chongqing 400016, China (J.M.)
| | - Xiangqian He
- College of Medical Informatics, Chongqing Medical University, Chongqing 400016, China (J.M.)
| | - Fajin Lv
- Department of Radiology, The First Affiliated Hospital of Chongqing Medical University, Chongqing 400016, China
| | - Du Lei
- College of Medical Informatics, Chongqing Medical University, Chongqing 400016, China (J.M.)
| | - Mengqi Liu
- Department of Radiology, The First Affiliated Hospital of Chongqing Medical University, Chongqing 400016, China
| |
Collapse
|
2
|
Lei D, Li W, Tallman MJ, Strakowski SM, DelBello MP, Rodrigo Patino L, Fleck DE, Lui S, Gong Q, Sweeney JA, Strawn JR, Nery FG, Welge JA, Rummelhoff E, Adler CM. Changes in the structural brain connectome over the course of a nonrandomized clinical trial for acute mania. Neuropsychopharmacology 2022; 47:1961-1968. [PMID: 35585125 PMCID: PMC9485114 DOI: 10.1038/s41386-022-01328-y] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/14/2021] [Revised: 03/17/2022] [Accepted: 04/11/2022] [Indexed: 02/05/2023]
Abstract
Disrupted topological organization of brain functional networks has been widely reported in bipolar disorder. However, the potential clinical implications of structural connectome abnormalities have not been systematically investigated. The present study included 109 unmedicated subjects with acute mania who were assigned to 8 weeks of treatment with quetiapine or lithium and 60 healthy controls. High resolution 3D-T1 weighted magnetic resonance images (MRI) were collected from both groups at baseline, week 1 and week 8. Brain networks were constructed based on the similarity of morphological features across brain regions and analyzed using graph theory approaches. At baseline, individuals with bipolar disorder illness showed significantly lower clustering coefficient (Cp) (p = 0.012) and normalized characteristic path length (λ) (p = 0.004) compared to healthy individuals, as well as differences in nodal centralities across multiple brain regions. No baseline or post-treatment differences were identified between drug treatment conditions, so change after treatment were considered in the combined treatment groups. Relative to healthy individuals, differences in Cp, λ and cingulate gyrus nodal centrality were significantly reduced with treatment; changes in these parameters correlated with changes in Young Mania Rating Scale scores. Baseline structural connectome matrices significantly differentiated responder and non-responder groups at 8 weeks with 74% accuracy. Global and nodal network alterations evident at baseline were normalized with treatment and these changes associated with symptomatic improvement. Further, baseline structural connectome matrices predicted treatment response. These findings suggest that structural connectome abnormalities are clinically significant and may be useful for predicting clinical outcome of treatment and tracking drug effects on brain anatomy in bipolar disorder. CLINICAL TRIALS REGISTRATION Name: Functional and Neurochemical Brain Changes in First-episode Bipolar Mania Following Successful Treatment with Lithium or Quetiapine. URL: https://clinicaltrials.gov/ . REGISTRATION NUMBER NCT00609193. Name: Neurofunctional and Neurochemical Markers of Treatment Response in Bipolar Disorder. URL: https://clinicaltrials.gov/ . REGISTRATION NUMBER NCT00608075.
Collapse
Affiliation(s)
- Du Lei
- Department of Psychiatry and Behavioral Neuroscience, University of Cincinnati College of Medicine, Cincinnati, 45219, OH, USA.
| | - Wenbin Li
- Department of Psychiatry and Behavioral Neuroscience, University of Cincinnati College of Medicine, Cincinnati, 45219, OH, USA
- Huaxi MR Research Center (HMRRC), Department of Radiology, The Center for Medical Imaging, West China Hospital of Sichuan University, Chengdu, 610041, Sichuan, P.R. China
- Department of the Magnetic Resonance Imaging, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, 450052, Henan, P.R. China
| | - Maxwell J Tallman
- Department of Psychiatry and Behavioral Neuroscience, University of Cincinnati College of Medicine, Cincinnati, 45219, OH, USA
| | - Stephen M Strakowski
- Department of Psychiatry & Behavioral Sciences, Dell Medical School of The University of Texas at Austin, Austin, 78712, TX, USA
| | - Melissa P DelBello
- Department of Psychiatry and Behavioral Neuroscience, University of Cincinnati College of Medicine, Cincinnati, 45219, OH, USA
| | - L Rodrigo Patino
- Department of Psychiatry and Behavioral Neuroscience, University of Cincinnati College of Medicine, Cincinnati, 45219, OH, USA
| | - David E Fleck
- Department of Psychiatry and Behavioral Neuroscience, University of Cincinnati College of Medicine, Cincinnati, 45219, OH, USA
| | - Su Lui
- Huaxi MR Research Center (HMRRC), Department of Radiology, The Center for Medical Imaging, West China Hospital of Sichuan University, Chengdu, 610041, Sichuan, P.R. China
| | - Qiyong Gong
- Huaxi MR Research Center (HMRRC), Department of Radiology, The Center for Medical Imaging, West China Hospital of Sichuan University, Chengdu, 610041, Sichuan, P.R. China
| | - John A Sweeney
- Department of Psychiatry and Behavioral Neuroscience, University of Cincinnati College of Medicine, Cincinnati, 45219, OH, USA
- Huaxi MR Research Center (HMRRC), Department of Radiology, The Center for Medical Imaging, West China Hospital of Sichuan University, Chengdu, 610041, Sichuan, P.R. China
| | - Jeffrey R Strawn
- Department of Psychiatry and Behavioral Neuroscience, University of Cincinnati College of Medicine, Cincinnati, 45219, OH, USA
| | - Fabiano G Nery
- Department of Psychiatry and Behavioral Neuroscience, University of Cincinnati College of Medicine, Cincinnati, 45219, OH, USA
| | - Jeffrey A Welge
- Department of Psychiatry and Behavioral Neuroscience, University of Cincinnati College of Medicine, Cincinnati, 45219, OH, USA
| | - Emily Rummelhoff
- Department of Psychiatry and Behavioral Neuroscience, University of Cincinnati College of Medicine, Cincinnati, 45219, OH, USA
| | - Caleb M Adler
- Department of Psychiatry and Behavioral Neuroscience, University of Cincinnati College of Medicine, Cincinnati, 45219, OH, USA
| |
Collapse
|