Personalized prediction of transcranial magnetic stimulation clinical response in patients with treatment-refractory depression using neuroimaging biomarkers and machine learning

被引:38
作者
Hopman, H. J. [1 ]
Chan, S. M. S. [2 ]
Chu, W. C. W. [3 ]
Lu, H. [1 ]
Tse, C-Y [4 ,7 ]
Chau, S. W. H. [5 ]
Lam, L. C. W. [1 ]
Mak, A. D. P. [1 ]
Neggers, S. F. W. [6 ]
机构
[1] Chinese Univ Hong Kong, Unit L,19-F Kings Wing Plaza 1,3 Kwan St, Hong Kong, Peoples R China
[2] Chinese Univ Hong Kong, G30 G-F Multictr,Tai Po Hosp 9 Chuen Rd, Hong Kong, Peoples R China
[3] Prince Wales Hosp, Rm 27023 G-F, Hong Kong, Peoples R China
[4] Chinese Univ Hong Kong, Sino Bldg,Rm 352,Chung Chi Rd, Hong Kong, Peoples R China
[5] Chinese Univ Hong Kong, Prince Wales Hosp, Jockey Club Sch Publ Hlth, 3-F Rm 327,30 Ngan Shing St, Hong Kong, Peoples R China
[6] Univ Med Ctr Utrecht, Brain Ctr Rudolf Magnus, Heidelberglaan 100, NL-3584 CX Utrecht, Netherlands
[7] City Univ Hong Kong, Dept Social & Behav Sci, Hong Kong, Peoples R China
关键词
Transcranial magnetic stimulation; Treatment response; Biomarkers; Depression; Dorsolateral prefrontal cortex; Subgenual anterior cingulate cortex; STATE FUNCTIONAL CONNECTIVITY; CEREBRAL-BLOOD-FLOW; NETWORK MECHANISMS; BRAIN; DEEP; RTMS; DISORDER; EFFICACY; TARGETS; CORTEX;
D O I
10.1016/j.jad.2021.04.081
中图分类号
R74 [神经病学与精神病学];
学科分类号
摘要
Background: Functional connectivity between the left dorsolateral prefrontal cortex (DLPFC) and subgenual cingulate (sgACC) may serve as a biomarker for transcranial magnetic stimulation (rTMS) treatment response. The first aim was to establish whether this finding is veridical or artifactually induced by the pre-processing method. Furthermore, alternative biomarkers were identified and the clinical utility for personalized medicine was examined. Methods: Resting-state fMRI data were collected in medication-refractory depressed patients (n = 70, 16 males) before undergoing neuronavigated left DLPFC rTMS. Seed-based analyses were performed with and without global signal regression pre-processing to identify biomarkers of short-term and long-term treatment response. Receiver Operating Characteristic curve and supervised machine learning analyses were applied to assess the clinical utility of these biomarkers for the classification of categorical rTMS response. Results: Regardless of the pre-processing method, DLPFC-sgACC connectivity was not associated with treatment outcome. Instead, poorer connectivity between the sgACC and three clusters (peak locations: frontal pole, superior parietal lobule, occipital cortex) and DLPFC-central opercular cortex were observed in long-term nonresponders. The identified connections could serve as acceptable to excellent markers. Combining the features using supervised machine learning reached accuracy rates of 95.35% (CI=82.94-100.00) and 88.89% (CI=63.96-100.00) in the cross-validation and test dataset, respectively. Limitations: The sample size was moderate, and features for machine learning were based on group differences. Conclusions: Long-term nonresponders showed greater disrupted connectivity in regions involving the central executive network. Our findings may aid the development of personalized medicine for medication-refractory depression.
引用
收藏
页码:261 / 271
页数:11
相关论文
共 66 条
[1]  
Ahern E., 2019, Clinical Psychology in Europe, V1, DOI DOI 10.32872/CPE.V1I3.34396
[2]   Repetitive transcranial magnetic stimulation for treatment resistant depression: Re-establishing connections [J].
Anderson, Rodney J. ;
Hoy, Kate E. ;
Daskalakis, Zafiris J. ;
Fitzgerald, Paul B. .
CLINICAL NEUROPHYSIOLOGY, 2016, 127 (11) :3394-3405
[3]   Single subject prediction of brain disorders in neuroimaging: Promises and pitfalls [J].
Arbabshirani, Mohammad R. ;
Plis, Sergey ;
Sui, Jing ;
Calhoun, Vince D. .
NEUROIMAGE, 2017, 145 :137-165
[4]   Subgenual Anterior Cingulate-Medial Orbitofrontal Functional Connectivity in Medication-Resistant Major Depression: A Neurobiological Marker for Accelerated Intermittent Theta Burst Stimulation Treatment? [J].
Baeken, Chris ;
Duprat, Romain ;
Wu, Guo-Rong ;
De Raedt, Rudi ;
van Heeringen, Kees .
BIOLOGICAL PSYCHIATRY-COGNITIVE NEUROSCIENCE AND NEUROIMAGING, 2017, 2 (07) :556-565
[5]   The tract terminations in the temporal lobe: Their location and associated functions [J].
Bajada, Claude J. ;
Haroon, Hamied A. ;
Azadbakht, Hojjatollah ;
Parker, Geoff J. M. ;
Ralph, Matthew A. Lambon ;
Cloutman, Lauren L. .
CORTEX, 2017, 97 :277-290
[6]   An efficient and accurate new method for locating the F3 position for prefrontal TMS applications [J].
Beam, William ;
Borckardt, Jeffrey J. ;
Reeves, Scott T. ;
George, Mark S. .
BRAIN STIMULATION, 2009, 2 (01) :50-54
[7]   A component based noise correction method (CompCor) for BOLD and perfusion based fMRI [J].
Behzadi, Yashar ;
Restom, Khaled ;
Liau, Joy ;
Liu, Thomas T. .
NEUROIMAGE, 2007, 37 (01) :90-101
[8]   Data-driven biological subtypes of depression: systematic review of biological approaches to depression subtyping [J].
Beijers, Lian ;
Wardenaar, Klaas J. ;
van Loo, Hanna M. ;
Schoevers, Robert A. .
MOLECULAR PSYCHIATRY, 2019, 24 (06) :888-900
[9]   CHANGES IN REGIONAL CEREBRAL BLOOD-FLOW ON RECOVERY FROM DEPRESSION [J].
BENCH, CJ ;
FRACKOWIAK, RSJ ;
DOLAN, RJ .
PSYCHOLOGICAL MEDICINE, 1995, 25 (02) :247-261
[10]  
Bijsterbosch Janine, 2017, Introduction to Resting State fMRI Functional Connectivity, V1st