Background
Posttraumatic stress disorder (PTSD) is a delayed and lasting dysfunctional response to psychological stress. Patients usually have a long illness with recurring symptoms, often complicated by comorbidities such as substance abuse, depression, anxiety disorder, aggressive behavior, self-injury and suicide, as well as medical complications such as chronic pain and infection, cardiovascular disease and increased risk of dementia [
1,
2]. The overall burden of disability and premature death caused by PTSD is therefore high [
3]. Children are more vulnerable to PTSD than adults, being 12–25% more likely to develop depression, suicidal behavior and cognitive impairment [
4]. The etiology and neuropathology of this complex disease are still not clear [
5], and accurate prognosis suffers from the lack of reliable biomarkers.
Two decades ago it was hoped that neuroimaging-based biomarkers would prove diagnostically and prognostically effective in a number of neuropsychiatric diseases. This hope has not yet been realized, as research has revealed an increasingly complex picture of subtle, distributed brain changes varying with individual clinical characteristics. Neuroimaging biomarkers capable of distinguishing PTSD from non-PTSD subjects have received attention [
6‐
9], and two recent studies obtained good results using resting-state fMRI [
7,
9]. The brain is a highly interconnected network, and the development of psychiatric illness appears increasingly linked to dysfunctional integration of networks between the cortex and subcortical regions. Many studies have therefore taken whole-brain network metrics and used them as input to a single subject classification [
10‐
12]. Recent advances in psychoradiology, allow the direct noninvasive characterization of brain network topology in neuropsychiatric patients [
13‐
15] and advances in graph-based theoretical analysis have enabled quantification of the whole brain’s topological properties [
16,
17], revealing a ‘small-world’ organization (characterized by both high local specialization and high global integration between brain regions) [
18,
19], whose networks are anatomically and functionally disrupted in psychiatric disease [
20]. We used graph-based analysis to investigate the disrupted topology of the functional brain connectome in PTSD, which throws some light on the pathogenesis of pediatric PTSD as well as yielding potential biomarkers of the disease [
21].
‘Deep learning’ (DL) describes a group of representation-learning methods that can automatically identify the optimal representation from the raw data with high order complexity and abstraction [
22]. A number of studies have applied DL techniques to the classification of psychiatric disorders based on anatomical brain images obtained by MRI [
23] or functional MRI images [
24] or by combining structural and functional neuroimaging data [
25,
26]. Also, DL has yielded promising results in medical image analysis [
27,
28], and may yield higher classification accuracy than alternative methods such as support vector machines (SVM) [
29,
30]. It can use the trained network to calculate the low-dimensional code of individual brain features quickly and effectively, so as to deduce the deep structure and further characterise the complex nonlinear relationships [
31,
32]. There is precedent in PTSD for nonlinear responses to e.g. therapy [
33], and it seems reasonable to expect that the complexity of functional and structural patterns in the pathophysiology might be beyond what traditional linear methods (e.g., PCA, sparse learning) can explain [
34].
To date, most studies of neuroimaging-based predictors of classification have examined adult patients or mixed pediatric and adult samples. However, biomarkers may be differentially expressed in pediatric and adult patients [
35], and studying patients early in their illness course with limited psychotropic exposure can minimize the confounding effects of illness course and medication. Here we confined ourselves to pediatric patients and age-matched controls.
Recent studies of other neuropsychiatric diseases have used novel graph-based analytic methods as input for single-subject classification [
36,
37]. To extend these, we combined them with DL, by following a DL-based dimension reduction phase by an SVM classification phase [
34]. We hypothesized (i) that the use of DL would enhance the effectiveness of graph-based metrics derived from resting-state fMRI data. Given previous reports that the central executive network (CEN), amygdala, and parietal gyrus are important siters of dysregulation areas in PTSD [
21,
38], we also hypothesized (ii) that these regions would make the greatest contributions to classification performance.
Discussion
We set out to classify between pediatric PTSD and HC using the DL model applied to graphic topological measures, and then explored the regions making the greatest contribution to classification performance. Consistent with our first hypothesis, we found that using topological properties in DL we could distinguish PTSD from HC at the individual level with significant accuracy. This supports the emerging notion that graphic topological properties based on resting-state functional neuroimaging data can be a powerful tool for characterizing brain disorders at the level of the individual [
21]. Such methods have achieved 86% accuracy in distinguishing patients with amnestic mild cognitive impairment from healthy controls [
9], and 70–80% accuracy in distinguishing schizophrenic patients from non-psychiatric controls [
10]. In PTSD, Zilcha-Mano et al. [
9] were able to discriminate between 51 PTSD individuals and 76 trauma-exposed healthy control subjects with an accuracy of up to 70.6% by using a whole-brain data-driven definition of functional connectivity biomarkers and regularized partial correlations which revealed differences in functional connectivity within executive control network and salience network between the two groups.
DL methods can automatically identify the optimal representation from the raw data without the need for specialized feature engineering. This is achieved by using a hierarchical structure with varying levels of complexity, including the application of consecutive nonlinear transformations to the raw data. An essential aspect of DL that differentiates it from other machine learning methods is that the features are not manually engineered; instead, they are learned from the data, resulting in a more objective and less bias-prone process. Compared with other machine learning methods such as SVM, DL can achieve higher orders of abstraction, complexity and higher classifier accuracy [
29,
30], which makes DL more suitable for detecting complex, scattered and subtle patterns in the data [
59].
Consistent with our second hypothesis, a few regions make the largest contribution to classification performance: frontoparietal regions (central executive, CEN) and subcortical areas like (median and anterior) cingulate cortex and amygdala. The CEN is associated with the progress of goal-directed behaviors, such as working memory and attention control [
60], and it has also been reported as impaired in PTSD [
21,
38]. Specifically, CEN functional disruptions are associated with PTSD symptoms of decreased cognitive functioning across multiple domains, as well as emotion under-modulation associated with impaired regulation of limbic structures [
61‐
63]. For instance, a recent study found that in the resting-state, subtype non-differentiated PTSD patients demonstrate reduced CEN convergence, which was associated with decrease orbitofrontal-amygdala connectivity in PTSD, an indicator of reduced prefrontal regulation acting on the resting limbic system [
63]. The amygdala is a core area in current neurocircuit models of stress and PTSD [
64,
65]. Among its multiple functions, the best known is to encode and extinguish the memory of fearful stimuli [
65,
66] so as to direct physiological and behavioral responses to such stimuli. In addition, the amygdala plays an essential role in fear generalization [
67], arousal [
68] and processing of rewards [
69], all of which may be disrupted in PTSD. Exaggerated amygdala activity in response to trauma-related and more generic stimuli is a frequent finding in fMRI studies of PTSD [
70,
71]. Recent research has enlarged the functions traditionally ascribed to the cingulate to include emotion [
72], pain management [
73] and cognitive control [
74,
75]. A recent meta-analysis concludes that cingulate plays an important role in emotion and cognitive processing in patients with PTSD [
76].
Neuroimaging is still far from becoming a routine tool in clinical psychiatry, mainly because there is still insufficient evidence of diagnostic and prognostic effectiveness. We followed recent recommendations on avoiding methodological issues that may in the past led to overoptimistic results [
77‐
79]. A major challenge in applying machine learning to high-dimensional neuroimaging data is the risk of overfitting, i.e., the learning of irrelevant fluctuations within a dataset that limits generalizability to other datasets. To avoid that, we applied DL technology to conduct a dimension reduction and mitigate the effect of spurious signals. We also tried to minimize the risk of overfitting through the use of region-level features rather than voxel-level data (which are associated with more noise and a higher risk of overfitting) [
30]. One limitation is that we only explored topological properties based on the AAL brain atlas. Although AAL is widely accepted in neuroimaging studies, it has drawbacks. Future studies should verify our results using the new brain atlases that are now being used in neuroimaging and machine learning studies, such as the Power 264-region atlas [
80] and the Dosenbach’s 160 functional atlas [
81]. Another limitation is that our PTSD participants were exposed to a specific traumatic event (an earthquake), which might limit the generalizability of our results. This can be tested by replication using subjects exposed to other traumatic events.
Conclusion
Despite these limitations, the present study demonstrates DL as an objective and useful classifier which could differentiate pediatric PTSD and HC based on graphic topological measures using resting-state MRI data with promising accuracy. Further, the CEN, parietal gyrus, cingulate cortex, and amygdala provide the greatest contribution to classification performance in DL model, suggesting that investigating these core nodes may give insight into the heterogeneous clinical profiles of individuals with PTSD. Further studies will be needed to assess the clinical applicability of our method.
Open AccessThis article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit
http://creativecommons.org/licenses/by/4.0/. The Creative Commons Public Domain Dedication waiver (
http://creativecommons.org/publicdomain/zero/1.0/) applies to the data made available in this article, unless otherwise stated in a credit line to the data.
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.