Exploring memory function in earthquake trauma survivors with resting-state fMRI and machine learning

Cognitive, social, and mental health functions of refugee children - screening and supportive actions at school: a study protocol

BACKGROUND

Despite a world-leading educational system, an achievement gap in educational outcomes exists between children of refugee background and native-born peers in Finland. To offer targeted support for children at schools, we need to be able to reliably assess and understand the interplay of the aspects of children's cognitive, social, and mental health functions that may explain the underachievement of refugee children. This study tests a novel research-based, universally applicable screening battery for evaluating cognitive, social, and mental health functioning of children at schools and planning supportive actions. It aims to answer research questions about a) the cognitive, social, and mental health functioning of refugee children compared with non-refugee immigrant and native-born children, b) the interplay of these different functions among refugee and other children, c) whether implementing a screening battery can inform schools in planning supportive actions for (refugee) children, and d) whether such supportive actions result in improvements in cognitive, social, and mental health functioning.

METHODS

Four hundred fifty children aged 10-12 will be recruited from primary schools, including 150 children of refugee background, 150 of non-refugee immigrant background, and 150 native-born Finnish children. A screening battery including tasks and questionnaires on different aspects of cognitive, social, and mental health functioning will be used to assess the children in their classrooms at the start and end of a school year. Supporting information will also be collected from parents and teachers. The information gathered will be collated into class-level feedback reports for teachers and, with parental permission, individualized reports for multiprofessional student welfare bodies, for informing supportive actions. Correlational and latent profile analyses, ANOVAs, and linear regression will be used to answer the research questions.

DISCUSSION

This study will help clarify how the interplay of cognitive, social, and mental health factors may explain underachievement at school among refugee children. It will provide evidence about the extent to which a standardized screening battery could be helpful in informing and planning supportive actions for children at schools, and whether such supportive actions can lead to positive cognitive, social, or mental health outcomes.

TRIAL REGISTRATION

The study will be preregistered on the Open Science Framework.

Neuroimaging-based classification of PTSD using data-driven computational approaches: A multisite big data study from the ENIGMA-PGC PTSD consortium

BACKGROUND

Recent advances in data-driven computational approaches have been helpful in devising tools to objectively diagnose psychiatric disorders. However, current machine learning studies limited to small homogeneous samples, different methodologies, and different imaging collection protocols, limit the ability to directly compare and generalize their results. Here we aimed to classify individuals with PTSD versus controls and assess the generalizability using a large heterogeneous brain datasets from the ENIGMA-PGC PTSD Working group.

METHODS

We analyzed brain MRI data from 3,477 structural-MRI; 2,495 resting state-fMRI; and 1,952 diffusion-MRI. First, we identified the brain features that best distinguish individuals with PTSD from controls using traditional machine learning methods. Second, we assessed the utility of the denoising variational autoencoder (DVAE) and evaluated its classification performance. Third, we assessed the generalizability and reproducibility of both models using leave-one-site-out cross-validation procedure for each modality.

RESULTS

We found lower performance in classifying PTSD vs. controls with data from over 20 sites (60 % test AUC for s-MRI, 59 % for rs-fMRI and 56 % for d-MRI), as compared to other studies run on single-site data. The performance increased when classifying PTSD from HC without trauma history in each modality (75 % AUC). The classification performance remained intact when applying the DVAE framework, which reduced the number of features. Finally, we found that the DVAE framework achieved better generalization to unseen datasets compared with the traditional machine learning frameworks, albeit performance was slightly above chance.

CONCLUSION

These results have the potential to provide a baseline classification performance for PTSD when using large scale neuroimaging datasets. Our findings show that the control group used can heavily affect classification performance. The DVAE framework provided better generalizability for the multi-site data. This may be more significant in clinical practice since the neuroimaging-based diagnostic DVAE classification models are much less site-specific, rendering them more generalizable.

Association between spatial working memory and Re-experiencing symptoms in PTSD

BACKGROUND AND OBJECTIVES

Few studies have evaluated the link between working memory (WM) and post-traumatic stress disorder (PTSD). Further, it is unknown whether this relationship is accounted for by other relevant variables including negative affect, emotional dysregulation, or general non-WM-related cognitive control deficits, which are associated with PTSD. The purpose of this study was to determine the extent to which a computerized WM task could predict PTSD symptomology incrementally beyond the contribution of other relevant variables associated with PTSD.

METHODS

Thirty veterans were eligible to complete emotional symptom questionnaires, a heart-rate variability measure, and computerized tasks (i.e., emotional Stroop and automated complex span tasks). A three-stage hierarchical regression was conducted with the PCL-5 total score and symptom clusters (i.e., re-experiencing, avoidance, hyperarousal, and negative cognition/mood) as the dependent variable.

RESULTS

Results revealed that only the re-experiencing symptom cluster was significantly predicted by executive, verbal, and visuospatial WM tasks, which explained an additional 29.7% of the variance over and above other relevant variables. Most notably, the visuospatial task was the only WM task that significantly explained PCL-5 re-experiencing symptoms.

LIMITATIONS

This study was based on a small sample of veterans with PTSD and causality cannot be determined with this cross-sectional study.

CONCLUSIONS

Overall, the results suggest that deficits in visuospatial WM are significantly associated with PTSD re-experiencing symptoms after controlling for other relevant variables. Further research should evaluate whether an intervention to improve visuospatial WM capacity can be implemented to reduce re-experiencing symptoms.

Flights and Perchings of the BrainMind: A Temporospatial Approach to Psychotherapy

This article introduces a process-oriented approach for improving present moment conceptualization in psychotherapy that is in alignment with neuroscience: the Temporospatial movements of mind (TSMM) model. We elaborate on seven temporal movements that describe the moment-to-moment morphogenesis of emotional feelings and thoughts from inception to maturity. Temporal refers to the passage of time through which feelings and thoughts develop, and electromagnetic activity, that among other responsibilities, bind information across time. Spatial dynamics extend from an undifferentiated to three dimensional experiences of emotional and cognitive processes. Neurophysiologically, spatial refers to structures within the brain and their varying interactions with one another. This article culminates in the development of an atheoretical temporospatial grid that may help clinicians conceptualize where patients are in their cognitive and emotional development to further guide technique.

Hippocampal Resting-State Functional Connectivity Forecasts Individual Posttraumatic Stress Disorder Symptoms: A Data-Driven Approach

BACKGROUND

Posttraumatic stress disorder (PTSD) is a debilitating disorder, and there is no current accurate prediction of who develops it after trauma. Neurobiologically, individuals with chronic PTSD exhibit aberrant resting-state functional connectivity (rsFC) between the hippocampus and other brain regions (e.g., amygdala, prefrontal cortex, posterior cingulate), and these aberrations correlate with severity of illness. Previous small-scale research (n < 25) has also shown that hippocampal rsFC measured acutely after trauma is predictive of future severity using a region-of-interest-based approach. While this is a promising biomarker, to date, no study has used a data-driven approach to test whole-brain hippocampal FC patterns in forecasting the development of PTSD symptoms.

METHODS

A total of 98 adults at risk of PTSD were recruited from the emergency department after traumatic injury and completed resting-state functional magnetic resonance imaging (8 min) within 1 month; 6 months later, they completed the Clinician-Administered PTSD Scale for DSM-5 for assessment of PTSD symptom severity. Whole-brain rsFC values with bilateral hippocampi were extracted (using CONN) and used in a machine learning kernel ridge regression analysis (PRoNTo); a k-folds (k = 10) and 70/30 testing versus training split approach were used for cross-validation (1000 iterations to bootstrap confidence intervals for significance values).

RESULTS

Acute hippocampal rsFC significantly predicted Clinician-Administered PTSD Scale for DSM-5 scores at 6 months (r = 0.30, p = .006; mean squared error = 120.58, p = .006; R² = 0.09, p = .025). In post hoc analyses, hippocampal rsFC remained significant after controlling for demographics, PTSD symptoms at baseline, and depression, anxiety, and stress severity at 6 months (B = 0.59, SE = 0.20, p = .003).

CONCLUSIONS

Findings suggest that functional connectivity of the hippocampus across the brain acutely after traumatic injury is associated with prospective PTSD symptom severity.

The Contributing Factors of Delayed-Onset Post-traumatic Stress Disorder Symptoms: A Nested Case-Control Study Conducted After the 2008 Wenchuan Earthquake

Background: Delayed-onset post-traumatic stress disorder after catastrophes is a major public health issue. However, good designs for identifying post-traumatic stress disorder (PTSD) among earthquake survivors are rare. This is the first nested case-control study to explore the possible factors associated with delayed-onset PTSD symptoms. Methods: A nested case-control study was conducted. The baseline (2011) and follow-up (2018) surveys were utilized to collect data. A total of 361 survivors of the Wenchuan earthquake were investigated and 340 survivors underwent follow-up. The survivors, from the hardest-hit areas, who met the criteria for PTSD were included in the case group, and PTSD-free survivors from the same area, matched for age, were included in the control group, with a ratio of one to four. Conditional logistic regression was used to evaluate the variables' odds ratio (OR). Results: The overall prevalence of delayed-onset PTSD symptoms in survivors of the Wenchuan earthquake was 9.7% (33/340). The unemployed earthquake survivors had a higher risk of developing delayed-onset PTSD symptoms (OR = 4.731, 95% CI = 1.408-15.901), while higher perceived social support was a protective factor against delayed-onset PTSD symptoms (OR = 0.172, 95% CI = 0.052-0.568). Conclusion: Delayed-onset PTSD symptoms, after a disaster, should not be ignored. Active social support and the provision of stable jobs can contribute to the earthquake survivors' mental health.

Using deep learning to classify pediatric posttraumatic stress disorder at the individual level

BACKGROUND

Children exposed to natural disasters are vulnerable to developing posttraumatic stress disorder (PTSD). Previous studies using resting-state functional neuroimaging have revealed alterations in graph-based brain topological network metrics in pediatric PTSD patients relative to healthy controls (HC). Here we aimed to apply deep learning (DL) models to neuroimaging markers of classification which may be of assistance in diagnosis of pediatric PTSD.

METHODS

We studied 33 pediatric PTSD and 53 matched HC. Functional connectivity between 90 brain regions from the automated anatomical labeling atlas was established using partial correlation coefficients, and the whole-brain functional connectome was constructed by applying a threshold to the resultant 90 * 90 partial correlation matrix. Graph theory analysis was used to examine the topological properties of the functional connectome. A DL algorithm then used this measure to classify pediatric PTSD vs HC.

RESULTS

Graphic topological measures using DL provide a potentially clinically useful classifier for differentiating pediatric PTSD and HC (overall accuracy 71.2%). Frontoparietal areas (central executive network), cingulate cortex, and amygdala contributed the most to the DL model's performance.

CONCLUSIONS

Graphic topological measures based on fMRI data could contribute to imaging models of clinical utility in distinguishing pediatric PTSD from HC. DL model may be a useful tool in the identification of brain mechanisms PTSD participants.

An SBM-based machine learning model for identifying mild cognitive impairment in patients with Parkinson's disease

OBJECTIVE

To identify Parkinson's disease with mild cognitive impairment (PD-MCI) through surface-based morphometry (SBM) based machine learning model.

METHODS

93 patients with parkinson's disease (35 PD with normal cognition, 58 PD-MCI) were examined, obtaining 276 SBM variables per subject. 20 healthy control subjects were used as the reference. After extracting features with statistically significance, support vector machine (SVM) model with grid search method was applied to identify patients with PD-MCI. Accuracy, matthews correlation coefficient (MCC), receiver operating characteristic curve (ROC), precision-recall curve (PR), AUC-ROC, AUC-PR and leave-one-out cross validation (LOOCV) strategy were employed for model evaluation.

RESULTS

PD-MCI is characterized by widespread structural abnormality. SVM model with SBM features achieved an accuracy of 80.00% and area under the ROC of 0.86 for identifying PD-MCI. MCC, AUC-PR, and LOOCV classification accuracy were 0.56, 0.89, and 78.08%, respectively.

CONCLUSION

Automatic identification of PD-MCI could be realized by SBM-based machine learning model.