Integrating sleep, neuroimaging, and computational approaches for precision psychiatry

Treatment resistant late-life depression: A narrative review of psychosocial risk factors, non-pharmacological interventions, and the role of clinical phenotyping

BACKGROUND

Treatment resistant depression (TRD) is a subset of major depressive disorder (MDD) in which symptoms do not respond to front line therapies. In older adults, the assessment and treatment of TRD is complicated by psychosocial risk factors unique to this population, as well as a relative paucity of research.

METHODS

Narrative review aimed at (1) defining TRLLD for clinical practice and research; (2) describing psychosocial risk factors; (3) reviewing psychological and non-pharmacological treatments; (4) discussing the role of clinical phenotyping for personalized treatment; and (5) outlining research priorities.

RESULTS

Our definition of TRLLD centers on response to medication and neuromodulation in primary depressive disorders. Psychosocial risk factors include trauma and early life adversity, chronic physical illness, social isolation, personality, and barriers to care. Promising non-pharmacological treatments include cognitive training, psychotherapy, and lifestyle interventions. The utility of clinical phenotyping is highlighted by studies examining the impact of comorbidities, symptom dimensions (e.g., apathy), and structural/functional brain changes.

LIMITATIONS

There is a relative paucity of TRLLD research. This limits the scope of empirical data from which to derive reliable patterns and complicates efforts to evaluate the literature quantitatively.

CONCLUSIONS

TRLLD is a complex disorder that demands further investigation given our aging population. While this review highlights the promising breadth of TRLLD research to date, more research is needed to help elucidate, for example, the optimal timing for implementing risk mitigation strategies, the value of collaborative care approaches, specific treatment components associated with more robust response, and phenotyping to help inform treatment decisions.

Precision psychiatry and Research Domain Criteria: Implications for clinical trials and future practice

Psychiatric disorders are associated with significant social and economic burdens, many of which are related to issues with current diagnosis and treatments. The coronavirus (COVID-19) pandemic is estimated to have increased the prevalence and burden of major depressive and anxiety disorders, indicating an urgent need to strengthen mental health systems globally. To date, current approaches adopted in drug discovery and development for psychiatric disorders have been relatively unsuccessful. Precision psychiatry aims to tailor healthcare more closely to the needs of individual patients and, when informed by neuroscience, can offer the opportunity to improve the accuracy of disease classification, treatment decisions, and prevention efforts. In this review, we highlight the growing global interest in precision psychiatry and the potential for the National Institute of Health-devised Research Domain Criteria (RDoC) to facilitate the implementation of transdiagnostic and improved treatment approaches. The need for current psychiatric nosology to evolve with recent scientific advancements and increase awareness in emerging investigators/clinicians of the value of this approach is essential. Finally, we examine current challenges and future opportunities of adopting the RDoC-associated translational and transdiagnostic approaches in clinical studies, acknowledging that the strength of RDoC is that they form a dynamic framework of guiding principles that is intended to evolve continuously with scientific developments into the future. A collaborative approach that recruits expertise from multiple disciplines, while also considering the patient perspective, is needed to pave the way for precision psychiatry that can improve the prognosis and quality of life of psychiatric patients.

Neuroimaging profiles of the negative affective network predict anxiety severity in patients with chronic insomnia disorder: A machine learning study

BACKGROUND

Sleep is instrumental in safeguarding emotional well-being. While the susceptibility to both insomnia and anxiety has been demonstrated to involve intricate brain systems, the neuroimaging profile of chronic insomnia disorder with comorbid anxiety symptoms (CID-A) remains unexplored. Employing machine learning methodologies, this study aims to elucidate the distinct neural substrates underlying CID-A and to investigate whether these cerebral markers can prognosticate anxiety symptoms in patients with insomnia.

METHODS

Functional magnetic resonance imaging (fMRI) data were procured from a relatively large cohort (dataset 1) comprised of 47 CID-A patients, 49 CID patients without anxiety (CID-NA), and 48 good sleeper controls (GSC). Aberrant cerebral functional alterations were assessed through functional connectivity strength (FCS) and resting-state functional connectivity (rsFC). Subsequently, Support Vector Regression (SVR) models were constructed to predict anxiety symptoms in CID patients based on neuroimaging features, which were validated utilizing an external cohort (dataset 2).

RESULTS

In comparison to CID-NA and GSC subjects, CID-A patients exhibited heightened FCS in the right dorsomedial prefrontal cortex (DMPFC), a central hub within the negative affective network. Moreover, the SVR models revealed that DMPFC-related rsFC/FCS features could be employed to predict anxiety symptoms in two independent cohorts of CID patients.

LIMITATION

Modifications in brain functionality might vary across insomnia subtypes.

CONCLUSION

The present findings suggest a potential negative affective network model for the neuropathophysiology of CID accompanied by anxiety. Importantly, the negative affective network pattern may serve as a predictor for anxiety symptoms in CID patients.

Prediction of early improvement of major depressive disorder to antidepressant medication in adolescents with radiomics analysis after ComBat harmonization based on multiscale structural MRI

BACKGROUND

Due to individual differences and lack of objective biomarkers, only 30-40% patients with major depressive disorder (MDD) achieve remission after initial antidepressant medication (ADM). We aimed to employ radiomics analysis after ComBat harmonization to predict early improvement to ADM in adolescents with MDD by using brain multiscale structural MRI (sMRI) and identify the radiomics features with high prediction power for selection of selective serotonin reuptake inhibitors (SSRIs) and serotonin norepinephrine reuptake inhibitors (SNRIs).

METHODS

121 MDD patients were recruited for brain sMRI, including three-dimensional T1 weighted imaging (3D-T₁WI)and diffusion tensor imaging (DTI). After receiving SSRIs or SNRIs for 2 weeks, the subjects were divided into ADM improvers (SSRIs improvers and SNRIs improvers) and non-improvers according to reduction rate of the Hamilton Depression Rating Scale, 17 item (HAM-D₁₇) score. Then, sMRI data were preprocessed, and conventional imaging indicators and radiomics features of gray matter (GM) based on surface-based morphology (SBM) and voxel-based morphology (VBM) and diffusion properties of white matter (WM) were extracted and harmonized with ComBat harmonization. Two-level reduction strategy with analysis of variance (ANOVA) and recursive feature elimination (RFE) was utilized sequentially to decrease high-dimensional features. Support vector machine with radial basis function kernel (RBF-SVM) was used to integrate multiscale sMRI features to construct models for early improvement prediction. Area under the curve (AUC), accuracy, sensitivity, and specificity based on the leave-one-out cross-validation (LOO-CV) and receiver operating characteristic (ROC) curve analysis were calculated to evaluate the model performance. Permutation tests were used for assessing the generalization rate.

RESULTS

After 2-week ADM, 121 patients were divided into 67 ADM improvers (31 SSRIs improvers and 36 SNRIs improvers) and 54 ADM non-improvers. After two-level dimensionality reduction, 8 conventional indicators (2 VBM-based features and 6 diffusion features) and 49 radiomics features (16 VBM-based features and 33 diffusion features) were selected. The overall accuracy of RBF-SVM models based on conventional indicators and radiomics features was 74.80% and 88.19%. The radiomics model achieved the AUC, sensitivity, specificity, and accuracy of 0.889, 91.2%, 80.1% and 85.1%, 0.954, 89.2%, 87.4% and 88.5%, 0.942, 91.9%, 82.5% and 86.8% for predicting ADM improvers, SSRIs improvers and SNRIs improvers, respectively. P value of permutation tests were less than 0.001. The radiomics features predicting ADM improver were mainly located in the hippocampus, medial orbitofrontal gyrus, anterior cingulate gyrus, cerebellum (lobule vii-b), body of corpus callosum, etc. The radiomics features predicting SSRIs improver were primarily distributed in hippocampus, amygdala, inferior temporal gyrus, thalamus, cerebellum (lobule vi), fornix, cerebellar peduncle, etc. The radiomics features predicting SNRIs improver were primarily located in the medial orbitofrontal cortex, anterior cingulate gyrus, ventral striatum, corpus callosum, etc. CONCLUSIONS: These findings suggest the radiomics analysis based on brain multiscale sMRI after ComBat harmonization could effectively predict the early improvement of ADM in adolescent MDD patients with a high accuracy, which was superior to the model based on the conventional indicators. The radiomics features with high prediction power may help for the individual selection of SSRIs and SNRIs.

Discriminating Paradoxical and Psychophysiological Insomnia Based on Structural and Functional Brain Images: A Preliminary Machine Learning Study

Insomnia disorder (ID) is a prevalent mental illness. Several behavioral and neuroimaging studies suggested that ID is a heterogenous condition with various subtypes. However, neurobiological alterations in different subtypes of ID are poorly understood. We aimed to assess whether unimodal and multimodal whole-brain neuroimaging measurements can discriminate two commonly described ID subtypes (i.e., paradoxical and psychophysiological insomnia) from each other and healthy subjects. We obtained T1-weighted images and resting-state fMRI from 34 patients with ID and 48 healthy controls. The outcome measures were grey matter volume, cortical thickness, amplitude of low-frequency fluctuation, degree centrality, and regional homogeneity. Subsequently, we applied support vector machines to classify subjects via unimodal and multimodal measures. The results of the multimodal classification were superior to those of unimodal approaches, i.e., we achieved 81% accuracy in separating psychophysiological vs. control, 87% for paradoxical vs. control, and 89% for paradoxical vs. psychophysiological insomnia. This preliminary study provides evidence that structural and functional brain data can help to distinguish two common subtypes of ID from each other and healthy subjects. These initial findings may stimulate further research to identify the underlying mechanism of each subtype and develop personalized treatments for ID in the future.

Topologically Disrupted Gray Matter Networks in Drug-Naïve Essential Tremor Patients With Poor Sleep Quality

Background

Sleep disturbances are widespread among patients with essential tremor (ET) and may have adverse effects on patients' quality of life. However, the pathophysiology underlying poor quality of sleep (QoS) in patients with ET remains unclear. Our study aimed to identify gray matter (GM) network alterations in the topological properties of structural MRI related to QoS in patients with ET.

Method

We enrolled 45 ET patients with poor QoS (SleET), 59 ET patients with normal QoS (NorET), and 66 healthy controls (HC), and they all underwent a three-dimensional T1-weighted MRI scan. We used a graph-theoretical approach to investigate the topological organization of GM morphological networks, and individual morphological brain networks were constructed according to the interregional similarity of GM volume distributions. Furthermore, we performed network-based statistics, and partial correlation analyses between topographic features and clinical characteristics were conducted.

Results

Global network organization was disrupted in patients with ET. Compared with the NorET group, the SleET group exhibited disrupted topological GM network organization with a shift toward randomization. Moreover, they showed altered nodal centralities in mainly the frontal, temporal, parietal, and cerebellar lobes. Morphological connection alterations within the default mode network (DMN), salience, and basal ganglia networks were observed in the SleET group and were generally more extensive than those in the NorET and HC groups. Alterations within the cerebello-thalamo-(cortical) network were only detected in the SleET group. The nodal degree of the left thalamus was negatively correlated with the Fahn-Tolosa-Marin Tremor Rating Scale score (r = −0.354, p =0.027).

Conclusion

Our findings suggest that potential complex interactions underlie tremor and sleep disruptions in patients with ET. Disruptions within the DMN and the cerebello-thalamo-(cortical) network may have a broader impact on sleep quality in patients with ET. Our results offer valuable insight into the neural mechanisms underlying poor QoS in patients with ET.

Disrupted Brain Functional Network Topology in Essential Tremor Patients With Poor Sleep Quality

Sleep disturbances, especially poor quality of sleep (QoS), are common among essential tremor (ET) patients and may have adverse effects on their quality of life, but the etiology driving the poor QoS in these individuals remains inadequately understood. Few data are available on the neuroimaging alterations of ET with poor QoS. Thirty-eight ET patients with poor QoS (SleET), 48 ET patients with normal QoS (NorET), and 80 healthy controls (HCs) participated in this study. All subjects underwent a 3.0-T magnetic resonance imaging (MRI) scan for resting-state functional MRI data collection. Then, the whole-brain functional connectome was constructed by thresholding the partial correlation matrices of 116 brain regions. Graph theory and network-based statistical analyses were performed. We used a non-parametric permutation test for group comparisons of topological metrics. Partial correlation analyses between the topographical features and clinical characteristics were conducted. The SleET and NorET groups exhibited decreased clustering coefficients, global efficiency, and local efficiency and increased the characteristic path length. Both of these groups also showed reduced nodal degree and nodal efficiency in the left superior dorsolateral frontal gyrus, superior frontal medial gyrus (SFGmed), posterior cingulate gyrus (PCG), lingual gyrus, superior occipital gyrus, right middle occipital gyrus, and right fusiform gyrus. The SleET group additionally presented reduced nodal degrees and nodal efficiency in the right SFGmed relative to the NorET and HC groups, and nodal efficiency in the right SFGmed was negatively correlated with the Pittsburgh Sleep Quality Index score. The observed impaired topographical organizations of functional brain networks within the central executive network (CEN), default mode network (DMN), and visual network serve to further our knowledge of the complex interactions between tremor and sleep, adding to our understanding of the underlying neural mechanisms of ET with poor QoS.

Left superior temporal sulcus morphometry mediates the impact of anxiety and depressive symptoms on sleep quality in healthy adults

Anxiety and depressive symptoms may predispose individuals to sleep disturbance. Understanding how these emotional symptoms affect sleep quality, especially the underlying neural basis, could support the development of effective treatment. The aims of the present study were therefore to investigate potential changes in brain morphometry associated with poor sleep quality and whether this structure played a mediating role between the emotional symptoms and sleep quality. One hundred and forty-one healthy adults (69 women, mean age = 26.06 years, SD = 6.36 years) were recruited. A structural magnetic resonance imaging investigation was performed, and self-reported measures of anxiety, depressive symptoms and sleep quality were obtained for each participant. Whole-brain regression analysis revealed that worse sleep quality was associated with thinner cortex in left superior temporal sulcus (STS). Furthermore, the thickness of left STS mediated the association between the emotional symptoms and sleep quality. A subsequent commonality analysis showed that physiological component of the depressive symptoms had the greatest influence on sleep quality. In conclusion, thinner cortex in left STS may represent a neural substrate for the association between anxiety and depressive symptoms and poor sleep quality and may thus serve as a potential target for neuromodulatory treatment of sleep problems.

Expert opinion in obsessive-compulsive disorder: Treating patients with obsessive-compulsive disorder during the COVID-19 pandemic

This commentary outlines assessment and treatment of patients with OCD during the era of COVID-19. The ongoing COVID-19 pandemic has required providers to make important considerations in treatment, including how usual risk is defined, as well as the use of personal protective equipment and telehealth services. These considerations have allowed providers to continue using both reliable and valid assessment procedures, as well as previously established and efficacious interventions. These adjustments create a context in which patient care for OCD remains fundamentally unchanged; however, important considerations should still be made because of the COVID-19 pandemic.

Design of MRI structured spiking neural networks and learning algorithms for personalized modelling, analysis, and prediction of EEG signals

This paper proposes a novel method and algorithms for the design of MRI structured personalized 3D spiking neural network models (MRI-SNN) for a better analysis, modeling, and prediction of EEG signals. It proposes a novel gradient-descent learning algorithm integrated with a spike-time-dependent-plasticity algorithm. The models capture informative personal patterns of interaction between EEG channels, contrary to single EEG signal modeling methods or to spike-based approaches which do not use personal MRI data to pre-structure a model. The proposed models can not only learn and model accurately measured EEG data, but they can also predict signals at 3D model locations that correspond to non-monitored brain areas, e.g. other EEG channels, from where data has not been collected. This is the first study in this respect. As an illustration of the method, personalized MRI-SNN models are created and tested on EEG data from two subjects. The models result in better prediction accuracy and a better understanding of the personalized EEG signals than traditional methods due to the MRI and EEG information integration. The models are interpretable and facilitate a better understanding of related brain processes. This approach can be applied for personalized modeling, analysis, and prediction of EEG signals across brain studies such as the study and prediction of epilepsy, peri-perceptual brain activities, brain-computer interfaces, and others.

Sex-specific association of poor sleep quality with gray matter volume

STUDY OBJECTIVES

Previous studies were inconsistent with regard to the association of sleep dysfunction on the brain's gray matter volume (GMV). The current study set out to investigate if there is a moderating effect of sex on the relationship between sleep quality in healthy individuals and GMV.

METHODS

We applied voxel-based morphometry in 1,074 young adults of the "Human Connectome Project." An analysis of variance with the factors "sleep quality" (good/poor according to the Pittsburgh Sleep Quality Index, cutoff >5) and "sex" (male, female) on GMV was conducted. Additionally, linear relationships between sleep quality and GMV were tested.

RESULTS

The analysis of variance yielded no main effect for sleep quality, but an interaction between sex and sleep quality for the right superior frontal gyrus. Post hoc t-tests showed that female good sleepers in comparison to female poor sleepers had larger GMV in the right parahippocampal gyrus extending to the right hippocampus (whole-brain family-wise error [FWE]-corrected), as well as smaller GMV in the right inferior parietal lobule (whole-brain FWE-corrected) and the right inferior temporal gyrus (whole brain FWE-corrected). There were no significant effects when comparing male good sleepers to male poor sleepers. Linear regression analyses corroborated smaller GMV in the right parahippocampal gyrus in women with poor sleep quality.

CONCLUSIONS

Poor sleep quality was associated with altered GMV in females, but not in males. Future studies are needed to investigate the neurobiological mechanisms that underlie the sex differences in the association of sleep quality and brain differences found in this study.

Repeated Digitized Assessment of Risk and Symptom Profiles During Inpatient Treatment of Affective Disorder: Observational Study

BACKGROUND

Predictive models have revealed promising results for the individual prognosis of treatment response and relapse risk as well as for differential diagnosis in affective disorders. Yet, in order to translate personalized predictive modeling from research contexts to psychiatric clinical routine, standardized collection of information of sufficient detail and temporal resolution in day-to-day clinical care is needed. Digital collection of self-report measures by patients is a time- and cost-efficient approach to gain such data throughout treatment.

OBJECTIVE

The objective of this study was to investigate whether patients with severe affective disorders were willing and able to participate in such efforts, whether the feasibility of such systems might vary depending on individual patient characteristics, and if digitally acquired assessments were of sufficient diagnostic validity.

METHODS

We implemented a system for longitudinal digital collection of risk and symptom profiles based on repeated self-reports via tablet computers throughout inpatient treatment of affective disorders at the Department of Psychiatry at the University of Münster. Tablet-handling competency and the speed of data entry were assessed. Depression severity was additionally assessed by a clinical interviewer at baseline and before discharge.

RESULTS

Of 364 affective disorder patients who were approached, 242 (66.5%) participated in the study; 88.8% of participants (215/242) were diagnosed with major depressive disorder, and 27 (11.2%) had bipolar disorder. During the duration of inpatient treatment, 79% of expected assessments were completed, with an average of 4 completed assessments per participant; 4 participants (4/242, 1.6%) dropped out of the study prematurely. During data entry, 89.3% of participants (216/242) did not require additional support. Needing support with tablet handling and slower data entry pace were predicted by older age, whereas depression severity at baseline did not influence these measures. Patient self-reporting of depression severity showed high agreement with standardized external assessments by a clinical interviewer.

CONCLUSIONS

Our results indicate that digital collection of self-report measures is a feasible, accessible, and valid method for longitudinal data collection in psychiatric routine, which will eventually facilitate the identification of individual risk and resilience factors for affective disorders and pave the way toward personalized psychiatric care.

Major depressive disorder and insomnia: Exploring a hypothesis of a common neurological basis using waking and sleep-derived heart rate variability

It remains unclear whether neurobiological dysfunction observed in major depressive disorder (MDD) and insomnia is an expression of common or independent bases. The present investigation sought to explore differences in heart rate variability (HRV)-a widely utilized biomarker of neurobiological functioning-among individuals with MDD, insomnia, and healthy controls, while awake and during distinct sleep stages (REM, N2), with the goal of improving our understanding of shared neurobiological factors in depression and insomnia. Participants were 73 adults who underwent home polysomnography. All N2 and REM sleep epochs with a duration greater than or equal to 5 min were identified for HRV analysis. Additionally, a single waking epoch was defined for each participant. From waking to N2 sleep, and waking to REM sleep, changes in HRV indices indicated participants experienced reductions in sympathetic arousal and increases in parasympathetic arousal. Contrary to hypotheses, however, no between group differences were observed in HRV. Though the present findings do not support the hypotheses of a shard neurobiological pathway between MDD and insomnia, more work is warranted to advance our understanding of the neurobiological bases of these common, debilitating, and frequently co-occurring psychiatric conditions, to improve early detection and identify novel intervention targets for these disorders.

Precision Psychiatry Applications with Pharmacogenomics: Artificial Intelligence and Machine Learning Approaches

A growing body of evidence now suggests that precision psychiatry, an interdisciplinary field of psychiatry, precision medicine, and pharmacogenomics, serves as an indispensable foundation of medical practices by offering the accurate medication with the accurate dose at the accurate time to patients with psychiatric disorders. In light of the latest advancements in artificial intelligence and machine learning techniques, numerous biomarkers and genetic loci associated with psychiatric diseases and relevant treatments are being discovered in precision psychiatry research by employing neuroimaging and multi-omics. In this review, we focus on the latest developments for precision psychiatry research using artificial intelligence and machine learning approaches, such as deep learning and neural network algorithms, together with multi-omics and neuroimaging data. Firstly, we review precision psychiatry and pharmacogenomics studies that leverage various artificial intelligence and machine learning techniques to assess treatment prediction, prognosis prediction, diagnosis prediction, and the detection of potential biomarkers. In addition, we describe potential biomarkers and genetic loci that have been discovered to be associated with psychiatric diseases and relevant treatments. Moreover, we outline the limitations in regard to the previous precision psychiatry and pharmacogenomics studies. Finally, we present a discussion of directions and challenges for future research.

Sleep Problems and Workplace Violence: A Systematic Review and Meta-Analysis

Background: This systematic review with meta-analysis was carried out to study the relationship between workplace violence and sleep problems.

Methods: The PRISMA statement was used to conduct a systematic search of the literature on PubMed/MEDLINE, Scopus, Sociological abstract, DOAJ, Web of Science, and Google Scholar databases. Of the original number of 749 studies, 34 were included in the systematic review, and 7 in the meta-analysis.

Results: A total of 119,361 participants from 15 different countries took part in these studies which were published between 1999 and 2019. Significant heterogeneity was observed among the studies (I² = 96%). In a random-effects meta-analysis model, pooled odds ratio (OR) analysis revealed that there was a direct relationship between occupational exposure to violence and sleep problems (OR = 2.55; 95% CI = 1.77–3.66). According to the GRADE guidelines, the quality of evidence of the association was low.

Conclusions: The findings of this study demonstrate that occupational exposure to physical, verbal, or sexual violence is associated with sleep problems. Further research on the relationship between violence and sleep is needed so that appropriate measures can be taken to prevent violence and improve sleep hygiene in the workplace.

Trial Registration Number: PROSPERO International prospective register of systematic reviews (CRD42019124903) February 9, 2019.