Use of machine learning in predicting clinical response to transcranial magnetic stimulation in comorbid posttraumatic stress disorder and major depression: A resting state electroencephalography study

Transcranial Magnetic Stimulation-Based Machine Learning Prediction of Tumor Grading in Motor-Eloquent Gliomas

BACKGROUND

Navigated transcranial magnetic stimulation (nTMS) is a well-established preoperative mapping tool for motor-eloquent glioma surgery. Machine learning (ML) and nTMS may improve clinical outcome prediction and histological correlation.

METHODS

This was a retrospective cohort study of patients who underwent surgery for motor-eloquent gliomas between 2018 and 2022. Ten healthy subjects were included. Preoperative nTMS-derived variables were collected: resting motor threshold (RMT), interhemispheric RMT ratio (iRMTr)-abnormal if above 10%-and cortical excitability score-number of abnormal iRMTrs. World Health Organization (WHO) grade and molecular profile were collected to characterize each tumor. ML models were fitted to the data after statistical feature selection to predict tumor grade.

RESULTS

A total of 177 patients were recruited: WHO grade 2-32 patients, WHO grade 3-65 patients, and WHO grade 4-80 patients. For the upper limb, abnormal iRMTr were identified in 22.7% of WHO grade 2, 62.5% of WHO grade 3, and 75.4% of WHO grade 4 patients. For the lower limb, iRMTr was abnormal in 23.1% of WHO grade 2, 67.6% of WHO grade 3%, and 63.6% of WHO grade 4 patients. Cortical excitability score (P = .04) was statistically significantly related with WHO grading. Using these variables as predictors, the ML model had an accuracy of 0.57 to predict WHO grade 4 lesions. In subgroup analysis of high-grade gliomas vs low-grade gliomas, the accuracy for high-grade gliomas prediction increased to 0.83. The inclusion of molecular data into the model-IDH mutation and 1p19q codeletion status-increases the accuracy of the model in predicting tumor grading (0.95 and 0.74, respectively).

CONCLUSION

ML algorithms based on nTMS-derived interhemispheric excitability assessment provide accurate predictions of HGGs affecting the motor pathway. Their accuracy is further increased when molecular data are fitted onto the model paving the way for a joint preoperative approach with radiogenomics.

Electroencephalography oscillations can predict the cortical response following theta burst stimulation

BACKGROUND

Continuous theta burst stimulation and intermittent theta burst stimulation are clinically popular models of repetitive transcranial magnetic stimulation. However, they are limited by high variability between individuals in cortical excitability changes following stimulation. Although electroencephalography oscillations have been reported to modulate the cortical response to transcranial magnetic stimulation, their association remains unclear. This study aims to explore whether machine learning models based on EEG oscillation features can predict the cortical response to transcranial magnetic stimulation.

METHOD

Twenty-three young, healthy adults attended two randomly assigned sessions for continuous and intermittent theta burst stimulation. In each session, ten minutes of resting-state electroencephalography were recorded before delivering brain stimulation. Participants were classified as responders or non-responders based on changes in resting motor thresholds. Support vector machines and multi-layer perceptrons were used to establish predictive models of individual responses to transcranial magnetic stimulation.

RESULT

Among the evaluated algorithms, support vector machines achieved the best performance in discriminating responders from non-responders for intermittent theta burst stimulation (accuracy: 91.30%) and continuous theta burst stimulation (accuracy: 95.66%). The global clustering coefficient and global characteristic path length in the beta band had the greatest impact on model output.

CONCLUSION

These findings suggest that EEG features can serve as markers of cortical response to transcranial magnetic stimulation. They offer insights into the association between neural oscillations and variability in individuals' responses to transcranial magnetic stimulation, aiding in the optimization of individualized protocols.

Elevating the field for applying neuroimaging to individual patients in psychiatry

Although neuroimaging has been widely applied in psychiatry, much of the exuberance in decades past has been tempered by failed replications and a lack of definitive evidence to support the utility of imaging to inform clinical decisions. There are multiple promising ways forward to demonstrate the relevance of neuroimaging for psychiatry at the individual patient level. Ultra-high field magnetic resonance imaging is developing as a sensitive measure of neurometabolic processes of particular relevance that holds promise as a new way to characterize patient abnormalities as well as variability in response to treatment. Neuroimaging may also be particularly suited to the science of brain stimulation interventions in psychiatry given that imaging can both inform brain targeting as well as measure changes in brain circuit communication as a function of how effectively interventions improve symptoms. We argue that a greater focus on individual patient imaging data will pave the way to stronger relevance to clinical care in psychiatry. We also stress the importance of using imaging in symptom-relevant experimental manipulations and how relevance will be best demonstrated by pairing imaging with differential treatment prediction and outcome measurement. The priorities for using brain imaging to inform psychiatry may be shifting, which compels the field to solidify clinical relevance for individual patients over exploratory associations and biomarkers that ultimately fail to replicate.

Pre-treatment frontal beta events are associated with executive dysfunction improvement after repetitive transcranial magnetic stimulation for depression: A preliminary report

Repetitive transcranial magnetic stimulation (rTMS) is an established clinical treatment for major depressive disorder (MDD) that has also been found to improve aspects of executive functioning. The objective of this study was to examine whether oscillatory burst-like events within the beta band (15-29 Hz) prior to treatment could predict subsequent change in self-reported executive dysfunction (EDF) across a clinical course of rTMS for MDD. Twenty-eight adults (64% female) with MDD completed the self-report Frontal Systems Behavior Scale (FrSBe) and provided eyes-closed resting-state electroencephalography (EEG) before and after a clinical course of rTMS therapy for primary MDD. The rate, power, duration, and frequency span of transient EEG measured oscillatory beta events were calculated. Events within delta/theta and alpha bands were examined to assess for beta specificity. After controlling for improvement in primary depressive symptoms, a lower rate of beta events at F3, Fz, F4, and Cz prior to rTMS treatment was associated with a larger improvement in EDF after rTMS treatment. In addition, a decrease in beta event rate at Fz pre-to-post treatment was associated with a larger improvement in EDF after treatment. Results were largely specific to the beta band. In this study, the rate of frontrocentral beta events prior to treatment significantly predicted the likelihood of subsequent improvement in EDF symptoms following a clinical course of rTMS for MDD. These preliminary findings suggest the potential utility of EEG measured beta events and rTMS for targeting EDF across an array of neuropsychiatric disorders.

Identifying predictive biomarkers for repetitive transcranial magnetic stimulation response in depression patients with explainability

Repetitive Transcranial Magnetic Stimulation (rTMS) is an evidence-based treatment for depression. However, the patterns of response to this treatment modality are inconsistent. Whilst many people see a significant reduction in the severity of their depression following rTMS treatment, some patients do not. To support and improve patient outcomes, recent work is exploring the possibility of using Machine Learning to predict rTMS treatment outcomes. Our proposed model is the first to combine functional magnetic resonance imaging (fMRI) connectivity with deep learning techniques to predict treatment outcomes before treatment starts. Furthermore, with the use of Explainable AI (XAI) techniques, we identify potential biomarkers that may discriminate between rTMS responders and non-responders. Our experiments utilize 200 runs of repeated bootstrap sampling on two rTMS datasets. We compare performances between our proposed feedforward deep neural network against existing methods, and compare the average accuracy, balanced accuracy and F1-score on a held-out test set. The results of these experiments show that our model outperforms existing methods with an average accuracy of 0.9423, balanced accuracy of 0.9423, and F1-score of 0.9461 in a sample of 61 patients. We found that functional connectivity measures between the Subgenual Anterior Cingulate Cortex and Centeral Opercular Cortex are a key determinant of rTMS treatment response. This knowledge provides psychiatrists with further information to explore the potential mechanisms of responses to rTMS treatment. Our developed prototype is ready to be deployed across large datasets in multiple centres and different countries.

Examining the neural mechanisms of rTMS: a naturalistic pilot study of acute and serial effects in pharmacoresistant depression

Introduction

Previous studies have demonstrated the effectiveness of therapeutic repetitive transcranial magnetic stimulation (rTMS) to treat pharmacoresistant depression. Nevertheless, these trials have primarily focused on the therapeutic and neurophysiological effects of rTMS following a long-term treatment course. Identifying brain-based biomarkers of early rTMS therapeutic response remains an important unanswered question. In this pilot study, we examined the effects of rTMS on individuals with pharmacoresistant depression using a graph-based method, called Functional Cortical Networks (FCN), and serial electroencephalography (EEG). We hypothesized that changes in brain activity would occur early in treatment course.

Methods

A total of 15 patients with pharmacoresistant depression underwent five rTMS sessions (5Hz over the left dorsolateral prefrontal cortex, 120%MT, up to 4,000 pulses/session). Five participants received additional rTMS treatment, up to 40 sessions. Resting EEG activity was measured at baseline and following every five sessions, using 64-channel EEG, for 10 minutes with eyes closed. An FCN model was constructed using time-varying graphs and motif synchronization. The primary outcome was acute changes in weighted-node degree. Secondary outcomes included serial FFT-based power spectral analysis and changes in depressive symptoms measured by the 9-Item Patient Health Questionnaire (PHQ-9) and the 30-item Inventory of Depressive Symptoms-Self Report (IDS-SR).

Results

We found a significant acute effect over the left posterior area after five sessions, as evidenced by an increase in weighted-node degree of 37,824.59 (95% CI, 468.20 to 75,180.98) and a marginal enhancement in the left frontal region (t (14) = 2.0820, p = 0.056). One-way repeated measures ANOVA indicated a significant decrease in absolute beta power over the left prefrontal cortex (F (7, 28) = 2.37, p = 0.048) following ten rTMS sessions. Furthermore, a significant clinical improvement was observed following five rTMS sessions on both PHQ-9 (t (14) = 2.7093, p = 0.017) and IDS-SR (t (14) = 2.5278, p = 0.024) and progressed along the treatment course.

Discussion

Our findings suggest that FCN models and serial EEG may contribute to a deeper understanding of mechanisms underlying rTMS treatment. Additional research is required to investigate the acute and serial effects of rTMS in pharmacoresistant depression and assess whether early EEG changes could serve as predictors of therapeutic rTMS response.

Modeling the antidepressant treatment response to transcranial magnetic stimulation using an exponential decay function

Recovery from depression often demonstrates a nonlinear pattern of treatment response, where the largest reduction in symptoms is observed early followed by smaller improvements. This study investigated whether this exponential pattern could model the antidepressant response to repetitive transcranial magnetic stimulation (TMS). Symptom ratings from 97 patients treated with TMS for depression were collected at baseline and after every five sessions. A nonlinear mixed-effects model was constructed using an exponential decay function. This model was also applied to group-level data from several published clinical trials of TMS for treatment-resistant depression. These nonlinear models were compared to corresponding linear models. In our clinical sample, response to TMS was well modeled with the exponential decay function, yielding significant estimates for all parameters and demonstrating superior fit compared to a linear model. Similarly, when applied to multiple studies comparing TMS modalities as well as to previously identified treatment response trajectories, the exponential decay models yielded consistently better fits compared to linear models. These results demonstrate that the antidepressant response to TMS follows a nonlinear pattern of improvement that is well modeled with an exponential decay function. This modeling offers a simple and useful framework to inform clinical decisions and future studies.

Deep learning and machine learning in psychiatry: a survey of current progress in depression detection, diagnosis and treatment

Informatics paradigms for brain and mental health research have seen significant advances in recent years. These developments can largely be attributed to the emergence of new technologies such as machine learning, deep learning, and artificial intelligence. Data-driven methods have the potential to support mental health care by providing more precise and personalised approaches to detection, diagnosis, and treatment of depression. In particular, precision psychiatry is an emerging field that utilises advanced computational techniques to achieve a more individualised approach to mental health care. This survey provides an overview of the ways in which artificial intelligence is currently being used to support precision psychiatry. Advanced algorithms are being used to support all phases of the treatment cycle. These systems have the potential to identify individuals suffering from mental health conditions, allowing them to receive the care they need and tailor treatments to individual patients who are mostly to benefit. Additionally, unsupervised learning techniques are breaking down existing discrete diagnostic categories and highlighting the vast disease heterogeneity observed within depression diagnoses. Artificial intelligence also provides the opportunity to shift towards evidence-based treatment prescription, moving away from existing methods based on group averages. However, our analysis suggests there are several limitations currently inhibiting the progress of data-driven paradigms in care. Significantly, none of the surveyed articles demonstrate empirically improved patient outcomes over existing methods. Furthermore, greater consideration needs to be given to uncertainty quantification, model validation, constructing interdisciplinary teams of researchers, improved access to diverse data and standardised definitions within the field. Empirical validation of computer algorithms via randomised control trials which demonstrate measurable improvement to patient outcomes are the next step in progressing models to clinical implementation.

Fronto-central resting-state 15-29 Hz transient beta events change with therapeutic transcranial magnetic stimulation for posttraumatic stress disorder and major depressive disorder

Repetitive transcranial magnetic stimulation (rTMS) is an established treatment for major depressive disorder (MDD) and shows promise for posttraumatic stress disorder (PTSD), yet effectiveness varies. Electroencephalography (EEG) can identify rTMS-associated brain changes. EEG oscillations are often examined using averaging approaches that mask finer time-scale dynamics. Recent advances show some brain oscillations emerge as transient increases in power, a phenomenon termed "Spectral Events," and that event characteristics correspond with cognitive functions. We applied Spectral Event analyses to identify potential EEG biomarkers of effective rTMS treatment. Resting 8-electrode EEG was collected from 23 patients with MDD and PTSD before and after 5 Hz rTMS targeting the left dorsolateral prefrontal cortex. Using an open-source toolbox ( https://github.com/jonescompneurolab/SpectralEvents ), we quantified event features and tested for treatment associated changes. Spectral Events in delta/theta (1-6 Hz), alpha (7-14 Hz), and beta (15-29 Hz) bands occurred in all patients. rTMS-induced improvement in comorbid MDD PTSD were associated with pre- to post-treatment changes in fronto-central electrode beta event features, including frontal beta event frequency spans and durations, and central beta event maxima power. Furthermore, frontal pre-treatment beta event duration correlated negatively with MDD symptom improvement. Beta events may provide new biomarkers of clinical response and advance the understanding of rTMS.

Real world transcranial magnetic stimulation for major depression: A multisite, naturalistic, retrospective study

BACKGROUND

In 2008, the U.S. FDA approved rTMS as a treatment against medication-resistant depression. However, real-world rTMS outcomes remain understudied. This study investigates how rTMS for depression is delivered in routine clinical practice in France, and measures its effectiveness as well as its moderators.

METHODS

Five centers provided retrospective data on patients who were treated with rTMS for treatment-resistant depression from January 2015 to December 2020. Patients were assessed twice using a hetero-questionnaire, with baseline and immediate post-treatment assessments. We conducted univariate analyses to study which factors were significantly associated with rTMS effectiveness. We then included age, gender, and significant factors in a multivariate model.

RESULTS

We collected data from 435 patients with a mean age of 51.27 (14.91): 66 % were female, and 26 % suffered from bipolar depression. Stimulation was delivered using four different stimulation parameters: 1 Hz (7 % of the individuals), 10 Hz (43 %), 20 Hz (12 %), and 50 Hz (intermittent Theta Burst Stimulation, iTBS) (38 %). The mean improvement of depressive symptoms was 33 % (p < 0.001, effect-size: 0.79). Response and remission rates were of 31 % and 22.8 %, respectively. In the multivariate analysis, improvement in depressive symptoms was associated with higher baseline symptoms.

CONCLUSION

This is one of the largest studies that investigates, with careful clinician-rated scales by trained psychiatrists, the effect of rTMS in naturalistic settings. Repetitive TMS appears to be effective in routine clinical practice, although its efficacy could be improved by analyzing predictors of response, as well as personalized targeting of specific brain areas.

Intermittent theta burst stimulation to the left dorsolateral prefrontal cortex improves working memory of subjects with methamphetamine use disorder

BACKGROUND

Repetitive transcranial magnetic stimulation has been employed to treat drug dependence, reduce drug use and improve cognition. The aim of the study was to analyze the effectiveness of intermittent theta-burst stimulation (iTBS) on cognition in individuals with methamphetamine use disorder (MUD).

METHODS

This was a secondary analysis of 40 MUD subjects receiving left dorsolateral prefrontal cortex (L-DLPFC) iTBS or sham iTBS for 20 times over 10 days (twice-daily). Changes in working memory (WM) accuracy, reaction time, and sensitivity index were analyzed before and after active and sham rTMS treatment. Resting-state EEG was also acquired to identify potential biological changes that may relate to any cognitive improvement.

RESULTS

The results showed that iTBS increased WM accuracy and discrimination ability, and improved reaction time relative to sham iTBS. iTBS also reduced resting-state delta power over the left prefrontal region. This reduction in resting-state delta power correlated with the changes in WM.

CONCLUSIONS

Prefrontal iTBS may enhance WM performance in MUD subjects. iTBS induced resting EEG changes raising the possibility that such findings may represent a biological target of iTBS treatment response.

Fronto-central resting-state 15-29Hz transient beta events change with therapeutic transcranial magnetic stimulation for posttraumatic stress disorder and major depressive disorder

Repetitive transcranial magnetic stimulation (rTMS) is an established treatment for major depressive disorder (MDD) and shows promise for posttraumatic stress disorder (PTSD), yet effectiveness varies. Electroencephalography (EEG) can identify rTMS-associated brain changes. EEG oscillations are often examined using averaging approaches that mask finer time-scale dynamics. Recent advances show some brain oscillations emerge as transient increases in power, a phenomenon termed "Spectral Events," and that event characteristics correspond with cognitive functions. We applied Spectral Event analyses to identify potential EEG biomarkers of effective rTMS treatment. Resting 8-electrode EEG was collected from 23 patients with MDD and PTSD before and after 5Hz rTMS targeting the left dorsolateral prefrontal cortex. Using an open-source toolbox ( https://github.com/jonescompneurolab/SpectralEvents ), we quantified event features and tested for treatment associated changes. Spectral Events in delta/theta (1-6 Hz), alpha (7-14 Hz), and beta (15-29 Hz) bands occurred in all patients. rTMS-induced improvement in comorbid MDD PTSD were associated with pre-to post-treatment changes in fronto-central electrode beta event features, including frontal beta event frequency spans and durations, and central beta event maxima power. Furthermore, frontal pre-treatment beta event duration correlated negatively with MDD symptom improvement. Beta events may provide new biomarkers of clinical response and advance the understanding of rTMS.

Methodological and Quality Flaws in the Use of Artificial Intelligence in Mental Health Research: Systematic Review

BACKGROUND

Artificial intelligence (AI) is giving rise to a revolution in medicine and health care. Mental health conditions are highly prevalent in many countries, and the COVID-19 pandemic has increased the risk of further erosion of the mental well-being in the population. Therefore, it is relevant to assess the current status of the application of AI toward mental health research to inform about trends, gaps, opportunities, and challenges.

OBJECTIVE

This study aims to perform a systematic overview of AI applications in mental health in terms of methodologies, data, outcomes, performance, and quality.

METHODS

A systematic search in PubMed, Scopus, IEEE Xplore, and Cochrane databases was conducted to collect records of use cases of AI for mental health disorder studies from January 2016 to November 2021. Records were screened for eligibility if they were a practical implementation of AI in clinical trials involving mental health conditions. Records of AI study cases were evaluated and categorized by the International Classification of Diseases 11th Revision (ICD-11). Data related to trial settings, collection methodology, features, outcomes, and model development and evaluation were extracted following the CHARMS (Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies) guideline. Further, evaluation of risk of bias is provided.

RESULTS

A total of 429 nonduplicated records were retrieved from the databases and 129 were included for a full assessment-18 of which were manually added. The distribution of AI applications in mental health was found unbalanced between ICD-11 mental health categories. Predominant categories were Depressive disorders (n=70) and Schizophrenia or other primary psychotic disorders (n=26). Most interventions were based on randomized controlled trials (n=62), followed by prospective cohorts (n=24) among observational studies. AI was typically applied to evaluate quality of treatments (n=44) or stratify patients into subgroups and clusters (n=31). Models usually applied a combination of questionnaires and scales to assess symptom severity using electronic health records (n=49) as well as medical images (n=33). Quality assessment revealed important flaws in the process of AI application and data preprocessing pipelines. One-third of the studies (n=56) did not report any preprocessing or data preparation. One-fifth of the models were developed by comparing several methods (n=35) without assessing their suitability in advance and a small proportion reported external validation (n=21). Only 1 paper reported a second assessment of a previous AI model. Risk of bias and transparent reporting yielded low scores due to a poor reporting of the strategy for adjusting hyperparameters, coefficients, and the explainability of the models. International collaboration was anecdotal (n=17) and data and developed models mostly remained private (n=126).

CONCLUSIONS

These significant shortcomings, alongside the lack of information to ensure reproducibility and transparency, are indicative of the challenges that AI in mental health needs to face before contributing to a solid base for knowledge generation and for being a support tool in mental health management.

Electroencephalography for predicting antidepressant treatment success: A systematic review and meta-analysis

BACKGROUND

Patients suffering from major depressive disorder (MDD) regularly experience non-response to treatment for their depressive episode. Personalized clinical decision making could shorten depressive episodes and reduce patient suffering. Although no clinical tools are currently available, machine learning analysis of electroencephalography (EEG) shows promise in treatment response prediction.

METHODS

With a systematic review and meta-analysis, we evaluated the accuracy of EEG for individual patient response prediction. Importantly, we included only prediction studies that used cross-validation. We used a bivariate model to calculate prediction success, as expressed by area-under the curve, sensitivity and specificity. Furthermore, we analyzed prediction success for separate antidepressant interventions.

RESULTS

15 studies with 12 individual patient samples and a total of 479 patients were included. Research methods varied considerably between studies. Meta-analysis of results from this heterogeneous set of studies resulted in an area under the curve of 0.91, a sensitivity of 83 % (95 % CI 74-89 %), and a specificity of 86 % (95 % CI 81-90 %). Classification performance did not significantly differ between treatments. Although studies were all internally validated, no externally validated studies have been reported. We found substantial risk of bias caused by methodological shortcomings such as non-independent feature selection, though performance of non-biased studies was comparable.

LIMITATIONS

Sample sizes were relatively small and no study used external validation, increasing the risk of overestimation of accuracy.

CONCLUSIONS

Electroencephalography can predict the response to antidepressant treatment with high accuracy. However, future studies with more rigorous validation are needed to produce a clinical tool to guide interventions in MDD.

PROSPERO REGISTRATION NUMBER

CRD42021268169.

Burning down the house: reinventing drug discovery in psychiatry for the development of targeted therapies

Despite advances in neuroscience, limited progress has been made in developing new and better medications for psychiatric disorders. Available treatments in psychiatry rely on a few classes of drugs that have a broad spectrum of activity across disorders with limited understanding of mechanism of action. While the added value of more targeted therapies is apparent, a dearth of pathophysiologic mechanisms exists to support targeted treatments, and where mechanisms have been identified and drugs developed, results have been disappointing. Based on serendipity and early successes that led to the current drug armamentarium, a haunting legacy endures that new drugs should align with outdated and overinclusive diagnostic categories, consistent with the idea that "one size fits all". This legacy has fostered clinical trial designs focused on heterogenous populations of patients with a single diagnosis and non-specific outcome variables. Disturbingly, this approach likely contributed to missed opportunities for drugs targeting the hypothalamic-pituitary-adrenal axis and now inflammation. Indeed, cause-and-effect data support the role of inflammatory processes in neurotransmitter alterations that disrupt specific neurocircuits and related behaviors. This pathway to pathology occurs across disorders and warrants clinical trial designs that enrich for patients with increased inflammation and use primary outcome variables associated with specific effects of inflammation on brain and behavior. Nevertheless, such trial designs have not been routinely employed, and results of anti-inflammatory treatments have been underwhelming. Thus, to accelerate development of targeted therapeutics including in the area of inflammation, regulatory agencies and the pharmaceutical industry must embrace treatments and trials focused on pathophysiologic pathways that impact specific symptom domains in subsets of patients, agnostic to diagnosis. Moreover, closer collaboration among basic and clinical investigators is needed to apply neuroscience knowledge to reveal disease mechanisms that drive psychiatric symptoms. Together, these efforts will support targeted treatments, ultimately leading to new and better therapeutics in psychiatry.

Contemporary Approaches Toward Neuromodulation of Fear Extinction and Its Underlying Neural Circuits

Neuroscience and neuroimaging research have now identified brain nodes that are involved in the acquisition, storage, and expression of conditioned fear and its extinction. These brain regions include the ventromedial prefrontal cortex (vmPFC), dorsal anterior cingulate cortex (dACC), amygdala, insular cortex, and hippocampus. Psychiatric neuroimaging research shows that functional dysregulation of these brain regions might contribute to the etiology and symptomatology of various psychopathologies, including anxiety disorders and post traumatic stress disorder (PTSD) (Barad et al. Biol Psychiatry 60:322-328, 2006; Greco and Liberzon Neuropsychopharmacology 41:320-334, 2015; Milad et al. Biol Psychiatry 62:1191-1194, 2007a, Biol Psychiatry 62:446-454, b; Maren and Quirk Nat Rev Neurosci 5:844-852, 2004; Milad and Quirk Annu Rev Psychol 63:129, 2012; Phelps et al. Neuron 43:897-905, 2004; Shin and Liberzon Neuropsychopharmacology 35:169-191, 2009). Combined, these findings indicate that targeting the activation of these nodes and modulating their functional interactions might offer an opportunity to further our understanding of how fear and threat responses are formed and regulated in the human brain, which could lead to enhancing the efficacy of current treatments or creating novel treatments for PTSD and other psychiatric disorders (Marin et al. Depress Anxiety 31:269-278, 2014; Milad et al. Behav Res Ther 62:17-23, 2014). Device-based neuromodulation techniques provide a promising means for directly changing or regulating activity in the fear extinction network by targeting functionally connected brain regions via stimulation patterns (Raij et al. Biol Psychiatry 84:129-137, 2018; Marković et al. Front Hum Neurosci 15:138, 2021). In the past ten years, notable advancements in the precision, safety, comfort, accessibility, and control of administration have been made to the established device-based neuromodulation techniques to improve their efficacy. In this chapter we discuss ten years of progress surrounding device-based neuromodulation techniques-Electroconvulsive Therapy (ECT), Transcranial Magnetic Stimulation (TMS), Magnetic Seizure Therapy (MST), Transcranial Focused Ultrasound (TUS), Deep Brain Stimulation (DBS), Vagus Nerve Stimulation (VNS), and Transcranial Electrical Stimulation (tES)-as research and clinical tools for enhancing fear extinction and treating PTSD symptoms. Additionally, we consider the emerging research, current limitations, and possible future directions for these techniques.

The modulation of attentional deployment on emotional sensitivity to missed opportunity in depressive individuals: An event-related potential study

BACKGROUND

Depression affects individuals' physical and mental health seriously. It's important to explore the pathological mechanisms underlying depression. However, the emotional sensitivity to missed opportunity in depressive individuals and whether attentional deployment influences it remain unclear. The exploration of these questions could help to find novel approaches for the treatment of depression.

METHODS

Experiment 1 investigated the emotional sensitivity to missed opportunity in depressive participants during a sequential risk-taking task relative to healthy participants. Experiment 2 added attentional deployment manipulation to the task, i.e., inducing participants to focus on the positive or negative part of decision outcome, and investigated the modulation of attentional deployment on depressive participants' emotional sensitivity to missed opportunity and the neural mechanisms underlying this process by using EEG.

RESULTS

Depressive participants showed stronger emotional sensitivity to missed opportunity and LPP was a biomarker of this sensitivity. Moreover, focusing on the positive part of outcome reduced depressive participants' emotional sensitivity to missed opportunity effectively, and alpha power in the parietal area played a key role in this process.

CONCLUSIONS

The current study primarily revealed that depressive individuals were more sensitive to missed opportunity and attentional deployment was an effective way to modulate this sensitivity.

Modern views of machine learning for precision psychiatry

In light of the National Institute of Mental Health (NIMH)'s Research Domain Criteria (RDoC), the advent of functional neuroimaging, novel technologies and methods provide new opportunities to develop precise and personalized prognosis and diagnosis of mental disorders. Machine learning (ML) and artificial intelligence (AI) technologies are playing an increasingly critical role in the new era of precision psychiatry. Combining ML/AI with neuromodulation technologies can potentially provide explainable solutions in clinical practice and effective therapeutic treatment. Advanced wearable and mobile technologies also call for the new role of ML/AI for digital phenotyping in mobile mental health. In this review, we provide a comprehensive review of ML methodologies and applications by combining neuroimaging, neuromodulation, and advanced mobile technologies in psychiatry practice. We further review the role of ML in molecular phenotyping and cross-species biomarker identification in precision psychiatry. We also discuss explainable AI (XAI) and neuromodulation in a closed human-in-the-loop manner and highlight the ML potential in multi-media information extraction and multi-modal data fusion. Finally, we discuss conceptual and practical challenges in precision psychiatry and highlight ML opportunities in future research.

Resting-state EEG functional connectivity predicts post-traumatic stress disorder subtypes in veterans

Objective. Post-traumatic stress disorder (PTSD) is highly heterogeneous, and identification of quantifiable biomarkers that could pave the way for targeted treatment remains a challenge. Most previous electroencephalography (EEG) studies on PTSD have been limited to specific handpicked features, and their findings have been highly variable and inconsistent. Therefore, to disentangle the role of promising EEG biomarkers, we developed a machine learning framework to investigate a wide range of commonly used EEG biomarkers in order to identify which features or combinations of features are capable of characterizing PTSD and potential subtypes.Approach. We recorded 5 min of eyes-closed and 5 min of eyes-open resting-state EEG from 202 combat-exposed veterans (53% with probable PTSD and 47% combat-exposed controls). Multiple spectral, temporal, and connectivity features were computed and logistic regression, random forest, and support vector machines with feature selection methods were employed to classify PTSD. To obtain robust results, we performed repeated two-layer cross-validation to test on an entirely unseen test set.Main results. Our classifiers obtained a balanced test accuracy of up to 62.9% for predicting PTSD patients. In addition, we identified two subtypes within PTSD: one where EEG patterns were similar to those of the combat-exposed controls, and another that were characterized by increased global functional connectivity. Our classifier obtained a balanced test accuracy of 79.4% when classifying this PTSD subtype from controls, a clear improvement compared to predicting the whole PTSD group. Interestingly, alpha connectivity in the dorsal and ventral attention network was particularly important for the prediction, and these connections were positively correlated with arousal symptom scores, a central symptom cluster of PTSD.Significance. Taken together, the novel framework presented here demonstrates how unsupervised subtyping can delineate heterogeneity and improve machine learning prediction of PTSD, and may pave the way for better identification of quantifiable biomarkers.

Involvement of the brain-heart axis in the link between PTSD and cardiovascular disease

Posttraumatic stress disorder (PTSD) has long been associated with a heightened risk of cardiovascular disease (CVD). A number of mechanisms have been implicated to underlie this brain-heart axis relationship, such as altered functioning of the autonomic nervous system and increased systemic inflammation. While neural alterations have repeatedly been observed in PTSD, they are rarely considered in the PTSD-CVD link. The brain-heart axis is a pathway connecting frontal and limbic brain regions to the brainstem and periphery via the autonomic nervous system and it may be a promising model for understanding CVD risk in PTSD given its overlap with PTSD neural deficits. We first provide a summary of the primary mechanisms implicated in the association between PTSD and CVD. We then review the brain-heart axis and its relevance to PTSD, as well as findings from PTSD trials demonstrating that a number of PTSD treatments have effects on areas of the brain-heart axis. Finally, we discuss sex considerations in the PTSD-CVD link. A critical next step in this study is to determine if PTSD treatments that affect the brain-heart axis (e.g., brain stimulation that improves autonomic function) also reduce the risk of CVD.

Predicting treatment response using EEG in major depressive disorder: A machine-learning meta-analysis

Selecting a course of treatment in psychiatry remains a trial-and-error process, and this long-standing clinical challenge has prompted an increased focus on predictive models of treatment response using machine learning techniques. Electroencephalography (EEG) represents a cost-effective and scalable potential measure to predict treatment response to major depressive disorder. We performed separate meta-analyses to determine the ability of models to distinguish between responders and non-responders using EEG across treatments, as well as a performed subgroup analysis of response to transcranial magnetic stimulation (rTMS), and antidepressants (Registration Number: CRD42021257477) in Major Depressive Disorder by searching PubMed, Scopus, and Web of Science for articles published between January 1960 and February 2022. We included 15 studies that predicted treatment responses among patients with major depressive disorder using machine-learning techniques. Within a random-effects model with a restricted maximum likelihood estimator comprising 758 patients, the pooled accuracy across studies was 83.93% (95% CI: 78.90-89.29), with an Area-Under-the-Curve (AUC) of 0.850 (95% CI: 0.747-0.890), and partial AUC of 0.779. The average sensitivity and specificity across models were 77.96% (95% CI: 60.05-88.70), and 84.60% (95% CI: 67.89-92.39), respectively. In a subgroup analysis, greater performance was observed in predicting response to rTMS (Pooled accuracy: 85.70% (95% CI: 77.45-94.83), Area-Under-the-Curve (AUC): 0.928, partial AUC: 0.844), relative to antidepressants (Pooled accuracy: 81.41% (95% CI: 77.45-94.83, AUC: 0.895, pAUC: 0.821). Furthermore, across all meta-analyses, the specificity (true negatives) of EEG models was greater than the sensitivity (true positives), suggesting that EEG models thus far better identify non-responders than responders to treatment in MDD. Studies varied widely in important features across models, although relevant features included absolute and relative power in frontal and temporal electrodes, measures of connectivity, and asymmetry across hemispheres. Predictive models of treatment response using EEG hold promise in major depressive disorder, although there is a need for prospective model validation in independent datasets, and a greater emphasis on replicating physiological markers. Crucially, standardization in cut-off values and clinical scales for defining clinical response and non-response will aid in the reproducibility of findings and the clinical utility of predictive models. Furthermore, several models thus far have used data from open-label trials with small sample sizes and evaluated performance in the absence of training and testing sets, which increases the risk of statistical overfitting. Large consortium studies are required to establish predictive signatures of treatment response using EEG, and better elucidate the replicability of specific markers. Additionally, it is speculated that greater performance was observed in rTMS models, since EEG is assessing neural networks more likely to be directly targeted by rTMS, comprising electrical activity primarily near the surface of the cortex. Prospectively, there is a need for models that examine the comparative effectiveness of multiple treatments across the same patients. However, this will require a thoughtful consideration towards cumulative treatment effects, and whether washout periods between treatments should be utilised. Regardless, longitudinal cross-over trials comparing multiple treatments across the same group of patients will be an important prerequisite step to both facilitate precision psychiatry and identify generalizable physiological predictors of response between and across treatment options.

White matter markers and predictors for subject-specific rTMS response in major depressive disorder

Repetitive transcranial magnetic stimulation (rTMS) has established therapeutic efficacy for major depressive disorder (MDD). While translational research has focused primarily on understanding the mechanism of action of TMS on functional activation and connectivity, the effects on structural connectivity remain largely unknown especially when rTMS is applied using subject-specific brain targets. This study aims to use novel diffusion magnetic resonance imaging (dMRI) analysis to examine microstructural changes related to rTMS treatment response using a unique cohort of 21 patients with MDD treated using rTMS with subject-specific targets. White matter dMRI microstructural measures and clinical scores were captured before and after the full course of treatment. We defined disease-relevant fiber bundles connected to different subregions of the left prefrontal cortex and analyzed changes in diffusion properties as well as correlations between the changes of dMRI measures and the changes in Hamilton Depression Rating Scale (HAMD). No significant changes were observed in tracts connected to the TMS targets. rTMS significantly increased the extra-axonal free-water volume, fractional anisotropy and decreased the radial diffusivity in anterior-medial prefrontal fiber bundles but did not lead to raw changes in lateral prefrontal tracts. That said, the microstructural changes in the lateral prefrontal white matter were significantly correlated with treatment response. Moreover, pre-rTMS dMRI measures of the dorsal anterior cingulate cortex and lateral prefrontal cortex connections are correlated with changes in HAMD scores. Microstructural changes in the anterior-medial and lateral prefrontal white matter are potentially involved in treatment response to TMS, though further investigation is needed using larger datasets.

A combination of P300 and eye movement data improves the accuracy of auxiliary diagnoses of depression

BACKGROUND

Exploratory eye movements (EEMs) and P300 are often used to facilitate the clinical diagnosis of depression. However, There were few studies using the combination of EEMs and P300 to build a model for detecting depression and predicting a curative effect.

METHODS

Sixty patients were recruited for 2 groups: high frequency repetitive transcranial magnetic stimulation(rTMS) combined with paroxetine group and simple paroxetine group. Clinical efficacy was evaluated by the Hamilton Depression scale-24(HAMD-24), EEMs and P300. The classification model of the auxiliary diagnosis of depression and the prediction model of the two treatments were developed based on a machine learning algorithm.

RESULTS

The classification model with the greatest accuracy for patients with depression and healthy controls was 95.24% (AUC = 0.75, recall = 1.00, precision = 0.95, F1-score = 0.97). The root mean square error (RMSE) of the model for predicting the efficacy of high frequency rTMS combined with paroxetine was 3.54 (MAE [mean absolute error] = 2.56, R² = -0.53). The RMSE of the model for predicting the efficacy of paroxetine was 4.97 (MAE = 4.00, R² = -0.91).

CONCLUSION

Based on the machine learning algorithm, P300 and EEMs data was suitable for modeling to distinguish depression patients and healthy individuals. However, it was not suitable for predicting the efficacy of high frequency rTMS combined with paroxetine or to predict the efficacy of paroxetine.

Abnormal degree centrality in first-episode medication-free adolescent depression at rest: A functional magnetic resonance imaging study and support vector machine analysis

BACKGROUND

Depression in adolescents is more heterogeneous and less often diagnosed than depression in adults. At present, reliable approaches to differentiating between adolescents who are and are not affected by depression are lacking. This study was designed to assess voxel-level whole-brain functional connectivity changes associated with adolescent depression in an effort to define an imaging-based biomarker associated with this condition.

MATERIALS AND METHODS

In total, 71 adolescents affected by major depressive disorder (MDD) and 71 age-, sex-, and education level-matched healthy controls were subjected to resting-state functional magnetic resonance imaging (rs-fMRI) based analyses of brain voxel-wise degree centrality (DC), with a support vector machine (SVM) being used for pattern classification analyses.

RESULTS

DC patterns derived from 16-min rs-fMRI analyses were able to effectively differentiate between adolescent MDD patients and healthy controls with 95.1% accuracy (136/143), and with respective sensitivity and specificity values of 92.1% (70/76) and 98.5% (66/67) based upon DC abnormalities detected in the right cerebellum. Specifically, increased DC was evident in the bilateral insula and left lingual area of MDD patients, together with reductions in the DC values in the right cerebellum and bilateral superior parietal lobe. DC values were not significantly correlated with disease severity or duration in these patients following correction for multiple comparisons.

CONCLUSION

These results suggest that whole-brain network centrality abnormalities may be present in many brain regions in adolescent depression patients. Accordingly, these DC maps may hold value as candidate neuroimaging biomarkers capable of differentiating between adolescents who are and are not affected by MDD, although further validation of these results will be critical.

Predictions of tDCS treatment response in PTSD patients using EEG based classification

Transcranial direct current stimulation (tDCS) is an emerging therapeutic tool for treating posttraumatic stress disorder (PTSD). Prior studies have shown that tDCS responses are highly individualized, thus necessitating the individualized optimization of treatment configurations. To date, an effective tool for predicting tDCS treatment outcomes in patients with PTSD has not yet been proposed. Therefore, we aimed to build and validate a tool for predicting tDCS treatment outcomes in patients with PTSD. Forty-eight patients with PTSD received 20 min of 2 mA tDCS stimulation in position of the anode over the F3 and cathode over the F4 region. Non-responders were defined as those with less than 50% improvement after reviewing clinical symptoms based on the Clinician-Administered DSM-5 PTSD Scale (before and after stimulation). Resting-state electroencephalograms were recorded for 3 min before and after stimulation. We extracted power spectral densities (PSDs) for five frequency bands. A support vector machine (SVM) model was used to predict responders and non-responders using PSDs obtained before stimulation. We investigated statistical differences in PSDs before and after stimulation and found statistically significant differences in the F8 channel in the theta band (p = 0.01). The SVM model had an area under the ROC curve (AUC) of 0.93 for predicting responders and non-responders using PSDs. To our knowledge, this study provides the first empirical evidence that PSDs can be useful biomarkers for predicting the tDCS treatment response, and that a machine learning model can provide robust prediction performance. Machine learning models based on PSDs can be useful for informing treatment decisions in tDCS treatment for patients with PTSD.

Electroencephalographic connectivity predicts clinical response to repetitive transcranial magnetic stimulation in patients with insomnia disorder

BACKGROUND

Accumulating evidence suggests that low frequency repetitive transcranial magnetic stimulation (rTMS), which generally decreases cortical excitability and remodels plastic connectivity, improves sleep quality in patients with insomnia disorder. However, the effects of rTMS vary substantially across individuals and treatment is sometimes unsatisfactory, calling for biomarkers for predicting clinical outcomes.

OBJECTIVE

This study aimed to investigate whether functional connectivity of the target network in electroencephalography is associated with the clinical response to low frequency rTMS in patients with insomnia disorder.

METHODS

Twenty-five patients with insomnia disorder were subjected to 10 sessions of treatment with 1 Hz rTMS over the right dorsolateral prefrontal cortex. Resting-state electroencephalography was collected before rTMS. Pittsburgh Sleep Quality Index, Hamilton Depression Rating Scale, Hamilton Anxiety Rating Scale, and Mini-Mental State Exam were performed before and after rTMS treatment, with a follow-up after one month. Electroencephalographic connectivity was measured by the power envelope connectivity at the source level. Partial least squares regression identified models of connectivity that maximally accounted for the rTMS response.

RESULTS

Scores of Pittsburgh Sleep Quality Index, Hamilton Depression Rating Scale, and Hamilton Anxiety Rating Scale were decreased after rTMS and one-month later. Baseline weaker connectivity of a network in the beta and alpha bands between a brain region approximating the stimulated right dorsolateral prefrontal cortex and areas located in the frontal, insular, and limbic cortices was associated with a greater change in Pittsburgh Sleep Quality Index and Hamilton Depression Rating Scale following rTMS.

CONCLUSIONS

Low frequency rTMS could improve sleep quality and depressive moods in patients with insomnia disorder. Moreover, electroencephalographic functional connectivity would potentially be a robust biomarker for predicting the therapeutic effects.

Transcranial magnetic stimulation for post-traumatic stress disorder

Post-traumatic stress disorder (PTSD) is a debilitating psychiatric disorder. While current treatment options are effective for some, many individuals fail to respond to first-line psychotherapies and pharmacotherapy. Transcranial magnetic stimulation (TMS) has emerged over the past several decades as a noninvasive neuromodulatory intervention for psychiatric disorders including depression, with mounting evidence for its safety, tolerability, and efficacy in treating PTSD. While several meta-analyses of TMS for PTSD have been published to date showing large effect sizes on PTSD overall, there is marked variability between studies, making it difficult to draw simple conclusions about how best to treat patients. The following review summarizes over 20 years of the existing literature on TMS as a PTSD treatment, and includes nine randomized controlled trials and many other prospective studies of TMS monotherapy, as well as five randomized controlled trials investigating TMS combined with psychotherapy. While the majority of studies utilize repetitive TMS targeted to the right dorsolateral prefrontal cortex (DLPFC) at low frequency (1 Hz) or high frequency (10 or 20 Hz), others have used alternative frequencies, targeted other regions (most commonly the left DLPFC), or trialed different stimulation protocols utilizing newer TMS modalities such as synchronized TMS and theta-burst TMS (TBS). Although it is encouraging that positive outcomes have been shown, there is a paucity of studies directly comparing available approaches. Biomarkers, such as functional imaging and electroencephalography, were seldomly incorporated yet remain crucial for advancing our knowledge of how to predict and monitor treatment response and for understanding mechanism of action of TMS in this population. Effects on PTSD are often sustained for up to 2-3 months, but more long-term studies are needed in order to understand and predict duration of response. In short, while TMS appears safe and effective for PTSD, important steps are needed to operationalize optimal approaches for patients suffering from this disorder.

[Rhythmic transcranial magnetic stimulation in the treatment of resistant depression in schizophrenia]

Rhythmic transcranial magnetic stimulation (rTMS) has long been actively used in the treatment of depressive disorders in various mental illnesses. At the same time, the question of the predictability of the results of this method for an individual patient remains open. Based on the existing ideas about the relationship of rTMS mechanisms with changes in the state of neural networks, one of the most perspective line is the search for prognostically significant neurophysiological markers. The study analyzed a wide range of EEG characteristics and evoked potentials recorded before treatment in the groups of responders and nonresponders in patients with depressive symptoms in schizophrenia, who have completed a course of rhythmic transcranial magnetic stimulation. The study revealed associations between an unfavorable treatment outcome and greater coherence in the alpha range (mainly in the caudal regions bilaterally) and less coherence in the beta1 range (involving temporal leads and left-hemisphere asymmetry). At the same time, such indicators as the amplitude of the N100 wave and the negativity of the mismatch were uninformative in terms of predicting the effectiveness of therapy.

The promise of machine learning in predicting treatment outcomes in psychiatry

For many years, psychiatrists have tried to understand factors involved in response to medications or psychotherapies, in order to personalize their treatment choices. There is now a broad and growing interest in the idea that we can develop models to personalize treatment decisions using new statistical approaches from the field of machine learning and applying them to larger volumes of data. In this pursuit, there has been a paradigm shift away from experimental studies to confirm or refute specific hypotheses towards a focus on the overall explanatory power of a predictive model when tested on new, unseen datasets. In this paper, we review key studies using machine learning to predict treatment outcomes in psychiatry, ranging from medications and psychotherapies to digital interventions and neurobiological treatments. Next, we focus on some new sources of data that are being used for the development of predictive models based on machine learning, such as electronic health records, smartphone and social media data, and on the potential utility of data from genetics, electrophysiology, neuroimaging and cognitive testing. Finally, we discuss how far the field has come towards implementing prediction tools in real-world clinical practice. Relatively few retrospective studies to-date include appropriate external validation procedures, and there are even fewer prospective studies testing the clinical feasibility and effectiveness of predictive models. Applications of machine learning in psychiatry face some of the same ethical challenges posed by these techniques in other areas of medicine or computer science, which we discuss here. In short, machine learning is a nascent but important approach to improve the effectiveness of mental health care, and several prospective clinical studies suggest that it may be working already.

An E-Mental Health Solution to Prevent and Manage Post-Traumatic Stress Injuries among First Responders in Alberta: Protocol for the Implementation and Evaluation of Text4PTSI and Text4Wellbeing (Preprint)

Background

First responders are confronted with traumatic events in their work that has a substantial toll on their psychological health and may contribute to or result in posttraumatic stress injuries (PTSIs) for many responders. Persons with a PTSI usually seek management therapies. Evidence indicates that digital delivery of these therapies is an innovative, efficient, and effective way to improve PTSI symptoms as an adjunct to in-person delivery.

Objective

This project aims to implement and provide accessible, convenient, and economical SMS text messaging services, known as Text4PTSI and Text4Wellbeing, to first responders in Alberta, Canada; to prevent and improve the symptoms of PTSI among first responders; and to improve their overall quality of life. We will evaluate posttraumatic symptoms and the impact of Text4PTSI and Text4Wellbeing on stress, anxiety, and depression in relation to the correspondents’ demographic backgrounds.

Methods

First responders who subscribe to Text4PTSI or Text4Wellbeing receive daily supportive and psychoeducational SMS text messages for 6 months. The SMS text messages are preprogrammed into an online software program that delivers messages to subscribers. Baseline and follow-up data are collected through online questionnaires using validated scales at enrollment, 6 weeks, 12 weeks, and 24 weeks (end point). In-depth interviews will be conducted to assess satisfaction with the text-based intervention.

Results

We hypothesize that participants who enroll in this program will have improved PTSI symptoms; increased or improved quality of life; and significant reduction in associated stress, depression, and anxiety symptoms, among other psychological concerns. Improvement will be determined in comparison to established baseline parameters.

Conclusions

This research will be beneficial for practitioners and will inform policy-making and decision-making regarding psychological interventions for PTSI. Lessons from this study will inform the scale-up of the intervention, a cost-effective, zero contact therapeutic option to manage PTSI.

International Registered Report Identifier (IRRID)

PRR1-10.2196/30680

Repetitive Transcranial Magnetic Stimulation for Treatment-Resistant Depression: Recent Critical Advances in Patient Care

PURPOSE

Transcranial magnetic stimulation (TMS) is an evidence-based treatment for pharmacoresistant major depressive disorder (MDD). In the last decade, the field has seen significant advances in the understanding and use of this new technology. This review aims to describe the large, randomized controlled studies leading to the modern use of rTMS for MDD. It also includes a special section briefly discussing the use of these technologies during the COVID-19 pandemic.

RECENT FINDINGS

Several new approaches and technologies are emerging in this field, including novel approaches to reduce treatment time and potentially yield new approaches to optimize and maximize clinical outcomes. Of these, theta burst TMS now has evidence indicating it is non-inferior to standard TMS and provides significant advantages in administration. Recent studies also indicate that neuroimaging and related approaches may be able to improve TMS targeting methods and potentially identify those patients most likely to respond to stimulation.

SUMMARY

While new data is promising, significant research remains to be done to individualize and optimize TMS procedures. Emerging new approaches, such as accelerated TMS and advanced targeting methods, require additional replication and demonstration of real-world clinical utility. Cautious administration of TMS during the pandemic is possible with careful attention to safety procedures.

Machine learning prediction of neurocognitive impairment among people with HIV using clinical and multimodal magnetic resonance imaging data

Diagnosis of HIV-associated neurocognitive impairment (NCI) continues to be a clinical challenge. The purpose of this study was to develop a prediction model for NCI among people with HIV using clinical- and magnetic resonance imaging (MRI)-derived features. The sample included 101 adults with chronic HIV disease. NCI was determined using a standardized neuropsychological testing battery comprised of seven domains. MRI features included gray matter volume from high-resolution anatomical scans and white matter integrity from diffusion-weighted imaging. Clinical features included demographics, substance use, and routine laboratory tests. Least Absolute Shrinkage and Selection Operator Logistic regression was used to perform variable selection on MRI features. These features were subsequently used to train a support vector machine (SVM) to predict NCI. Three different classification tasks were performed: one used only clinical features; a second used only selected MRI features; a third used both clinical and selected MRI features. Model performance was evaluated by area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity with a tenfold cross-validation. The SVM classifier that combined selected MRI with clinical features outperformed the model using clinical features or MRI features alone (AUC: 0.83 vs. 0.62 vs. 0.79; accuracy: 0.80 vs. 0.65 vs. 0.72; sensitivity: 0.86 vs. 0.85 vs. 0.86; specificity: 0.71 vs. 0.37 vs. 0.52). Our results provide preliminary evidence that combining clinical and MRI features can increase accuracy in predicting NCI and could be developed as a potential tool for NCI diagnosis in HIV clinical practice.

Changes in functional connectivity after theta-burst transcranial magnetic stimulation for post-traumatic stress disorder: a machine-learning study

Intermittent theta burst stimulation (iTBS) is a novel treatment approach for post-traumatic stress disorder (PTSD), and recent neuroimaging work indicates that functional connectivity profiles may be able to identify those most likely to respond. However, prior work has relied on functional magnetic resonance imaging, which is expensive and difficult to scale. Alternatively, electroencephalography (EEG) represents a different approach that may be easier to implement in clinical practice. To this end, we acquired an 8-channel resting-state EEG signal on participants before (n = 47) and after (n = 43) randomized controlled trial of iTBS for PTSD (ten sessions, delivered at 80% of motor threshold, 1,800 pulses, to the right dorsolateral prefrontal cortex). We used a cross-validated support vector machine (SVM) to track changes in EEG functional connectivity after verum iTBS stimulation. We found that an SVM classifier was able to successfully separate patients who received active treatment vs. sham treatment, with statistically significant findings in the Delta band (1-4 Hz, p = 0.002). Using Delta coherence, the classifier was 75.0% accurate in detecting sham vs. active iTBS, and observed changes represented an increase in functional connectivity between midline central/occipital and a decrease between frontal and central regions. The primary limitations of this work are the sparse electrode system and a modest sample size. Our findings raise the possibility that EEG and machine learning may be combined to provide a window into mechanisms of action of TMS, with the potential that these approaches can inform the development of individualized treatment methods.

Comorbidity Patterns of Older Lung Cancer Patients in Northeast China: An Association Rules Analysis Based on Electronic Medical Records

Purposes: This study aims to identify the comorbidity patterns of older men with lung cancer in China. Methods: We analyzed the electronic medical records (EMRs) of lung cancer patients over age 65 in the Jilin Province of China. The data studied were obtained from 20 hospitals of Jilin Province in 2018. In total, 1510 patients were identified. We conducted a rank–frequency analysis and social network analysis to identify the predominant comorbidities and comorbidity networks. We applied the association rules to mine the comorbidity combination with the values of confidence and lift. A heatmap was utilized to visualize the rules. Results: Our analyses discovered that (1) there were 31 additional medical conditions in older patients with lung cancer. The most frequent comorbidities were pneumonia, cerebral infarction, and hypertension. (2) The network-based analysis revealed seven subnetworks. (3) The association rules analysis provided 41 interesting rules. The results revealed that hypertension, ischemic cardiomyopathy, and pneumonia are the most frequent comorbid combinations. Heart failure may not have a strong implicating role in these comorbidity patterns. Cerebral infarction was rarely combined with other diseases. In addition, glycoprotein metabolism disorder comorbid with hyponatremia or hypokalemia increased the risk of anemia by more than eight times in older lung cancer patients. Conclusions: This study provides evidence on the comorbidity patterns of older men with lung cancer in China. Understanding the comorbidity patterns of older patients with lung cancer can assist clinicians in their diagnoses and contribute to developing healthcare policies, as well as allocating resources.

Predicting outcomes of cross-sex hormone therapy in transgender individuals with gender incongruence based on pre-therapy resting-state brain connectivity

Individuals with gender incongruence (GI) experience serious distress due to incongruence between their gender identity and birth-assigned sex. Sociological, cultural, interpersonal, and biological factors are likely contributory, and for some individuals medical treatment such as cross-sex hormone therapy and gender-affirming surgery can be helpful. Cross-sex hormone therapy can be effective for reducing body incongruence, but responses vary, and there is no reliable way to predict therapeutic outcomes. We used clinical and MRI data before cross-sex hormone therapy as features to train a machine learning model to predict individuals' post-therapy body congruence (the degree to which photos of their bodies match their self-identities). Twenty-five trans women and trans men with gender incongruence participated. The model significantly predicted post-therapy body congruence, with the highest predictive features coming from the cingulo-opercular (R² = 0.41) and fronto-parietal (R² = 0.30) networks. This study provides evidence that hormone therapy efficacy can be predicted from information collected before therapy, and that patterns of functional brain connectivity may provide insights into body-brain effects of hormones, affecting one's sense of body congruence. Results could help identify the need for personalized therapies in individuals predicted to have low body-self congruence after standard therapy.

Implementing Precision Psychiatry: A Systematic Review of Individualized Prediction Models for Clinical Practice

BACKGROUND

The impact of precision psychiatry for clinical practice has not been systematically appraised. This study aims to provide a comprehensive review of validated prediction models to estimate the individual risk of being affected with a condition (diagnostic), developing outcomes (prognostic), or responding to treatments (predictive) in mental disorders.

METHODS

PRISMA/RIGHT/CHARMS-compliant systematic review of the Web of Science, Cochrane Central Register of Reviews, and Ovid/PsycINFO databases from inception until July 21, 2019 (PROSPERO CRD42019155713) to identify diagnostic/prognostic/predictive prediction studies that reported individualized estimates in psychiatry and that were internally or externally validated or implemented. Random effect meta-regression analyses addressed the impact of several factors on the accuracy of prediction models.

FINDINGS

Literature search identified 584 prediction modeling studies, of which 89 were included. 10.4% of the total studies included prediction models internally validated (n = 61), 4.6% models externally validated (n = 27), and 0.2% (n = 1) models considered for implementation. Across validated prediction modeling studies (n = 88), 18.2% were diagnostic, 68.2% prognostic, and 13.6% predictive. The most frequently investigated condition was psychosis (36.4%), and the most frequently employed predictors clinical (69.5%). Unimodal compared to multimodal models (β = .29, P = .03) and diagnostic compared to prognostic (β = .84, p < .0001) and predictive (β = .87, P = .002) models were associated with increased accuracy.

INTERPRETATION

To date, several validated prediction models are available to support the diagnosis and prognosis of psychiatric conditions, in particular, psychosis, or to predict treatment response. Advancements of knowledge are limited by the lack of implementation research in real-world clinical practice. A new generation of implementation research is required to address this translational gap.

Resting-state global EEG connectivity predicts depression and anxiety severity

There is a recent interest in finding neurophysiological biomarkers which will facilitate the diagnosis and understanding of the neural basis of different psychiatric disorders. In this paper, we evaluated the resting-state global EEG connectivity as a potential biomarker for depressive and anxiety symptoms. For this, we evaluated a population of 119 subjects, including 75 healthy subjects and 44 patients with major depressive disorder. We calculated the global connectivity (spectral coherence) in a setup of 60 EEG channels, for six different spectral bands: theta, alpha1, alpha2, beta1, beta2, and gamma. These global connectivity scores were used to train a Support Vector Regressor to predict symptoms measured by the Beck Depression Inventory (BDI) and the Spielberger Trait Anxiety Inventory (TAI). Experiments showed a significant prediction of both symptoms, with a mean absolute error (MAE) of 8.07±6.98 and 11.52±8.7 points, respectively. Among the most discriminating features, the global connectivity in the alpha2 band (10.0-12.0Hz) presented significantly positive Spearman's correlation with the depressive (rho = 0.32, p_FDR <0.01), and the anxiety symptoms (rho = 0.26, p_FDR<0.01).Clinical relevance-This study demonstrates that EEG global connectivity can be used to predict depression and anxiety symptoms measured by widely used questionnaires.

The use of machine learning techniques in trauma-related disorders: a systematic review

Establishing the diagnosis of trauma-related disorders such as Acute Stress Disorder (ASD) and Posttraumatic Stress Disorder (PTSD) have always been a challenge in clinical practice and in academic research, due to clinical and biological heterogeneity. Machine learning (ML) techniques can be applied to improve classification of disorders, to predict outcomes or to determine person-specific treatment selection. We aim to review the existing literature on the use of machine learning techniques in the assessment of subjects with ASD or PTSD. We systematically searched PubMed, Embase and Web of Science for articles published in any language up to May 2019. We found 806 abstracts and included 49 studies in our review. Most of the included studies used multiple levels of biological data to predict risk factors or to identify early symptoms related to PTSD. Other studies used ML classification techniques to distinguish individuals with ASD or PTSD from other psychiatric disorder or from trauma-exposed and healthy controls. We also found studies that attempted to define outcome profiles using clustering techniques and studies that assessed the relationship among symptoms using network analysis. Finally, we proposed a quality assessment in this review, evaluating methodological and technical features on machine learning studies. We concluded that etiologic and clinical heterogeneity of ASD/PTSD patients is suitable to machine learning techniques and a major challenge for the future is to use it in clinical practice for the benefit of patients in an individual level.

Identification of Clinical Features and Biomarkers that may inform a Personalized Approach to rTMS for Depression

Repetitive transcranial magnetic stimulation (rTMS), an established treatment for treatment-resistant depression, may hold promise as a personalized medicine approach for the treatment of major depressive disorder (MDD). Clinical research has begun to identify patient-specific factors that could be used to guide rTMS treatment decisions or individualized treatment approaches. This literature review describes a range of patient factors which have been evaluated as potential biomarkers of rTMS treatment response, including patient- and illness-related characteristics, genetic factors, and biomarkers derived from neuroimaging and EEG. We highlight the need for validation data for imaging and electrophysiological biomarkers associated with rTMS as well as prospective evaluation of clinical predictors. Finally, we consider implications for future efforts to move toward a personalized medicine approach in the treatment of depression with rTMS.