Stress Markers for Mental States and Biotypes of Depression and Anxiety: A Scoping Review and Preliminary Illustrative Analysis.

Depression and anxiety disrupt daily function and their effects can be long-lasting and devastating, yet there are no established physiological indicators that can be used to predict onset, diagnose, or target treatments. In this review, we conceptualize depression and anxiety as maladaptive responses to repetitive stress. We provide an overview of the role of chronic stress in depression and anxiety and a review of current knowledge on objective stress indicators of depression and anxiety. We focused on cortisol, heart rate variability and skin conductance that have been well studied in depression and anxiety and implicated in clinical emotional states. A targeted PubMed search was undertaken prioritizing meta-analyses that have linked depression and anxiety to cortisol, heart rate variability and skin conductance. Consistent findings include reduced heart rate variability across depression and anxiety, reduced tonic and phasic skin conductance in depression, and elevated cortisol at different times of day and across the day in depression. We then provide a brief overview of neural circuit disruptions that characterize particular types of depression and anxiety. We also include an illustrative analysis using predictive models to determine how stress markers contribute to specific subgroups of symptoms and how neural circuits add meaningfully to this prediction. For this, we implemented a tree-based multi-class classification model with physiological markers of heart rate variability as predictors and four symptom subtypes, including normative mood, as target variables. We achieved 40% accuracy on the validation set. We then added the neural circuit measures into our predictor set to identify the combination of neural circuit dysfunctions and physiological markers that accurately predict each symptom subtype. Achieving 54% accuracy suggested a strong relationship between those neural-physiological predictors and the mental states that characterize each subtype. Further work to elucidate the complex relationships between physiological markers, neural circuit dysfunction and resulting symptoms would advance our understanding of the pathophysiological pathways underlying depression and anxiety.

Classifying Major Depressive Disorder and Response to Deep Brain Stimulation Over Time by Analyzing Facial Expressions.

OBJECTIVE: Major depressive disorder (MDD) is a common psychiatric disorder that leads to persistent changes in mood and interest among other signs and symptoms. We hypothesized that convolutional neural network (CNN) based automated facial expression recognition, pre-trained on an enormous auxiliary public dataset, could provide improve generalizable approach to MDD automatic assessment from videos, and classify remission or response to treatment. METHODS: We evaluated a novel deep neural network framework on 365 video interviews (88 hours) from a cohort of 12 depressed patients before and after deep brain stimulation (DBS) treatment. Seven basic emotions were extracted with a Regional CNN detector and an Imagenet pre-trained CNN, both of which were trained on large-scale public datasets (comprising over a million images). Facial action units were also extracted with the Openface toolbox. Statistics of the temporal evolution of these image features over each recording were extracted and used to classify MDD remission and response to DBS treatment. RESULTS: An Area Under the Curve of 0.72 was achieved using leave-one-subject-out cross-validation for remission classification and 0.75 for response to treatment. CONCLUSION: This work demonstrates the potential for the classification of MDD remission and response to DBS treatment from passively acquired video captured during unstructured, unscripted psychiatric interviews. SIGNIFICANCE: This novel MDD evaluation could be used to augment current psychiatric evaluations and allow automatic, low-cost, frequent use when an expert isn't readily available or the patient is unwilling or unable to engage. Potentially, the framework may also be applied to other psychiatric disorders.

Classifying Depression Severity in Recovery From Major Depressive Disorder via Dynamic Facial Features.

Major depressive disorder is a common psychiatric illness. At present, there are no objective, non-verbal, automated markers that can reliably track treatment response. Here, we explore the use of video analysis of facial expressivity in a cohort of severely depressed patients before and after deep brain stimulation (DBS), an experimental treatment for depression. We introduced a set of variability measurements to obtain unsupervised features from muted video recordings, which were then leveraged to build predictive models to classify three levels of severity in the patients' recovery from depression. Multiscale entropy was utilized to estimate the variability in pixel intensity level at various time scales. A dynamic latent variable model was utilized to learn a low-dimensional representation of factors that describe the dynamic relationship between high-dimensional pixels in each video frame and over time. Finally, a novel elastic net ordinal regression model was trained to predict the severity of depression, as independently rated by standard rating scales. Our results suggest that unsupervised features extracted from these video recordings, when incorporated in an ordinal regression predictor, can discriminate different levels of depression severity during ongoing DBS treatment. Objective markers of patient response to treatment have the potential to standardize treatment protocols and enhance the design of future clinical trials.

Addressing the Credit Assignment Problem in Treatment Outcome Prediction using Temporal Difference Learning.

Mental health patients often undergo a variety of treatments before finding an effective one. Improved prediction of treatment response can shorten the duration of trials. A key challenge of applying predictive modeling to this problem is that often the effectiveness of a treatment regimen remains unknown for several weeks, and therefore immediate feedback signals may not be available for supervised learning. Here we propose a Machine Learning approach to extracting audio-visual features from weekly video interview recordings for predicting the likely outcome of Deep Brain Stimulation (DBS) treatment several weeks in advance. In the absence of immediate treatment-response feedback, we utilize a joint state-estimation and temporal difference learning approach to model both the trajectory of a patient's response and the delayed nature of feedbacks. Our results based on longitudinal recordings from 12 patients with depression show that the learned state values are predictive of the long-term success of DBS treatments. We achieve an area under the receiver operating characteristic curve of 0.88, beating all baseline methods.

Cingulum stimulation enhances positive affect and anxiolysis to facilitate awake craniotomy.

BACKGROUND: Awake neurosurgery requires patients to converse and respond to visual or verbal prompts to identify and protect brain tissue supporting essential functions such as language, primary sensory modalities, and motor function. These procedures can be poorly tolerated because of patient anxiety, yet acute anxiolytic medications typically cause sedation and impair cortical function. METHODS: In this study, direct electrical stimulation of the left dorsal anterior cingulum bundle was discovered to reliably evoke positive affect and anxiolysis without sedation in a patient with epilepsy undergoing research testing during standard inpatient intracranial electrode monitoring. These effects were quantified using subjective and objective behavioral measures, and stimulation was found to evoke robust changes in local and distant neural activity. RESULTS: The index patient ultimately required an awake craniotomy procedure to confirm safe resection margins in the treatment of her epilepsy. During the procedure, cingulum bundle stimulation enhanced positive affect and reduced the patient's anxiety to the point that intravenous anesthetic/anxiolytic medications were discontinued and cognitive testing was completed. Behavioral responses were subsequently replicated in 2 patients with anatomically similar electrode placements localized to an approximately 1-cm span along the anterior dorsal cingulum bundle above genu of the corpus callosum. CONCLUSIONS: The current study demonstrates a robust anxiolytic response to cingulum bundle stimulation in 3 patients with epilepsy. TRIAL REGISTRATION: The current study was not affiliated with any formal clinical trial. FUNDING: This project was supported by the American Foundation for Suicide Prevention and the NIH.

Depression Severity Classification from Speech Emotion.

Major Depressive Disorder (MDD) is a common psychiatric illness. Automatically classifying depression severity using audio analysis can help clinical management decisions during Deep Brain Stimulation (DBS) treatment of MDD patients. Leveraging the link between short-term emotions and long-term depressed mood states, we build our predictive model on the top of emotion-based features. Because acquiring emotion labels of MDD patients is a challenging task, we propose to use an auxiliary emotion dataset to train a Deep Neural Network (DNN) model. The DNN is then applied to audio recordings of MDD patients to find their low dimensional representation to be used in the classification algorithm. Our preliminary results indicate that the proposed approach, in comparison to the alternatives, effectively classifies depressed and improved phases of DBS treatment with an AUC of 0.80.

The OncoPPi network of cancer-focused protein-protein interactions to inform biological insights and therapeutic strategies.

As genomics advances reveal the cancer gene landscape, a daunting task is to understand how these genes contribute to dysregulated oncogenic pathways. Integration of cancer genes into networks offers opportunities to reveal protein-protein interactions (PPIs) with functional and therapeutic significance. Here, we report the generation of a cancer-focused PPI network, termed OncoPPi, and identification of >260 cancer-associated PPIs not in other large-scale interactomes. PPI hubs reveal new regulatory mechanisms for cancer genes like MYC, STK11, RASSF1 and CDK4. As example, the NSD3 (WHSC1L1)-MYC interaction suggests a new mechanism for NSD3/BRD4 chromatin complex regulation of MYC-driven tumours. Association of undruggable tumour suppressors with drug targets informs therapeutic options. Based on OncoPPi-derived STK11-CDK4 connectivity, we observe enhanced sensitivity of STK11-silenced lung cancer cells to the FDA-approved CDK4 inhibitor palbociclib. OncoPPi is a focused PPI resource that links cancer genes into a signalling network for discovery of PPI targets and network-implicated tumour vulnerabilities for therapeutic interrogation.

MEDICI: Mining Essentiality Data to Identify Critical Interactions for Cancer Drug Target Discovery and Development.

Protein-protein interactions (PPIs) mediate the transmission and regulation of oncogenic signals that are essential to cellular proliferation and survival, and thus represent potential targets for anti-cancer therapeutic discovery. Despite their significance, there is no method to experimentally disrupt and interrogate the essentiality of individual endogenous PPIs. The ability to computationally predict or infer PPI essentiality would help prioritize PPIs for drug discovery and help advance understanding of cancer biology. Here we introduce a computational method (MEDICI) to predict PPI essentiality by combining gene knockdown studies with network models of protein interaction pathways in an analytic framework. Our method uses network topology to model how gene silencing can disrupt PPIs, relating the unknown essentialities of individual PPIs to experimentally observed protein essentialities. This model is then deconvolved to recover the unknown essentialities of individual PPIs. We demonstrate the validity of our approach via prediction of sensitivities to compounds based on PPI essentiality and differences in essentiality based on genetic mutations. We further show that lung cancer patients have improved overall survival when specific PPIs are no longer present, suggesting that these PPIs may be potentially new targets for therapeutic development. Software is freely available at https://github.com/cooperlab/MEDICI. Datasets are available at https://ctd2.nci.nih.gov/dataPortal.

Discriminating clinical phases of recovery from major depressive disorder using the dynamics of facial expression.

We used several metrics of variability to extract unsupervised features from video recordings of patients before and after deep brain stimulation (DBS) treatment for major depressive disorder (MDD). Our goal was to quantify the treatment effects on facial expressivity. Multiscale entropy (MSE) was used to capture the temporal variability in pixel intensity level at multiple time-scales. A dynamic latent variable model (DLVM) was used to learn a low dimensional (D = 20) set of dynamic factors that explain the observed covariance across the high-dimensional pixels (M = 30 × 30) within each video frame and across time. Our preliminary results indicate that unsupervised features learned from these video recordings can distinguish different phases of depression and recovery. The overarching goal of this research is to develop more refined markers of clinical response to treatment for depression.

Investigation of factors affecting RNA-seq gene expression calls.

RNA-seq enables quantification of the human transcriptome. Estimation of gene expression is a fundamental issue in the analysis of RNA-seq data. However, there is an inherent ambiguity in distinguishing between genes with very low expression and experimental or transcriptional noise. We conducted an exploratory investigation of some factors that may affect gene expression calls. We observed that the distribution of reads that map to exonic, intronic, and intergenic regions are distinct. These distributions may provide useful insights into the behavior of gene expression noise. Moreover, we observed that these distributions are qualitatively similar between two sequence mapping algorithms. Finally, we examined the relationship between gene length and gene expression calls, and observed that they are correlated. This preliminary investigation is important for RNA-seq gene expression analysis because it may lead to more effective algorithms for distinguishing between true gene expression and experimental or transcriptional noise.