Multimodal Data Integration Advances Longitudinal Prediction of the Naturalistic Course of Depression and Reveals a Multimodal Signature of Remission During 2-Year Follow-up.

BACKGROUND: The ability to predict the disease course of individuals with major depressive disorder (MDD) is essential for optimal treatment planning. Here, we used a data-driven machine learning approach to assess the predictive value of different sets of biological data (whole-blood proteomics, lipid metabolomics, transcriptomics, genetics), both separately and added to clinical baseline variables, for the longitudinal prediction of 2-year remission status in MDD at the individual-subject level. METHODS: Prediction models were trained and cross-validated in a sample of 643 patients with current MDD (2-year remission n = 325) and subsequently tested for performance in 161 individuals with MDD (2-year remission n = 82). RESULTS: Proteomics data showed the best unimodal data predictions (area under the receiver operating characteristic curve = 0.68). Adding proteomic to clinical data at baseline significantly improved 2-year MDD remission predictions (area under the receiver operating characteristic curve = 0.63 vs. 0.78, p = .013), while the addition of other omics data to clinical data did not yield significantly improved model performance. Feature importance and enrichment analysis revealed that proteomic analytes were involved in inflammatory response and lipid metabolism, with fibrinogen levels showing the highest variable importance, followed by symptom severity. Machine learning models outperformed psychiatrists' ability to predict 2-year remission status (balanced accuracy = 71% vs. 55%). CONCLUSIONS: This study showed the added predictive value of combining proteomic data, but not other omics data, with clinical data for the prediction of 2-year remission status in MDD. Our results reveal a novel multimodal signature of 2-year MDD remission status that shows clinical potential for individual MDD disease course predictions from baseline measurements.

Patient specific intracranial neural signatures of obsessions and compulsions in the ventral striatum.

Objective. Deep brain stimulation is a treatment option for patients with refractory obsessive-compulsive disorder. A new generation of stimulators hold promise for closed loop stimulation, with adaptive stimulation in response to biologic signals. Here we aimed to discover a suitable biomarker in the ventral striatum in patients with obsessive compulsive disorder using local field potentials.Approach.We induced obsessions and compulsions in 11 patients undergoing deep brain stimulation treatment using a symptom provocation task. Then we trained machine learning models to predict symptoms using the recorded intracranial signal from the deep brain stimulation electrodes.Main results.Average areas under the receiver operating characteristics curve were 62.1% for obsessions and 78.2% for compulsions for patient specific models. For obsessions it reached over 85% in one patient, whereas performance was near chance level when the model was trained across patients. Optimal performances for obsessions and compulsions was obtained at different recording sites.Significance. The results from this study suggest that closed loop stimulation may be a viable option for obsessive-compulsive disorder, but that intracranial biomarkers are patient and not disorder specific.Clinical Trial:Netherlands trial registry NL7486.

Functional connectivity signatures of major depressive disorder: machine learning analysis of two multicenter neuroimaging studies.

The promise of machine learning has fueled the hope for developing diagnostic tools for psychiatry. Initial studies showed high accuracy for the identification of major depressive disorder (MDD) with resting-state connectivity, but progress has been hampered by the absence of large datasets. Here we used regular machine learning and advanced deep learning algorithms to differentiate patients with MDD from healthy controls and identify neurophysiological signatures of depression in two of the largest resting-state datasets for MDD. We obtained resting-state functional magnetic resonance imaging data from the REST-meta-MDD (N = 2338) and PsyMRI (N = 1039) consortia. Classification of functional connectivity matrices was done using support vector machines (SVM) and graph convolutional neural networks (GCN), and performance was evaluated using 5-fold cross-validation. Features were visualized using GCN-Explainer, an ablation study and univariate t-testing. The results showed a mean classification accuracy of 61% for MDD versus controls. Mean accuracy for classifying (non-)medicated subgroups was 62%. Sex classification accuracy was substantially better across datasets (73-81%). Visualization of the results showed that classifications were driven by stronger thalamic connections in both datasets, while nearly all other connections were weaker with small univariate effect sizes. These results suggest that whole brain resting-state connectivity is a reliable though poor biomarker for MDD, presumably due to disease heterogeneity as further supported by the higher accuracy for sex classification using the same methods. Deep learning revealed thalamic hyperconnectivity as a prominent neurophysiological signature of depression in both multicenter studies, which may guide the development of biomarkers in future studies.

Grey Matter Loss at Different Stages of Cognitive Decline: A Role for the Thalamus in Developing Alzheimer's Disease.

BACKGROUND: Alzheimer's disease (AD) is characterized by cognitive impairment and large loss of grey matter volume and is the most prevalent form of dementia worldwide. Mild cognitive impairment (MCI) is the stage that precedes the AD dementia stage, but individuals with MCI do not always convert to the AD dementia stage, and it remains unclear why. OBJECTIVE: We aimed to assess grey matter loss across the brain at different stages of the clinical continuum of AD to gain a better understanding of disease progression. METHODS: In this large-cohort study (N = 1,386) using neuroimaging data from the Alzheimer's Disease Neuroimaging Initiative, voxel-based morphometry analyses were performed between healthy controls, individuals with early and late and AD dementia stage. RESULTS: Clear patterns of grey matter loss in mostly hippocampal and temporal regions were found across clinical stages, though not yet in early MCI. In contrast, thalamic volume loss seems one of the first signs of cognitive decline already during early MCI, whereas this volume loss does not further progress from late MCI to AD dementia stage. AD dementia stage converters already show grey matter loss in hippocampal and mid-temporal areas as well as the posterior thalamus (pulvinar) and angular gyrus at baseline. CONCLUSION: This study confirms the role of temporal brain regions in AD development and suggests additional involvement of the thalamus/pulvinar and angular gyrus that may be linked to visuospatial, attentional, and memory related problems in both early MCI and AD dementia stage conversion.

Predicting mortality of individual patients with COVID-19: a multicentre Dutch cohort.

OBJECTIVE: Develop and validate models that predict mortality of patients diagnosed with COVID-19 admitted to the hospital. DESIGN: Retrospective cohort study. SETTING: A multicentre cohort across 10 Dutch hospitals including patients from 27 February to 8 June 2020. PARTICIPANTS: SARS-CoV-2 positive patients (age ≥18) admitted to the hospital. MAIN OUTCOME MEASURES: 21-day all-cause mortality evaluated by the area under the receiver operator curve (AUC), sensitivity, specificity, positive predictive value and negative predictive value. The predictive value of age was explored by comparison with age-based rules used in practice and by excluding age from the analysis. RESULTS: 2273 patients were included, of whom 516 had died or discharged to palliative care within 21 days after admission. Five feature sets, including premorbid, clinical presentation and laboratory and radiology values, were derived from 80 features. Additionally, an Analysis of Variance (ANOVA)-based data-driven feature selection selected the 10 features with the highest F values: age, number of home medications, urea nitrogen, lactate dehydrogenase, albumin, oxygen saturation (%), oxygen saturation is measured on room air, oxygen saturation is measured on oxygen therapy, blood gas pH and history of chronic cardiac disease. A linear logistic regression and non-linear tree-based gradient boosting algorithm fitted the data with an AUC of 0.81 (95% CI 0.77 to 0.85) and 0.82 (0.79 to 0.85), respectively, using the 10 selected features. Both models outperformed age-based decision rules used in practice (AUC of 0.69, 0.65 to 0.74 for age >70). Furthermore, performance remained stable when excluding age as predictor (AUC of 0.78, 0.75 to 0.81). CONCLUSION: Both models showed good performance and had better test characteristics than age-based decision rules, using 10 admission features readily available in Dutch hospitals. The models hold promise to aid decision-making during a hospital bed shortage.

Deep learning applications for the classification of psychiatric disorders using neuroimaging data: Systematic review and meta-analysis.

Deep learning (DL) methods have been increasingly applied to neuroimaging data to identify patients with psychiatric and neurological disorders. This review provides an overview of the different DL applications within psychiatry and compares DL model accuracy to standard machine learning (SML). Fifty-three articles were included for qualitative analysis, primarily investigating autism spectrum disorder (ASD; n = 22), schizophrenia (SZ; n = 22) and attention-deficit/hyperactivity disorder (ADHD; n = 9). Thirty-two of the thirty-five studies that directly compared DL to SML reported a higher accuracy for DL. Only sixteen studies could be included in a meta-regression to quantitatively compare DL and SML performance. This showed a higher odds ratio for DL models, though the comparison attained significance only for ASD. Our results suggest that deep learning of neuroimaging data is a promising tool for the classification of individual psychiatric patients. However, it is not yet used to its full potential: most studies use pre-engineered features, whereas one of the main advantages of DL is its ability to learn representations of minimally processed data. Our current evaluation is limited by minimal reporting of performance measures to enable quantitative comparisons, and the restriction to ADHD, SZ and ASD as current research focusses on large publicly available datasets. To truly uncover the added value of DL, we need carefully designed comparisons of SML and DL models which are yet rarely performed.

[Clinical course of COVID-19 in the Netherlands: an overview of 2607 patients in hospital during the first wave]. / Klinisch beloop van covid-19 in Nederland.

OBJECTIVE: To systematically collect clinical data from patients with a proven COVID-19 infection in the Netherlands. DESIGN: Data from 2579 patients with COVID-19 admitted to 10 Dutch centers in the period February to July 2020 are described. The clinical data are based on the WHO COVID case record form (CRF) and supplemented with patient characteristics of which recently an association disease severity has been reported. METHODS: Survival analyses were performed as primary statistical analysis. These Kaplan-Meier curves for time to (early) death (3 weeks) have been determined for pre-morbid patient characteristics and clinical, radiological and laboratory data at hospital admission. RESULTS: Total in-hospital mortality after 3 weeks was 22.2% (95% CI: 20.7% - 23.9%), hospital mortality within 21 days was significantly higher for elderly patients (> 70 years; 35, 0% (95% CI: 32.4% - 37.8%) and patients who died during the 21 days and were admitted to the intensive care (36.5% (95% CI: 32.1% - 41.3%)). Apart from that, in this Dutch population we also see a risk of early death in patients with co-morbidities (such as chronic neurological, nephrological and cardiac disorders and hypertension), and in patients with more home medication and / or with increased urea and creatinine levels. CONCLUSION: Early death due to a COVID-19 infection in the Netherlands appears to be associated with demographic variables (e.g. age), comorbidity (e.g. cardiovascular disease) but also disease char-acteristics at admission.

Structural neuroimaging biomarkers for obsessive-compulsive disorder in the ENIGMA-OCD consortium: medication matters.

No diagnostic biomarkers are available for obsessive-compulsive disorder (OCD). Here, we aimed to identify magnetic resonance imaging (MRI) biomarkers for OCD, using 46 data sets with 2304 OCD patients and 2068 healthy controls from the ENIGMA consortium. We performed machine learning analysis of regional measures of cortical thickness, surface area and subcortical volume and tested classification performance using cross-validation. Classification performance for OCD vs. controls using the complete sample with different classifiers and cross-validation strategies was poor. When models were validated on data from other sites, model performance did not exceed chance-level. In contrast, fair classification performance was achieved when patients were grouped according to their medication status. These results indicate that medication use is associated with substantial differences in brain anatomy that are widely distributed, and indicate that clinical heterogeneity contributes to the poor performance of structural MRI as a disease marker.

Classifying Autism Spectrum Disorder Using the Temporal Statistics of Resting-State Functional MRI Data With 3D Convolutional Neural Networks.

Resting-state functional magnetic resonance imaging (rs-fMRI) data are 4-dimensional volumes (3-space + 1-time) that have been posited to reflect the underlying mechanisms of information exchange between brain regions, thus making it an attractive modality to develop diagnostic biomarkers of brain dysfunction. The enormous success of deep learning in computer vision has sparked recent interest in applying deep learning in neuroimaging. But the dimensionality of rs-fMRI data is too high (~20 M), making it difficult to meaningfully process the data in its raw form for deep learning experiments. It is currently not clear how the data should be engineered to optimally extract the time information, and whether combining different representations of time could provide better results. In this paper, we explored various transformations that retain the full spatial resolution by summarizing the temporal dimension of the rs-fMRI data, therefore making it possible to train a full three-dimensional convolutional neural network (3D-CNN) even on a moderately sized [~2,000 from Autism Brain Imaging Data Exchange (ABIDE)-I and II] data set. These transformations summarize the activity in each voxel of the rs-fMRI or that of the voxel and its neighbors to a single number. For each brain volume, we calculated regional homogeneity, the amplitude of low-frequency fluctuations, the fractional amplitude of low-frequency fluctuations, degree centrality, eigenvector centrality, local functional connectivity density, entropy, voxel-mirrored homotopic connectivity, and auto-correlation lag. We trained the 3D-CNN on a publically available autism dataset to classify the rs-fMRI images as being from individuals with autism spectrum disorder (ASD) or from healthy controls (CON) at an individual level. We attained results competitive on this task for a combined ABIDE-I and II datasets of ~66%. When all summary measures were combined the result was still only as good as that of the best single measure which was regional homogeneity (ReHo). In addition, we also applied the support vector machine (SVM) algorithm on the same dataset and achieved comparable results, suggesting that 3D-CNNs could not learn additional information from these temporal transformations that were more useful to differentiate ASD from CON.

Bidirectional cingulate-dependent danger information transfer across rats.

Social transmission of freezing behavior has been conceived of as a one-way phenomenon in which an observer "catches" the fear of another. Here, we use a paradigm in which an observer rat witnesses another rat receiving electroshocks. Bayesian model comparison and Granger causality show that rats exchange information about danger in both directions: how the observer reacts to the demonstrator's distress also influences how the demonstrator responds to the danger. This was true to a similar extent across highly familiar and entirely unfamiliar rats but is stronger in animals preexposed to shocks. Injecting muscimol in the anterior cingulate of observers reduced freezing in the observers and in the demonstrators receiving the shocks. Using simulations, we support the notion that the coupling of freezing across rats could be selected for to more efficiently detect dangers in a group, in a way similar to cross-species eavesdropping.

Individual prediction of psychotherapy outcome in posttraumatic stress disorder using neuroimaging data.

Trauma-focused psychotherapy is the first-line treatment for posttraumatic stress disorder (PTSD) but 30-50% of patients do not benefit sufficiently. We investigated whether structural and resting-state functional magnetic resonance imaging (MRI/rs-fMRI) data could distinguish between treatment responders and non-responders on the group and individual level. Forty-four male veterans with PTSD underwent baseline scanning followed by trauma-focused psychotherapy. Voxel-wise gray matter volumes were extracted from the structural MRI data and resting-state networks (RSNs) were calculated from rs-fMRI data using independent component analysis. Data were used to detect differences between responders and non-responders on the group level using permutation testing, and the single-subject level using Gaussian process classification with cross-validation. A RSN centered on the bilateral superior frontal gyrus differed between responders and non-responder groups (PFWE < 0.05) while a RSN centered on the pre-supplementary motor area distinguished between responders and non-responders on an individual-level with 81.4% accuracy (P < 0.001, 84.8% sensitivity, 78% specificity and AUC of 0.93). No significant single-subject classification or group differences were observed for gray matter volume. This proof-of-concept study demonstrates the feasibility of using rs-fMRI to develop neuroimaging biomarkers for treatment response, which could enable personalized treatment of patients with PTSD.

A deep learning virtual instrument for monitoring extreme UV solar spectral irradiance.

Measurements of the extreme ultraviolet (EUV) solar spectral irradiance (SSI) are essential for understanding drivers of space weather effects, such as radio blackouts, and aerodynamic drag on satellites during periods of enhanced solar activity. In this paper, we show how to learn a mapping from EUV narrowband images to spectral irradiance measurements using data from NASA's Solar Dynamics Observatory obtained between 2010 to 2014. We describe a protocol and baselines for measuring the performance of models. Our best performing machine learning (ML) model based on convolutional neural networks (CNNs) outperforms other ML models, and a differential emission measure (DEM) based approach, yielding average relative errors of under 4.6% (maximum error over emission lines) and more typically 1.6% (median). We also provide evidence that the proposed method is solving this mapping in a way that makes physical sense and by paying attention to magnetic structures known to drive EUV SSI variability.

Individual Prediction of Behavioral Variant Frontotemporal Dementia Development Using Multivariate Pattern Analysis of Magnetic Resonance Imaging Data.

BACKGROUND: Patients with behavioral variant of frontotemporal dementia (bvFTD) initially may only show behavioral and/or cognitive symptoms that overlap with other neurological and psychiatric disorders. The diagnostic accuracy is dependent on progressive symptoms worsening and frontotemporal abnormalities on neuroimaging findings. Predictive biomarkers could facilitate the early detection of bvFTD. OBJECTIVE: To determine the prognostic accuracy of clinical and structural MRI data using a support vector machine (SVM) classification to predict the 2-year clinical follow-up diagnosis in a group of patients presenting late-onset behavioral changes. METHODS: Data from 73 patients were included and divided into probable/definite bvFTD (n = 18), neurological (n = 28), and psychiatric (n = 27) groups based on 2-year follow-up diagnosis. Grey-matter volumes were extracted from baseline structural MRI scans. SVM classifiers were used to perform three binary classifications: bvFTD versus neurological and psychiatric, bvFTD versus neurological, and bvFTD versus psychiatric group(s), and one multi-class classification. Classification performance was determined for clinical and neuroimaging data separately and their combination using 5-fold cross-validation. RESULTS: Accuracy of the binary classification tasks ranged from 72-82% (p < 0.001) with adequate sensitivity (67-79%), specificity (77-88%), and area-under-the-receiver-operator-curve (0.80-0.9). Multi-class accuracy ranged between 55-59% (p < 0.001). The combination of clinical and voxel-wise whole brain data showed the best performance overall. CONCLUSION: These results show the potential for automated early confirmation of diagnosis for bvFTD using machine learning analysis of clinical and neuroimaging data in a diverse and clinically relevant sample of patients.

Disentangling subgroups of participants recruiting shared as well as different brain regions for the execution of the verb generation task: A data-driven fMRI study.

The spatial pattern of task-related brain activity in fMRI studies might be expected to change according to several variables such as handedness and age. However this spatial heterogeneity might also be due to other unmodeled sources of inter-subject variability. Since group-level results reflect patterns of task-evoked brain activity common to most of the subjects in the sample, they could conceal the presence of subgroups recruiting other brain regions beyond the common pattern. To deal with these issues, data-driven methods can be used to detect the presence of sources of inter-subject variability that might be hard to identify and therefore model a priori. Here we assess the potential of Independent Component Analysis (ICA) to detect the presence of unexpected subgroups of participants. To this end, we acquired task-evoked fMRI data on 45 healthy adults using the verb generation (VGEN) task, in which participants are visually presented with the noun of an object of everyday use, and asked to covertly generate a verb describing the corresponding action. As expected, the task elicited activity in a temporo-parieto-frontal network typically found in previous VGEN experiments. We then quantified the contribution of every subject to nine task-related spatio-temporal processes identified by ICA. A cluster analysis of this quantity yielded three subgroups of participants. Differences between the three identified subgroups were distributed in left and right prefrontal, posterior parietal and extrastriate occipital regions. These results could not be explained by differences in sex, age or handedness across the participants. Furthermore, some regions where a significant difference was found between subgroups were not present in the group-level pattern of task-related activity. We discuss the potential application of this approach for characterizing brain activity in different subgroups of patients with neuropsychiatric or neurological conditions.

Increased Functional Connectivity Between Subcortical and Cortical Resting-State Networks in Autism Spectrum Disorder.

IMPORTANCE: Individuals with autism spectrum disorder (ASD) exhibit severe difficulties in social interaction, motor coordination, behavioral flexibility, and atypical sensory processing, with considerable interindividual variability. This heterogeneous set of symptoms recently led to investigating the presence of abnormalities in the interaction across large-scale brain networks. To date, studies have focused either on constrained sets of brain regions or whole-brain analysis, rather than focusing on the interaction between brain networks. OBJECTIVES: To compare the intrinsic functional connectivity between brain networks in a large sample of individuals with ASD and typically developing control subjects and to estimate to what extent group differences would predict autistic traits and reflect different developmental trajectories. DESIGN, SETTING, AND PARTICIPANTS: We studied 166 male individuals (mean age, 17.6 years; age range, 7-50 years) diagnosed as having DSM-IV-TR autism or Asperger syndrome and 193 typical developing male individuals (mean age, 16.9 years; age range, 6.5-39.4 years) using resting-state functional magnetic resonance imaging (MRI). Participants were matched for age, IQ, head motion, and eye status (open or closed) in the MRI scanner. We analyzed data from the Autism Brain Imaging Data Exchange (ABIDE), an aggregated MRI data set from 17 centers, made public in August 2012. MAIN OUTCOMES AND MEASURES: We estimated correlations between time courses of brain networks extracted using a data-driven method (independent component analysis). Subsequently, we associated estimates of interaction strength between networks with age and autistic traits indexed by the Social Responsiveness Scale. RESULTS: Relative to typically developing control participants, individuals with ASD showed increased functional connectivity between primary sensory networks and subcortical networks (thalamus and basal ganglia) (all t ≥ 3.13, P < .001 corrected). The strength of such connections was associated with the severity of autistic traits in the ASD group (all r ≥ 0.21, P < .0067 corrected). In addition, subcortico-cortical interaction decreased with age in the entire sample (all r ≤ -0.09, P < .012 corrected), although this association was significant only in typically developing participants (all r ≤ -0.13, P < .009 corrected). CONCLUSIONS AND RELEVANCE: Our results showing ASD-related impairment in the interaction between primary sensory cortices and subcortical regions suggest that the sensory processes they subserve abnormally influence brain information processing in individuals with ASD. This might contribute to the occurrence of hyposensitivity or hypersensitivity and of difficulties in top-down regulation of behavior.

Functional magnetic resonance imaging connectivity analyses reveal efference-copy to primary somatosensory area, BA2.

Some theories of motor control suggest efference-copies of motor commands reach somatosensory cortices. Here we used functional magnetic resonance imaging to test these models. We varied the amount of efference-copy signal by making participants squeeze a soft material either actively or passively. We found electromyographical recordings, an efference-copy proxy, to predict activity in primary somatosensory regions, in particular Brodmann Area (BA) 2. Partial correlation analyses confirmed that brain activity in cortical structures associated with motor control (premotor and supplementary motor cortices, the parietal area PF and the cerebellum) predicts brain activity in BA2 without being entirely mediated by activity in early somatosensory (BA3b) cortex. Our study therefore provides valuable empirical evidence for efference-copy models of motor control, and shows that signals in BA2 can indeed reflect an input from motor cortices and suggests that we should interpret activations in BA2 as evidence for somatosensory-motor rather than somatosensory coding alone.

Probabilistic tractography recovers a rostrocaudal trajectory of connectivity variability in the human insular cortex.

The insular cortex of macaques has a wide spectrum of anatomical connections whose distribution is related to its heterogeneous cytoarchitecture. Although there is evidence of a similar cytoarchitectural arrangement in humans, the anatomical connectivity of the insula in the human brain has not yet been investigated in vivo. In the present work, we used in vivo probabilistic white-matter tractography and Laplacian eigenmaps (LE) to study the variation of connectivity patterns across insular territories in humans. In each subject and hemisphere, we recovered a rostrocaudal trajectory of connectivity variation ranging from the anterior dorsal and ventral insula to the dorsal caudal part of the long insular gyri. LE suggested that regional transitions among tractography patterns in the insula occur more gradually than in other brain regions. In particular, the change in tractography patterns was more gradual in the insula than in the medial premotor region, where a sharp transition between different tractography patterns was found. The recovered trajectory of connectivity variation in the insula suggests a relation between connectivity and cytoarchitecture in humans resembling that previously found in macaques: tractography seeds from the anterior insula were mainly found in limbic and paralimbic regions and in anterior parts of the inferior frontal gyrus, while seeds from caudal insular territories mostly reached parietal and posterior temporal cortices. Regions in the putative dysgranular insula displayed more heterogeneous connectivity patterns, with regional differences related to the proximity with either putative granular or agranular regions.