Deep neural networks in psychiatry

Neural Decoding and Feature Selection Techniques for Closed-Loop Control of Defensive Behavior

Objective

Many psychiatric disorders involve excessive avoidant or defensive behavior, such as avoidance in anxiety and trauma disorders or defensive rituals in obsessive-compulsive disorders. Developing algorithms to predict these behaviors from local field potentials (LFPs) could serve as foundational technology for closed-loop control of such disorders. A significant challenge is identifying the LFP features that encode these defensive behaviors.

Approach

We analyzed LFP signals from the infralimbic cortex and basolateral amygdala of rats undergoing tone-shock conditioning and extinction, standard for investigating defensive behaviors. We utilized a comprehensive set of neuro-markers across spectral, temporal, and connectivity domains, employing SHapley Additive exPlanations for feature importance evaluation within Light Gradient-Boosting Machine models. Our goal was to decode three commonly studied avoidance/defensive behaviors: freezing, bar-press suppression, and motion (accelerometry), examining the impact of different features on decoding performance.

Main results

Band power and band power ratio between channels emerged as optimal features across sessions. High-gamma (80-150 Hz) power, power ratios, and inter-regional correlations were more informative than other bands that are more classically linked to defensive behaviors. Focusing on highly informative features enhanced performance. Across 4 recording sessions with 16 subjects, we achieved an average coefficient of determination of 0.5357 and 0.3476, and Pearson correlation coefficients of 0.7579 and 0.6092 for accelerometry jerk and bar press rate, respectively. Utilizing only the most informative features revealed differential encoding between accelerometry and bar press rate, with the former primarily through local spectral power and the latter via inter-regional connectivity. Our methodology demonstrated remarkably low time complexity, requiring < 110 ms for training and < 1 ms for inference.

Significance

Our results demonstrate the feasibility of accurately decoding defensive behaviors with minimal latency, using LFP features from neural circuits strongly linked to these behaviors. This methodology holds promise for real-time decoding to identify physiological targets in closed-loop psychiatric neuromodulation.

Development of a differential treatment selection model for depression on consolidated and transformed clinical trial datasets

Major depressive disorder (MDD) is the leading cause of disability worldwide, yet treatment selection still proceeds via "trial and error". Given the varied presentation of MDD and heterogeneity of treatment response, the use of machine learning to understand complex, non-linear relationships in data may be key for treatment personalization. Well-organized, structured data from clinical trials with standardized outcome measures is useful for training machine learning models; however, combining data across trials poses numerous challenges. There is also persistent concern that machine learning models can propagate harmful biases. We have created a methodology for organizing and preprocessing depression clinical trial data such that transformed variables harmonized across disparate datasets can be used as input for feature selection. Using Bayesian optimization, we identified an optimal multi-layer dense neural network that used data from 21 clinical and sociodemographic features as input in order to perform differential treatment benefit prediction. With this combined dataset of 5032 individuals and 6 drugs, we created a differential treatment benefit prediction model. Our model generalized well to the held-out test set and produced similar accuracy metrics in the test and validation set with an AUC of 0.7 when predicting binary remission. To address the potential for bias propagation, we used a bias testing performance metric to evaluate the model for harmful biases related to ethnicity, age, or sex. We present a full pipeline from data preprocessing to model validation that was employed to create the first differential treatment benefit prediction model for MDD containing 6 treatment options.

Robust and replicable functional brain signatures of 22q11.2 deletion syndrome and associated psychosis: a deep neural network-based multi-cohort study

A major genetic risk factor for psychosis is 22q11.2 deletion (22q11.2DS). However, robust and replicable functional brain signatures of 22q11.2DS and 22q11.2DS-associated psychosis remain elusive due to small sample sizes and a focus on small single-site cohorts. Here, we identify functional brain signatures of 22q11.2DS and 22q11.2DS-associated psychosis, and their links with idiopathic early psychosis, using one of the largest multi-cohort data to date. We obtained multi-cohort clinical phenotypic and task-free fMRI data from 856 participants (101 22q11.2DS, 120 idiopathic early psychosis, 101 idiopathic autism, 123 idiopathic ADHD, and 411 healthy controls) in a case-control design. A novel spatiotemporal deep neural network (stDNN)-based analysis was applied to the multi-cohort data to identify functional brain signatures of 22q11.2DS and 22q11.2DS-associated psychosis. Next, stDNN was used to test the hypothesis that the functional brain signatures of 22q11.2DS-associated psychosis overlap with idiopathic early psychosis but not with autism and ADHD. stDNN-derived brain signatures distinguished 22q11.2DS from controls, and 22q11.2DS-associated psychosis with very high accuracies (86-94%) in the primary cohort and two fully independent cohorts without additional training. Robust distinguishing features of 22q11.2DS-associated psychosis emerged in the anterior insula node of the salience network and the striatum node of the dopaminergic reward pathway. These features also distinguished individuals with idiopathic early psychosis from controls, but not idiopathic autism or ADHD. Our results reveal that individuals with 22q11.2DS exhibit a highly distinct functional brain organization compared to controls. Additionally, the brain signatures of 22q11.2DS-associated psychosis overlap with those of idiopathic early psychosis in the salience network and dopaminergic reward pathway, providing substantial empirical support for the theoretical aberrant salience-based model of psychosis. Collectively, our findings, replicated across multiple independent cohorts, advance the understanding of 22q11.2DS and associated psychosis, underscoring the value of 22q11.2DS as a genetic model for probing the neurobiological underpinnings of psychosis and its progression.

Deep Learning and Geriatric Mental Health

The goal of this overview is to help clinicians develop basic proficiency with the terminology of deep learning and understand its fundamentals and early applications. We describe what machine learning and deep learning represent and explain the underlying data science principles. We also review current promising applications and identify ethical issues that bear consideration. Deep Learning is a new type of machine learning that is remarkably good at finding patterns in data, and in some cases generating realistic new data. We provide insights into how deep learning works and discuss its relevance to geriatric psychiatry.

The Deep Learning Method Differentiates Patients with Bipolar Disorder from Controls with High Accuracy Using EEG Data

Background: Bipolar disorder (BD) is a mental disorder characterized by depressive and manic or hypomanic episodes. The complexity in the diagnosis of Bipolar disorder (BD) due to its overlapping symptoms with other mood disorders prompted researchers and clinicians to seek new and advanced techniques for the precise detection of Bipolar disorder (BD). One of these methods is the use of advanced machine learning algorithms such as deep learning (DL). However, no study of BD has previously adopted DL techniques using EEG signals. Method: EEG signals of 169 BD patients and 45 controls were cleaned from the artifacts and processed using two different DL methods: a one-dimensional convolutional neural network (1D-CNN) combined with the long-short term memory (LSTM) and a two-dimensional convolutional neural network (2D-CNN). Additionally, Class Activation Maps (CAMs) acquired from the bipolar and control groups were used to obtain distinctive regions to specify a particular class in an image. Results: Group identifications were confirmed with 95.91% overall accuracy through the 2D-CNN method, demonstrating very high sensitivity and lower specificity. Also, the overall accuracy obtained from the 1D-CNN + LSTM method was 93%. We also found that F4, C3, F7, and F8 electrode activities produce predominant features to detect the bipolar group. Conclusion: To our knowledge, this study used EEG-based DL analysis for the first time in BD. Our results suggest that the raw EEG-based DL algorithm can successfully differentiate individuals with BD from controls. Class Activation Map (CAM) analysis suggests that prefrontal changes are predominant in EEG data of patients with BD.

Deep learning models reveal replicable, generalizable, and behaviorally relevant sex differences in human functional brain organization

Sex plays a crucial role in human brain development, aging, and the manifestation of psychiatric and neurological disorders. However, our understanding of sex differences in human functional brain organization and their behavioral consequences has been hindered by inconsistent findings and a lack of replication. Here, we address these challenges using a spatiotemporal deep neural network (stDNN) model to uncover latent functional brain dynamics that distinguish male and female brains. Our stDNN model accurately differentiated male and female brains, demonstrating consistently high cross-validation accuracy (>90%), replicability, and generalizability across multisession data from the same individuals and three independent cohorts (N ~ 1,500 young adults aged 20 to 35). Explainable AI (XAI) analysis revealed that brain features associated with the default mode network, striatum, and limbic network consistently exhibited significant sex differences (effect sizes > 1.5) across sessions and independent cohorts. Furthermore, XAI-derived brain features accurately predicted sex-specific cognitive profiles, a finding that was also independently replicated. Our results demonstrate that sex differences in functional brain dynamics are not only highly replicable and generalizable but also behaviorally relevant, challenging the notion of a continuum in male-female brain organization. Our findings underscore the crucial role of sex as a biological determinant in human brain organization, have significant implications for developing personalized sex-specific biomarkers in psychiatric and neurological disorders, and provide innovative AI-based computational tools for future research.

Interpretable deep learning model for major depressive disorder assessment based on functional near-infrared spectroscopy

BACKGROUND

Major depressive disorder (MDD) affects a substantial number of individuals worldwide. New approaches are required to improve the diagnosis of MDD, which relies heavily on subjective reports of depression-related symptoms.

AIM

Establish an objective measurement and evaluation of MDD.

METHODS

Functional near-infrared spectroscopy (fNIRS) was used to investigate the brain activity of MDD patients and healthy controls (HCs). Leveraging a sizeable fNIRS dataset of 263 HCs and 251 patients with MDD, including mild to moderate MDD (mMDD; n = 139) and severe MDD (sMDD; n = 77), we developed an interpretable deep learning model for screening MDD and staging its severity.

RESULTS

The proposed deep learning model achieved an accuracy of 80.9% in diagnostic classification and 78.6% in severity staging for MDD. We discerned five channels with the most significant contribution to MDD identification through Shapley additive explanations (SHAP), located in the right medial prefrontal cortex, right dorsolateral prefrontal cortex, right superior temporal gyrus, and left posterior superior frontal cortex. The findings corresponded closely to the features of haemoglobin responses between HCs and individuals with MDD, as we obtained a good discriminative ability for MDD using cortical channels that are related to the disorder, namely the frontal and temporal cortical channels with areas under the curve of 0.78 and 0.81, respectively.

CONCLUSION

Our study demonstrated the potential of integrating the fNIRS system with artificial intelligence algorithms to classify and stage MDD in clinical settings using a large dataset. This approach can potentially enhance MDD assessment and provide insights for clinical diagnosis and intervention.

Transdiagnostic subgroups of cognitive impairment in early affective and psychotic illness

Cognitively impaired and spared patient subgroups were identified in psychosis and depression, and in clinical high-risk for psychosis (CHR). Studies suggest differences in underlying brain structural and functional characteristics. It is unclear whether cognitive subgroups are transdiagnostic phenomena in early stages of psychotic and affective disorder which can be validated on the neural level. Patients with recent-onset psychosis (ROP; N = 140; female = 54), recent-onset depression (ROD; N = 130; female = 73), CHR (N = 128; female = 61) and healthy controls (HC; N = 270; female = 165) were recruited through the multi-site study PRONIA. The transdiagnostic sample and individual study groups were clustered into subgroups based on their performance in eight cognitive domains and characterized by gray matter volume (sMRI) and resting-state functional connectivity (rsFC) using support vector machine (SVM) classification. We identified an impaired subgroup (NROP = 79, NROD = 30, NCHR = 37) showing cognitive impairment in executive functioning, working memory, processing speed and verbal learning (all p < 0.001). A spared subgroup (NROP = 61, NROD = 100, NCHR = 91) performed comparable to HC. Single-disease subgroups indicated that cognitive impairment is stronger pronounced in impaired ROP compared to impaired ROD and CHR. Subgroups in ROP and ROD showed specific symptom- and functioning-patterns. rsFC showed superior accuracy compared to sMRI in differentiating transdiagnostic subgroups from HC (BACimpaired = 58.5%; BACspared = 61.7%, both: p < 0.01). Cognitive findings were validated in the PRONIA replication sample (N = 409). Individual cognitive subgroups in ROP, ROD and CHR are more informative than transdiagnostic subgroups as they map onto individual cognitive impairment and specific functioning- and symptom-patterns which show limited overlap in sMRI and rsFC. CLINICAL TRIAL REGISTRY NAME: German Clinical Trials Register (DRKS). Clinical trial registry URL: https://www.drks.de/drks_web/ . Clinical trial registry number: DRKS00005042.

Automated analysis of speech as a marker of sub-clinical psychotic experiences

Automated speech analysis techniques, when combined with artificial intelligence and machine learning, show potential in capturing and predicting a wide range of psychosis symptoms, garnering attention from researchers. These techniques hold promise in predicting the transition to clinical psychosis from at-risk states, as well as relapse or treatment response in individuals with clinical-level psychosis. However, challenges in scientific validation hinder the translation of these techniques into practical applications. Although sub-clinical research could aid to tackle most of these challenges, there have been only few studies conducted in speech and psychosis research in non-clinical populations. This work aims to facilitate this work by summarizing automated speech analytical concepts and the intersection of this field with psychosis research. We review psychosis continuum and sub-clinical psychotic experiences, and the benefits of researching them. Then, we discuss the connection between speech and psychotic symptoms. Thirdly, we overview current and state-of-the art approaches to the automated analysis of speech both in terms of language use (text-based analysis) and vocal features (audio-based analysis). Then, we review techniques applied in subclinical population and findings in these samples. Finally, we discuss research challenges in the field, recommend future research endeavors and outline how research in subclinical populations can tackle the listed challenges.

Artificial intelligence in mental healthcare: an overview and future perspectives

Artificial intelligence is disrupting the field of mental healthcare through applications in computational psychiatry, which leverages quantitative techniques to inform our understanding, detection, and treatment of mental illnesses. This paper provides an overview of artificial intelligence technologies in modern mental healthcare and surveys recent advances made by researchers, focusing on the nascent field of digital psychiatry. We also consider the ethical implications of artificial intelligence playing a greater role in mental healthcare.

Performance of advanced machine learning algorithms overlogistic regression in predicting hospital readmissions: A meta-analysis

Objectives

Machine learning algorithms are being increasingly used for predicting hospital readmissions. This meta-analysis evaluated the performance of logistic regression (LR) and machine learning (ML) models for the prediction of 30-day hospital readmission among patients in the US.

Methods

Electronic databases (i.e., Medline, PubMed, and Embase) were searched from January 2015 to December 2019. Only studies in the English language were included. Two reviewers performed studies screening, quality appraisal, and data collection. The quality of the studies was assessed using the Quality in Prognosis Studies (QUIPS) tool. Model performance was evaluated using the Area Under the Curve (AUC). A random-effects meta-analysis was performed using STATA 16.

Results

Nine studies were included based on the selection criteria. The most common ML techniques were tree-based methods such as boosting and random forest. Most of the studies had a low risk of bias (8/9). The AUC was greater with ML to predict 30-day all-cause hospital readmission compared with LR [Mean Difference (MD): 0.03; 95% Confidence Interval (CI) 0.01-0.05]. Subgroup analyses found that deep-learning methods had a better performance compared with LR (MD 0.06; 95% CI, 0.04-0.09), followed by neural networks (MD: 0.03; 95% CI, 0.03-0.03), while the AUCs of the tree-based (MD: 0.02; 95% CI -0.00-0.04) and kernel-based (MD: 0.02; 95% CI 0.02 (-0.13-0.16) methods were no different compared to LR. More than half of the studies evaluated heart failure-related rehospitalization (N = 5). For the readmission prediction among heart failure patients, ML performed better compared with LR, with a mean difference in AUC of 0.04 (95% CI, 0.01-0.07). The leave-one-out sensitivity analysis confirmed the robustness of the findings.

Conclusion

Multiple ML methods were used to predict 30-day all-cause hospital readmission. Performance varied across the ML methods, with deep-learning methods showing the best performance over the LR.

A novel breast cancer detection architecture based on a CNN-CBR system for mammogram classification

This paper presents a novel framework for breast cancer detection using mammogram images. The proposed solution aims to output an explainable classification from a mammogram image. The classification approach uses a Case-Based Reasoning system (CBR). CBR accuracy strongly depends on the quality of the extracted features. To achieve relevant classification, we propose a pipeline that includes image enhancement and data augmentation to improve the quality of extracted features and provide a final diagnosis. An efficient segmentation method based on a U-Net architecture is used to extract Regions of interest (RoI) from mammograms. The purpose is to combine deep learning (DL) with CBR to improve classification accuracy. DL provides accurate mammogram segmentation, while CBR gives an explainable and accurate classification. The proposed approach was tested on the CBIS-DDSM dataset and achieved high performance with an accuracy (Acc) of 86.71 % and a recall of 91.34 %, outperforming some well-known machine learning (ML) and DL approaches.

Automatic brain MRI motion artifact detection based on end-to-end deep learning is similarly effective as traditional machine learning trained on image quality metrics

Head motion artifacts in magnetic resonance imaging (MRI) are an important confounding factor concerning brain research as well as clinical practice. For this reason, several machine learning-based methods have been developed for the automatic quality control of structural MRI scans. Deep learning offers a promising solution to this problem, however, given its data-hungry nature and the scarcity of expert-annotated datasets, its advantage over traditional machine learning methods in identifying motion-corrupted brain scans is yet to be determined. In the present study, we investigated the relative advantage of the two methods in structural MRI quality control. To this end, we collected publicly available T1-weighted images and scanned subjects in our own lab under conventional and active head motion conditions. The quality of the images was rated by a team of radiologists from the point of view of clinical diagnostic use. We present a relatively simple, lightweight 3D convolutional neural network trained in an end-to-end manner that achieved a test set (N = 411) balanced accuracy of 94.41% in classifying brain scans into clinically usable or unusable categories. A support vector machine trained on image quality metrics achieved a balanced accuracy of 88.44% on the same test set. Statistical comparison of the two models yielded no significant difference in terms of confusion matrices, error rates, or receiver operating characteristic curves. Our results suggest that these machine learning methods are similarly effective in identifying severe motion artifacts in brain MRI scans, and underline the efficacy of end-to-end deep learning-based systems in brain MRI quality control, allowing the rapid evaluation of diagnostic utility without the need for elaborate image pre-processing.

Building Predictive Models for Schizophrenia Diagnosis with Peripheral Inflammatory Biomarkers

Machine learning and artificial intelligence technologies are known to be a convenient tool for analyzing multi-domain data in precision psychiatry. In the case of schizophrenia, the most commonly used data sources for such purposes are neuroimaging, voice and language patterns, and mobile phone data. Data on peripheral markers can also be useful for building predictive models. Here, we have developed five predictive models for the binary classification of schizophrenia patients and healthy individuals. Data on serum concentrations of cytokines, chemokines, growth factors, and age were among 38 parameters used to build these models. The sample consisted of 217 schizophrenia patients and 90 healthy individuals. The models architecture was involved logistic regression, deep neural networks, decision trees, support vector machine, and k-nearest neighbors algorithms. It was shown that the algorithm based on a deep neural network (consisting of five layers) showed a slightly higher sensitivity (0.87 ± 0.04) and specificity (0.52 ± 0.06) than other algorithms. Combining all variables into a single classifier showed a cumulative effect that exceeded the effectiveness of individual variables, indicating the need to use multiple biomarkers to diagnose schizophrenia. Thus, the data obtained showed the promise of using data on peripheral biomarkers and machine learning methods for diagnosing schizophrenia.

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.

Automatic depression severity assessment with deep learning using parameter-efficient tuning

Introduction

To assist mental health care providers with the assessment of depression, research to develop a standardized, accessible, and non-invasive technique has garnered considerable attention. Our study focuses on the application of deep learning models for automatic assessment of depression severity based on clinical interview transcriptions. Despite the recent success of deep learning, the lack of large-scale high-quality datasets is a major performance bottleneck for many mental health applications.

Methods

A novel approach is proposed to address the data scarcity problem for depression assessment. It leverages both pretrained large language models and parameter-efficient tuning techniques. The approach is built upon adapting a small set of tunable parameters, known as prefix vectors, to guide a pretrained model towards predicting the Patient Health Questionnaire (PHQ)-8 score of a person. Experiments were conducted on the Distress Analysis Interview Corpus - Wizard of Oz (DAIC-WOZ) benchmark dataset with 189 subjects, partitioned into training, development, and test sets. Model learning was done on the training set. Prediction performance mean and standard deviation of each model, with five randomly-initialized runs, were reported on the development set. Finally, optimized models were evaluated on the test set.

Results

The proposed model with prefix vectors outperformed all previously published methods, including models which utilized multiple types of data modalities, and achieved the best reported performance on the test set of DAIC-WOZ with a root mean square error of 4.67 and a mean absolute error of 3.80 on the PHQ-8 scale. Compared to conventionally fine-tuned baseline models, prefix-enhanced models were less prone to overfitting by using far fewer training parameters (<6% relatively).

Discussion

While transfer learning through pretrained large language models can provide a good starting point for downstream learning, prefix vectors can further adapt the pretrained models effectively to the depression assessment task by only adjusting a small number of parameters. The improvement is in part due to the fine-grain flexibility of prefix vector size in adjusting the model's learning capacity. Our results provide evidence that prefix-tuning can be a useful approach in developing tools for automatic depression assessment.

Systematic review of machine learning utilization within outpatient psychodynamic psychotherapy research

Introduction

Although outpatient psychodynamic psychotherapy is effective, there has been no improvement in treatment success in recent years. One way to improve psychodynamic treatment could be the use of machine learning to design treatments tailored to the individual patient's needs. In the context of psychotherapy, machine learning refers mainly to various statistical methods, which aim to predict outcomes (e.g., drop-out) of future patients as accurately as possible. We therefore searched various literature for all studies using machine learning in outpatient psychodynamic psychotherapy research to identify current trends and objectives.

Methods

For this systematic review, we applied the Preferred Reporting Items for systematic Reviews and Meta-Analyses Guidelines.

Results

In total, we found four studies that used machine learning in outpatient psychodynamic psychotherapy research. Three of these studies were published between 2019 and 2021.

Discussion

We conclude that machine learning has only recently made its way into outpatient psychodynamic psychotherapy research and researchers might not yet be aware of its possible uses. Therefore, we have listed a variety of perspectives on how machine learning could be used to increase treatment success of psychodynamic psychotherapies. In doing so, we hope to give new impetus to outpatient psychodynamic psychotherapy research on how to use machine learning to address previously unsolved problems.

Artificial intelligence ecosystem for computational psychiatry: Ideas to practice

Computational psychiatry is an emerging field that not only explores the biological basis of mental illness but also considers the diagnoses and identifies the underlying mechanisms. One of the key strengths of computational psychiatry is that it may identify patterns in large datasets that are not easily identifiable. This may help researchers develop more effective treatments and interventions for mental health problems. This paper is a narrative review that reviews the literature and produces an artificial intelligence ecosystem for computational psychiatry. The artificial intelligence ecosystem for computational psychiatry includes data acquisition, preparation, modeling, application, and evaluation. This approach allows researchers to integrate data from a variety of sources, such as brain imaging, genetics, and behavioral experiments, to obtain a more complete understanding of mental health conditions. Through the process of data preprocessing, training, and testing, the data that are required for model building can be prepared. By using machine learning, neural networks, artificial intelligence, and other methods, researchers have been able to develop diagnostic tools that can accurately identify mental health conditions based on a patient’s symptoms and other factors. Despite the continuous development and breakthrough of computational psychiatry, it has not yet influenced routine clinical practice and still faces many challenges, such as data availability and quality, biological risks, equity, and data protection. As we move progress in this field, it is vital to ensure that computational psychiatry remains accessible and inclusive so that all researchers may contribute to this significant and exciting field.

Multimodal predictions of treatment outcome in major depression: A comparison of data-driven predictors with importance ratings by clinicians

BACKGROUND

Reliable prediction models of treatment outcome in Major Depressive Disorder (MDD) are currently lacking in clinical practice. Data-driven outcome definitions, combining data from multiple modalities and incorporating clinician expertise might improve predictions.

METHODS

We used unsupervised machine learning to identify treatment outcome classes in 1060 MDD inpatients. Subsequently, classification models were created on clinical and biological baseline information to predict treatment outcome classes and compared to the performance of two widely used classical outcome definitions. We also related the findings to results from an online survey that assessed which information clinicians use for outcome prognosis.

RESULTS

Three and four outcome classes were identified by unsupervised learning. However, data-driven outcome classes did not result in more accurate prediction models. The best prediction model was targeting treatment response in its standard definition and reached accuracies of 63.9 % in the test sample, and 59.5 % and 56.9 % in the validation samples. Top predictors included sociodemographic and clinical characteristics, while biological parameters did not improve prediction accuracies. Treatment history, personality factors, prior course of the disorder, and patient attitude towards treatment were ranked as most important indicators by clinicians.

LIMITATIONS

Missing data limited the power to identify biological predictors of treatment outcome from certain modalities.

CONCLUSIONS

So far, the inclusion of available biological measures in addition to psychometric and clinical information did not improve predictive value of the models, which was overall low. Optimized biomarkers, stratified predictions and the inclusion of clinical expertise may improve future prediction models.

Applications of artificial intelligence-machine learning for detection of stress: a critical overview

Psychological distress is a major contributor to human physiology and pathophysiology, and it has been linked to several conditions, such as auto-immune diseases, metabolic syndrome, sleep disorders, and suicidal thoughts and inclination. Therefore, early detection and management of chronic stress is crucial for the prevention of several diseases. Artificial intelligence (AI) and Machine Learning (ML) have promoted a paradigm shift in several areas of biomedicine including diagnosis, monitoring, and prognosis of disease. Here, our review aims to present some of the AI and ML applications for solving biomedical issues related to psychological stress. We provide several lines of evidence from previous studies highlighting that AI and ML have been able to predict stress and detect the brain normal states vs. abnormal states (notably, in post-traumatic stress disorder (PTSD)) with accuracy around 90%. Of note, AI/ML-driven technology applied to identify ubiquitously present stress exposure may not reach its full potential, unless future analytics focus on detecting prolonged distress through such technology instead of merely assessing stress exposure. Moving forward, we propose that a new subcategory of AI methods called Swarm Intelligence (SI) can be used towards detecting stress and PTSD. SI involves ensemble learning techniques to efficiently solve a complex problem, such as stress detection, and it offers particular strength in clinical settings, such as privacy preservation. We posit that AI and ML approaches will be beneficial for the medical and patient community when applied to predict and assess stress levels. Last, we encourage additional research to bring AI and ML into the standard clinical practice for diagnostics in the not-too-distant future.

Qureshi A, Li J, Mahmood T. On the Analyses of Medical Images Using Traditional Machine Learning Techniques and Convolutional Neural Networks

Convolutional neural network (CNN) has shown dissuasive accomplishment on different areas especially Object Detection, Segmentation, Reconstruction (2D and 3D), Information Retrieval, Medical Image Registration, Multi-lingual translation, Local language Processing, Anomaly Detection on video and Speech Recognition. CNN is a special type of Neural Network, which has compelling and effective learning ability to learn features at several steps during augmentation of the data. Recently, different interesting and inspiring ideas of Deep Learning (DL) such as different activation functions, hyperparameter optimization, regularization, momentum and loss functions has improved the performance, operation and execution of CNN Different internal architecture innovation of CNN and different representational style of CNN has significantly improved the performance. This survey focuses on internal taxonomy of deep learning, different models of vonvolutional neural network, especially depth and width of models and in addition CNN components, applications and current challenges of deep learning.

Cytokine level in patients with mood disorder, alcohol use disorder and their comorbidity

OBJECTIVES

Because alcohol use disorder (AUD) is often accompanied by mood disorder (MD) and both alcoholism and depression result in activation of the immune system, this study compares serum cytokine levels in the presence of co-morbidity with those in either AUD or MD alone.

METHODS

In this naturalistic prospective study the levels of 15 different cytokines were measured in serum samples of patients with MD (n = 43), participants with combined AUD-MD (n = 44) and AUD without MD (n = 42). The levels were compared cross-sectionally among themselves and with those in 50 healthy volunteers.

RESULTS

Pro-inflammatory IFN-2α levels were consistently significantly higher and anti-inflammatory IL-1RA significantly lower in all study groups in comparison to healthy volunteers. In the MD only group we found increased IL-6 (p = 0.001), IL-7 (p = 0.001) and IL-13 (p = 0.006) levels, and decreased TNFα (p = 0.0001), IL-1RA (p = 0.012), IL-10 (p = 0.002) compared with group MD + AUD. Patients with AUD only showed elevated levels of IL-1β (p = 0.046), IL-2 (p = 0.004), IL-7 (p = 0.0001), IL-4 (p = 0.049) and IL-13 (p = 0.015) in contrast with MD + AUD group.

CONCLUSIONS

Because the interactions of alcohol with peripheral and cerebral immune systems are multifaceted, the pertinent connection to the mechanism how alcohol consumption contributes to the development of mood disorders cannot be properly explored.

Investigating White Matter Abnormalities Associated with Schizophrenia Using Deep Learning Model and Voxel-Based Morphometry

Schizophrenia (SCZ) is a devastating mental condition with significant negative consequences for patients, making correct and prompt diagnosis crucial. The purpose of this study is to use structural magnetic resonance image (MRI) to better classify individuals with SCZ from control normals (CN) and to locate a region of the brain that represents abnormalities associated with SCZ. Deep learning (DL), which is based on the nervous system, could be a very useful tool for doctors to accurately predict, diagnose, and treat SCZ. Gray Matter (GM), Cerebrospinal Fluid (CSF), and White Matter (WM) brain regions are extracted from 99 MRI images obtained from the open-source OpenNeuro database to demonstrate SCZ's regional relationship. In this paper, we use a pretrained ResNet-50 deep network to extract features from MRI images and an ensemble deep random vector functional link (edRVFL) network to classify those features. By examining the results obtained, the edRVFL deep model provides the highest classification accuracy of 96.5% with WM and is identified as the best-performing algorithm compared to the traditional algorithms. Furthermore, we examined the GM, WM, and CSF tissue volumes in CN subjects and SCZ patients using voxel-based morphometry (VBM), and the results show 1363 significant voxels, 6.90 T-value, and 6.21 Z-value in the WM region of SCZ patients. In SCZ patients, WM is most closely linked to structural alterations, as evidenced by VBM analysis and the DL model.

Predicting treatment outcome in depression: an introduction into current concepts and challenges

Improving response and remission rates in major depressive disorder (MDD) remains an important challenge. Matching patients to the treatment they will most likely respond to should be the ultimate goal. Even though numerous studies have investigated patient-specific indicators of treatment efficacy, no (bio)markers or empirical tests for use in clinical practice have resulted as of now. Therefore, clinical decisions regarding the treatment of MDD still have to be made on the basis of questionnaire- or interview-based assessments and general guidelines without the support of a (laboratory) test. We conducted a narrative review of current approaches to characterize and predict outcome to pharmacological treatments in MDD. We particularly focused on findings from newer computational studies using machine learning and on the resulting implementation into clinical decision support systems. The main issues seem to rest upon the unavailability of robust predictive variables and the lacking application of empirical findings and predictive models in clinical practice. We outline several challenges that need to be tackled on different stages of the translational process, from current concepts and definitions to generalizable prediction models and their successful implementation into digital support systems. By bridging the addressed gaps in translational psychiatric research, advances in data quantity and new technologies may enable the next steps toward precision psychiatry.

Predicting AT(N) pathologies in Alzheimer's disease from blood-based proteomic data using neural networks

BACKGROUND AND OBJECTIVE

Blood-based biomarkers represent a promising approach to help identify early Alzheimer's disease (AD). Previous research has applied traditional machine learning (ML) to analyze plasma omics data and search for potential biomarkers, but the most modern ML methods based on deep learning has however been scarcely explored. In the current study, we aim to harness the power of state-of-the-art deep learning neural networks (NNs) to identify plasma proteins that predict amyloid, tau, and neurodegeneration (AT[N]) pathologies in AD.

METHODS

We measured 3,635 proteins using SOMAscan in 881 participants from the European Medical Information Framework for AD Multimodal Biomarker Discovery study (EMIF-AD MBD). Participants underwent measurements of brain amyloid β (Aβ) burden, phosphorylated tau (p-tau) burden, and total tau (t-tau) burden to determine their AT(N) statuses. We ranked proteins by their association with Aβ, p-tau, t-tau, and AT(N), and fed the top 100 proteins along with age and apolipoprotein E (APOE) status into NN classifiers as input features to predict these four outcomes relevant to AD. We compared NN performance of using proteins, age, and APOE genotype with performance of using age and APOE status alone to identify protein panels that optimally improved the prediction over these main risk factors. Proteins that improved the prediction for each outcome were aggregated and nominated for pathway enrichment and protein-protein interaction enrichment analysis.

RESULTS

Age and APOE alone predicted Aβ, p-tau, t-tau, and AT(N) burden with area under the curve (AUC) scores of 0.748, 0.662, 0.710, and 0.795. The addition of proteins significantly improved AUCs to 0.782, 0.674, 0.734, and 0.831, respectively. The identified proteins were enriched in five clusters of AD-associated pathways including human immunodeficiency virus 1 infection, p53 signaling pathway, and phosphoinositide-3-kinase-protein kinase B/Akt signaling pathway.

CONCLUSION

Combined with age and APOE genotype, the proteins identified have the potential to serve as blood-based biomarkers for AD and await validation in future studies. While the NNs did not achieve better scores than the support vector machine model used in our previous study, their performances were likely limited by small sample size.

Artificial intelligence-informed mobile mental health apps for young people: a mixed-methods approach on users' and stakeholders' perspectives

BACKGROUND

Novel approaches in mobile mental health (mHealth) apps that make use of Artificial Intelligence (AI), Ecological Momentary Assessments, and Ecological Momentary Interventions have the potential to support young people in the achievement of mental health and wellbeing goals. However, little is known on the perspectives of young people and mental health experts on this rapidly advancing technology. This study aims to investigate the subjective needs, attitudes, and preferences of key stakeholders towards an AI-informed mHealth app, including young people and experts on mHealth promotion and prevention in youth.

METHODS

We used a convergent parallel mixed-method study design. Two semi-structured online focus groups (n = 8) and expert interviews (n = 5) to explore users and stakeholders perspectives were conducted. Furthermore a representative online survey was completed by young people (n = 666) to investigate attitudes, current use and preferences towards apps for mental health promotion and prevention.

RESULTS

Survey results show that more than two-thirds of young people have experience with mHealth apps, and 60% make regular use of 1-2 apps. A minority (17%) reported to feel negative about the application of AI in general, and 19% were negative about the embedding of AI in mHealth apps. This is in line with qualitative findings, where young people displayed rather positive attitudes towards AI and its integration into mHealth apps. Participants reported pragmatic attitudes towards data sharing and safety practices, implying openness to share data if it adds value for users and if the data request is not too intimate, however demanded transparency of data usage and control over personalization. Experts perceived AI-informed mHealth apps as a complementary solution to on-site delivered interventions in future health promotion among young people. Experts emphasized opportunities in regard with low-threshold access through the use of smartphones, and the chance to reach young people in risk situations.

CONCLUSIONS

The findings of this exploratory study highlight the importance of further participatory development of training components prior to implementation of a digital mHealth training in routine practice of mental health promotion and prevention. Our results may help to guide developments based on stakeholders' first recommendations for an AI-informed mHealth app.

Advancing translational research in neuroscience through multi-task learning

Translational research in neuroscience is increasingly focusing on the analysis of multi-modal data, in order to account for the biological complexity of suspected disease mechanisms. Recent advances in machine learning have the potential to substantially advance such translational research through the simultaneous analysis of different data modalities. This review focuses on one of such approaches, the so-called "multi-task learning" (MTL), and describes its potential utility for multi-modal data analyses in neuroscience. We summarize the methodological development of MTL starting from conventional machine learning, and present several scenarios that appear particularly suitable for its application. For these scenarios, we highlight different types of MTL algorithms, discuss emerging technological adaptations, and provide a step-by-step guide for readers to apply the MTL approach in their own studies. With its ability to simultaneously analyze multiple data modalities, MTL may become an important element of the analytics repertoire used in future neuroscience research and beyond.

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.

Automatic recognition of schizophrenia from facial videos using 3D convolutional neural network

Schizophrenia affects patients and their families and society because of chronic impairments in cognition, behavior, and emotion. However, its clinical diagnosis mainly depends on the clinicians' knowledge of the patients' symptoms. Other auxiliary diagnostic methods such as MRI and EEG are cumbersome and time-consuming. Recently, the convolutional neural network (CNN) has been applied to the auxiliary diagnosis of psychiatry. Hence, in this study, a method based on deep learning and facial videos is proposed for the rapid detection of schizophrenia. Herein, 125 videos from 125 schizophrenic patients and 75 videos from 75 healthy controls based on emotional stimulation tasks were obtained. The video preprocessing included the experiment clips extraction, face detection, facial region cropping, resizing to 500 × 500 pixel size, and uniform sampling of 100 frames. The preprocessed facial videos were used to train the Resnet18_3D. We utilized ten-fold cross-validation, and held-out testing set to evaluate the model with the accuracy, the precision, the sensitivity, the specificity, the balanced accuracy, and the AUC. The Resnet18_3D trained on Film_order achieved the best performance with accuracy, sensitivity, specificity, balanced accuracy, and AUC of 89.00%, 96.80%, 76.00%, 86.40% and 0.9397. The neural network model indeed recognizes healthy controls and schizophrenic patients through the changes in the area of the face. The results show that facial video under emotional stimulation can be used to classify schizophrenic patients and help clinicians with diagnosis in the clinical environment. Among the different types of stimuli, the video stimuli with fixed emotional order showed the best classification performance.

Deep learning in neuroimaging data analysis: Applications, challenges, and solutions

Methods for the analysis of neuroimaging data have advanced significantly since the beginning of neuroscience as a scientific discipline. Today, sophisticated statistical procedures allow us to examine complex multivariate patterns, however most of them are still constrained by assuming inherent linearity of neural processes. Here, we discuss a group of machine learning methods, called deep learning, which have drawn much attention in and outside the field of neuroscience in recent years and hold the potential to surpass the mentioned limitations. Firstly, we describe and explain the essential concepts in deep learning: the structure and the computational operations that allow deep models to learn. After that, we move to the most common applications of deep learning in neuroimaging data analysis: prediction of outcome, interpretation of internal representations, generation of synthetic data and segmentation. In the next section we present issues that deep learning poses, which concerns multidimensionality and multimodality of data, overfitting and computational cost, and propose possible solutions. Lastly, we discuss the current reach of DL usage in all the common applications in neuroimaging data analysis, where we consider the promise of multimodality, capability of processing raw data, and advanced visualization strategies. We identify research gaps, such as focusing on a limited number of criterion variables and the lack of a well-defined strategy for choosing architecture and hyperparameters. Furthermore, we talk about the possibility of conducting research with constructs that have been ignored so far or/and moving toward frameworks, such as RDoC, the potential of transfer learning and generation of synthetic data.

Artificial intelligence-assisted psychosis risk screening in adolescents: Practices and challenges

Artificial intelligence-based technologies are gradually being applied to psych-iatric research and practice. This paper reviews the primary literature concerning artificial intelligence-assisted psychosis risk screening in adolescents. In terms of the practice of psychosis risk screening, the application of two artificial intelligence-assisted screening methods, chatbot and large-scale social media data analysis, is summarized in detail. Regarding the challenges of psychiatric risk screening, ethical issues constitute the first challenge of psychiatric risk screening through artificial intelligence, which must comply with the four biomedical ethical principles of respect for autonomy, nonmaleficence, beneficence and impartiality such that the development of artificial intelligence can meet the moral and ethical requirements of human beings. By reviewing the pertinent literature concerning current artificial intelligence-assisted adolescent psychosis risk screens, we propose that assuming they meet ethical requirements, there are three directions worth considering in the future development of artificial intelligence-assisted psychosis risk screening in adolescents as follows: nonperceptual real-time artificial intelligence-assisted screening, further reducing the cost of artificial intelligence-assisted screening, and improving the ease of use of artificial intelligence-assisted screening techniques and tools.

Robust, Generalizable, and Interpretable Artificial Intelligence-Derived Brain Fingerprints of Autism and Social Communication Symptom Severity

BACKGROUND

Autism spectrum disorder (ASD) is among the most pervasive neurodevelopmental disorders, yet the neurobiology of ASD is still poorly understood because inconsistent findings from underpowered individual studies preclude the identification of robust and interpretable neurobiological markers and predictors of clinical symptoms.

METHODS

We leverage multiple brain imaging cohorts and exciting recent advances in explainable artificial intelligence to develop a novel spatiotemporal deep neural network (stDNN) model, which identifies robust and interpretable dynamic brain markers that distinguish ASD from neurotypical control subjects and predict clinical symptom severity.

RESULTS

stDNN achieved consistently high classification accuracies in cross-validation analysis of data from the multisite ABIDE (Autism Brain Imaging Data Exchange) cohort (n = 834). Crucially, stDNN also accurately classified data from independent Stanford (n = 202) and GENDAAR (Gender Exploration of Neurogenetics and Development to Advanced Autism Research) (n = 90) cohorts without additional training. stDNN could not distinguish attention-deficit/hyperactivity disorder from neurotypical control subjects, highlighting the model's specificity. Explainable artificial intelligence revealed that brain features associated with the posterior cingulate cortex and precuneus, dorsolateral and ventrolateral prefrontal cortex, and superior temporal sulcus, which anchor the default mode network, cognitive control, and human voice processing systems, respectively, most clearly distinguished ASD from neurotypical control subjects in the three cohorts. Furthermore, features associated with the posterior cingulate cortex and precuneus nodes of the default mode network emerged as robust predictors of the severity of core social and communication deficits but not restricted/repetitive behaviors in ASD.

CONCLUSIONS

Our findings, replicated across independent cohorts, reveal robust individualized functional brain fingerprints of ASD psychopathology, which could lead to more objective and precise phenotypic characterization and targeted treatments.

A multi-task FP-GNN framework enables accurate prediction of selective PARP inhibitors

PARP (poly ADP-ribose polymerase) family is a crucial DNA repair enzyme that responds to DNA damage, regulates apoptosis, and maintains genome stability; therefore, PARP inhibitors represent a promising therapeutic strategy for the treatment of various human diseases including COVID-19. In this study, a multi-task FP-GNN (Fingerprint and Graph Neural Networks) deep learning framework was proposed to predict the inhibitory activity of molecules against four PARP isoforms (PARP-1, PARP-2, PARP-5A, and PARP-5B). Compared with baseline predictive models based on four conventional machine learning methods such as RF, SVM, XGBoost, and LR as well as six deep learning algorithms such as DNN, Attentive FP, MPNN, GAT, GCN, and D-MPNN, the evaluation results indicate that the multi-task FP-GNN method achieves the best performance with the highest average BA, F1, and AUC values of 0.753 ± 0.033, 0.910 ± 0.045, and 0.888 ± 0.016 for the test set. In addition, Y-scrambling testing successfully verified that the model was not results of chance correlation. More importantly, the interpretability of the multi-task FP-GNN model enabled the identification of key structural fragments associated with the inhibition of each PARP isoform. To facilitate the use of the multi-task FP-GNN model in the field, an online webserver called PARPi-Predict and its local version software were created to predict whether compounds bear potential inhibitory activity against PARPs, thereby contributing to design and discover better selective PARP inhibitors.

University Archives Autonomous Management Control System under the Internet of Things and Deep Learning Professional Certification

The current work aims to meet the needs of the development of archives work in colleges and universities and the modernization of management to realize the standards and standardization of all aspects of archives business construction in colleges and universities, so as to improve the political and professional quality of archives cadres. First, the radio frequency identification (RFID) technology based on the Internet of things (IoT) digitizes the university archive labels. Meanwhile, the filing cabinet's intelligent security system preserves confidential files. Second, the convolutional neural network (CNN) algorithm under deep learning is introduced and college profile information is identified. Finally, the concept of professional certification is used to clarify the purpose of the university archives automation management system. Different activation functions are used to analyze the recognition accuracy loss and recognition accuracy of university archives. The identification error of You Only Look Once (YOLO) of the ReLU-convolutional neural network (R–CNN) of college archives is analyzed. The results show that the selection of rectified linear units (ReLU) activation function for CNN can effectively reduce the loss of identification accuracy of college archives and can improve the accuracy of identification of college archives. The algorithm based on the ReLU activation function has a smaller recognition error accuracy in college archives than that of the YOLO algorithm. The recognition error of the YOLO algorithm is slightly higher than that of the R–CNN. The font recognition error of archival information based on the R–CNN is relatively large. However, the conclusion is reasonable due to the recognition difficulties of handwritten archival fonts. The file positioning recognition error rate is 19.00%, the file printing font recognition error rate is 4.75%, and the image recognition error rate is 1.90%. These results have a certain reference value for the process of identifying information in the automatic management of university archives by CNN under different activation functions.

Neural Network Model for Perceptual Evaluation of Product Modelling Design Based on Multimodal Image Recognition

With the homogenization of product function and performance, the design technology for product appearance quality has been increasingly valued by academia and industry and has become an effective technical way to meet the continuously growing diversified and personalized needs of consumers. The appearance quality attribute of a product can be characterized or described by its appearance image. Data-driven product appearance image design is based on the quantitative data of product appearance and consumer emotional needs and completes the product appearance through computer-aided design technology and intelligent algorithms. Design innovation can help companies quickly respond to consumers' emotional needs and effectively improve design quality and product competitiveness. When visual objects are disturbed in complex scenes, the issues such as how the human brain coordinates multisensory information processing and what neural processing mechanisms follow are still unclear. In this paper, a visual object recognition experiment in a complex scene was designed and the brain activation signals of three modalities of noise, added audio-visual (AVd), single visual noise and noise (Vd), and single-audio (A), were recorded. The properties and neural processing mechanisms of multisensory modulation of auditory stimuli during noisy image recognition were explored. Using the conjunction method combined with the classic "max criterion" rule, it was found that only when a certain amount of noise was added to the visual stimulus, the integration area changed. The product appearance has a decisive influence on the user's product perceptual attribute preference and greatly affects the consumer's satisfaction. The importance of product appearance image design is increasingly prominent. In addition, pattern analysis of brain activation signals confirmed that semantically consistent sounds can facilitate the recognition of noisy images and this facilitation shows a certain category selectivity when subdivided into categories. Using the analysis method of functional connectivity, a functional connectivity network containing nodes at different integration levels was constructed to explore the overall characteristics and processing patterns of the multisensory network. Through the analysis of the network connection relationship, it is found that the prefrontal cortex, STS, and lateral occipital lobe are the nodes with more aggregation in the network, and their functions are similar to the hub in the network. The brain functional network was constructed, and functional connectivity was used to explore the connection characteristics of the network and the multisensory modulation mechanism between different processing levels of the brain.

Neural Networks for Early Diagnosis of Postpartum PTSD in Women after Cesarean Section

The correlation between the kind of cesarean section and post-traumatic stress disorder (PTSD) in Greek women after a traumatic birth experience has been recognized in previous studies along with other risk factors, such as perinatal conditions and traumatic life events. Data from early studies have suggested some possible links between some vulnerable factors and the potential development of postpartum PTSD. The classification of each case in three possible states (PTSD, profile PTSD, and free of symptoms) is typically performed using the guidelines and the metrics of the version V of the Diagnostic and Statistical Manual of Mental Disorders (DSM-V) which requires the completion of several questionnaires during the postpartum period. The motivation in the present work is the need for a model that can detect possible PTSD cases using a minimum amount of information and produce an early diagnosis. The early PTSD diagnosis is critical since it allows the medical personnel to take the proper measures as soon as possible. Our sample consists of 469 women who underwent emergent or elective cesarean delivery in a university hospital in Greece. The methodology which is followed is the application of random decision forests (RDF) to detect the most suitable and easily accessible information which is then used by an artificial neural network (ANN) for the classification. As is demonstrated from the results, the derived decision model can reach high levels of accuracy even when only partial and quickly available information is provided.

Creating sparser prediction models of treatment outcome in depression: a proof-of-concept study using simultaneous feature selection and hyperparameter tuning

Background

Predicting treatment outcome in major depressive disorder (MDD) remains an essential challenge for precision psychiatry. Clinical prediction models (CPMs) based on supervised machine learning have been a promising approach for this endeavor. However, only few CPMs have focused on model sparsity even though sparser models might facilitate the translation into clinical practice and lower the expenses of their application.

Methods

In this study, we developed a predictive modeling pipeline that combines hyperparameter tuning and recursive feature elimination in a nested cross-validation framework. We applied this pipeline to a real-world clinical data set on MDD treatment response and to a second simulated data set using three different classification algorithms. Performance was evaluated by permutation testing and comparison to a reference pipeline without nested feature selection.

Results

Across all models, the proposed pipeline led to sparser CPMs compared to the reference pipeline. Except for one comparison, the proposed pipeline resulted in equally or more accurate predictions. For MDD treatment response, balanced accuracy scores ranged between 61 and 71% when models were applied to hold-out validation data.

Conclusions

The resulting models might be particularly interesting for clinical applications as they could reduce expenses for clinical institutions and stress for patients.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12911-022-01926-2.

Towards a neural network hypothesis for functional cognitive disorders: an extension of the Overfitted Brain Hypothesis

Introduction: Whilst the empirical understanding of functional cognitive disorders (FCD) has advanced in recent years, theoretical and conceptual models have evolved more slowly. Existing frameworks for FCD are based on models of other functional neurological disorders or of metacognitive processes and are recognised to lack mechanistic precision.Methods: In this article, a novel application to FCD of Hoel's Overfitted Brain Hypothesis of the evolved function of dreaming is attempted.Results: This posits that the empirically observed sleep disturbance in FCD entails impaired dreaming which causes the brain to be overfitted and hence unable to generalise appropriately, producing mismatch between memory expectations and memory performance.Conclusions: This formulation of FCD is based on considerations derived from the study of neural networks and shares commonalities with Bayesian models of functional neurological disorders. Additionally, it has implications for future hypothesis-driven research in FCD and suggests a pragmatic basis for management strategies.

Mapping relationships among schizophrenia, bipolar and schizoaffective disorders: A deep classification and clustering framework using fMRI time series

BACKGROUND

Psychiatric disorders are categorized using self-report and observational information rather than biological data. There is also considerable symptomatic overlap between different types of psychiatric disorders, which makes diagnostic categorization and multi-class classification challenging.

METHODS

In this work, we propose a unified framework for supervised classification and unsupervised clustering of psychotic disorders using brain imaging data. A new multi-scale recurrent neural network (MsRNN) model was developed and applied to fMRI time courses (TCs) for multi-class classification. The high-level representations of the original TCs were then submitted to a tSNE clustering model for visualizing the group differences between disorders. A leave-one-feature-out approach was used for disorder-related biomarker identification.

RESULTS

When studying fMRI from schizophrenia, psychotic bipolar disorder, schizoaffective disorder, and healthy individuals, the accuracy of a 4-class classification reached 46%, significantly above chance. The hippocampus, supplementary motor area and paracentral lobule were discovered as the most contributing regional TCs in the multi-class classification. Beyond this, visualization of the tSNE clustering suggested that the disease severity can be captured and schizoaffective disorder (SAD) may be separated into two subtypes. SAD cluster1 has significantly higher Positive And Negative Syndrome Scale (PANSS) scores than SAD cluster2 in PANSS negative2 (emotional withdrawal), general2 (anxiety), general3 (guilt feelings), general4 (tension).

CONCLUSIONS

The proposed deep classification and clustering framework is not only able to identify psychiatric disorders with high accuracy, but also interpret the correlation between brain networks and specific psychiatric disorders, and reveal the relationship between them. This work provides a promising way to investigate a spectrum of similar disorders using neuroimaging-based measures.

A Quantitative Model of International Trade Based on Deep Neural Network

This paper is an in-depth study of international trade quantification models based on deep neural networks. Based on an in-depth analysis of global trade characteristics, a summary of existing problems, and a comparative analysis of various prediction methods, this paper constructs the ARIMA model, BP neural network (BPNN) model, and deep neural network (DNN) model to make a comprehensive comparison of international trade quantification. The results show that the nonlinear model has a global trade quantification has some advantages over linear models, and the deep model shows better prediction performance than the shallow model. In addition, preprocessing of the time series is considered to improve the prediction accuracy or shorten the model training time. The empirical modal analysis method (EMD) is introduced to decompose the time series into eigenmodal functions (IMFs) of different scales. Then the decomposed IMF series are arranged into a matrix using principal component analysis (PCA) to reduce the dimensionality and extract the data containing the most stock index information features; these features are then input into BPNN and DNN for combined prediction, thus constructing the combined models EMD-PCA-BPNN and EMD-PCA-DNN. Based on Melitz's heterogeneous firm trade theory and its development by Chaney, a quantitative trade model incorporating production heterogeneity is constructed through a multisector extension. This paper adopts a general equilibrium analysis, which makes the modeling process pulse clear. The completed model has high flexibility and scalability, which can be applied to quantitative analysis of various problems.

The potential of precision psychiatry: what is in reach?

Progress in developing personalised care for mental disorders is supported by numerous proof-of-concept machine learning studies in the area of risk assessment, diagnostics and precision prescribing. Most of these studies primarily use clinical data, but models might benefit from additional neuroimaging, blood and genetic data to improve accuracy. Combined, multimodal models might offer potential for stratification of patients for treatment. Clinical implementation of machine learning is impeded by a lack of wider generalisability, with efforts primarily focused on psychosis and dementia. Studies across all diagnostic groups should work to test the robustness of machine learning models, which is an essential first step to clinical implementation, and then move to prospective clinical validation. Models need to exceed clinicians' heuristics to be useful, and safe, in routine decision-making. Engagement of clinicians, researchers and patients in digitalisation and 'big data' approaches are vital to allow the generation and accessibility of large, longitudinal, prospective data needed for precision psychiatry to be applied into real-world psychiatric care.

MRI-Based Classification of Neuropsychiatric Systemic Lupus Erythematosus Patients With Self-Supervised Contrastive Learning

Introduction/Purpose

Systemic lupus erythematosus (SLE) is a chronic auto-immune disease with a broad spectrum of clinical presentations, including heterogeneous neuropsychiatric (NP) syndromes. Structural brain abnormalities are commonly found in SLE and NPSLE, but their role in diagnosis is limited, and their usefulness in distinguishing between NPSLE patients and patients in which the NP symptoms are not primarily attributed to SLE (non-NPSLE) is non-existent. Self-supervised contrastive learning algorithms proved to be useful in classification tasks in rare diseases with limited number of datasets. Our aim was to apply self-supervised contrastive learning on T1-weighted images acquired from a well-defined cohort of SLE patients, aiming to distinguish between NPSLE and non-NPSLE patients.

Subjects and Methods

We used 3T MRI T1-weighted images of 163 patients. The training set comprised 68 non-NPSLE and 34 NPSLE patients. We applied random geometric transformations between iterations to augment our data sets. The ML pipeline consisted of convolutional base encoder and linear projector. To test the classification task, the projector was removed and one linear layer was measured. Validation of the method consisted of 6 repeated random sub-samplings, each using a random selection of a small group of patients of both subtypes.

Results

In the 6 trials, between 79% and 83% of the patients were correctly classified as NPSLE or non-NPSLE. For a qualitative evaluation of spatial distribution of the common features found in both groups, Gradient-weighted Class Activation Maps (Grad-CAM) were examined. Thresholded Grad-CAM maps show areas of common features identified for the NPSLE cohort, while no such communality was found for the non-NPSLE group.

Discussion/Conclusion

The self-supervised contrastive learning model was effective in capturing common brain MRI features from a limited but well-defined cohort of SLE patients with NP symptoms. The interpretation of the Grad-CAM results is not straightforward, but indicates involvement of the lateral and third ventricles, periventricular white matter and basal cisterns. We believe that the common features found in the NPSLE population in this study indicate a combination of tissue loss, local atrophy and to some extent that of periventricular white matter lesions, which are commonly found in NPSLE patients and appear hypointense on T1-weighted images.

Deep learning identifies robust gender differences in functional brain organization and their dissociable links to clinical symptoms in autism

BACKGROUND

Autism spectrum disorder (ASD) is a highly heterogeneous disorder that affects nearly 1 in 189 females and 1 in 42 males. However, the neurobiological basis of gender differences in ASD is poorly understood, as most studies have neglected females and used methods ill-suited to capture such differences.

AIMS

To identify robust functional brain organisation markers that distinguish between females and males with ASD and predict symptom severity.

METHOD

We leveraged multiple neuroimaging cohorts (ASD n = 773) and developed a novel spatiotemporal deep neural network (stDNN), which uses spatiotemporal convolution on functional magnetic resonance imaging data to distinguish between groups.

RESULTS

stDNN achieved consistently high classification accuracy in distinguishing between females and males with ASD. Notably, stDNN trained to distinguish between females and males with ASD could not distinguish between neurotypical females and males, suggesting that there are gender differences in the functional brain organisation in ASD that differ from normative gender differences. Brain features associated with motor, language and visuospatial attentional systems reliably distinguished between females and males with ASD. Crucially, these results were observed in a large multisite cohort and replicated in a fully independent cohort. Furthermore, brain features associated with the motor network's primary motor cortex node predicted the severity of restricted/repetitive behaviours in females but not in males with ASD.

CONCLUSIONS

Our replicable findings reveal that the brains of females and males with ASD are functionally organised differently, contributing to their clinical symptoms in distinct ways. They inform the development of gender-specific diagnoses and treatment strategies for ASD, and ultimately advance precision psychiatry.

Artificial Intelligence: Review of Current and Future Applications in Medicine

Background

The role of artificial intelligence (AI) in health care is expanding rapidly. Currently, there are at least 29 US Food and Drug Administration-approved AI health care devices that apply to numerous medical specialties and many more are in development.

Observations

With increasing expectations for all health care sectors to deliver timely, fiscally-responsible, high-quality health care, AI has potential utility in numerous areas, such as image analysis, improved workflow and efficiency, public health, and epidemiology, to aid in processing large volumes of patient and medical data. In this review, we describe basic terminology, principles, and general AI applications relating to health care. We then discuss current and future applications for a variety of medical specialties. Finally, we discuss the future potential of AI along with the potential risks and limitations of current AI technology.

Conclusions

AI can improve diagnostic accuracy, increase patient safety, assist with patient triage, monitor disease progression, and assist with treatment decisions.

Classification of amyotrophic lateral sclerosis by brain volume, connectivity, and network dynamics

Emerging studies corroborate the importance of neuroimaging biomarkers and machine learning to improve diagnostic classification of amyotrophic lateral sclerosis (ALS). While most studies focus on structural data, recent studies assessing functional connectivity between brain regions by linear methods highlight the role of brain function. These studies have yet to be combined with brain structure and nonlinear functional features. We investigate the role of linear and nonlinear functional brain features, and the benefit of combining brain structure and function for ALS classification. ALS patients (N = 97) and healthy controls (N = 59) underwent structural and functional resting state magnetic resonance imaging. Based on key hubs of resting state networks, we defined three feature sets comprising brain volume, resting state functional connectivity (rsFC), as well as (nonlinear) resting state dynamics assessed via recurrent neural networks. Unimodal and multimodal random forest classifiers were built to classify ALS. Out-of-sample prediction errors were assessed via five-fold cross-validation. Unimodal classifiers achieved a classification accuracy of 56.35-61.66%. Multimodal classifiers outperformed unimodal classifiers achieving accuracies of 62.85-66.82%. Evaluating the ranking of individual features' importance scores across all classifiers revealed that rsFC features were most dominant in classification. While univariate analyses revealed reduced rsFC in ALS patients, functional features more generally indicated deficits in information integration across resting state brain networks in ALS. The present work undermines that combining brain structure and function provides an additional benefit to diagnostic classification, as indicated by multimodal classifiers, while emphasizing the importance of capturing both linear and nonlinear functional brain properties to identify discriminative biomarkers of ALS.