Deep learning for small and big data in psychiatry

Review of machine learning solutions for eating disorders

BACKGROUND

Eating Disorders (EDs) are one of the most complex psychiatric disorders, with significant impairment of psychological and physical health, and psychosocial functioning, and are associated with low rates of early detection, low recovery and high relapse rates. This underscores the need for better diagnostic and treatment methods.

OBJECTIVE

This narrative review explores current Machine Learning (ML) and Artificial Intelligence (AI) applications in the domain of EDs, with a specific emphasis on clinical management in treatment settings. The primary objective are to (i) decrease the knowledge gap between ED researchers and AI-practitioners, by presenting the current state-of-the-art AI applications (including models for causality) in different ED use-cases; (ii) identify limitations of these existing AI interventions and how to address them.

RESULTS

AI/ML methods have been applied in different ED use-cases, including ED risk factor identification and incidence prediction (including the analysis of social media content in the general population), diagnosis, monitoring patients and treatment response and prognosis in clinical populations. A comparative analysis of AI-techniques deployed in these use-cases have been performed, considering factors such as complexity, flexibility, functionality, explainability and adaptability to healthcare constraints.

CONCLUSION

Multiple restrictions have been identified in the existing methods in ML and Causality in terms of achieving actionable healthcare for ED, like lack of good quality and quantity of data for models to train on, while requiring models to be flexible, high-performing, yet being explainable and producing counterfactual explanations, for ensuring the fairness and trustworthiness of its decisions. We conclude that to overcome these limitations and for future AI research and application in clinical management of ED, (i) careful considerations are required with regards to AI-model selection, and (ii) joint efforts from ED researcher and patient community are essential in building better quality and quantity of dedicated ED datasets and secure AI-solution framework.

Quantifying brain-functional dynamics using deep dynamical systems: Technical considerations

Both mental health and mental illness unfold in complex and unpredictable ways. Novel artificial intelligence approaches from the area of dynamical systems reconstruction can characterize such dynamics and help understand the underlying brain mechanisms, which can also be used as potential biomarkers. However, applying deep learning to model dynamical systems at the individual level must overcome numerous computational challenges to be reproducible and clinically useful. In this study, we performed an extensive analysis of these challenges using generative modeling of brain dynamics from fMRI data as an example and demonstrated their impact on classifying patients with schizophrenia and major depression. This study highlights the tendency of deep learning models to identify functionally unique solutions during parameter optimization, which severely impacts the reproducibility of downstream predictions. We hope this study guides the future development of individual-level generative models and similar machine learning approaches aimed at identifying reproducible biomarkers of mental illness.

War, emotions, mental health, and artificial intelligence

During the war time dysregulation of negative emotions such as fear, anger, hatred, frustration, sadness, humiliation, and hopelessness can overrule normal societal values, culture, and endanger global peace and security, and mental health in affected societies. Therefore, it is understandable that the range and power of negative emotions may play important roles in consideration of human behavior in any armed conflict. The estimation and assessment of dominant negative emotions during war time are crucial but are challenged by the complexity of emotions' neuro-psycho-physiology. Currently available natural language processing (NLP) tools have comprehensive computational methods to analyze and understand the emotional content of related textual data in war-inflicted societies. Innovative AI-driven technologies incorporating machine learning, neuro-linguistic programming, cloud infrastructure, and novel digital therapeutic tools and applications present an immense potential to enhance mental health care worldwide. This advancement could make mental health services more cost-effective and readily accessible. Due to the inadequate number of psychiatrists and limited psychiatric resources in coping with mental health consequences of war and traumas, new digital therapeutic wearable devices supported by AI tools and means might be promising approach in psychiatry of future. Transformation of negative dominant emotional maps might be undertaken by the simultaneous combination of online cognitive behavioral therapy (CBT) on individual level, as well as usage of emotionally based strategic communications (EBSC) on a public level. The proposed positive emotional transformation by means of CBT and EBSC may provide important leverage in efforts to protect mental health of civil population in war-inflicted societies. AI-based tools that can be applied in design of EBSC stimuli, like Open AI Chat GPT or Google Gemini may have great potential to significantly enhance emotionally based strategic communications by more comprehensive understanding of semantic and linguistic analysis of available text datasets of war-traumatized society. Human in the loop enhanced by Chat GPT and Gemini can aid in design and development of emotionally annotated messages that resonate among targeted population, amplifying the impact of strategic communications in shaping human dominant emotional maps into a more positive by CBT and EBCS.

Simultaneous Utilization of Mood Disorder Questionnaire and Bipolar Spectrum Diagnostic Scale for Machine Learning-Based Classification of Patients With Bipolar Disorders and Depressive Disorders

OBJECTIVE

Bipolar and depressive disorders are distinct disorders with clearly different clinical courses, however, distinguishing between them often presents clinical challenges. This study investigates the utility of self-report questionnaires, the Mood Disorder Questionnaire (MDQ) and Bipolar Spectrum Diagnostic Scale (BSDS), with machine learning-based multivariate analysis, to classify patients with bipolar and depressive disorders.

METHODS

A total of 189 patients with bipolar disorders and depressive disorders were included in the study, and all participants completed both the MDQ and BSDS questionnaires. Machine-learning classifiers, including support vector machine (SVM) and linear discriminant analysis (LDA), were exploited for multivariate analysis. Classification performance was assessed through cross-validation.

RESULTS

Both MDQ and BSDS demonstrated significant differences in each item and total scores between the two groups. Machine learning-based multivariate analysis, including SVM, achieved excellent discrimination levels with area under the ROC curve (AUC) values exceeding 0.8 for each questionnaire individually. In particular, the combination of MDQ and BSDS further improved classification performance, yielding an AUC of 0.8762.

CONCLUSION

This study suggests the application of machine learning to MDQ and BSDS can assist in distinguishing between bipolar and depressive disorders. The potential of combining high-dimensional psychiatric data with machine learning-based multivariate analysis as an effective approach to psychiatric disorders.

Exploring the potential of representation and transfer learning for anatomical neuroimaging: Application to psychiatry

The perspective of personalized medicine for brain disorders requires efficient learning models for anatomical neuroimaging-based prediction of clinical conditions. There is now a consensus on the benefit of deep learning (DL) in addressing many medical imaging tasks, such as image segmentation. However, for single-subject prediction problems, recent studies yielded contradictory results when comparing DL with Standard Machine Learning (SML) on top of classical feature extraction. Most existing comparative studies were limited in predicting phenotypes of little clinical interest, such as sex and age, and using a single dataset. Moreover, they conducted a limited analysis of the employed image pre-processing and feature selection strategies. This paper extensively compares DL and SML prediction capacity on five multi-site problems, including three increasingly complex clinical applications in psychiatry namely schizophrenia, bipolar disorder, and Autism Spectrum Disorder (ASD) diagnosis. To compensate for the relative scarcity of neuroimaging data on these clinical datasets, we also evaluate three pre-training strategies for transfer learning from brain imaging of the general healthy population: self-supervised learning, generative modeling and supervised learning with age. Overall, we find similar performance between randomly initialized DL and SML for the three clinical tasks and a similar scaling trend for sex prediction. This was replicated on an external dataset. We also show highly correlated discriminative brain regions between DL and linear ML models in all problems. Nonetheless, we demonstrate that self-supervised pre-training on large-scale healthy population imaging datasets (N≈10k), along with Deep Ensemble, allows DL to learn robust and transferable representations to smaller-scale clinical datasets (N≤1k). It largely outperforms SML on 2 out of 3 clinical tasks both in internal and external test sets. These findings suggest that the improvement of DL over SML in anatomical neuroimaging mainly comes from its capacity to learn meaningful and useful abstract representations of the brain anatomy, and it sheds light on the potential of transfer learning for personalized medicine in psychiatry.

Prospective prediction of anxiety onset in the Canadian longitudinal study on aging (CLSA): A machine learning study

BACKGROUND

Anxiety disorders are among the most common mental health disorders in the middle aged and older population. Because older individuals are more likely to have multiple comorbidities or increased frailty, the impact of anxiety disorders on their overall well-being is exacerbated. Early identification of anxiety disorders using machine learning (ML) can potentially mitigate the adverse consequences associated with these disorders.

METHODS

We applied ML to the data from the Canadian Longitudinal Study on Aging (CLSA) to predict the onset of anxiety disorders approximately three years in the future. We used Shapley value-based methods to determine the top factor for prediction. We also investigated whether anxiety onset can be predicted by baseline depression-related predictors alone.

RESULTS

Our model was able to predict anxiety onset accurately (Area under the Receiver Operating Characteristic Curve or AUC = 0.814 ± 0.016 (mean ± standard deviation), balanced accuracy = 0.741 ± 0.016, sensitivity = 0.743 ± 0.033, and specificity = 0.738 ± 0.010). The top predictive factors included prior depression or mood disorder diagnosis, high frailty, anxious personality, and low emotional stability. Depression and mood disorders are well known comorbidity of anxiety; however a prior depression or mood disorder diagnosis could not predict anxiety onset without other factors.

LIMITATION

While our findings underscore the importance of a prior depression diagnosis in predicting anxiety, they also highlight that it alone is inadequate, signifying the necessity to incorporate additional predictors for improved prediction accuracy.

CONCLUSION

Our study showcases promising prospects for using machine learning to develop personalized prediction models for anxiety onset in middle-aged and older adults using easy-to-access survey data.

Exploring Pattern of Relapse in Pediatric Patients with Acute Lymphocytic Leukemia and Acute Myeloid Leukemia Undergoing Stem Cell Transplant Using Machine Learning Methods

Background. Leukemic relapse remains the primary cause of treatment failure and death after allogeneic hematopoietic stem cell transplant. Changes in post-transplant donor chimerism have been identified as a predictor of relapse. A better predictive model of relapse incorporating donor chimerism has the potential to improve leukemia-free survival by allowing earlier initiation of post-transplant treatment on individual patients. We explored the use of machine learning, a suite of analytical methods focusing on pattern recognition, to improve post-transplant relapse prediction. Methods. Using a cohort of 63 pediatric patients with acute lymphocytic leukemia (ALL) and 46 patients with acute myeloid leukemia (AML) who underwent stem cell transplant at a single institution, we built predictive models of leukemic relapse with both pre-transplant and post-transplant patient variables (specifically lineage-specific chimerism) using the random forest classifier. Local Interpretable Model-Agnostic Explanations, an interpretable machine learning tool was used to confirm our random forest classification result. Results. Our analysis showed that a random forest model using these hyperparameter values achieved 85% accuracy, 85% sensitivity, 89% specificity for ALL, while for AML 81% accuracy, 75% sensitivity, and 100% specificity at predicting relapses within 24 months post-HSCT in cross validation. The Local Interpretable Model-Agnostic Explanations tool was able to confirm many variables that the random forest classifier identified as important for the relapse prediction. Conclusions. Machine learning methods can reveal the interaction of different risk factors of post-transplant leukemic relapse and robust predictions can be obtained even with a modest clinical dataset. The random forest classifier distinguished different important predictive factors between ALL and AML in our relapse models, consistent with previous knowledge, lending increased confidence to adopting machine learning prediction to clinical management.

Graph Embedded Ensemble Deep Randomized Network for Diagnosis of Alzheimer's Disease

Randomized shallow/deep neural networks with closed form solution avoid the shortcomings that exist in the back propagation (BP) based trained neural networks. Ensemble deep random vector functional link (edRVFL) network utilize the strength of two growing fields, i.e., deep learning and ensemble learning. However, edRVFL model doesn't consider the geometrical relationship of the data while calculating the final output parameters corresponding to each layer considered as base model. In the literature, graph embedded frameworks have been successfully used to describe the geometrical relationship within data. In this paper, we propose an extended graph embedded RVFL (EGERVFL) model that, unlike standard RVFL, employs both intrinsic and penalty subspace learning (SL) criteria under the graph embedded framework in its optimization process to calculate the model's output parameters. The proposed shallow EGERVFL model has only single hidden layer and hence, has less representation learning. Therefore, we further develop an ensemble deep EGERVFL (edEGERVFL) model that can be considered a variant of edRVFL model. Unlike edRVFL, the proposed edEGERVFL model solves graph embedded based optimization problem in each layer and hence, has better generalization performance than edRVFL model. We evaluated the proposed approaches for the diagnosis of Alzheimer's disease and furthermore on UCI datasets. The experimental results demonstrate that the proposed models perform better than baseline models. The source code of the proposed models is available at https://github.com/mtanveer1/.

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.

Gauge-Optimal Approximate Learning for Small Data Classification

Small data learning problems are characterized by a significant discrepancy between the limited number of response variable observations and the large feature space dimension. In this setting, the common learning tools struggle to identify the features important for the classification task from those that bear no relevant information and cannot derive an appropriate learning rule that allows discriminating among different classes. As a potential solution to this problem, here we exploit the idea of reducing and rotating the feature space in a lower-dimensional gauge and propose the gauge-optimal approximate learning (GOAL) algorithm, which provides an analytically tractable joint solution to the dimension reduction, feature segmentation, and classification problems for small data learning problems. We prove that the optimal solution of the GOAL algorithm consists in piecewise-linear functions in the Euclidean space and that it can be approximated through a monotonically convergent algorithm that presents-under the assumption of a discrete segmentation of the feature space-a closed-form solution for each optimization substep and an overall linear iteration cost scaling. The GOAL algorithm has been compared to other state-of-the-art machine learning tools on both synthetic data and challenging real-world applications from climate science and bioinformatics (i.e., prediction of the El Niño Southern Oscillation and inference of epigenetically induced gene-activity networks from limited experimental data). The experimental results show that the proposed algorithm outperforms the reported best competitors for these problems in both learning performance and computational cost.

Large-Scale Neuroimaging of Mental Illness

Neuroimaging has provided important insights into the brain variations related to mental illness. Inconsistencies in prior studies, however, call for methods that lead to more replicable and generalizable brain markers that can reliably predict illness severity, treatment course, and prognosis. A paradigm shift is underway with large-scale international research teams actively pooling data and resources to drive consensus findings and test emerging methods aimed at achieving the goals of precision psychiatry. In parallel with large-scale psychiatric genomics studies, international consortia combining neuroimaging data are mapping the transdiagnostic brain signatures of mental illness on an unprecedented scale. This chapter discusses the major challenges, recent findings, and a roadmap for developing better neuroimaging-based tools and markers for mental illness.

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.

Municipal solid waste management for low-carbon transition: A systematic review of artificial neural network applications for trend prediction

Improper municipal solid waste (MSW) management contributes to greenhouse gas emissions, necessitating emissions reduction strategies such as waste reduction, recycling, and composting to move towards a more sustainable, low-carbon future. Machine learning models are applied for MSW-related trend prediction to provide insights on future waste generation or carbon emissions trends and assist the formulation of effective low-carbon policies. Yet, the existing machine learning models are diverse and scattered. This inconsistency poses challenges for researchers in the MSW domain who seek to identify and optimize the machine learning techniques and configurations for their applications. This systematic review focuses on MSW-related trend prediction using the most frequently applied machine learning model, artificial neural network (ANN), while addressing potential methodological improvements for reducing prediction uncertainty. Thirty-two papers published from 2013 to 2023 are included in this review, all applying ANN for MSW-related trend prediction. Observing a decrease in the size of data samples used in studies from daily to annual timescales, the summarized statistics suggest that well-performing ANN models can still be developed with approximately 33 annual data samples. This indicates promising opportunities for modeling macroscale greenhouse gas emissions in future works. Existing literature commonly used the grid search (manual) technique for hyperparameter (e.g., learning rate, number of neurons) optimization and should explore more time-efficient automated optimization techniques. Since there are no one-size-fits-all performance indicators, it is crucial to report the model's predictive performance based on more than one performance indicator and examine its uncertainty. The predictive performance of newly-developed integrated models should also be benchmarked to show performance improvement clearly and promote similar applications in future works. The review analyzed the shortcomings, best practices, and prospects of ANNs for MSW-related trend predictions, supporting the realization of practical applications of ANNs to enhance waste management practices and reduce carbon emissions.

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.

An efficient consolidation of word embedding and deep learning techniques for classifying anticancer peptides: FastText+BiLSTM

Anticancer peptides (ACPs) are a group of peptides that exhibit antineoplastic properties. The utilization of ACPs in cancer prevention can present a viable substitute for conventional cancer therapeutics, as they possess a higher degree of selectivity and safety. Recent scientific advancements generate an interest in peptide-based therapies which offer the advantage of efficiently treating intended cells without negatively impacting normal cells. However, as the number of peptide sequences continues to increase rapidly, developing a reliable and precise prediction model becomes a challenging task. In this work, our motivation is to advance an efficient model for categorizing anticancer peptides employing the consolidation of word embedding and deep learning models. First, Word2Vec, GloVe, FastText, One-Hot-Encoding approaches are evaluated as embedding techniques for the purpose of extracting peptide sequences. Then, the output of embedding models are fed into deep learning approaches CNN, LSTM, BiLSTM. To demonstrate the contribution of proposed framework, extensive experiments are carried on widely-used datasets in the literature, ACPs250 and independent. Experiment results show the usage of proposed model enhances classification accuracy when compared to the state-of-the-art studies. The proposed combination, FastText+BiLSTM, exhibits 92.50% of accuracy for ACPs250 dataset, and 96.15% of accuracy for the Independent dataset, thence determining new state-of-the-art.

A primer on the use of machine learning to distil knowledge from data in biological psychiatry

Applications of machine learning in the biomedical sciences are growing rapidly. This growth has been spurred by diverse cross-institutional and interdisciplinary collaborations, public availability of large datasets, an increase in the accessibility of analytic routines, and the availability of powerful computing resources. With this increased access and exposure to machine learning comes a responsibility for education and a deeper understanding of its bases and bounds, borne equally by data scientists seeking to ply their analytic wares in medical research and by biomedical scientists seeking to harness such methods to glean knowledge from data. This article provides an accessible and critical review of machine learning for a biomedically informed audience, as well as its applications in psychiatry. The review covers definitions and expositions of commonly used machine learning methods, and historical trends of their use in psychiatry. We also provide a set of standards, namely Guidelines for REporting Machine Learning Investigations in Neuropsychiatry (GREMLIN), for designing and reporting studies that use machine learning as a primary data-analysis approach. Lastly, we propose the establishment of the Machine Learning in Psychiatry (MLPsych) Consortium, enumerate its objectives, and identify areas of opportunity for future applications of machine learning in biological psychiatry. This review serves as a cautiously optimistic primer on machine learning for those on the precipice as they prepare to dive into the field, either as methodological practitioners or well-informed consumers.

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.

Current and Emerging Technologies to Address the Placebo Response Challenge in CNS Clinical Trials: Promise, Pitfalls, and Pathways Forward

Excessive placebo response rates have long been a major challenge for central nervous system (CNS) drug discovery. As CNS trials progressively shift toward digitalization, decentralization, and novel remote assessment approaches, questions are emerging about whether innovative technologies can help mitigate the placebo response. This article begins with a conceptual framework for understanding placebo response. We then critically evaluate the potential of a range of innovative technologies and associated research designs that might help mitigate the placebo response and enhance detection of treatment signals. These include technologies developed to directly address placebo response; technology-based approaches focused on recruitment, retention, and data collection with potential relevance to placebo response; and novel remote digital phenotyping technologies. Finally, we describe key scientific and regulatory considerations when evaluating and selecting innovative strategies to mitigate placebo response. While a range of technological innovations shows potential for helping to address the placebo response in CNS trials, much work remains to carefully evaluate their risks and benefits.

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.

Classifying Children with ADHD Based on Prefrontal Functional Near-infrared Spectroscopy Using Machine Learning

Objective

: Attention deficit hyperactivity disorder (ADHD) is a common neurodevelopmental disorder in children and adults characterized by cognitive and emotional self-control deficiencies. Previous functional near-infrared spectroscopy (fNIRS) studies found significant group differences between ADHD children and healthy controls during cognitive flexibility tasks in several brain regions. This study aims to apply a machine learning approach to identify medication-naive ADHD patients and healthy control (HC) groups using task-based fNIRS data.

Methods

: fNIRS signals from 33 ADHD children and 39 HC during the Stroop task were analyzed. In addition, regularized linear discriminant analysis (RLDA) was used to identify ADHD individuals from healthy controls, and classification performance was evaluated.

Results

: We found that participants can be correctly classified in RLDA leave-one-out cross validation, with a sensitivity of 0.67, specificity of 0.93, and accuracy of 0.82.

Conclusion

: RLDA using only fNIRS data can effectively discriminate children with ADHD from HC. This study suggests the potential utility of the fNIRS signal as a diagnostic biomarker for ADHD children.

Machine learning prediction will be part of future treatment of depression

Machine learning (ML) is changing the way that medicine is practiced. While already clinically utilised in diagnostic radiology and outcome prediction in intensive care unit, ML approaches in psychiatry remain nascent. Implementing ML algorithms in psychiatry, particularly in the treatment of depression, is significantly more challenging than other areas of medicine in part because of the less demarcated disease nosology and greater variability in practice. Given the current exiguous capacity of clinicians to predict patient and treatment outcomes in depression, there is a significantly greater need for better predictive capability. Early studies have shown promising results. ML predictions were significantly better than chance within the sequenced treatment alternatives to relieve depression (STAR*D) trial (accuracy 64.6%, p < 0.0001) and combining medications to enhance depression outcomes (COMED) randomised Controlled Trial (RCT) (accuracy 59.6%, p = 0.043), with similar results found in larger scale, retrospective studies. The greater flexibility and dimensionality of ML approaches has been demonstrated in studies incorporating diverse input variables including electroencephalography scans, achieving 88% accuracy for treatment response, and cognitive test scores, achieving up to 72% accuracy for treatment response. The predicting response to depression treatment (PReDicT) trial tested ML informed prescribing of antidepressants against standard therapy and found there was both better outcomes for anxiety and functional endpoints despite the algorithm only having a balanced accuracy of 57.5%. Impeding the progress of ML algorithms in psychiatry are pragmatic hurdles, including accuracy, expense, acceptability and comprehensibility, and ethical hurdles, including medicolegal liability, clinical autonomy and data privacy. Notwithstanding impediments, it is clear that ML prediction algorithms will be part of depression treatment in the future and clinicians should be prepared for their arrival.

Seed correlation analysis based on brain region activation for ADHD diagnosis in a large-scale resting state data set

Background

Attention-deficit/hyperactivity disorder (ADHD) is a neurodevelopmental disorder of multifactorial pathogenesis, which is often accompanied by dysfunction in several brain functional connectivity. Resting-state functional MRI have been used in ADHD, and they have been proposed as a possible biomarker of diagnosis information. This study's primary aim was to offer an effective seed-correlation analysis procedure to investigate the possible biomarker within resting state brain networks as diagnosis information.

Method

Resting-state functional magnetic resonance imaging (rs-fMRI) data of 149 childhood ADHD were analyzed. In this study, we proposed a two-step hierarchical analysis method to extract functional connectivity features and evaluation by linear classifiers and random sampling validation.

Result

The data-driven method-ReHo provides four brain regions (mPFC, temporal pole, motor area, and putamen) with regional homogeneity differences as second-level seeds for analyzing functional connectivity differences between distant brain regions. The procedure reduces the difficulty of seed selection (location, shape, and size) in estimations of brain interconnections, improving the search for an effective seed; The features proposed in our study achieved a success rate of 83.24% in identifying ADHD patients through random sampling (saving 25% as the test set, while the remaining data was the training set) validation (using a simple linear classifier), surpassing the use of traditional seeds.

Conclusion

This preliminary study examines the feasibility of diagnosing ADHD by analyzing the resting-state fMRI data from the ADHD-200 NYU dataset. The data-driven model provides a precise way to find reliable seeds. Data-driven models offer precise methods for finding reliable seeds and are feasible across different datasets. Moreover, this phenomenon may reveal that using a data-driven approach to build a model specific to a single data set may be better than combining several data and creating a general model.

Single-label machine learning classification revealed some hidden but inter-related causes of five psychotic disorder diseases

Psychotic disorder diseases (PDD) or mental illnesses are group of illnesses that affect the minds and impair the cognitive ability, retard emotional ability and obstruct the process of communication and relationship with others and are characterized by delusions, hallucinations and disoriented or disordered pattern of thinking. Prognosis of PDD is not sufficient because of the nature of the diseases and as such adequate form of diagnosis is required to detect, manage and treat the illness. This paper applied the single-label classification (SLC) machine learning approach in mining of electronic health records of people with PDD in Nigeria using eleven independent (demographic) variables and five PDD as target variables. The five PDDs are Insomnia, Schizophrenia, Minimal Brain dysfunction (MBD), which is also known as Attention-Deficit/Hyperactivity Disorder (ADHD), Vascular Dementia (VD) and Bipolar Disorder (BD). The aim of using SLC is that it would be easier to detect some PDDs that are related to each other without the loss of information, which is a plus over multi-label classification (MLC). ReliefF algorithm was used at each experiment to precipitate the order of importance of the independent variables and redundant variables were excluded from the analysis. The order of the variables in feature selection was matched with feature importance after the classifications and quantified using the Spearman rank correlation coefficient. The data was divided into: 70% for training and 30% for testing. Four new performance metrics adapted from the root mean square (RMSE) were proposed and used to measure the differences between the performance results of the 10 Machine learning models in terms of the training and testing and secondly, feature and without feature selection. The new metrics are close to zero which is an indication that the use of feature selection and cross validation may not greatly affects the accuracy of the SLC. When the PDDs are included as predictors for classifying others, there was a tremendous improvement as revealed by the four new metrics for classification accuracy (CA), precision and recall. Analysis of variance showed the four different metrics differs significantly for classification accuracy (CA) and precision. However, there were no significant difference between the CA and precision when the duo are compared together across the four evaluation metrics at p value less than 0.05.

Whole Person Modeling: a transdisciplinary approach to mental health research

The growing global burden of mental illness has prompted calls for innovative research strategies. Theoretical models of mental health include complex contributions of biological, psychosocial, experiential, and other environmental influences. Accordingly, neuropsychiatric research has self-organized into largely isolated disciplines working to decode each individual contribution. However, research directly modeling objective biological measurements in combination with cognitive, psychological, demographic, or other environmental measurements is only now beginning to proliferate. This review aims to (1) to describe the landscape of modern mental health research and current movement towards integrative study, (2) to provide a concrete framework for quantitative integrative research, which we call Whole Person Modeling, (3) to explore existing and emerging techniques and methods used in Whole Person Modeling, and (4) to discuss our observations about the scarcity, potential value, and untested aspects of highly transdisciplinary research in general. Whole Person Modeling studies have the potential to provide a better understanding of multilevel phenomena, deliver more accurate diagnostic and prognostic tests to aid in clinical decision making, and test long standing theoretical models of mental illness. Some current barriers to progress include challenges with interdisciplinary communication and collaboration, systemic cultural barriers to transdisciplinary career paths, technical challenges in model specification, bias, and data harmonization, and gaps in transdisciplinary educational programs. We hope to ease anxiety in the field surrounding the often mysterious and intimidating world of transdisciplinary, data-driven mental health research and provide a useful orientation for students or highly specialized researchers who are new to this area.

Reinforcement learning deficits exhibited by postnatal PCP-treated rats enable deep neural network classification

The ability to appropriately update the value of a given action is a critical component of flexible decision making. Several psychiatric disorders, including schizophrenia, are associated with impairments in flexible decision making that can be evaluated using the probabilistic reversal learning (PRL) task. The PRL task has been reverse-translated for use in rodents. Disrupting glutamate neurotransmission during early postnatal neurodevelopment in rodents has induced behavioral, cognitive, and neuropathophysiological abnormalities relevant to schizophrenia. Here, we tested the hypothesis that using the NMDA receptor antagonist phencyclidine (PCP) to disrupt postnatal glutamatergic transmission in rats would lead to impaired decision making in the PRL. Consistent with this hypothesis, compared to controls the postnatal PCP-treated rats completed fewer reversals and exhibited disruptions in reward and punishment sensitivity (i.e., win-stay and lose-shift responding, respectively). Moreover, computational analysis of behavior revealed that postnatal PCP-treatment resulted in a pronounced impairment in the learning rate throughout PRL testing. Finally, a deep neural network (DNN) trained on the rodent behavior could accurately predict the treatment group of subjects. These data demonstrate that disrupting early postnatal glutamatergic neurotransmission impairs flexible decision making and provides evidence that DNNs can be trained on behavioral datasets to accurately predict the treatment group of new subjects, highlighting the potential for DNNs to aid in the diagnosis of schizophrenia.

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.

A roadmap for applying machine learning when working with privacy-sensitive data: predicting non-response to treatment for eating disorders

OBJECTIVES

Applying machine-learning methodology to clinical data could present a promising avenue for predicting outcomes in patients receiving treatment for psychiatric disorders. However, preserving privacy when working with patient data remains a critical concern.

METHODS

In showcasing how machine-learning can be used to build a clinically relevant prediction model on clinical data, we apply two commonly used machine-learning algorithms (Random Forest and least absolute shrinkage and selection operator) to routine outcome monitoring data collected from 593 patients with eating disorders to predict absence of reliable improvement 12 months after entering outpatient treatment.

RESULTS

An RF model trained on data collected at baseline and after three months made 31.3% fewer errors in predicting lack of reliable improvement at 12 months, in comparison with chance. Adding data from a six-month follow-up resulted in only marginal improvements to accuracy.

CONCLUSION

We were able to build and validate a model that could aid clinicians and researchers in more accurately predicting treatment response in patients with EDs. We also demonstrated how this could be done without compromising privacy. ML presents a promising approach to developing accurate prediction models for psychiatric disorders such as ED.

Advancing glaucoma detection with convolutional neural networks: a paradigm shift in ophthalmology

A leading cause of irreversible vision loss, glaucoma needs early detection for effective management. Intraocular Pressure (IOP) is a significant risk factor for glaucoma. Convolutional Neural Networks (CNN) demonstrate exceptional capabilities in analyzing retinal fundus images, a non-invasive and cost-effective imaging technique widely used in glaucoma diagnosis. By learning from large datasets of annotated images, CNN can identify subtle changes in the optic nerve head and retinal structures indicative of glaucoma. This enables early and precise glaucoma diagnosis, empowering clinicians to implement timely interventions. CNNs excel in analyzing complex medical images, detecting subtle changes indicative of glaucoma with high precision. Another valuable diagnostic tool for glaucoma evaluation, Optical Coherence Tomography (OCT), provides high-resolution cross-sectional images of the retina. CNN can effectively analyze OCT scans and extract meaningful features, facilitating the identification of structural abnormalities associated with glaucoma. Visual field testing, performed using devices like the Humphrey Field Analyzer, is crucial for assessing functional vision loss in glaucoma. The integration of CNN with retinal fundus images, OCT scans, visual field testing, and IOP measurements represents a transformative approach to glaucoma detection. These advanced technologies have the potential to revolutionize ophthalmology by enabling early detection, personalized management, and improved patient outcomes. CNNs facilitate remote expert opinions and enhance treatment monitoring. Overcoming challenges such as data scarcity and interpretability can optimize CNN utilization in glaucoma diagnosis. Measuring retinal nerve fiber layer thickness as a diagnostic marker proves valuable. CNN implementation reduces healthcare costs and improves access to quality eye care. Future research should focus on optimizing architectures and incorporating novel biomarkers. CNN integration in glaucoma detection revolutionizes ophthalmology, improving patient outcomes and access to care. This review paves the way for innovative CNN-based glaucoma detection methods. Abbreviations: CNN = Convolutional Neural Networks, AI = Artificial Intelligence, IOP = Intraocular Pressure, OCT = Optical Coherence Tomography, CLSO = Confocal Scanning Laser Ophthalmoscopy, AUC-ROC = Area Under the Receiver Operating Characteristic Curve, RNFL = Retinal Nerve Fiber Layer, RNN = Recurrent Neural Networks, VF = Visual Field, AP = Average Precision, MD = Mean Defect, sLV = square-root of Loss Variance, NN = Neural Network, WHO = World Health Organization.

Performance of deep learning algorithms to distinguish high-grade glioma from low-grade glioma: A systematic review and meta-analysis

This study aims to evaluate deep learning (DL) performance in differentiating low- and high-grade glioma. Search online database for studies continuously published from 1st January 2015 until 16th August 2022. The random-effects model was used for synthesis, based on pooled sensitivity (SE), specificity (SP), and area under the curve (AUC). Heterogeneity was estimated using the Higgins inconsistency index (I²). 33 were ultimately included in the meta-analysis. The overall pooled SE and SP were 94% and 93%, with an AUC of 0.98. There was great heterogeneity in this field. Our evidence-based study shows DL achieves high accuracy in glioma grading. Subgroup analysis reveals several limitations in this field: 1) Diagnostic trials require standard method for data merging for AI; 2) small sample size; 3) poor-quality image preprocessing; 4) not standard algorithm development; 5) not standard data report; 6) different definition of HGG and LGG; and 7) poor extrapolation.

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.

Predictors of perceived symptom change with acute cannabis use for mental health conditions in a naturalistic sample: A machine learning approach

BACKGROUND

Despite limited clinical evidence of its efficacy, cannabis use has been commonly reported for the management of various mental health concerns in naturalistic field studies. The aim of the current study was to use machine learning methods to investigate predictors of perceived symptom change across various mental health symptoms with acute cannabis use in a large naturalistic sample.

METHODS

Data from 68,819 unique observations of cannabis use from 1307 individuals using cannabis to manage mental health symptoms were analyzed. Data were extracted from Strainprint®, a mobile app that allows users to monitor their cannabis use for therapeutic purposes. Machine learning models were employed to predict self-perceived symptom change after cannabis use, and SHapley Additive exPlanations (SHAP) value plots were used to assess feature importance of individual predictors in the model. Interaction effects of symptom severity pre-scores of anxiety, depression, insomnia, and gender were also examined.

RESULTS

The factors that were most strongly associated with perceived symptom change following acute cannabis use were pre-symptom severity, age, gender, and the ratio of CBD to THC. Further examination on the impact of baseline severity for the most commonly reported symptoms revealed distinct responses, with cannabis being reported to more likely benefit individuals with lower pre-symptom severity for depression, and higher pre-symptom severity for insomnia. Responses to cannabis use also differed between genders.

CONCLUSIONS

Findings from this study highlight the importance of several factors in predicting perceived symptom change with acute cannabis use for mental health symptom management. Mental health profiles and baseline symptom severity may play a large role in perceived responses to cannabis. Distinct response patterns were also noted across commonly reported mental health symptoms, emphasizing the need for placebo-controlled cannabis trials for specific user profiles.

Deep Learning for Cross-Diagnostic Prediction of Mental Disorder Diagnosis and Prognosis Using Danish Nationwide Register and Genetic Data

Importance

Diagnoses and treatment of mental disorders are hampered by the current lack of objective markers needed to provide a more precise diagnosis and treatment strategy.

Objective

To develop deep learning models to predict mental disorder diagnosis and severity spanning multiple diagnoses using nationwide register data, family and patient-specific diagnostic history, birth-related measurement, and genetics.

Design, Setting, and Participants

This study was conducted from May 1, 1981, to December 31, 2016. For the analysis, which used a Danish population-based case-cohort sample of individuals born between 1981 and 2005, genotype data and matched longitudinal health register data were taken from the longitudinal Danish population-based Integrative Psychiatric Research Consortium 2012 case-cohort study. Included were individuals with mental disorders (attention-deficit/hyperactivity disorder [ADHD]), autism spectrum disorder (ASD), major depressive disorder (MDD), bipolar disorder (BD), schizophrenia spectrum disorders (SCZ), and population controls. Data were analyzed from February 1, 2021, to January 24, 2022.

Exposure

At least 1 hospital contact with diagnosis of ADHD, ASD, MDD, BD, or SCZ.

Main Outcomes and Measures

The predictability of (1) mental disorder diagnosis and (2) severity trajectories (measured by future outpatient hospital contacts, admissions, and suicide attempts) were investigated using both a cross-diagnostic and single-disorder setup. Predictive power was measured by AUC, accuracy, and Matthews correlation coefficient (MCC), including an estimate of feature importance.

Results

A total of 63 535 individuals (mean [SD] age, 23 [7] years; 34 944 male [55%]; 28 591 female [45%]) were included in the model. Based on data prior to diagnosis, the specific diagnosis was predicted in a multidiagnostic prediction model including the background population with an overall area under the curve (AUC) of 0.81 and MCC of 0.28, whereas the single-disorder models gave AUCs/MCCs of 0.84/0.54 for SCZ, 0.79/0.41 for BD, 0.77/0.39 for ASD, 0.74/0.38, for ADHD, and 0.74/0.38 for MDD. The most important data sets for multidiagnostic prediction were previous mental disorders and age (11%-23% reduction in prediction accuracy when removed) followed by family diagnoses, birth-related measurements, and genetic data (3%-5% reduction in prediction accuracy when removed). Furthermore, when predicting subsequent disease trajectories of the disorder, the most severe cases were the most easily predictable, with an AUC of 0.72.

Conclusions and Relevance

Results of this diagnostic study suggest the possibility of combining genetics and registry data to predict both mental disorder diagnosis and disorder progression in a clinically relevant, cross-diagnostic setting prior to clinical assessment.

Using Machine Learning to Predict Cognitive Impairment Among Middle-Aged and Older Chinese: A Longitudinal Study

Objective: To explore the predictive value of machine learning in cognitive impairment, and identify important factors for cognitive impairment. Methods: A total of 2,326 middle-aged and elderly people completed questionnaire, and physical examination evaluation at baseline, Year 2, and Year 4 follow-ups. A random forest machine learning (ML) model was used to predict the cognitive impairment at Year 2 and Year 4 longitudinally. Based on Year 4 cross-sectional data, the same method was applied to establish a prediction model and verify its longitudinal prediction accuracy for cognitive impairment. Meanwhile, the ability of random forest and traditional logistic regression model to longitudinally predict 2-year and 4-year cognitive impairment was compared. Results: Random forest models showed high accuracy for all outcomes at Year 2, Year 4, and cross-sectional Year 4 [AUC = 0.81, 0.79, 0.80] compared with logistic regression [AUC = 0.61, 0.62, 0.70]. Baseline physical examination (e.g., BMI, Blood pressure), biomarkers (e.g., cholesterol), functioning (e.g., functional limitations), demography (e.g., age), and emotional status (e.g., depression) characteristics were identified as the top ten important predictors of cognitive impairment. Conclusion: ML algorithms could enhance the prediction of cognitive impairment among the middle-aged and older Chinese for 4 years and identify essential risk markers.

Model-based experimental manipulation of probabilistic behavior in interpretable behavioral latent variable models

Introduction

Interpretable latent variable models that probabilistically link behavioral observations to an underlying latent process have increasingly been used to draw inferences on cognition from observed behavior. The latent process usually connects experimental variables to cognitive computation. While such models provide important insights into the latent processes generating behavior, one important aspect has often been overlooked. They may also be used to generate precise and falsifiable behavioral predictions as a function of the modeled experimental variables. In doing so, they pinpoint how experimental conditions must be designed to elicit desired behavior and generate adaptive experiments.

Methods

These ideas are exemplified on the process of delay discounting (DD). After inferring DD models from behavior on a typical DD task, the models are leveraged to generate a second adaptive DD task. Experimental trials in this task are designed to elicit 9 graded behavioral discounting probabilities across participants. Models are then validated and contrasted to competing models in the field by assessing the ouf-of-sample prediction error.

Results

The proposed framework induces discounting probabilities on nine levels. In contrast to several alternative models, the applied model exhibits high validity as indicated by a comparably low prediction error. We also report evidence for inter-individual differences with respect to the most suitable models underlying behavior. Finally, we outline how to adapt the proposed method to the investigation of other cognitive processes including reinforcement learning.

Discussion

Inducing graded behavioral frequencies with the proposed framework may help to highly resolve the underlying cognitive construct and associated neuronal substrates.

Machine Learning and Pharmacogenomics at the Time of Precision Psychiatry

Traditional medicine and biomedical sciences are reaching a turning point because of the constantly growing impact and volume of Big Data. Machine Learning (ML) techniques and related algorithms play a central role as diagnostic, prognostic, and decision-making tools in this field. Another promising area becoming part of everyday clinical practice is personalized therapy and pharmacogenomics. Applying ML to pharmacogenomics opens new frontiers to tailored therapeutical strategies to help clinicians choose drugs with the best response and fewer side effects, operating with genetic information and combining it with the clinical profile. This systematic review aims to draw up the state-of-the-art ML applied to pharmacogenomics in psychiatry. Our research yielded fourteen papers; most were published in the last three years. The sample comprises 9,180 patients diagnosed with mood disorders, psychoses, or autism spectrum disorders. Prediction of drug response and prediction of side effects are the most frequently considered domains with the supervised ML technique, which first requires training and then testing. The random forest is the most used algorithm; it comprises several decision trees, reduces the training set's overfitting, and makes precise predictions. ML proved effective and reliable, especially when genetic and biodemographic information were integrated into the algorithm. Even though ML and pharmacogenomics are not part of everyday clinical practice yet, they will gain a unique role in the next future in improving personalized treatments in psychiatry.

Automatic diagnosis of late-life depression by 3D convolutional neural networks and cross-sample Entropy analysis from resting-state fMRI

Resting-state fMRI has been widely used in investigating the pathophysiology of late-life depression (LLD). Unlike the conventional linear approach, cross-sample entropy (CSE) analysis shows the nonlinear property in fMRI signals between brain regions. Moreover, recent advances in deep learning, such as convolutional neural networks (CNNs), provide a timely application for understanding LLD. Accurate and prompt diagnosis is essential in LLD; hence, this study aimed to combine CNN and CSE analysis to discriminate LLD patients and non-depressed comparison older adults based on brain resting-state fMRI signals. Seventy-seven older adults, including 49 patients and 28 comparison older adults, were included for fMRI scans. Three-dimensional CSEs with volumes corresponding to 90 seed regions of interest of each participant were developed and fed into models for disease classification and depression severity prediction. We obtained a diagnostic accuracy > 85% in the superior frontal gyrus (left dorsolateral and right orbital parts), left insula, and right middle occipital gyrus. With a mean root-mean-square error (RMSE) of 2.41, three separate models were required to predict depressive symptoms in the severe, moderate, and mild depression groups. The CSE volumes in the left inferior parietal lobule, left parahippocampal gyrus, and left postcentral gyrus performed best in each respective model. Combined complexity analysis and deep learning algorithms can classify patients with LLD from comparison older adults and predict symptom severity based on fMRI data. Such application can be utilized in precision medicine for disease detection and symptom monitoring in LLD.

Breaking the binary: Gender versus sex analysis in human brain imaging

Despite decades of pursuit, human brain imaging has yet to uncover clear neural correlates of male-female behavioral differences. Given that such behavior does not always align with sex categories, we argue that neuroimaging research may find more success by partitioning subjects along nonbinary gender attributes in addition to sex. We review the handful of studies that have done this, several of which find as good or better association between brain measures and "gender" as they do with "sex." Recent advances in operationalizing "gender" as a multidimensional variable should facilitate such studies, along with discovery-based approaches that mine brain imaging data for gender-associated attributes, independent of sex.

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.

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.

Psychiatric diagnosis and treatment in the 21st century: paradigm shifts versus incremental integration

Psychiatry has always been characterized by a range of different models of and approaches to mental disorder, which have sometimes brought progress in clinical practice, but have often also been accompanied by critique from within and without the field. Psychiatric nosology has been a particular focus of debate in recent decades; successive editions of the DSM and ICD have strongly influenced both psychiatric practice and research, but have also led to assertions that psychiatry is in crisis, and to advocacy for entirely new paradigms for diagnosis and assessment. When thinking about etiology, many researchers currently refer to a biopsychosocial model, but this approach has received significant critique, being considered by some observers overly eclectic and vague. Despite the development of a range of evidence-based pharmacotherapies and psychotherapies, current evidence points to both a treatment gap and a research-practice gap in mental health. In this paper, after considering current clinical practice, we discuss some proposed novel perspectives that have recently achieved particular prominence and may significantly impact psychiatric practice and research in the future: clinical neuroscience and personalized pharmacotherapy; novel statistical approaches to psychiatric nosology, assessment and research; deinstitutionalization and community mental health care; the scale-up of evidence-based psychotherapy; digital phenotyping and digital therapies; and global mental health and task-sharing approaches. We consider the extent to which proposed transitions from current practices to novel approaches reflect hype or hope. Our review indicates that each of the novel perspectives contributes important insights that allow hope for the future, but also that each provides only a partial view, and that any promise of a paradigm shift for the field is not well grounded. We conclude that there have been crucial advances in psychiatric diagnosis and treatment in recent decades; that, despite this important progress, there is considerable need for further improvements in assessment and intervention; and that such improvements will likely not be achieved by any specific paradigm shifts in psychiatric practice and research, but rather by incremental progress and iterative integration.

Accelerated functional brain aging in major depressive disorder: evidence from a large scale fMRI analysis of Chinese participants

Major depressive disorder (MDD) is one of the most common mental health conditions that has been intensively investigated for its association with brain atrophy and mortality. Recent studies suggest that the deviation between the predicted and the chronological age can be a marker of accelerated brain aging to characterize MDD. However, current conclusions are usually drawn based on structural MRI information collected from Caucasian participants. The universality of this biomarker needs to be further validated by subjects with different ethnic/racial backgrounds and by different types of data. Here we make use of the REST-meta-MDD, a large scale resting-state fMRI dataset collected from multiple cohort participants in China. We develop a stacking machine learning model based on 1101 healthy controls, which estimates a subject's chronological age from fMRI with promising accuracy. The trained model is then applied to 1276 MDD patients from 24 sites. We observe that MDD patients exhibit a +4.43 years (p < 0.0001, Cohen's d = 0.31, 95% CI: 2.23-3.88) higher brain-predicted age difference (brain-PAD) compared to controls. In the MDD subgroup, we observe a statistically significant +2.09 years (p < 0.05, Cohen's d = 0.134525) brain-PAD in antidepressant users compared to medication-free patients. The statistical relationship observed is further checked by three different machine learning algorithms. The positive brain-PAD observed in participants in China confirms the presence of accelerated brain aging in MDD patients. The utilization of functional brain connectivity for age estimation verifies existing findings from a new dimension.

OpenBHB: a Large-Scale Multi-Site Brain MRI Data-set for Age Prediction and Debiasing

Prediction of chronological age from neuroimaging in the healthy population is an important issue because the deviations from normal brain age may highlight abnormal trajectories towards brain disorders. As a first step, ML models have emerged to predict chronological age from brain MRI, as a proxy measure of biological age. However, there is currently no consensus w.r.t which Machine Learning (ML) model is best suited for this task, largely because of a lack of public benchmark. Furthermore, new large emerging population neuroimaging datasets are often biased by the acquisition center images are coming from. This bias heavily deteriorates models generalization capacities, especially for Deep Learning (DL) algorithms that are known to overfit rapidly on the simplest features (known as simplicity bias). Here we propose a new public benchmarking resource, namely Open Big Healthy Brains (OpenBHB), along with a challenge for both brain age prediction and site-effect removal through a representation learning framework. OpenBHB is large-scale, gathering >5K 3D T1 brain MRI from Healthy Controls (HC) and highly multi-sites, aggregating >60 centers worldwide and 10 studies. OpenBHB is expected to grow both in terms of available modalities and number of subjects. All OpenBHB datasets are uniformly preprocessed, including quality check, with container technologies that consist in: 3D Voxel-Based Morphometry maps (VBM from CAT12), quasi-raw (simple linear alignment of images), and Surface-Based Morphometry indices (SBM, from FreeSurfer). The OpenBHB challenge is permanent and we provide all tools, materials and tutorials for participants to easily submit and benchmark their model against each other on a public leaderboard.

Transdiagnostic inflammatory subgroups among psychiatric disorders and their relevance to role functioning: a nested case-control study of the ALSPAC cohort

Individuals with psychotic disorders and depressive disorder exhibit altered concentrations of peripheral inflammatory markers. It has been suggested that clinical trials of anti-inflammatory therapies for psychiatric disorders should stratify patients by their inflammatory profile. Hence, we investigated whether different subgroups of individuals exist across psychiatric disorders, based on their inflammatory biomarker signatures. We measured the plasma concentrations of 17 inflammatory markers and receptors in 380 participants with psychotic disorder, depressive disorder or generalised anxiety disorder and 399 controls without psychiatric symptoms from the ALSPAC cohort at age 24. We employed a semi-supervised clustering algorithm, which discriminates multiple clusters of psychiatric disorder cases from controls. The best fit was for a two-cluster model of participants with psychiatric disorders (Adjusted Rand Index (ARI) = 0.52 ± 0.01) based on the inflammatory markers. Permutation analysis indicated the stability of the clustering solution performed better than chance (ARI = 0.43 ± 0.11; p < 0.001), and the clusters explained the inflammatory marker data better than a Gaussian distribution (p = 0.021). Cluster 2 exhibited marked increases in sTNFR1/2, suPAR, sCD93 and sIL-2RA, compared to cluster 1. Participants in the cluster exhibiting higher inflammation were less likely to be in employment, education or training, indicating poorer role functioning. This study found evidence for a novel pattern of inflammatory markers specific to psychiatric disorders and strongly associated with a transdiagnostic measure of illness severity. sTNFR1/2, suPAR, sCD93 and sIL-2RA could be used to stratify clinical trials of anti-inflammatory therapies for psychiatric disorders.

Predicting remission after internet-delivered psychotherapy in patients with depression using machine learning and multi-modal data

This study applied supervised machine learning with multi-modal data to predict remission of major depressive disorder (MDD) after psychotherapy. Genotyped adult patients (n = 894, 65.5% women, age 18-75 years) diagnosed with mild-to-moderate MDD and treated with guided Internet-based Cognitive Behaviour Therapy (ICBT) at the Internet Psychiatry Clinic in Stockholm were included (2008-2016). Predictor types were demographic, clinical, process (e.g., time to complete online questionnaires), and genetic (polygenic risk scores). Outcome was remission status post ICBT (cut-off ≤10 on MADRS-S). Data were split into train (60%) and validation (40%) given ICBT start date. Predictor selection employed human expertise followed by recursive feature elimination. Model derivation was internally validated through cross-validation. The final random forest model was externally validated against a (i) null, (ii) logit, (iii) XGBoost, and (iv) blended meta-ensemble model on the hold-out validation set. Feature selection retained 45 predictors representing all four predictor types. With unseen validation data, the final random forest model proved reasonably accurate at classifying post ICBT remission (Accuracy 0.656 [0.604, 0.705], P vs null model = 0.004; AUC 0.687 [0.631, 0.743]), slightly better vs logit (bootstrap D = 1.730, P = 0.084) but not vs XGBoost (D = 0.463, P = 0.643). Transparency analysis showed model usage of all predictor types at both the group and individual patient level. A new, multi-modal classifier for predicting MDD remission status after ICBT treatment in routine psychiatric care was derived and empirically validated. The multi-modal approach to predicting remission may inform tailored treatment, and deserves further investigation to attain clinical usefulness.

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.

Deep learning-based integration of genetics with registry data for stratification of schizophrenia and depression

Currently, psychiatric diagnoses are, in contrast to most other medical fields, based on subjective symptoms and observable signs and call for new and improved diagnostics to provide the most optimal care. On the basis of a deep learning approach, we performed unsupervised patient stratification of 19,636 patients with depression [major depressive disorder (MDD)] and/or schizophrenia (SCZ) and 22,467 population controls from the iPSYCH2012 case cohort. We integrated data of disorder severity, history of mental disorders and disease comorbidities, genetics, and medical birth data. From this, we stratified the individuals in six and seven unique clusters for MDD and SCZ, respectively. When censoring data until diagnosis, we could predict MDD clusters with areas under the curve (AUCs) of 0.54 to 0.80 and SCZ clusters with AUCs of 0.71 to 0.86. Overall cases and controls could be predicted with an AUC of 0.81, illustrating the utility of data-driven subgrouping in psychiatry.

A Model Guided Approach to Evoke Homogeneous Behavior During Temporal Reward and Loss Discounting

Background

The tendency to devaluate future options as a function of time, known as delay discounting, is associated with various factors such as psychiatric illness and personality. Under identical experimental conditions, individuals may therefore strongly differ in the degree to which they discount future options. In delay discounting tasks, this inter-individual variability inevitably results in an unequal number of discounted trials per subject, generating difficulties in linking delay discounting to psychophysiological and neural correlates. Many studies have therefore focused on assessing delay discounting adaptively. Here, we extend these approaches by developing an adaptive paradigm which aims at inducing more comparable and homogeneous discounting frequencies across participants on a dimensional scale.

Method

The proposed approach probabilistically links a (common) discounting function to behavior to obtain a probabilistic model, and then exploits the model to obtain a formal condition which defines how to construe experimental trials so as to induce any desired discounting probability. We first infer subject-level models on behavior on a non-adaptive delay discounting task and then use these models to generate adaptive trials designed to evoke graded relative discounting frequencies of 0.3, 0.5, and 0.7 in each participant. We further compare and evaluate common models in the field through out-of-sample prediction error estimates, to iteratively improve the trial-generating model and paradigm.

Results

The developed paradigm successfully increases discounting behavior during both reward and loss discounting. Moreover, it evokes graded relative choice frequencies in line with model-based expectations (i.e., 0.3, 0.5, and 0.7) suggesting that we can successfully homogenize behavior. Our model comparison analyses indicate that hyperboloid models are superior in predicting unseen discounting behavior to more conventional hyperbolic and exponential models. We report out-of-sample error estimates as well as commonalities and differences between reward and loss discounting, demonstrating for instance lower discounting rates, as well as differences in delay perception in loss discounting.

Conclusion

The present work proposes a model-based framework to evoke graded responses linked to cognitive function at a single subject level. Such a framework may be used in the future to measure cognitive functions on a dimensional rather than dichotomous scale.

An fMRI Sequence Representation Learning Framework for Attention Deficit Hyperactivity Disorder Classification

For attention deficit hyperactivity disorder (ADHD), a common neurological disease, accurate identification is the basis for treatment. In this paper, a novel end-to-end representation learning framework for ADHD classification of functional magnetic resonance imaging (fMRI) sequences is proposed. With such a framework, the complexity of the sequence representation learning neural network decreases, the overfitting problem of deep learning for small samples cases is solved effectively, and superior classification performance is achieved. Specifically, a data conversion module was designed to convert a two-dimensional sequence into a three-dimensional image, which expands the modeling area and greatly reduces the computational complexity. The transfer learning method was utilized to freeze or fine-tune the parameters of the pre-trained neural network to reduce the risk of overfitting in the cases with small samples. Hierarchical feature extraction can be performed automatically by combining the sequence representation learning modules with a weighted cross-entropy loss. Experiments were conducted both with individual imaging sites and combining them, and the results showed that the classification average accuracies with the proposed framework were 73.73% and 72.02%, respectively, which are much higher than those of the existing methods.