Correction: Evaluating the Clinical Feasibility of an Artificial Intelligence-Powered, Web-Based Clinical Decision Support System for the Treatment of Depression in Adults: Longitudinal Feasibility Study.

[This corrects the article DOI: 10.2196/31862.].

A systematic meta-review of patient-level predictors of psychological therapy outcome in major depressive disorder.

BACKGROUND: Psychological therapies are effective for treating major depressive disorder, but current clinical guidelines do not provide guidance on the personalization of treatment choice. Established predictors of psychotherapy treatment response could help inform machine learning models aimed at predicting individual patient responses to different therapy options. Here we sought to comprehensively identify known predictors. METHODS: EMBASE, Medline, PubMed, PsycINFO were searched for systematic reviews with or without meta-analysis published until June 2020 to identify individual patient-level predictors of response to psychological treatments. 3113 abstracts were identified and 300 articles assessed. We qualitatively synthesized our findings by predictor category (sociodemographic; symptom profile; social support; personality features; affective, cognitive, and behavioural; comorbidities; neuroimaging; genetics) and treatment type. We used the AMSTAR 2 to evaluate the quality of included reviews. RESULTS: Following screening and full-text assessment, 27 systematic reviews including 12 meta-analyses were eligible for inclusion. 74 predictors emerged for various psychological treatments, primarily cognitive behavioural therapy, interpersonal therapy, and mindfulness-based cognitive therapy. LIMITATIONS: A paucity of studies examining predictors of psychological treatment outcome, as well as methodological heterogeneities and publication biases limit the strength of the identified predictors. CONCLUSIONS: The synthesized predictors could be used to supplement clinical decision-making in selecting psychological therapies based on individual patient characteristics. These predictors could also be used as a priori input features for machine learning models aimed at predicting a given patient's likelihood of response to different treatment options for depression, and may contribute toward the development of patient-specific treatment recommendations in clinical guidelines.

Evaluating the perceived utility of an artificial intelligence-powered clinical decision support system for depression treatment using a simulation center.

Aifred is a clinical decision support system (CDSS) that uses artificial intelligence to assist physicians in selecting treatments for major depressive disorder (MDD) by providing probabilities of remission for different treatment options based on patient characteristics. We evaluated the utility of the CDSS as perceived by physicians participating in simulated clinical interactions. Twenty physicians who were either staff or residents in psychiatry or family medicine completed a study in which they had three 10-minute clinical interactions with standardized patients portraying mild, moderate, and severe episodes of MDD. During these scenarios, physicians were given access to the CDSS, which they could use in their treatment decisions. The perceived utility of the CDSS was assessed through self-report questionnaires, scenario observations, and interviews. 60% of physicians perceived the CDSS to be a useful tool in their treatment-selection process, with family physicians perceiving the greatest utility. Moreover, 50% of physicians would use the tool for all patients with depression, with an additional 35% noting that they would reserve the tool for more severe or treatment-resistant patients. Furthermore, clinicians found the tool to be useful in discussing treatment options with patients. The efficacy of this CDSS and its potential to improve treatment outcomes must be further evaluated in clinical trials.

Arts-based methods for hallucination research.

INTRODUCTION: Neurocognitive models of hallucinations posit theories of misattribution and deficits in the monitoring of mental or perceptual phenomena but cannot yet account for the subjective experience of hallucinations across individuals and diagnostic categories. Arts-based research methods (ABRM) have potential for advancing research, as art depicts experiences which cognitive neuropsychiatry seeks to explain. METHODS: To examine how incorporating ABRM may advance hallucination research and theories, we explore data on the lived experiences of hallucinations in psychiatric and neurological populations. We present a multiple case study of two empirical ABRM studies, which used participant-generated artwork and artist collaborations alongside interviews. RESULTS: ABRM combined with interviews illustrated that hallucinations were infused with sensory features, characterised by embodiment, and situated within lived circumstances. These findings advance neurocognitive models of hallucinations by nuancing their multimodal nature, illustrating their embodied feelings, and exploring their content and themes. The process of generating artworks aided in disclosing difficult to discuss hallucinations, promoted participant self-reflection, and clarified multimodal details that may have been misconstrued through interview alone. ABRM were relevant and acceptable for participants and researchers. CONCLUSION: ABRM may contribute to the development of neurocognitive models of hallucinations by making hallucination experiences more visible, tangible, and accessible.

Evaluating the Clinical Feasibility of an Artificial Intelligence-Powered, Web-Based Clinical Decision Support System for the Treatment of Depression in Adults: Longitudinal Feasibility Study.

BACKGROUND: Approximately two-thirds of patients with major depressive disorder do not achieve remission during their first treatment. There has been increasing interest in the use of digital, artificial intelligence-powered clinical decision support systems (CDSSs) to assist physicians in their treatment selection and management, improving the personalization and use of best practices such as measurement-based care. Previous literature shows that for digital mental health tools to be successful, the tool must be easy for patients and physicians to use and feasible within existing clinical workflows. OBJECTIVE: This study aims to examine the feasibility of an artificial intelligence-powered CDSS, which combines the operationalized 2016 Canadian Network for Mood and Anxiety Treatments guidelines with a neural network-based individualized treatment remission prediction. METHODS: Owing to the COVID-19 pandemic, the study was adapted to be completed entirely remotely. A total of 7 physicians recruited outpatients diagnosed with major depressive disorder according to the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition criteria. Patients completed a minimum of one visit without the CDSS (baseline) and 2 subsequent visits where the CDSS was used by the physician (visits 1 and 2). The primary outcome of interest was change in appointment length after the introduction of the CDSS as a proxy for feasibility. Feasibility and acceptability data were collected through self-report questionnaires and semistructured interviews. RESULTS: Data were collected between January and November 2020. A total of 17 patients were enrolled in the study; of the 17 patients, 14 (82%) completed the study. There was no significant difference in appointment length between visits (introduction of the tool did not increase appointment length; F2,24=0.805; mean squared error 58.08; P=.46). In total, 92% (12/13) of patients and 71% (5/7) of physicians felt that the tool was easy to use; 62% (8/13) of patients and 71% (5/7) of physicians rated that they trusted the CDSS. Of the 13 patients, 6 (46%) felt that the patient-clinician relationship significantly or somewhat improved, whereas 7 (54%) felt that it did not change. CONCLUSIONS: Our findings confirm that the integration of the tool does not significantly increase appointment length and suggest that the CDSS is easy to use and may have positive effects on the patient-physician relationship for some patients. The CDSS is feasible and ready for effectiveness studies. TRIAL REGISTRATION: ClinicalTrials.gov NCT04061642; http://clinicaltrials.gov/ct2/show/NCT04061642.

Using a simulation centre to evaluate preliminary acceptability and impact of an artificial intelligence-powered clinical decision support system for depression treatment on the physician-patient interaction.

BACKGROUND: Recently, artificial intelligence-powered devices have been put forward as potentially powerful tools for the improvement of mental healthcare. An important question is how these devices impact the physician-patient interaction. AIMS: Aifred is an artificial intelligence-powered clinical decision support system (CDSS) for the treatment of major depression. Here, we explore the use of a simulation centre environment in evaluating the usability of Aifred, particularly its impact on the physician-patient interaction. METHOD: Twenty psychiatry and family medicine attending staff and residents were recruited to complete a 2.5-h study at a clinical interaction simulation centre with standardised patients. Each physician had the option of using the CDSS to inform their treatment choice in three 10-min clinical scenarios with standardised patients portraying mild, moderate and severe episodes of major depression. Feasibility and acceptability data were collected through self-report questionnaires, scenario observations, interviews and standardised patient feedback. RESULTS: All 20 participants completed the study. Initial results indicate that the tool was acceptable to clinicians and feasible for use during clinical encounters. Clinicians indicated a willingness to use the tool in real clinical practice, a significant degree of trust in the system's predictions to assist with treatment selection, and reported that the tool helped increase patient understanding of and trust in treatment. The simulation environment allowed for the evaluation of the tool's impact on the physician-patient interaction. CONCLUSIONS: The simulation centre allowed for direct observations of clinician use and impact of the tool on the clinician-patient interaction before clinical studies. It may therefore offer a useful and important environment in the early testing of new technological tools. The present results will inform further tool development and clinician training materials.

Evidence in cortical folding patterns for prenatal predispositions to hallucinations in schizophrenia.

All perception is a construction of the brain from sensory input. Our first perceptions begin during gestation, making fetal brain development fundamental to how we experience a diverse world. Hallucinations are percepts without origin in physical reality that occur in health and disease. Despite longstanding research on the brain structures supporting hallucinations and on perinatal contributions to the pathophysiology of schizophrenia, what links these two distinct lines of research remains unclear. Sulcal patterns derived from structural magnetic resonance (MR) images can provide a proxy in adulthood for early brain development. We studied two independent datasets of patients with schizophrenia who underwent clinical assessment and 3T MR imaging from the United Kingdom and Shanghai, China (n = 181 combined) and 63 healthy controls from Shanghai. Participants were stratified into those with (n = 79 UK; n = 22 Shanghai) and without (n = 43 UK; n = 37 Shanghai) hallucinations from the PANSS P3 scores for hallucinatory behaviour. We quantified the length, depth, and asymmetry indices of the paracingulate and superior temporal sulci (PCS, STS), which have previously been associated with hallucinations in schizophrenia, and constructed cortical folding covariance matrices organized by large-scale functional networks. In both ethnic groups, we demonstrated a significantly shorter left PCS in patients with hallucinations compared to those without, and to healthy controls. Reduced PCS length and STS depth corresponded to focal deviations in their geometry and to significantly increased covariance within and between areas of the salience and auditory networks. The discovery of neurodevelopmental alterations contributing to hallucinations establishes testable models for these enigmatic, sometimes highly distressing, perceptions and provides mechanistic insight into the pathological consequences of prenatal origins.

Meta-analytic Evidence for the Plurality of Mechanisms in Transdiagnostic Structural MRI Studies of Hallucination Status.

BACKGROUND: Hallucinations are transmodal and transdiagnostic phenomena, occurring across sensory modalities and presenting in psychiatric, neurodegenerative, neurological, and non-clinical populations. Despite their cross-category occurrence, little empirical work has directly compared between-group neural correlates of hallucinations. METHODS: We performed whole-brain voxelwise meta-analyses of hallucination status across diagnoses using anisotropic effect-size seed-based d mapping (AES-SDM), and conducted a comprehensive systematic review in PubMed and Web of Science until May 2018 on other structural correlates of hallucinations, including cortical thickness and gyrification. FINDINGS: 3214 abstracts were identified. Patients with psychiatric disorders and hallucinations (eight studies) exhibited reduced gray matter (GM) in the left insula, right inferior frontal gyrus, left anterior cingulate/paracingulate gyrus, left middle temporal gyrus, and increased in the bilateral fusiform gyrus, while patients with neurodegenerative disorders with hallucinations (eight studies) showed GM decreases in the left lingual gyrus, right supramarginal gyrus/parietal operculum, left parahippocampal gyrus, left fusiform gyrus, right thalamus, and right lateral occipital gyrus. Group differences between psychiatric and neurodegenerative hallucination meta-analyses were formally confirmed using Monte Carlo randomizations to determine statistical significance, and a jackknife sensitivity analysis established the reproducibility of results across nearly all study combinations. For other structural measures (28 studies), the most consistent findings associated with hallucination status were reduced cortical thickness in temporal gyri in schizophrenia and altered hippocampal volume in Parkinson's disease and dementia. Additionally, increased severity of hallucinations in schizophrenia correlated with GM reductions within the left superior temporal gyrus, right middle temporal gyrus, bilateral supramarginal and angular gyri. INTERPRETATION: Distinct patterns of neuroanatomical alteration characterize hallucination status in patients with psychiatric and neurodegenerative diseases, suggesting a plurality of anatomical signatures. This approach has implications for treatment, theoretical frameworks, and generates refutable predictions for hallucinations in other diseases and their occurrence within the general population. FUNDING: None.

Contributions of a high-fat diet to Alzheimer's disease-related decline: A longitudinal behavioural and structural neuroimaging study in mouse models.

Obesity is recognized as a significant risk factor for Alzheimer's disease (AD). Studies have supported that obesity accelerates AD-related pathophysiology and memory impairment in mouse models of AD. However, the nature of the brain structure-behaviour relationship mediating this acceleration remains unclear. In this manuscript we evaluated the impact of adolescent obesity on the brain morphology of the triple transgenic mouse model of AD (3xTg) and a non-transgenic control model of the same background strain (B6129s) using longitudinally acquired structural magnetic resonance imaging (MRI). At 8 weeks of age, animals were placed on a high-fat diet (HFD) or an ingredient-equivalent control diet (CD). Structural images were acquired at 8, 16, and 24 weeks. At 25 weeks, animals underwent the novel object recognition (NOR) task and the Morris water maze (MWM) to assess short-term non-associative memory and spatial memory, respectively. All analyses were carried out across four groups: B6129s-CD and -HFD and 3xTg-CD and -HFD. Neuroanatomical changes in MRI-derived brain morphology were assessed using volumetric and deformation-based analyses. HFD-induced obesity during adolescence exacerbated brain volume alterations by adult life in the 3xTg mouse model in comparison to control-fed mice and mediated volumetric alterations of select brain regions, such as the hippocampus. Further, HFD-induced obesity aggravated memory in all mice, lowering certain memory measures of B6129s control mice to the level of 3xTg mice maintained on a CD. Moreover, decline in the volumetric trajectories of hippocampal regions for all mice were associated with the degree of spatial memory impairments on the MWM. Our results suggest that obesity may interact with the brain changes associated with AD-related pathology in the 3xTg mouse model to aggravate brain atrophy and memory impairments and similarly impair brain structural integrity and memory capacity of non-transgenic mice. Further insight into this process may have significant implications in the development of lifestyle interventions for treatment of AD.

A systematic meta-review of predictors of antidepressant treatment outcome in major depressive disorder.

INTRODUCTION: The heterogeneity of symptoms and complex etiology of depression pose a significant challenge to the personalization of treatment. Meanwhile, the current application of generic treatment approaches to patients with vastly differing biological and clinical profiles is far from optimal. Here, we conduct a meta-review to identify predictors of response to antidepressant therapy in order to select robust input features for machine learning models of treatment response. These machine learning models will allow us to learn associations between patient features and treatment response which have predictive value at the individual patient level; this learning can be optimized by selecting high-quality input features for the model. While current research is difficult to directly apply to the clinic, machine learning models built using knowledge gleaned from current research may become useful clinical tools. METHODS: The EMBASE and MEDLINE/PubMed online databases were searched from January 1996 to August 2017, using a combination of MeSH terms and keywords to identify relevant literature reviews. We identified a total of 1909 articles, wherein 199 articles met our inclusion criteria. RESULTS: An array of genetic, immune, endocrine, neuroimaging, sociodemographic, and symptom-based predictors of treatment response were extracted, varying widely in clinical utility. LIMITATIONS: Due to heterogeneous sample sizes, effect sizes, publication biases, and methodological disparities across reviews, we could not accurately assess the strength and directionality of every predictor. CONCLUSION: Notwithstanding our cautious interpretation of the results, we have identified a multitude of predictors that can be used to formulate a priori hypotheses regarding the input features for a computational model. We highlight the importance of large-scale research initiatives and clinically accessible biomarkers, as well as the need for replication studies of current findings. In addition, we provide recommendations for future improvement and standardization of research efforts in this field.

Analysis of Features Selected by a Deep Learning Model for Differential Treatment Selection in Depression.

Background: Deep learning has utility in predicting differential antidepressant treatment response among patients with major depressive disorder, yet there remains a paucity of research describing how to interpret deep learning models in a clinically or etiologically meaningful way. In this paper, we describe methods for analyzing deep learning models of clinical and demographic psychiatric data, using our recent work on a deep learning model of STAR*D and CO-MED remission prediction. Methods: Our deep learning analysis with STAR*D and CO-MED yielded four models that predicted response to the four treatments used across the two datasets. Here, we use classical statistics and simple data representations to improve interpretability of the features output by our deep learning model and provide finer grained understanding of their clinical and etiological significance. Specifically, we use representations derived from our model to yield features predicting both treatment non-response and differential treatment response to four standard antidepressants, and use linear regression and t-tests to address questions about the contribution of trauma, education, and somatic symptoms to our models. Results: Traditional statistics were able to probe the input features of our deep learning models, reproducing results from previous research, while providing novel insights into depression causes and treatments. We found that specific features were predictive of treatment response, and were able to break these down by treatment and non-response categories; that specific trauma indices were differentially predictive of baseline depression severity; that somatic symptoms were significantly different between males and females, and that education and low income proved important psycho-social stressors associated with depression. Conclusion: Traditional statistics can augment interpretation of deep learning models. Such interpretation can lend us new hypotheses about depression and contribute to building causal models of etiology and prognosis. We discuss dataset-specific effects and ideal clinical samples for machine learning analysis aimed at improving tools to assist in optimizing treatment.

Early-in-life neuroanatomical and behavioural trajectories in a triple transgenic model of Alzheimer's disease.

Animal models of Alzheimer's disease (AD) can be used to determine the progressive neurodegeneration characteristics of AD in vivo using magnetic resonance imaging (MRI). Given the need for therapeutic interventions before the onset of frank AD, it is critical to examine if AD models demonstrate neuroanatomical remodeling in an equivalent preclinical phase. This manuscript examines the trajectories of brain and behavioural changes in the Triple transgenic mouse model (3xTg) prior to the development of AD-like behaviours. The 3xTg mimics both ß-amyloid plaques and neurofibrillary tangles through three mutations associated with familial AD, namely: PS1M146V, APPSwe, and tauP301L transgenes. We performed detailed investigation using longitudinal structural MRI at 6, 8, 12, 16, 20, and 24 weeks old to assess neuroanatomical changes using volumetric and deformation-based analyses. Learning- and memory-related behaviour were assessed through the Morris water maze at 9, 17, and 25 weeks of age. There was the absence of major memory deficits with the notable exception of water maze conducted at 17 weeks old, where 3xTg group spent significantly less time in the quadrant of interest in the probe trial. Through volumetric and deformation-based analyses, we observed relative decrease over time in the 3xTg group in the third ventricle, piriform cortex, fornix, and fimbria relative to the control group. We also observed decreases over time in the control mice in the hippocampus, entorhinal cortex, cerebellum, and olfactory bulb. In many of these cases, we note a delay in the attainment of peak volume in the 3xTgs relative to the control group, suggesting a possible neurodevelopmental and maturational delay given the likely over-expression of AD-related pathology from birth. Importantly, neuroanatomical alterations are observed prior to the manifestation of AD-like behaviours, suggesting that mutated amyloid and tau are, indeed, sufficient to cause changes in the neuroanatomy in 3xTg mice, but potentially insufficient to be responsible for behavioural changes in the earlier stages of life.