Search

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.

A common thread in the variable experience of voice-hearing may be the breakdown in an individual’s ability to distinguish speech perceived in the surrounding world from verbal thoughts or ‘inner speech’. Failures in reality monitoring processes involved in such discrimination of internally and externally generated information have been linked to structural differences in the medial prefrontal cortex, a brain region involved in recognition of the self. This chapter explores the role of reality monitoring in voice-hearing, its brain basis, and how an understanding of the neural correlates and phenomenological experiences of voice-hearing can inform one another.

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.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.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.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.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.

ObjectiveWe examine the feasibility of an Artificial Intelligence (AI)-powered clinical decision support system (CDSS), which combines the operationalized 2016 Canadian Network for Mood and Anxiety Treatments guidelines with a neural-network based individualized treatment remission prediction.MethodsDue to COVID-19, the study was adapted to be completed entirely at a distance. Seven physicians recruited outpatients diagnosed with major depressive disorder (MDD) as per DSM-V criteria. Patients completed a minimum of one visit without the CDSS (baseline) and two subsequent visits where the CDSS was used by the physician (visit 1 and 2). The primary outcome of interest was change in session length after CDSS introduction, as a proxy for feasibility. Feasibility and acceptability data were collected through self-report questionnaires and semi-structured interviews.ResultsSeventeen patients enrolled in the study; 14 completed. There was no significant difference between appointment length between visits (introduction of the tool did not increase session length). 92.31% of patients and 71.43% of physicians felt that the tool was easy to use. 61.54% of the patients and 71.43% of the physicians rated that they trusted the CDSS. 46.15% of patients felt that the patient-clinician relationship significantly or somewhat improved, while the other 53.85% felt that it did not change.ConclusionsOur results confirm the primary hypothesis that the integration of the tool does not increase appointment length. Findings suggest the CDSS is easy to use and may have some positive effects on the patient-physician relationship. The CDSS is feasible and ready for effectiveness studies.

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. CLINICALTRIAL ClinicalTrials.gov NCT04061642; http://clinicaltrials.gov/ct2/show/NCT04061642

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

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.

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.

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.

Mental health conditions cause a great deal of distress or impairment; depression alone will affect 11% of the world’s population. The application of Artificial Intelligence (AI) and big-data technologies to mental health has great potential for personalizing treatment selection, prognosticating, monitoring for relapse, detecting and helping to prevent mental health conditions before they reach clinical-level symptomatology, and even delivering some treatments. However, unlike similar applications in other fields of medicine, there are several unique challenges in mental health applications, which currently pose barriers toward the implementation of these technologies. Specifically, there are very few widely used or validated biomarkers in mental health, leading to a heavy reliance on patient- and clinician-derived questionnaire data as well as interpretation of new signals such as digital phenotyping. In addition, diagnosis also lacks the same objective “gold standard” as in other conditions such as oncology, where clinicians and researchers can often rely on pathological analysis for confirmation of diagnosis. In this chapter, we discuss the major opportunities, limitations, and techniques used for improving mental healthcare through AI and big data. We explore both the computational, clinical, and ethical considerations and best practices as well as lay out the major researcher directions for the near future.

BackgroundAll 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.MethodsWe studied two independent datasets of patients with schizophrenia who underwent clinical assessment and 3T structural magnetic resonance (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) from MR images and constructed cortical folding covariance matrices organized by large-scale networks.ResultsIn both ethnic groups, we replicated a significantly shorter left PCS in patients with hallucinations compared to those without, and 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.ConclusionThe 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.

ObjectiveAifred is an artificial intelligence (AI)-powered clinical decision support system (CDSS) for the treatment of major depression. Here, we explore use of a simulation centre environment in evaluating the usability of Aifred, particularly its impact on the physician-patient interaction.MethodsTwenty psychiatry and family medicine attending staff and residents were recruited to complete a 2.5-hour study at a clinical interaction simulation centre with standardized patients. Each physician had the option of using the CDSS to inform their treatment choice in three 10-minute clinical scenarios with standardized patients portraying mild, moderate, and severe episodes of major depression. Feasibility and acceptability data were collected through self-report questionnaires, scenario observations, interviews, and standardized patient feedback.ResultsAll twenty 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 AI’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.ConclusionsThe simulation centre allowed for direct observations of clinician use and impact of the tool on the clinician-patient interaction prior to 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.

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 β-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.

Many architectures of deep neural networks have been designed to solve specific biomedical problems, among which segmentation is a critical step to detect and locate the boundaries of the target object from an image. In this paper, we develop a deep learning based framework to automatically segment the paracingulate sulcus (PCS) from the MRI scan and estimate lengths for its segments. The study is the first work on segmentation and characterisation of the PCS, and the model achieves a Dice score of over 0.77 on segmentation, which demonstrates its potential for clinical use to assist human annotation. Moreover, the proposed architecture as a solution can be generalised to other problems where the object has similar patterns.

BACKGROUNDHallucinations 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.METHODSWe performed whole-brain voxelwise meta-analyses of hallucination status across diagnoses using 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.FINDINGS3214 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 meta-analyses were formally confirmed and a jackknife sensitivity analysis established the reproducibility of results across nearly all study combinations. For other 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.INTERPRETATIONDistinct 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.FUNDINGNone.Research in contextEvidence before this studyThere is increasing recognition that hallucinations occur beyond the archetype of schizophrenia, presenting in other psychiatric disorders, neurological and neurodegenerative conditions, and among the general population. Not only are hallucinations a transdiagnostic phenomenon, but also the experience of hallucinating is phenomenologically diverse, varying in modality, content, frequency, and affect. It has been suggested that no one type of hallucination is pathognomic to any one disorder, but rather that hallucinations may exist on a continuum. However, limited research has been done to directly compare the underlying neuroanatomy of hallucinations between different disorders. With this aim, we conducted a meta-analysis and systematic review of structural MRI studies comparing individuals who experience hallucinations with those who do not, to investigate the brain morphology related to the transdiagnostic presentation of hallucinations. We searched PubMed and Web of Science with no start date limit, up to May 2018 using the keyword combination (hallucinat*) AND (MRI OR magnetic resonance imaging OR morphology OR voxel?based OR morphometr* OR neural correlate OR structur*). We included only studies with a within-group no-hallucination control to tease out structural changes specific to hallucinations from effects of the broader pathology. Neuroimaging meta-analyses were conducted on studies performing whole-brain voxelwise gray matter differences, while studies assessing other structural correlates were qualitatively synthesized.Added value of this studyThis is the first meta-analysis to illustrate the brain structural correlates of hallucination occurrence derived from T1-weighted MRI, and to do so in a comparative manner across clinical groups. We identified two distinct gray matter substrates for hallucination presence in psychiatric compared to neurodegenerative diseases, which we hypothesise constitute at least two distinct mechanisms. In addition, we qualitatively assessed other structural neuroimaging studies over a variety of morphometric indices. We therefore provide a complete characterization of current knowledge of the brain morphology associated with hallucinations across clinical status and modality.Implications of all the available evidenceOur findings show at least two structural substrates that link to the hallucinatory experience. This informs theoretical work on hallucinations which have to date been limited in generating unifying direction-specific predictions of brain structure and function. Understanding the plurality of anatomical signatures of hallucinations may also inform treatment strategies. We predict that other disorders in which patients experience hallucinations can be categorised by our approach based on the broader phenotype; for example, hallucinations in personality disorder may be of the psychiatric type, and similarly for early onset hallucinations in the general population, whilst later onset will be neurodegenerative. Moreover, by differentiating the mechanisms of hallucinations we recommend the contextualising of research by the appropriate phenotype.

Aifred Health, one of the top two teams in the first round of the IBM Watson AI XPRIZE competition, is using deep learning to solve the problem of treatment selection and prognosis prediction in mental health, starting with depression. Globally, depression affects over 300 million people and is the leading cause of disability. While a range of effective treatments do exist, patients’ responses to treatments vary to a large degree. Some patients spend years going through a frustrating ‘trial-and-error’ process in order to find an effective treatment. The Aifred Health solution is a deep learning-powered Clinical Decision Support System (CDSS) aimed at helping clinicians select the most effective treatment plans for depression in collaboration with their patients. In this chapter, we discuss problem of treatment selection in depression and explore the technical, clinical, and ethical dimensions of building a CDSS for mental health based on deep learning technology.