David A Benrimoh

McGill University | McGill · Department of Psychiatry

Major depressive disorder (MDD) is the leading cause of disability worldwide, yet treatment selection still proceeds via “trial and error”. Given the varied presentation of MDD and heterogeneity of treatment response, the use of machine learning to understand complex, non-linear relationships in data may be key for treatment personalization. Well-o...

Major Depressive Disorder (MDD) is a leading cause of disability and there is a paucity of tools to personalize and manage treatments. A cluster-randomized, patient-and-rater-blinded, clinician-partially-blinded study was conducted to assess the effectiveness and safety of the Aifred Clinical Decision Support System (CDSS) facilitating algorithm-gu...

Major Depressive Disorder (MDD) is a leading cause of disability and there is a paucity of tools to personalize and manage treatments. A cluster-randomized, patient-and-rater-blinded, clinician-partially-blinded study was conducted to assess the effectiveness and safety of the Aifred Clinical Decision Support System (CDSS) facilitating algorithm-gu...

INTRODUCTION: The pharmacological treatment of Major Depressive Disorder (MDD) relies on a trial-and-error approach. We introduce an artificial intelligence (AI) model aiming to personalize treatment and improve outcomes, which was deployed in the Artificial Intelligence in Depression Medication Enhancement (AIDME) Study. OBJECTIVES: 1) Develop a m...

The mechanisms of psychotic symptoms like hallucinations and delusions are often investigated in fully-formed illness, well after symptoms emerge. These investigations have yielded key insights, but are not well-positioned to reveal the dynamic forces underlying symptom formation itself. Understanding symptom development over time would allow us to...

Background: Preventing or delaying the onset of psychosis requires identification of those at risk for developing psychosis. For predictive purposes, the prodrome - a constellation of symptoms which may occur before the onset of psychosis - has been increasingly recognized as having utility. However, it is unclear what proportion of patients exper...

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

Background There is increasing evidence that people with hallucinations overweight perceptual beliefs relative to incoming sensory evidence. Past work demonstrating prior overweighting has used simple, nonlinguistic stimuli. However, auditory hallucinations in psychosis are often complex and linguistic. There may be an interaction between the type...

There is increasing evidence that people with hallucinations overweight perceptual beliefs relative to incoming sensory evidence. Much past work demonstrating prior overweighting has used simple, non-linguistic stimuli. However, auditory hallucinations in psychosis are often complex and linguistic. There may be an interaction between the type of au...

Computational psychiatry is a field aimed at developing formal models of information processing in the human brain, and how alterations in this processing can lead to clinical phenomena. There has been significant progress in the development of tasks and how to model them, presenting an opportunity to incorporate computational psychiatry methodolog...

BACKGROUND: Preventing or delaying the onset of psychosis requires identification of those at risk for developing psychosis. For predictive purposes, the prodrome, a constellation of symptoms which may occur before the onset of psychosis, has been increasingly recognized as having utility. However, it is unclear what proportion of patients are expe...

Psychotic disorders are highly heterogeneous. Understanding relationships between symptoms will be relevant to their underlying pathophysiology. We apply dimensionality-reduction methods across two unique samples to characterize the patterns of symptom organization. We analyzed publicly-available data from 153 participants diagnosed with schizophre...

Major depressive disorder (MDD) is a heterogeneous condition; multiple underlying neurobiological substrates could be associated with treatment response variability. Understanding the sources of this variability and predicting outcomes has been elusive. Machine learning has shown promise in predicting treatment response in MDD, but one limitation h...

The landscape of psychiatry is ever evolving and has recently begun to be influenced more heavily by new technologies. One novel technology which may have particular application to psychiatry is the metaverse, a three-dimensional digital social platform accessed via augmented, virtual, and mixed reality (AR/VR/MR). The metaverse allows the interact...

Clinical decision support systems (CDSS) augmented with artificial intelligence (AI) models are emerging as potentially valuable tools in healthcare. Despite their promise, the development and implementation of these systems typically encounter several barriers, hindering the potential for widespread adoption. Here we present a case study of a rece...

Disrupted language in psychotic disorders, such as schizophrenia, can manifest as false contents and formal deviations, often described as thought disorder. These features play a critical role in the social dysfunction associated with psychosis, but we continue to lack insights regarding how these symptoms develop. Natural language Generation (NLG)...

Computational psychiatry is a field aimed at developing formal models of information processing in the human brain, and how alterations in this processing can lead to clinical phenomena. Despite significant progress in the development of tasks and how to model them, computational psychiatry methodologies have yet to be incorporated into large-scale...

BACKGROUND: Artificial intelligence-powered clinical decision support systems (AI-CDSS) have recently become foci of research. When clinicians face decisions about treatment selection, they must contemplate multiple criteria simultaneously. The relative importance of these criteria often depends on the clinical scenario, as well as clinician and pa...

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 differen...

Flexible approaches have been proposed for individually randomized trials to save time or reduce sample size. However, flexible designs for cluster‐randomized trials in which groups of participants rather than individuals are randomized to treatment arms are less common. Motivated by a cluster‐randomized trial designed to assess the effectiveness o...

UNSTRUCTURED The Metaverse- a virtual world accessed via virtual reality technology- has been heralded as the next key digital experience. It is meant to provide the next evolution of human interaction via social media and telework. However, in the context of growing awareness of the risks to mental health posed by current social media technologies...

The metaverse-a virtual world accessed via virtual reality technology-has been heralded as the next key digital experience. It is meant to provide the next evolution of human interaction after social media and telework. However, in the context of the growing awareness of the risks to mental health posed by current social media technologies, there i...

Background Recent advances in computational psychiatry have identified latent cognitive and perceptual states that predispose to psychotic symptoms. Behavioral data fit to Bayesian models have demonstrated an over-reliance on priors (i.e., prior over-weighting) during perception in select samples of individuals with hallucinations, corresponding to...

The objective of this paper is to discuss perceived clinical utility and impact on physician-patient relationship of a novel, artificial-intelligence (AI) enabled clinical decision support system (CDSS) for use in the treatment of adults with major depression. Patients had a baseline appointment, followed by a minimum of two appointments with the C...

Adaptive approaches, allowing for more flexible trial design, have been proposed for individually randomized trials to save time or reduce sample size. However, adaptive designs for cluster-randomized trials in which groups of participants rather than individuals are randomized to treatment arms are less common. Motivated by a cluster-randomized tr...

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...

Machine-assisted treatment selection commonly follows one of two paradigms: a fully personalized paradigm which ignores any possible clustering of patients; or a sub-grouping paradigm which ignores personal differences within the identified groups. While both paradigms have shown promising results, each of them suffers from important limitations. I...

Delusions are, by popular definition, false beliefs that are held with certainty and resistant to contradictory evidence. They seem at odds with the notion that the brain at least approximates Bayesian inference. This is especially the case in schizophrenia, a disorder thought to relate to decreased – rather than increased – certainty in the brain'...

The computational underpinnings of positive psychotic symptoms have recently received significant attention. Candidate mechanisms include some combination of maladaptive priors and reduced updating of these priors during perception. A potential benefit of models with such mechanisms is their ability to link multiple levels of explanation, from the...

BACKGROUND Approximately two thirds of patients with major depressive disorder (MDD) do not achieve remission during their first treatment. There has been increasing interest in the use of digital, artificial intelligence (AI)-powered clinical decision support systems (CDSS) to assist physicians in their treatment selection and management, improvin...

Objective: We 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. Methods: Due to COVID-19, the study was adapted to be...

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 pe...

Introduction: Suicidal ideation (SI) is prevalent in the general population, and is a risk factor for suicide. Predicting which patients are likely to have SI remains challenging. Deep Learning (DL) may be a useful tool in this context, as it can be used to find patterns in complex, heterogeneous, and incomplete datasets. An automated screening sys...

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...

The computational underpinnings of positive psychotic symptoms have recently received significant attention. Candidate mechanisms include some combination of maladaptive priors and reduced updating of these priors during perception. A potential benefit of models with such mechanisms is their ability to link multiple levels of explanation. This is k...

Objective PTSD is increasingly recognized following medical traumas although is highly heterogeneous. It is difficult to judge which medical contexts have the most traumatic potential and where to concentrate further research and clinical attention for prevention, early detection and treatment. The objective of this study was to compare PTSD preval...

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 o...

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 pre...

We present the case of likely COVID-19 associated encephalopathy in a male in his early 50s with a history of non-psychotic depression and personality disorder who presented with delirium, new psychotic symptoms and who developed paratonia and obtundation. After initial questions of neuroleptic malignant syndrome, serotonin syndrome, and stiff pers...

Depression affects one in nine people, but treatment response rates remain low. There is significant potential in the use of computational modeling techniques to predict individual patient responses and thus provide more personalized treatment. Deep learning is a promising computational technique that can be used for differential treatment selectio...

This paper offers a formal account of policy learning, or habitual behavioral optimization, under the framework of Active Inference. In this setting, habit formation becomes an autodidactic, experience-dependent process, based upon what the agent sees itself doing. We focus on the effect of environmental volatility on habit formation by simulating...

The theme of this special issue of the Journal of Abnormal Psychology is on predictive processing and how it can improve our fundamental understanding of neuropsychiatric disorders. Several articles focus on psychosis and demonstrate how the field of computational psychosis research has evolved and matured in recent years through the application of...

Objective: Aifred 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. Methods: Twenty psychiatry and family medicine attend...

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 mod...

Introduction: Suicidal ideation (SI) is prevalent in the general population, and is a prominent risk factor for suicide. However, predicting which patients are likely to have SI remains a challenge. Deep Learning (DL) may be a useful tool in this context, as it can be used to find patterns in complex, heterogeneous, and incomplete psychiatric datas...

This chapter explores the evidence of disturbances in various neurobiological pathways in depression. No unifying pathophysiological mechanism has yet been discovered. Depression is more than simply a deficiency in a single neurotransmitter or pathway, as neurobiological correlates of depression have been identified in diverse studies. This chapter...

Major depressive disorder is a serious, debilitating, life-shortening illness that affects many persons of all ages and backgrounds. The point prevalence is high (2.3%–3.2% in men, 4.5%–9.3% in women) and the lifetime risk is 7% to 12% for men and 20% to 25% for women. Major depression is a disabling disorder that costs the United States over $200...

The Canadian province of Quebec enacted in 2014 a legislation that permitted medical assistance in dying (MAID) under specific conditions and the rest of Canada followed suit in June 2016. In this article, which is the second in a set of case series of requests for MAID in Canadian psychiatry, we present the cases of two patients who made a request...

Hallucinations, including auditory verbal hallucinations (AVH), occur in both the healthy population and in psychotic conditions such as schizophrenia (often developing after a prodromal period). In addition, hallucinations can be in-context (they can be consistent with the environment, such as when one hallucinates the end of a sentence that has b...

Power and leadership are intimately related. While physician leadership is widely discussed in healthcare, power has received less attention. Formal organisational leadership by physicians is increasingly common even though the evidence for the effectiveness of physician leadership is still evolving. There is an expectation of leadership by all phy...

Living creatures must accurately infer the nature of their environments. They do this despite being confronted by stochastic and context sensitive contingencies-and so must constantly update their beliefs regarding their uncertainty about what might come next. In this work, we examine how we deal with uncertainty that evolves over time. This prospe...

Background Depression affects one in nine people, but treatment response rates remain low. There is significant potential in the use of computational modelling techniques to predict individual patient responses and thus provide more personalized treatment. Deep learning is a promising computational technique that can be used for differential treatm...

This paper offers a formal account of policy learning, or habitual behavioural optimisation, under the framework of Active Inference. In this setting, habit formation becomes an autodidactic, experience-dependent process, based upon what the agent sees itself doing. We focus on the effect of environmental volatility on habit formation by simulating...

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 pre...

Hallucinations, including auditory verbal hallucinations (AVH), occur in both the healthy population and in psychotic conditions such as schizophrenia (often developing after a prodromal period). In addition, hallucinations can be in-context (they can be consistent with the environment, such as when one hallucinates the end of a sentence that has b...

Schizophrenia-spectrum psychoses are highly complex and heterogeneous disorders that necessitate multiple lines of scientific inquiry and levels of explanation. In recent years, both computational and phenomenological approaches to the understanding of mental illness have received much interest , and significant progress has been made in both field...

Auditory verbal hallucinations (AVH) are often distressing symptoms of several neuropsychiatric conditions, including schizophrenia. Using a Markov decision process formulation of active inference, we develop a novel model of AVH as false (positive) inference. Active inference treats perception as a process of hypothesis testing, in which sensory d...

The diagnostic category of "organic disorders" was officially removed from the psychiatric nosology in DSM-IV, published in 1994. Despite this change, physicians continue to use the term "organic causes" to refer to medical and neurological causes of psychiatric symptoms, and it remains part of the ICD-10 classification. In the context of increasin...

The competencies required of the well-trained physician are constantly evolving, and medical education must adapt accordingly. In response, a growing number of influential medical education licensing and accreditation bodies have proposed frameworks that outline society’s expectations of physician competencies. In Canada, undergraduate and graduate...

Accurate perceptual inference fundamentally depends upon accurate beliefs about the reliability of sensory data. In this paper, we describe a Bayes optimal and biologically plausible scheme that refines these beliefs through a gradient descent on variational free energy. To illustrate this, we simulate belief updating during visual foraging and sho...

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 predic...

Globally, depression affects over 300 million people at any given time and is the leading cause of disability. While different patients may benefit more from different therapies, there is no principled way for clinicians to predict individual patient responses or side effect profiles. Deep learning is a form of machine learning based on artificial...

Physicians are often required to lead teams in clinical and non-clinical environments but may not receive formal training in advance of these opportunities. In this commentary, three medical learners discuss their views on leadership education in undergraduate and postgraduate medicine, arguing that leadership development should be more explicitly...

Euthanasia was decriminalized in Quebec in December 2015, and Canada-wide in June 2016. Both the Provincial and Federal legislation have limited the right to medical assistance in dying (MAID) to end-of-life cases; which makes MAID inaccessible to most patients solely suffering from psychiatric illness. While some end-stage anorexia nervosa or elde...

Physician advocacy and leadership is increasingly recognized as an important part of our social responsibility. Frameworks, such as CanMEDS, have set out definitions of health advocacy and leadership for medical education. Despite calls for mandatory advocacy and leadership teaching and potential wellness benefits, presently medical curricula do no...

Background: The incidence of mood disorders has long been associated with childhood adversity (CA) yet a model that fully explains the association is lacking. One possible pathway is that childhood adversity may lead to maladaptive cognitive styles (CS) which in turn predisposes individuals to mood disorders. Methods: We studied a sample of 162 ad...