Sandra Vieira

King's College London | KCL · Department of Psychosis Studies

Cognitive-behavioural therapy (CBT) is the first line of treatment for several mental health disorders. However, not all patients show clinical improvements after receiving CBT. Machine learning allows inferences at the individual level and therefore is a promising approach for predicting who will and will not benefit from CBT. A comprehensive lite...

Background and Hypothesis Schizophrenia is increasingly understood as a disorder of brain dysconnectivity. Recently, graph-based approaches such as graph convolutional network (GCN) have been leveraged to explore complex pairwise similarities in imaging features among brain regions, which can reveal abstract and complex relationships within brain n...

The rise of machine learning has unlocked new ways of analysing structural neuroimaging data, including brain age prediction. In this state-of-the-art review, we provide an introduction to the methods and potential clinical applications of brain age prediction. Studies on brain age typically involve the creation of a regression machine learning mod...

Normative modelling is an emerging method for quantifying how individuals deviate from the healthy populational pattern. Several machine learning models have been implemented to develop normative models to investigate brain disorders, including regression, support vector machines and Gaussian process models. With the advance of deep learning techno...

Brain morphology varies across the ageing trajectory and the prediction of a person's age using brain features can aid the detection of abnormalities in the ageing process. Existing studies on such “brain age prediction” vary widely in terms of their methods and type of data, so at present the most accurate and generalisable methodological approach...

Aims Around 15% of patients at clinical high risk for psychosis (CHR‐P) experience symptomatic remission and functional recovery at follow‐up, yet the definition of a good outcome (GO) in this population requires further development. Outcomes are typically designed and rated by clinicians rather than patients, to measure adverse as opposed to GOs....

A pivotal aim of psychiatric and neurological research is to promote the translation of the findings into clinical practice to improve diagnostic and prognostic assessment of individual patients. Structural neuroimaging holds much promise, with neuroanatomical measures accounting for up to 40% of the variance in clinical outcome. Building on these...

Normative modelling is an emerging method for quantifying how individuals deviate from the healthy populational pattern. Several machine learning models have been implemented to develop normative models to investigate brain disorders, including regression, support vector machines and Gaussian process models. With the advance of deep learning techno...

In this chapter, we explore the potential applications of machine learning to brain disorders. Specifically, we illustrate why the use of machine learning in brain disorders is attracting so much interest among researchers and clinicians by highlighting three key applications: prediction of illness onset, assistance with diagnosis, and prediction o...

Background: Neuroanatomical abnormalities in first-episode psychosis (FEP) tend to be subtle and widespread. The vast majority of previous studies have used small samples, and therefore may have been underpowered. In addition, most studies have examined participants at a single research site, and therefore the results may be specific to the local s...

Background Neuroanatomical abnormalities in first-episode psychosis (FEP) tend to be subtle and widespread. The vast majority of previous studies have used small samples, and therefore may have been underpowered. In addition, most studies have examined participants at a single research site, and therefore the results may be specific to the local sa...

Deep learning (DL) is a family of machine learning methods capable of detecting multiple levels of latent representations from the data. This is achieved by combining consecutive layers of simple nonlinear transformations that allow the extraction of increasingly abstract features. DL has become one of the most popular and promising approaches in m...

Machine learning is becoming increasingly popular in the neuroscientific literature. However, navigating the literature can easily become overwhelming, especially for the nonexpert. In this chapter, we provide an introduction to machine learning aimed at researchers, clinicians, and students with an interest in brain disorders, including psychiatry...

The last decade has seen a surge in machine learning studies in psychiatric and neurological disorders. Given its translational potential, machine learning is also capturing the interest of clinicians and other mental health practitioners. It is therefore important that these research and clinical communities develop a good appreciation of the natu...

Multimodal machine learning is a recent yet fast-growing topic in brain disorders research. The aim is to capitalize on the complementary nature of different modalities to build better prediction models for psychiatric and neurologic disorders. In this chapter, we focus on three groups of methods for multimodal integration that differ with respect...

In this chapter, we provide a step-by-step tutorial on the implementation of a standard supervised machine learning pipeline using Python programming language. We use a toy dataset with neuroimaging-based data (i.e., gray matter volume and thickness from different brain regions extracted with FreeSurfer) to classify patients with schizophrenia and...

Convolutional neural networks (CNNs or ConvNets) are a popular group of neural networks that belong to a wider family of methods known as deep learning. The secret for their success lies in their carefully designed architecture capable of considering the local and global characteristics of the input data. Initially, CNNs have been designed to proce...

The study of psychiatric and neurologic disorders typically involves the acquisition of a wide range of different types of data, such as brain images, electronic health records, and mobile phone sensors data. Each type of data has its unique temporal and spatial characteristics, and the process of extracting useful information from them can be very...

Schizophrenia is a severe psychiatric disorder associated with both structural and functional brain abnormalities. In the past few years, there has been growing interest in the application of machine learning techniques to neuroimaging data for the diagnostic and prognostic assessment of this disorder. However, the vast majority of studies publishe...

Machine Learning is an area of artificial intelligence involving the development of algorithms to discover trends and patterns in existing data, and the use of this information to make predictions on new data. Over the past decade, the application of Machine Learning in the field of neuroscience has gained considerable attention. Machine Learning:...

Background Previous studies using resting-state functional neuroimaging have revealed alterations in whole-brain images, connectome-wide functional connectivity and graph-based metrics in groups of patients with schizophrenia relative to groups of healthy controls. However, it is unclear which of these measures best captures the neural correlates o...

Despite the high level of interest in the use of machine learning (ML) and neuroimaging to detect psychosis at the individual level, the reliability of the findings is unclear due to potential methodological issues that may have inflated the existing literature. This study aimed to elucidate the extent to which the application of ML to neuroanatomi...

Despite the high level of interest in the use of machine learning (ML) and neuroimaging to detect psychosis at the individual level, the reliability of the findings is unclear due to potential methodological issues that may have inflated the existing literature. This study aimed to elucidate the extent to which the application of ML to neuroanatomi...

Background: Outcomes in people at clinical high risk for psychosis (CHRP) have usually been defined in terms of psychosis onset. However, within the subgroup of individuals who do not develop psychosis, some have persistent symptoms; while in others, symptoms resolve and functioning is restored. Currently, little is known about what predicts a goo...

Despite an increasing focus on transdiagnostic approaches to mental health, it remains unclear whether different diagnostic categories share a common neuronatomical basis. The current investigation sought to investigate whether a transdiagnostic set of structural alterations characterized schizophrenia, depression, post-traumatic stress disorder, a...

Background Long-term outcomes for individuals at risk of developing psychosis are heterogeneous; some develop a psychotic disorder, others continue to experience attenuated psychotic symptoms (APS) and some experience clinical remission and functional recovery. Existing UHR literature is primarily vulnerability- and disease-focused. In recent years...

Background: Deep learning (DL) is a family of machine learning methods that has gained considerable attention in the scientific community, breaking benchmark records in areas such as speech and visual recognition. DL differs from conventional machine learning methods by virtue of its ability to learn the optimal representation from the raw data thr...

Deep learning (DL) is a family of machine learning methods that has gained considerable attention in the scientific community, breaking benchmark records in areas such as speech and visual recognition. DL differs from conventional machine learning methods by virtue of its ability to learn the optimal representation from the raw data through consecu...

Mental health literacy (MHL) and mental illness stigma (MIS) represent new horizons of study and intervention, particularly important, for both communities and clinical settings (European Commission & Portuguese Ministry of Health, 2010). In this paper we aimed to: a) describe a clinical sample (CS) and non clinical group (NCG) in aspects related t...

Mental health literacy (MHL) and mental illness stigma (MIS) represent new horizons of study and intervention , particularly important, for both communities and clinical settings (European Commission & Portuguese Ministry of Health, 2010). In this paper we aimed to: a) describe a clinical sample (CS) and non clinical group (NCG) in aspects related...

The Social Phobia and Anxiety Inventory - brief report (SPAI-B) is a questionnaire for adolescents developed from the Social Phobia and Anxiety Inventory (SPAI), one of the most studied and used instruments for the assessment of social anxiety in adults which additionally presents excellent psychometric properties. The present study analyzed the fa...