‘Big data’ in mental health research: current status and emerging possibilities

Stewart, Robert; Davis, Katrina

doi:10.1007/s00127-016-1266-8

Cited by 67 publications

(52 citation statements)

References 193 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Mental health problems represent a major public health challenge worldwide, and the accumulation of big data offers the opportunity for improving healthcare processes, interventions, and public health policies (Stewart and Davis, 2016). Recent advances in data science, machine learning and Natural Language Processing (NLP) hold great promise in providing technical solutions for the analysis of large sets of clinically relevant information in Psychiatry (Torous and Baker, 2016).…”

Section: Introductionmentioning

confidence: 99%

Hierarchical neural model with attention mechanisms for the classification of social media text related to mental health

Ive¹,

Gkotsis²,

Dutta³

et al. 2018

Proceedings of the Fifth Workshop on Computational Linguistics And Clinical Psychology: From Keyboard to Clinic

Self Cite

View full text Add to dashboard Cite

Mental health problems represent a major public health challenge. Automated analysis of text related to mental health is aimed to help medical decision-making, public health policies and to improve health care. Such analysis may involve text classification. Traditionally, automated classification has been performed mainly using machine learning methods involving costly feature engineering. Recently, the performance of those methods has been dramatically improved by neural methods. However, mainly Convolutional neural networks (CNNs) have been explored. In this paper, we apply a hierarchical Recurrent neural network (RNN) architecture with an attention mechanism on social media data related to mental health. We show that this architecture improves overall classification results as compared to previously reported results on the same data. Benefitting from the attention mechanism, it can also efficiently select text elements crucial for classification decisions, which can also be used for in-depth analysis.

show abstract

Section: Introductionmentioning

confidence: 99%

Hierarchical neural model with attention mechanisms for the classification of social media text related to mental health

Ive¹,

Gkotsis²,

Dutta³

et al. 2018

Proceedings of the Fifth Workshop on Computational Linguistics And Clinical Psychology: From Keyboard to Clinic

Self Cite

View full text Add to dashboard Cite

show abstract

“…The mining and exploitation of such big data resources as Electronic Healthcare Records (EHRs) present an exciting challenge to the field of psychiatric epidemiology. The number of big data projects within psychiatric research is growing, and Stewart and Davis's literature review is, therefore, timely [2].…”

mentioning

confidence: 99%

“…As described in detail by Stewart and Davis, the challenging aspects of working with 'big data' are captured by the taxonomy of 'Vs'-volume, velocity, and variety-first described by Laney [4] and extended since [1,2]. There are additional issues to working with healthcare big data specifically, including that clinical administrative data are generally not collected, curated, or formatted in a manner optimised for research, and the inherent sensitivity of the data in terms of personal privacy.…”

mentioning

confidence: 99%

“…Within psychiatry, the move towards near real-time access to clinical data incorporated in the SLaM BRC Clinical Record Interactive Search (CRIS) [10] will hopefully be among the first of many such resources. In addition, we are witnessing a broadening of the horizons of clinical record linkage, to encompass linkage to birth cohorts, genetic, and imaging repositories, but also to other administrative data in social, economic, and educational fields [2]. This will allow future studies to better model the 'bio-psycho-social' outcomes of psychiatric illness for the benefit of patients, researchers, and policymakers.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Invited Commentary on Stewart and Davis “ ‘Big data’ in mental health research—current status and emerging possibilities”

Hafferty

Smith

McIntosh

2016

Soc Psychiatry Psychiatr Epidemiol

View full text Add to dashboard Cite

“…While there has been a long tradition of using routine data and harnessing case registers in psychiatric epidemiology, data resources now accumulate in larger volumes in electronic format; Stewart and Davis [40] will review the current status and emerging possibilities of such ‘big data’ in mental health research in the next issue of SPPE. The series will then continue with reviews of recent developments in the closely related area of e-health, in particular, the use of ecological and geographic momentary assessment for measuring moment-to-moment variation in socio-environmental exposures, mental health, and substance use outcomes [41–44], and for investigating causal criteria under real-world conditions [44].…”

mentioning

confidence: 99%

Novel methods in psychiatric epidemiology

Reininghaus

Keyes

Morgan

2016

Soc Psychiatry Psychiatr Epidemiol

View full text Add to dashboard Cite

, SPPE began to publish a series of reviews, editorials, and commentaries with the goal of synthesising evidence and providing a platform for discussing and advancing the state of the art in social psychiatry and psychiatric epidemiology. More than 2 years into these series, it is useful to take stock, look back, and provide an overview of what comes next.The series set off to synthesise and discuss evidence on the biological and psychological mechanisms through which social contexts and experiences increase risk of adverse mental health outcomes [1,2], reflecting the recent shift in theoretical and measurement foundations towards integrated models of aetiology. This included reviews and commentaries on gene-environment interactions [3][4][5][6] and on epigenetic [7,8], inflammatory [9,10], cognitive, affective [11][12][13], and neurobiological mechanisms [14] through which stress, adversity, and other key socio-environmental exposures may affect mental health. These reviews and commentaries highlight the rapid technological and subsequent scientific advances in psychiatry in uncovering mechanisms that underlie the epidemiological associations between adversity and illness that have been documented, since the advent of psychiatric epidemiology, yet also reveal a paradigm shift in its beginning stages of formation. In view of recent and impending revisions of the Diagnostic and Statistical Manual of Mental Disorders and International Classification of Diseases as well as movements towards non-binary classifications of psychiatric phenomena, the series then addressed current challenges in diagnostic classification in psychiatry [15][16][17][18][19], reviewing the enduring challenge of high comorbidity rates [19], methodological considerations in the use of latent variable models of psychopathology [16], and the evidence on transdiagnostic factors [17,18] that may underlie individual common mental disorders [17,18], personality disorders [18], and psychotic disorders [18,[20][21][22]. This was followed by reviews pulling together and discussing key findings from major epidemiological studies in the context of new challenges in the field and directions for future research [23][24][25][26][27][28][29][30]. It is abundantly clear, particularly from large-scale epidemiological studies, that the origins of most mental health problems trace back to childhood and adolescence [1] and the series continued with reviews and commentaries on youth mental health [31][32][33][34][35][36], including key findings from developmental epidemiology [32][33][34], protective and promotive factors [31], and the ongoing youth mental health reform in several countries [35,36]. These reviews and commentaries testify to the continued value and vigour of social epidemiological research in mental health. However, there are of course challenges that remain to be addressed. The rapid advances in design, measurement, and statistics are often difficult to convey to a wider research audience and considered in isolation [39]. While there has been a ...

show abstract

‘Big data’ in mental health research: current status and emerging possibilities

Cited by 67 publications

References 193 publications

Hierarchical neural model with attention mechanisms for the classification of social media text related to mental health

Hierarchical neural model with attention mechanisms for the classification of social media text related to mental health

Invited Commentary on Stewart and Davis “ ‘Big data’ in mental health research—current status and emerging possibilities”

Novel methods in psychiatric epidemiology

Contact Info

Product

Resources

About