Data Science in Computational Psychiatry and Psychiatric Research

Special Session at IEEE DSAA 2018


The Statistical Learning Group at the Institute of Psychiatry, Psychology and Neuroscience King's College London, and the Data Science & Soft Computing Lab London organise the:

Data Science in Computational Psychiatry and Psychiatric Research - CompPsyDS Special Session at the IEEE Data Science and Advanced Analytics 2018

Aims and scope

Psychiatric research entered the age of big data with patient databases now available with thousands of clinical, demographical, social, environmental, neuroimaging, genomic, proteonomic and other -omic measures.

The analysis of such data is often more challenging than in other medical research areas because i) psychiatrists study traits which are not easily measurable; they need to be measured indirectly e.g. by questionnaires, ii) the definition of a mental disease is often very broad and often includes distinct but unknown subcategories, iii) there is a high proportion of drop-out in many studies and patients often do not adhere to the treatment and iv) treatment interventions often have several interacting and it is often difficult to measure components (complex interventions). Psychiatric research therefore presents special problems for researchers in addition to the standard methodological challenges, such as the number of variables exceeding the number of patients.

Machine learning techniques are increasingly being used to address problems in psychiatric and psychological research, including bioinformatics, neuroimaging, prediction modelling and personalized medicine, causal modelling, epidemiology and many other research areas. Machine learning plays also an important role in the definition of the modern field of Computational Psychiatry.

We would like to invite researchers from both academia and industry to participate in this workshop to present, discuss, and share the latest findings in the field, and exchange ideas that address real-world problems with real-world solutions, as well as to discuss future research directions and applications. This special session is open to all interested persons.


Topics of interest

Topics of interest include but are not limited to applications of Data Science in:

·         Computational Psychiatry

·         Prediction models of differential treatment success (Personalized medicine)

·         Development of diagnostic, risk and prognostic models (e.g. predicting risk of dementia, psychosis, etc)

·         Big data and highly dimensional data analysis in psychiatric research

·         Improving apparent validity of prediction models

·         Methods for prediction and knowledge discovery from Electronic Health Record (EHR) data

·         Adaptive clinical trials and machine learning

·         Causal modelling, including Mendelian Randomization

·         Neuroimaging, EEG and ERP studies

·         Bioinformatics and -omics studies

·         Modelling selection bias in case-control studies

·         Machine learning application to reduce the problem of selective inference and low reproducibility of research studies

·         Methods for predicting from streaming activity and other data from wearable sensor data and real-time prediction methods (“mobile health”)

·         Handling informative missing or censored outcome data

·         Identifying subgroups of patients with schizophrenia, depression or other mental health problems

·         Machine learning and the development of measurement scales

Important dates and submission information:
https://dsaa2018.isi.it/calls/call-for-special-session-papers


Organisers and Special Session Chairs
(please contact for enquiries)

Dr. Daniel Stahl
Department of Biostatistics and Health Informatics
King’s College London, UK
daniel.r.stahl@kcl.ac.uk


Dr. Daniel Stamate
Data Science & Soft Computing Lab, and
Department of Computing
Goldsmiths, University London, UK
d.stamate@gold.ac.uk

Daniel Stahl is a Reader in Biostatistics and Head of the Statistical Learning Group in the Department of Biostatistics and Health Informatics of the Institute of Psychiatry, Psychology and Neuroscience (IoPPN), King’s College London. He first studied animal physiology at the University of Tuebingen, Germany (1991) and a PhD degree in Behavioural Biology (1998) from the German Primate Center, Goettingen and the University of Tuebingen. He then obtained an MSc equivalent in Biostatistics (1999) from the German Section of the International Biometrical Society and worked since then as a data scientist in Behavioural biology and psychiatry. He established and organized the 1st UK  “Prediction modelling in psychiatric research” (UK-PMPR) workshop in London in 2016. His interest is applying statistical and machine learning methods to build robust prediction models of prognosis and of differential treatment success of psychiatric patients. He is also interested in improving the methodology to identify predictors, mediators and moderators of prediction and causal models and to develop methodologies of handling missing outcome data in medical data sets. 

Daniel Stamate leads the team of the Data Science & Soft Computing Lab, and conducts his research work as a Computer Science academic in the Department of Computing at Goldsmiths College, University of London. He is also a Data Analytics consultant, and often acts as a Data Science panel expert and speaker in top events of the FinTech sector (e.g. FIMA Europe etc). Daniel got a BSc and MSc degree in Computer Science & Mathematics from University of Iasi, and a PhD in Computer Science from University of Paris-Sud, Orsay, at LRI Laboratory for Research in Computer Science.  His team at the Data Science & Soft Computing Lab in London develops fundamental and applicative research in Machine and Statistical Learning, in particular in Sentiment Analysis & Stock Market Prediction, Behavioural Finance, and in Prediction Modelling Approaches to Medical Data Mining  – collaborating in particular in Data-driven Computational Psychiatry research with Institute of Psychiatry, Psychology and Neuroscience London and with the Department of Psychiatry and Neuropsychology at Maastricht University Medical Centre, and in Predicting Risk of Dementia with Machine Learning, with the School of Health Sciences at University of Manchester. Daniel established and runs one of the first cutting edge Data Science MSc programmes in UK at Goldsmiths, University of London.  He serves in the programme committee of several Computer Science conferences, and is a member of the Editorial Board of the Journal of Multiple-Valued Logic and Soft Computing.

Keynote Speaker (TBC)

Prof. Fionn Murtagh, Director of the Centre for Mathematics and Data Science, University of Huddersfield, UK

Program Committee Members

Prof. Fionn Murtagh, Centre for Mathematics and Data Science, University of Huddersfield, UK

Dr. Sinan Guloksuz, Dep. of Psychiatry and Neuropsychology, Maastricht University Medical Centre, the Netherlands, Dep. of Psychiatry, Yale School of Medicine, USA, and Data Science & Soft Computing Lab, UK

Dr. Raquel Iniesta, Dep. of Biostatistics and Health Informatics, King’s College London, UK

Dr. Danielle Belgrave,  Microsoft Research Cambridge, and Dep. of Medicine, Imperial College London, UK

Dr. David Reeves, Division of Population Health, Health Services Research & Primary Care, University of Manchester, UK

Prof. Evan Kontopantelis, Division of Population Health, Health Services Research & Primary Care, University of Manchester, UK

Prof. Richard Emsley,  Dep. of Biostatistics and Health Informatics, King’s College London, UK

Dr. Taposhri Ganguly, Data Science & Soft Computing Lab, UK

Dr. Mattias Pierce,  Division of Population Health, Health Services Research & Primary Care, University of Manchester, UK

Dr. Cedric Ginestet, Dep. of Biostatistics and Health Informatics, King's College London, UK

Dr. Erik J. Linstead, Schmid College of Science and Technology, Chapman University, USA

Prof. Alexander Zamyatin, Faculty of Informatics , National Research Tomsk State University, Russia, and Data Science & Soft Computing Lab, UK

Dr. Yuelin Li, Departments of Epidemiology and Biostatistics and Psychiatry & Behavioral Sciences, Memorial Sloan Kettering Cancer Center, New York, USA