Event: Suicide detection and prevention using mobile technology, social media and informatics

Date: Monday 12 December, 2016

Time: 1100 - 1230

Location: Henry Wellcome Building, Seminar Room, Institute of Psychiatry, Psychology & Neuroscience, 16 De Crespigny Park, London SE5 8AF

We are delighted to be hosting a visit from Professor Helen Christensen (Black Dog Institute, Australia) and Professor Svetha Venkatesh (Deakin University, Australia) who will be describing the use of mobile technology and social media to help detect and prevent suicide.  Refreshments will be served from 10:30am.

1100: Detect and Deliver - Professor Helen Christensen, Director & Chief Scientist of the Black Dog Institute at the University of New South Wales, Australia

Mental health problems are pervasive, costly and potentially deadly. Less than 50% of those with a disorder seek help. We have no useful biological markers of suicide risk - nor indeed of any mental illness - and prospects of finding any are poor. Most suicides are unheralded. The problem is exacerbated because young people do not seek help, prodromal signs of mental health distress are often invisible or masked, leaving parents, workmates and friends unaware. For 40% who die by suicide, no indication of previous self-harm was present. This presentation examines the potential of smartphone technology, social media and big data to detect suicide and mental health risk and to deliver when-needed timely interventions. We examine research from our lab looking at blogs, twitter, voice, and Bluetooth captured social networks. We review the research findings supporting the use of automated online programs and apps for suicide prevention.

1145: Beyond data: delivering efficiencies in health care and pervasive systems - Professor Svetha Venkatesh, Alfred Deakin Professor, Director Centre for Pattern Recognition and Data Analytics, Deakin University, Australia

Data is compelling, seducing us to believe that analysis will always empower us. But this is often not true. Particularly, when events are rare or predictions are poor. This talk considers what to do when confronted with failures with current data or analysis by addressing two main questions:

1.  What to do when current predictions for rare events are poor? Instead of focusing on rare event classification, for example, suicide prediction, we focus on identifying the riskiest events with minimal error. Such events are likely precursors to outliers of interest. We demonstrate our results through outlier detection in surveillance (leading to our start-up company iCetana, Australia) and in suicide risk prediction (implemented in Barwon Health, Geelong, Australia). We discuss the challenges in data modeling, pitfalls and our outcomes.

2.  How can we use new sensors as they emerge? Our current focus is to monitor people through social media ‘in the wild’. We track mental health and mood stability of users, and detect deviations from norm. We report results in our joint work with the Black Dog Institute, Australia.

Professor Helen Christensen is Director & Chief Scientist of the Black Dog Institute at the University of New South Wales. She is an international leader in the use of technology to both detect poor mental health and to deliver quality evidence-based therapies. Her current research focuses on the effective integration of websites, apps, sensors, social media and Smartphone tools into large-scale prevention and intervention programs for anxiety, depression and suicide. Professor Christensen is also a vocal advocate for evidence informed policy to improve universal access to quality mental health care.

Svetha Venkatesh is Alfred Deakin Professor and Director of Centre for Pattern Recognition and Data Analytics (PRaDA) at Deakin University, Australia. She has developed frontier technologies in large-scale pattern recognition which is reflected by full patents (3) and publications (529) as well highly novel outcomes, that include 3 start-up companies (Icetana.com, Virtual observer.com, iHosp) and a significant product (TOBY). Her current research interests are in large scale data mining problems in diverse domains including healthcare and in developing the new science of lean data. She was elected a Fellow of the International Association of Pattern Recognition in 2004 for contributions to formulation and extraction of semantics in multimedia data, and a Fellow of the Australian Academy of Technological Sciences and Engineering in 2006.