Professional Documents
Culture Documents
Mark E. Larsen, Nicholas Cummins, Tjeerd W. Boonstra, Bridianne O’Dea, Joe Tighe, Jennifer
Nicholas, Fiona Shand, Julien Epps, and Helen Christensen
7317
Figure 3 – A comparison of spectrograms showing four repetitions of B. ibobbly
the phrase ‘PATAKA’ for an individual in a normal mood state (top)
and very severe depressed state (bottom). Low energy regions are Although there is a general lack of evidence-based,
darker, high energy regions are lighter. Notice the lack of sustained interactive apps currently publicly available, this situation is
energy in the 1kHz and 3kHz regions in the very severe example. changing. One example of an innovative suicide prevention
Figure reproduced from [24]. app is ibobbly, which was designed to reduce the suicide rate
amongst young Aboriginal Australians [29]. This is a
particularly high-risk group, in which the suicide rate is four
times higher than the non-Indigenous population, and one
which has a high rate of adoption of smartphones and social
media use [30].
The ibobbly app was designed with extensive
consultation with the local community, and in a culturally-
relevant manner. The app is based on proven Acceptance and
Commitment Therapy, but presented in a highly graphical
form (see Fig. 4) with artwork by local Aboriginal artists. It
also incorporates audio playback of the text components, to
aid accessibility in a population with various levels of
English literacy. Self-reported data were collected through
the app using custom measures and standard
Research into links between changes in suicide risk and psychometrically validated measures of depression, distress,
changes in paralinguistic cues is still in its infancy. Many suicidality, and impulsiveness. The ibobbly app has been
results have been found in small datasets recorded under non- piloted in a randomised controlled trial in eight communities
ideal conditions, raising issues relating to their validity and in the Kimberley region of Western Australia and the results
generalisability. However they show future speech research will be available shortly.
can potentially yield a simple, low cost, automated, and
Figure 4 – Screenshot from one of the ibobbly modules.
objective crisis detection aid.
III. INTERVENTIONS
Following the identification of a potentially suicidal
individual, effective interventions are required in order to
manage the crisis situation. The screening methods identified
above are still in development and have not yet been
incorporated into an intervention, however, they are all well-
suited to incorporation into mobile applications (apps). Apps
provide a flexible platform from which a variety of
intervention strategies can be employed – including public
health and mental health techniques.
IV. DISCUSSION
A. Review of Mobile Apps
The field of suicide prevention is a relatively new
Mobile apps are a popular way of accessing health application for the engineering community. Nevertheless,
information and resources, despite a lack of evidence for
advancements are being made in multiple modes of
publicly available apps across a spectrum of mental health
disorders [28]. As there is no clear link between research and screening individuals who may be at risk, and the detection
public implementation, we have conducted a review to assess of possible suicidal crisis – we have described detection
whether existing apps for suicide prevention are consistent through passive sensor data collection, analysis of social
with established evidence-based practice. media content, and paralinguistic processing of speech.
Mobile apps are being used as a convenient platform for the
The review identified 123 apps from the iTunes and
Google Play app stores which were related to suicide. Of delivery of suicide prevention programs, and will be
these 123 apps, 12 (9.8%) contained potentially harmful enhanced by the incorporation of these novel screening
content which may encourage self-harming or suicidal techniques, for example in the use of adaptive interventions
behaviours. Exhaustive testing of the apps was not part of the in response to these measures.
review process, however 31 (25.2%) of the apps exhibited Developing tools for suicide prevention remains a
obvious bugs or reliability issues, excluding those related to challenge. It is a difficult population to access, and one
general usability. Despite the potential for apps to provide an which requires a high degree of sensitivity. Best practice for
interactive experience for users and to harness data from responding to an automatic indicator of suicidality is not yet
various sensors, only 54 (43.9%) of the apps offered any clear [31], and the expectations of privacy and the
interactive features beyond the passive consumption of, or
implications of false positives must be addressed. Ensuring
navigation through, content. Mapping individual components
of these apps to the evidence base is currently underway. appropriate safeguards and community consultation are
crucial to facilitating this important research topic.
Expanding the scope and availability of suicide prevention
7318
programs and translation into wider practice requires [13] M. Burke, C. Marlow, and T. Lento, "Social Network Activity
and Social Well-Being," Chi2010: Proceedings of the 28th
community and clinical engagement, as well as Annual Chi Conference on Human Factors in Computing
technological innovation and advancements, and engineering Systems, Vols 1-4, pp. 1909-1912, 2010.
skills will be a key component in this interdisciplinary field. [14] M. Larsen, T. Boonstra, P. Batterham, B. O'Dea, C. Paris, and H.
Christensen, "We Feel: Mapping emotion on Twitter," IEEE J
Biomed Health Inform, In press 2015.
ACKNOWLEDGMENT [15] Samaritans. (2014). Samaritans Launches Twitter App To Help
Identify Vulnerable People. Available:
M.E.L., T.W.B. and H.C. thank the staff and students at
http://www.samaritans.org/news/samaritans-launches-twitter-
the Black Dog Institute who participated in the pilot of the app-help-identify-vulnerable-people
social connectivity project. N.C. and J.E. thank National ICT [16] Facebook. (2015). Facebook Safety. Available:
Australia who support their work. B.O. and H.C. https://www.facebook.com/fbsafety/posts/817724748265365
[17] B. O'Dea, S. Wan, P. J. Batterham, A. L. Calear, C. Paris, and H.
acknowledge the efforts of Dr. Cecile Paris, Dr. Stephen Christensen, "Detecting suicidality on Twitter," Internet
Wan, Dr. David Milne (CSIRO) as well as Dr. Philip J Interventions, vol. 2, pp. 183-188, 2015.
Batterham and Dr. Alison L Calear (National Institute for [18] H. Hendin, J. T. Maltsberger, A. Lipschitz, A. P. Haas, and J.
Kyle, "Recognizing and responding to a suicide crisis," Ann N Y
Mental Health Research) who significantly contributed to Acad Sci, vol. 932, pp. 169-86; discussion 186-7, Apr 2001.
the ‘Detecting Suicidality on Twitter’ project. J.T., F.S. and [19] R. W. Maris, "Suicide," Lancet, vol. 360, pp. 319-26, Jul 27
H.C. thank Alive and Kicking Goals Suicide Prevention 2002.
[20] N. Cummins, S. Scherer, J. Krajewski, S. Schnieder, J. Epps,
Program (WA), the Young and Well Cooperative Research and T. Quatieri, "A Review of Depression and Suicide Risk
Centre, HITnet Innovations, Thought Works, Muru Marri Assessment using Speech Analysis," Speech Communication (In
Indigenous Health Unit UNSW, Kimberley Aboriginal Press), 2015.
[21] V. Sethu, J. Epps, and E. Ambikairajah, "Speech based emotion
community members, Men’s Outreach Service (WA), recognition," in Speech and audio processing for coding
Aboriginal Artists – Martha Lee, Danica Manado and Esah enhancement and recognition, T. Ogunfunmi, R. Togneri, and
Coffin, Nyamba Buru Yawuru Aboriginal Corporation, M. Narasimhai, Eds., ed New York: Springer, 2014, pp. 197-
Rubibi (Broome, WA), Goolarri Media (WA), Dr Kathy 228.
[22] Z. N. Karam, E. M. Provost, S. Singh, J. Montgomery, C.
McKay, BackTrack (NSW) and Samsung for their help and Archer, G. Harrington, et al., "Ecologically Valid Long-Term
support in the ibobbly study. Mood Monitoring of Individuals with Bipolar Disorder Using
Speech," 2014 IEEE International Conference on Acoustics,
Speech and Signal Processing (ICASSP), 2014.
REFERENCES [23] Mental Health America. Suicide. Available:
[1] World Health Organization, "Disease and injury regional http://www.mentalhealthamerica.net/suicide
mortality estimates, 2000–2012," 2012. [24] N. Cummins, J. Epps, V. Sethu, M. Breakspear, and R. Goecke,
[2] Australian Bureau of Statistics, "3303.0 - Causes of Death, "Modeling spectral variability for the classification of depressed
Australia, 2013," 2015. speech," in 14th Annual Conference of the International Speech
[3] Suicide Prevention Australia, "Overcoming the stigma of Communication Association, INTERSPEECH 2013, August 25,
suicide," 2010. 2013 - August 29, 2013, Lyon, France, 2013, pp. 857-861.
[4] D. J. France, R. G. Shiavi, S. Silverman, M. Silverman, and D. [25] N. W. Hashim, M. Wilkes, R. Salomon, and J. Meggs, "Analysis
M. Wilkes, "Acoustical properties of speech as indicators of of Timing Pattern of Speech as Possible Indicator for Near-Term
depression and suicidal risk," IEEE Trans Biomed Eng, vol. 47, Suicidal Risk and Depression in Male Patients," in 2012
pp. 829-37, Jul 2000. International Conference on Conference on Signal Processing
[5] A. Ozdas, R. G. Shiavi, S. E. Silverman, M. K. Silverman, and Systems (ICSPS 2012), 2012, pp. 6-13.
D. M. Wilkes, "Investigation of vocal jitter and glottal flow [26] T. Yingthawornsuk, H. Kaymaz Keskinpala, D. M. Wilkes, R.
spectrum as possible cues for depression and near-term suicidal G. Shiavi, and R. M. Salomon, "Direct acoustic feature using
risk," IEEE Trans Biomed Eng, vol. 51, pp. 1530-40, Sep 2004. iterative EM algorithm and spectral energy for classifying
[6] IEEE Engineering in Medicine & Biology Society, "IEEE suicidal speech," in 8th Annual Conference of the International
EMBS Code of Ethics." Speech Communication Association, Interspeech 2007, August
[7] P. A. Nutting, L. M. Dickinson, L. V. Rubenstein, R. D. Keeley, 27, 2007 - August 31, 2007, Antwerp, Belgium, 2007, pp. 749-
J. L. Smith, and C. E. Elliott, "Improving detection of suicidal 752.
ideation among depressed patients in primary care," Ann Fam [27] S. Scherer, J. Pestian, and L.-P. Morency, "Investigating the
Med, vol. 3, pp. 529-36, Nov-Dec 2005. speech characteristics of suicidal adolescents," in 2013 38th
[8] J. J. Mann, A. Apter, J. Bertolote, A. Beautrais, D. Currier, A. IEEE International Conference on Acoustics, Speech, and Signal
Haas, et al., "Suicide prevention strategies: a systematic review," Processing, ICASSP 2013, May 26, 2013 - May 31, 2013,
JAMA, vol. 294, pp. 2064-74, Oct 26 2005. Vancouver, BC, Canada, 2013, pp. 709-713.
[9] K. A. Van Orden, T. K. Witte, K. C. Cukrowicz, S. R. [28] T. Donker, K. Petrie, J. Proudfoot, J. Clarke, M. R. Birch, and H.
Braithwaite, E. A. Selby, and T. E. Joiner, Jr., "The interpersonal Christensen, "Smartphones for smarter delivery of mental health
theory of suicide," Psychol Rev, vol. 117, pp. 575-600, Apr programs: a systematic review," J Med Internet Res, vol. 15, p.
2010. e247, 2013.
[10] N. Eagle, A. S. Pentland, and D. Lazer, "Inferring friendship [29] Black Dog Institute. (2015). Overview of the iBobbly trial.
network structure by using mobile phone data," Proc Natl Acad Available: http://digitaldog.org.au/programs/ibobbly-black-dog-
Sci U S A, vol. 106, pp. 15274-8, Sep 8 2009. institute/
[11] J. N. Rosenquist, J. H. Fowler, and N. A. Christakis, "Social [30] T. Callinan. (2014). Remote Indigenous Australians rely on
network determinants of depression," Mol Psychiatry, vol. 16, Facebook to stay in touch. Available:
pp. 273-81, Mar 2011. http://www.sbs.com.au/news/article/2014/08/26/remote-
[12] M. C. Pachucki, E. J. Ozer, A. Barrat, and C. Cattuto, "Mental indigenous-australians-rely-facebook-stay-touch
health and social networks in early adolescence: a dynamic study [31] N. Lee, "Trouble on the radar," Lancet, vol. 384, p. 1917, 2014.
of objectively-measured social interaction behaviors," Soc Sci
Med, vol. 125, pp. 40-50, Jan 2015.
7319