ABSTRACT
Suicide has been considered as an important public health issue for a very long time, and is one of the main causes of death worldwide. Despite suicide prevention strategies being applied, the rate of suicide has not changed substantially over the past decades. Advances in machine learning make it possible to attempt to predict suicide based on the analysis of relevant data to inform clinical practice. This paper reports on findings from the analysis of data of patients who died by suicide in the period 2013-2016 and made use of both structured data and free-text medical notes. We focus on examining various text-mining approaches to support risk assessment. The results show that using advance machine learning and text-mining techniques, it is possible to predict within a specified period which people are most at risk of taking their own life at the time of referral to a mental health service.
- Marios Adamou, Grigoris Antoniou, Elissavet Greasidou, Vincenzo Lagani, Paulos Charonyktakis, Ioannis Tsamardinos, and Michael Doyle. {n. d.}. Towards Automatic Risk Assessment to Support Suicide Prevention. ({n. d.}). (to appear).Google Scholar
- Steven Bird, Ewan Klein, and Edward Loper. 2009. Natural language processing with Python: analyzing text with the natural language toolkit. " O'Reilly Media, Inc.". Google ScholarDigital Library
- David M Blei, Andrew Y Ng, and Michael I Jordan. 2003. Latent dirichlet allocation. Journal of machine Learning research 3, Jan (2003), 993--1022. Google ScholarDigital Library
- Giorgos Borboudakis, Taxiarchis Stergiannakos, Maria Frysali, Emmanuel Klontzas, Ioannis Tsamardinos, and George E Froudakis. 2017. Chemically intuited, large-scale screening of MOFs by machine learning techniques. npj Computational Materials 3, 1 (2017), 40.Google Scholar
- Bernhard E Boser, Isabelle M Guyon, and Vladimir N Vapnik. 1992. A training algorithm for optimal margin classifiers. In Proceedings of the fifth annual workshop on Computational learning theory. ACM, 144--152. Google ScholarDigital Library
- Leo Breiman. 2001. Random forests. Machine learning 45, 1 (2001), 5--32. Google ScholarDigital Library
- Leo Breiman, JH Friedman, Richard A Olshen, and Charles J Stone. 1984. Classification and Regression Trees. Wadsworth (1984).Google Scholar
- Gregory Carter, Allison Milner, Katie McGill, Jane Pirkis, Navneet Kapur, and Matthew J Spittal. 2017. Predicting suicidal behaviours using clinical instruments: systematic review and meta-analysis of positive predictive values for risk scales. The British Journal of Psychiatry (2017), bjp-bp.Google Scholar
- Andrea Fagiolini, Paola Rocca, Serafino De Giorgi, Edoardo Spina, Giovanni Amodeo, and Mario Amore. 2017. Clinical trial methodology to assess the efficacy/effectiveness of long-acting antipsychotics: Randomized controlled trials vs naturalistic studies. Psychiatry research 247 (2017), 257--264.Google Scholar
- National Center for Health Statistics (US et al. 2017. Health, United States, 2016: with chartbook on long-term trends in health. (2017).Google Scholar
- American Foundation for Suicide Prevention. 2017. Suicide Statistics. https://afsp.org/about-suicide/suicide-statistics/. (2017).Google Scholar
- Beth Han, WilsonMCompton, Joseph Gfroerer, and Richard McKeon. 2014. Mental health treatment patterns among adults with recent suicide attempts in the United States. American journal of public health 104, 12 (2014), 2359--2368.Google Scholar
- Arthur E Hoerl and Robert W Kennard. 1970. Ridge regression: Biased estimation for nonorthogonal problems. Technometrics 12, 1 (1970), 55--67.Google ScholarCross Ref
- Jeffrey Hyman, Robert Ireland, Lucinda Frost, and Linda Cottrell. 2012. Suicide incidence and risk factors in an active duty US military population. American journal of public health 102, S1 (2012), S138-S146.Google Scholar
- Ronald C Kessler, LTC Christopher H Warner, LTC Christopher Ivany, Maria V Petukhova, Sherri Rose, Evelyn J Bromet, LTC Millard Brown III, Tianxi Cai, Lisa J Colpe, Kenneth L Cox, et al. 2015. Predicting US Army suicides after hospitalizations with psychiatric diagnoses in the Army Study to Assess Risk and Resilience in Servicemembers (Army STARRS). JAMA psychiatry 72, 1 (2015), 49.Google Scholar
- Ron Kohavi et al. 1995. A study of cross-validation and bootstrap for accuracy estimation and model selection. In Ijcai, Vol. 14. Montreal, Canada, 1137--1145. Google ScholarDigital Library
- Vincenzo Lagani, Giorgos Athineou, Alessio Farcomeni, Michail Tsagris, and Ioannis Tsamardinos. 2016. Feature selection with the r package mxm: Discovering statistically-equivalent feature subsets. arXiv preprint arXiv: 1611.03227 (2016).Google Scholar
- Vincenzo Lagani, Giorgos Athineou, Alessio Farcomeni, Michail Tsagris, Ioannis Tsamardinos, et al. 2017. Feature Selection with the R Package MXM: Discovering Statistically Equivalent Feature Subsets. Journal of Statistical Software 80, i07 (2017).Google ScholarCross Ref
- Andrew Kachites McCallum. 2002. Mallet: A machine learning for language toolkit. (2002).Google Scholar
- House of Commons Health Committee. 2017. Suicide prevention: Sixth Report. (2017).Google Scholar
- Georgia Orfanoudaki, Maria Markaki, Katerina Chatzi, Ioannis Tsamardinos, and Anastassios Economou. 2017. MatureP: prediction of secreted proteins with exclusive information from their mature regions. Scientific reports 7, 1 (2017), 3263.Google Scholar
- Fabian Pedregosa, Gaël Varoquaux, Alexandre Gramfort, Vincent Michel, Bertrand Thirion, Olivier Grisel, Mathieu Blondel, Peter Prettenhofer, Ron Weiss, Vincent Dubourg, et al. 2011. Scikit-learn: Machine learning in Python. Journal of machine learning research 12, Oct (2011), 2825--2830. Google ScholarDigital Library
- Chris Poulin, Brian Shiner, Paul Thompson, Linas Vepstas, Yinong Young-Xu, Benjamin Goertzel, Bradley Watts, Laura Flashman, and Thomas McAllister. 2014. Predicting the risk of suicide by analyzing the text of clinical notes. PloS one 9, 1 (2014), e85733.Google ScholarCross Ref
- Pooja Saini, David While, Khatidja Chantler, Kirsten Windfuhr, and Navneet Kapur. 2014. Assessment and management of suicide risk in primary care. Crisis: The Journal of Crisis Intervention and Suicide Prevention 35, 6 (2014), 415.Google ScholarCross Ref
- G Salton andMJ McGill. 1983. Introduction to modern information Philadelphia, PA. American Association for Artificial Intelligence retrieval. (1983). Google ScholarDigital Library
- Olympia Simantiraki, Paulos Charonyktakis, Anastasia Pampouchidou, Manolis Tsiknakis, and Martin Cooke. 2017. Glottal Source Features for Automatic Speech-based Depression Assessment. Proc. Interspeech 2017 (2017), 2700--2704.Google ScholarCross Ref
- Karen Sparck Jones. 1972. A statistical interpretation of term specificity and its application in retrieval. Journal of documentation 28, 1 (1972), 11--21.Google ScholarCross Ref
- Ioannis Tsamardinos, Elissavet Greasidou, and Giorgos Borboudakis. {n. d.}. Bootstrapping the Out-of-sample Predictions for Efficient and Accurate Cross-Validation. Machine Learning ({n. d.}). to appear.Google Scholar
- Ioannis Tsamardinos, Amin Rakhshani, and Vincenzo Lagani. 2015. Performance-estimation properties of cross-validation-based protocols with simultaneous hyper-parameter optimization. International Journal on Artificial Intelligence Tools 24, 05 (2015), 1540023.Google ScholarCross Ref
- Sudhir Varma and Richard Simon. 2006. Bias in error estimation when using cross-validation for model selection. BMC bioinformatics 7, 1 (2006), 91.Google Scholar
- Colin G Walsh, Jessica D Ribeiro, and Joseph C Franklin. 2017. Predicting risk of suicide attempts over time through machine learning. Clinical Psychological Science 5, 3 (2017), 457--469.Google ScholarCross Ref
- Eric Youngstrom, Oren Meyers, Jennifer Kogos Youngstrom, Joseph R Calabrese, and Robert L Findling. 2006. Comparing the effects of sampling designs on the diagnostic accuracy of eight promising screening algorithms for pediatric bipolar disorder. Biological Psychiatry 60, 9 (2006), 1013--1019.Google ScholarCross Ref
- Eric A Youngstrom. 2013. A primer on receiver operating characteristic analysis and diagnostic efficiency statistics for pediatric psychology: we are ready to ROC. Journal of pediatric psychology 39, 2 (2013), 204--221.Google ScholarCross Ref
Index Terms
- Mining Free-Text Medical Notes for Suicide Risk Assessment
Recommendations
Identification of Imminent Suicide Risk Among Young Adults using Text Messages
CHI '18: Proceedings of the 2018 CHI Conference on Human Factors in Computing SystemsSuicide is the second leading cause of death among young adults but the challenges of preventing suicide are significant because the signs often seem invisible. Research has shown that clinicians are not able to reliably predict when someone is at ...
Automatically estimating the incidence of symptoms recorded in GP free text notes
MIXHS '11: Proceedings of the first international workshop on Managing interoperability and complexity in health systemsThe UK General Practice Research Database (GPRD) is a valuable source of information for health services research. It contains coded data supplemented by free text (physicians' notes and letters). However, due to the difficulty of extracting useful ...
Text Mining Applied to Electronic Medical Records: A Literature Review
The analysis of medical records is a major challenge, considering they are generally presented in plain text, have a very specific technical vocabulary and are nearly always unstructured. It is an interdisciplinary work that requires knowledge from ...
Comments