Text Classification to Inform Suicide Risk Assessment in Electronic Health Records

被引:12
作者
Bittar, Andre [1 ]
Velupillai, Sumithra [1 ,2 ]
Roberts, Angus [1 ]
Dutta, Rina [1 ,3 ]
机构
[1] Kings Coll London, Inst Psychiat Psychol & Neurosci, London, England
[2] KTH, Sch Elect Engn & Comp Sci, Stockholm, Sweden
[3] South London & Maudsley NHS Fdn Trust, London, England
来源
MEDINFO 2019: HEALTH AND WELLBEING E-NETWORKS FOR ALL | 2019年 / 264卷
基金
瑞典研究理事会;
关键词
Suicide; Risk Assessment; Natural Language Processing;
D O I
10.3233/SHTI190179
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Assessing a patient's risk of an impending suicide attempt has been hampered by limited information about dynamic factors that change rapidly in the days leading up to an attempt. The storage of patient data in electronic health records (EHRs) has facilitated population-level risk assessment studies using machine learning techniques. Until recently, most such work has used only structured EHR data and excluded the unstructured text of clinical notes. In this article, we describe our experiments on suicide risk assessment, modelling the problem as a classification task. Given the wealth of text data in mental health EHRs, we aimed to assess the impact of using this data in distinguishing periods prior to a suicide attempt from those not preceding such an attempt. We compare three different feature sets, one structured and two text-based, and show that inclusion of text features significantly improves classification accuracy in suicide risk assessment.
引用
收藏
页码:40 / 44
页数:5
相关论文
共 28 条
[1]  
AGUILAR EJ, 2009, J CLIN PSYCHIAT, P95
[2]  
Fernándes AA, 2018, REV CHIL ESTUD MEDIE, P8
[3]  
[Anonymous], 1985, Matrix Analysis
[4]  
[Anonymous], 2018, ASSESSMENT CLIN RISK
[5]   Predicting Suicidal Behavior From Longitudinal Electronic Health Records [J].
Barak-Corren, Yuval ;
Castro, Victor M. ;
Javitt, Solomon ;
Hoffnagle, Alison G. ;
Dai, Yael ;
Perlis, Roy H. ;
Nock, Matthew K. ;
Smoller, Jordan W. ;
Reis, Ben Y. .
AMERICAN JOURNAL OF PSYCHIATRY, 2017, 174 (02) :154-162
[6]   Text Mining the EMR for Modeling and Predicting Suicidal Behavior Among US Veterans of the 1991 Persian Gulf War [J].
Ben-Ari, Alon ;
Hammond, Kenric .
2015 48TH HAWAII INTERNATIONAL CONFERENCE ON SYSTEM SCIENCES (HICSS), 2015, :3168-U2073
[7]  
Bhat H.S., 2017, ARXIV171110057CSSTAT
[8]  
Chinchor N., 1992, P 4 C MESS UND MUC4, P8
[9]  
CORTES C, 1995, MACH LEARN, V20, P273, DOI 10.1023/A:1022627411411
[10]  
Downs Johnny, 2017, AMIA Annu Symp Proc, V2017, P641