Use of emergency department electronic medical records for automated epidemiological surveillance of suicide attempts: a French pilot study

The aim of this study was to determine whether an expert system based on automated processing of electronic health records (EHRs) could provide a more accurate estimate of the annual rate of emergency department (ED) visits for suicide attempts in France, as compared to the current national surveillance system based on manual coding by emergency practitioners. A feasibility study was conducted at Lyon University Hospital, using data for all ED patient visits in 2012. After automatic data extraction and pre‐processing, including automatic coding of medical free‐text through use of the Unified Medical Language System, seven different machine‐learning methods were used to classify the reasons for ED visits into “suicide attempts“ versus “other reasons“. The performance of these different methods was compared by using the F‐measure. In a test sample of 444 patients admitted to the ED in 2012 (98 suicide attempts, 48 cases of suicidal ideation, and 292 controls with no recorded non‐fatal suicidal behaviour), the F‐measure for automatic detection of suicide attempts ranged from 70.4% to 95.3%. The random forest and naïve Bayes methods performed best. This study demonstrates that machine‐learning methods can improve the quality of epidemiological indicators as compared to current national surveillance of suicide attempts.

[1]  Stéfan Jacques Darmoni,et al.  Natural Language Processing to Detect Risk Patterns Related to Hospital Acquired Infections , 2009, BiomedicalIE@RANLP.

[2]  Yvonne Vergouwe,et al.  Bmc Medical Research Methodology Open Access Advantages of the Nested Case-control Design in Diagnostic Research , 2022 .

[3]  Paul E. Utgoff,et al.  Incremental Learning , 2017, Encyclopedia of Machine Learning and Data Mining.

[4]  N. Japkowicz.  Learning from Imbalanced Data Sets: A Comparison of Various Strategies * , 2000 .

[5]  Nitesh V. Chawla,et al.  Data Mining for Imbalanced Datasets: An Overview , 2005, The Data Mining and Knowledge Discovery Handbook.

[6]  Min Li,et al.  A knowledge discovery and reuse pipeline for information extraction in clinical notes , 2011, J. Am. Medical Informatics Assoc..

[7]  Stéfan Jacques Darmoni,et al.  Evaluation of natural language processing from emergency department computerized medical records for intra-hospital syndromic surveillance , 2011, BMC Medical Informatics Decis. Mak..

[8]  J. Pathak,et al.  Electronic health records-driven phenotyping: challenges, recent advances, and perspectives. , 2013, Journal of the American Medical Informatics Association : JAMIA.

[9]  Jesús S. Aguilar-Ruiz,et al.  Knowledge discovery from data streams , 2009, Intell. Data Anal..

[10]  Wynne Hsu,et al.  Integrating Classification and Association Rule Mining , 1998, KDD.

[11]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[12]  Christopher G Chute,et al.  Invited commentary: Observational research in the age of the electronic health record. , 2014, American journal of epidemiology.

[13]  Mohammad Imran,et al.  Learning from Imbalanced Data of Diverse Strategies with Investigation , 2015 .

[14]  Marco Scutari,et al.  Learning Bayesian Networks with the bnlearn R Package , 2009, 0908.3817.

[15]  Omolola Ogunyemi,et al.  Evaluating Predictive Modeling's Potential to Improve Teleretinal Screening Participation in Urban Safety Net Clinics , 2013, MedInfo.

[16]  Philippe Courtet,et al.  ALGOS: the development of a randomized controlled trial testing a case management algorithm designed to reduce suicide risk among suicide attempters , 2011, BMC psychiatry.

[17]  J. Lonnqvist,et al.  Parasiticide in Europe: the WHO/EURO multicentre study on parasuicide. I. Introduction and preliminary analysis for 1989 , 1992, Acta psychiatrica Scandinavica.

[18]  E. Baca-García,et al.  SIAM (Suicide intervention assisted by messages): the development of a post-acute crisis text messaging outreach for suicide prevention , 2014, European Psychiatry.

[19]  Scott R. Halgrim,et al.  Using natural language processing to improve efficiency of manual chart abstraction in research: the case of breast cancer recurrence. , 2014, American journal of epidemiology.

[20]  J. de Pina-Cabral,et al.  World , 2004, Science.

[21]  Nancy Chinchor,et al.  MUC-4 evaluation metrics , 1992, MUC.

[22]  Tomasz Imielinski,et al.  Mining association rules between sets of items in large databases , 1993, SIGMOD Conference.

[23]  Lina Fatima Soualmia,et al.  Improving Information Retrieval by Meta-modelling Medical Terminologies , 2011, AIME.

[24]  Kurt Hornik,et al.  Introduction to arules – A computational environment for mining association rules and frequent item sets , 2009 .

[25]  David A. Hanauer,et al.  Enhanced identification of eligibility for depression research using an electronic medical record search engine , 2009, Int. J. Medical Informatics.

[26]  Thierry Durand,et al.  The use of regional platforms for managing electronic health records for the production of regional public health indicators in France , 2012, BMC Medical Informatics and Decision Making.

[27]  N. Tvardik,et al.  Use of Electronic Medical Records of the Emergency Department for an Automated Epidemiological Surveillance of Attempted Suicide: Pilot Study in a French University Hospital. , 2014 .

[28]  Stéfan Jacques Darmoni,et al.  Annotation methods to develop and evaluate an expert system based on natural language processing in electronic medical records , 2015, MedInfo.

[29]  G. Vaiva,et al.  Effect of telephone contact on further suicide attempts in patients discharged from an emergency department: randomised controlled study , 2006, BMJ : British Medical Journal.

[30]  I. Kohane,et al.  A clinical perspective on the relevance of research domain criteria in electronic health records. , 2015, The American journal of psychiatry.

[31]  Alisha R Pollastri,et al.  Validation of electronic health record phenotyping of bipolar disorder cases and controls. , 2015, The American journal of psychiatry.

[32]  Scott R. Halgrim,et al.  Carrell et al. respond to "Observational research and the EHR". , 2014, American journal of epidemiology.

[33]  K. Bretonnel Cohen,et al.  Current issues in biomedical text mining and natural language processing , 2009, J. Biomed. Informatics.

[34]  George Hripcsak,et al.  Next-generation phenotyping of electronic health records , 2012, J. Am. Medical Informatics Assoc..

[35]  Dimitrios I. Fotiadis,et al.  Machine learning applications in cancer prognosis and prediction , 2014, Computational and structural biotechnology journal.

[36]  A. Hoes.  Case-control studies. , 1995, The Netherlands journal of medicine.