Automated assessment of patients' self-narratives for posttraumatic stress disorder screening using natural language processing and text mining

Research output: Contribution to journalArticleAcademicpeer-review

7 Citations (Scopus)

Abstract

Patients’ narratives about traumatic experiences and symptoms are useful in clinical screening and diagnostic procedures. In this study, we presented an automated assessment system to screen patients for posttraumatic stress disorder via a natural language processing and text-mining approach. Four machine-learning algorithms—including decision tree, naive Bayes, support vector machine, and an alternative classification approach called the product score model—were used in combination with n-gram representation models to identify patterns between verbal features in self-narratives and psychiatric diagnoses. With our sample, the product score model with unigrams attained the highest prediction accuracy when compared with practitioners’ diagnoses. The addition of multigrams contributed most to balancing the metrics of sensitivity and specificity. This article also demonstrates that text mining is a promising approach for analyzing patients’ self-expression behavior, thus helping clinicians identify potential patients from an early stage.
Original languageEnglish
Pages (from-to)157-172
Number of pages16
JournalAssessment
Volume24
Issue number2
DOIs
Publication statusPublished - 2017

Fingerprint

Natural Language Processing
Data Mining
Post-Traumatic Stress Disorders
Helping Behavior
Decision Trees
Mental Disorders
Sensitivity and Specificity

Keywords

  • IR-97201
  • METIS-311742

Cite this

@article{38266f816bc94482b906c8958b6c8625,
title = "Automated assessment of patients' self-narratives for posttraumatic stress disorder screening using natural language processing and text mining",
abstract = "Patients’ narratives about traumatic experiences and symptoms are useful in clinical screening and diagnostic procedures. In this study, we presented an automated assessment system to screen patients for posttraumatic stress disorder via a natural language processing and text-mining approach. Four machine-learning algorithms—including decision tree, naive Bayes, support vector machine, and an alternative classification approach called the product score model—were used in combination with n-gram representation models to identify patterns between verbal features in self-narratives and psychiatric diagnoses. With our sample, the product score model with unigrams attained the highest prediction accuracy when compared with practitioners’ diagnoses. The addition of multigrams contributed most to balancing the metrics of sensitivity and specificity. This article also demonstrates that text mining is a promising approach for analyzing patients’ self-expression behavior, thus helping clinicians identify potential patients from an early stage.",
keywords = "IR-97201, METIS-311742",
author = "Qiwei He and Veldkamp, {Bernard P.} and Glas, {Cornelis A.W.} and {de Vries}, Theo",
year = "2017",
doi = "10.1177/1073191115602551",
language = "English",
volume = "24",
pages = "157--172",
journal = "Assessment",
issn = "1073-1911",
publisher = "SAGE Publications",
number = "2",

}

TY - JOUR

T1 - Automated assessment of patients' self-narratives for posttraumatic stress disorder screening using natural language processing and text mining

AU - He, Qiwei

AU - Veldkamp, Bernard P.

AU - Glas, Cornelis A.W.

AU - de Vries, Theo

PY - 2017

Y1 - 2017

N2 - Patients’ narratives about traumatic experiences and symptoms are useful in clinical screening and diagnostic procedures. In this study, we presented an automated assessment system to screen patients for posttraumatic stress disorder via a natural language processing and text-mining approach. Four machine-learning algorithms—including decision tree, naive Bayes, support vector machine, and an alternative classification approach called the product score model—were used in combination with n-gram representation models to identify patterns between verbal features in self-narratives and psychiatric diagnoses. With our sample, the product score model with unigrams attained the highest prediction accuracy when compared with practitioners’ diagnoses. The addition of multigrams contributed most to balancing the metrics of sensitivity and specificity. This article also demonstrates that text mining is a promising approach for analyzing patients’ self-expression behavior, thus helping clinicians identify potential patients from an early stage.

AB - Patients’ narratives about traumatic experiences and symptoms are useful in clinical screening and diagnostic procedures. In this study, we presented an automated assessment system to screen patients for posttraumatic stress disorder via a natural language processing and text-mining approach. Four machine-learning algorithms—including decision tree, naive Bayes, support vector machine, and an alternative classification approach called the product score model—were used in combination with n-gram representation models to identify patterns between verbal features in self-narratives and psychiatric diagnoses. With our sample, the product score model with unigrams attained the highest prediction accuracy when compared with practitioners’ diagnoses. The addition of multigrams contributed most to balancing the metrics of sensitivity and specificity. This article also demonstrates that text mining is a promising approach for analyzing patients’ self-expression behavior, thus helping clinicians identify potential patients from an early stage.

KW - IR-97201

KW - METIS-311742

U2 - 10.1177/1073191115602551

DO - 10.1177/1073191115602551

M3 - Article

VL - 24

SP - 157

EP - 172

JO - Assessment

JF - Assessment

SN - 1073-1911

IS - 2

ER -