Automated Assessment of Patients’ Self-Narratives for Posttraumatic Stress Disorder Screening Using Natural Language Processing and Text Mining

He, Qiwei; Veldkamp, Bernard P.; Glas, Cornelis A.W.; Vries, Theo de

doi:10.1177/1073191115602551

Cited by 60 publications

(57 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…screening) of PTSD is a major public health issue. He et al (He, Veldkamp, Glas, & de Vries, 2017) applied ML techniques to text mining to detect PTSD with excellent accuracy (82%). Text mining refers to a set of computational processes consisting in extracting knowledge according to certain criteria defined in texts, which makes it possible to model data from linguistic theories.…”

Section: Resultsmentioning

confidence: 99%

e-PTSD: an overview on how new technologies can improve prediction and assessment of Posttraumatic Stress Disorder (PTSD)

Bourla

Mouchabac

El‐Hage

et al. 2018

European Journal of Psychotraumatology

View full text Add to dashboard Cite

Background: New technologies may profoundly change our way of understanding psychiatric disorders including posttraumatic stress disorder (PTSD). Imaging and biomarkers, along with technological and medical informatics developments, might provide an answer regarding at-risk patient’s identification. Recent advances in the concept of ‘digital phenotype’, which refers to the capture of characteristics of a psychiatric disorder by computerized measurement tools, is one paradigmatic example. Objective: The impact of the new technologies on health professionals practice in PTSD care remains to be determined. The recent evolutions could disrupt the clinical practices and practitioners in their beliefs, ethics and representations, going as far as questioning their professional culture. In the present paper, we conducted an extensive search to highlight the articles which reflect the potential of these new technologies. Method: We conducted an overview by querying PubMed database with the terms [PTSD] [Posttraumatic stress disorder] AND [Computer] OR [Computerized] OR [Mobile] OR [Automatic] OR [Automated] OR [Machine learning] OR [Sensor] OR [Heart rate variability] OR [HRV] OR [actigraphy] OR [actimetry] OR [digital] OR [motion] OR [temperature] OR [virtual reality]. Results: We summarized the synthesized literature in two categories: prediction and assessment (including diagnostic, screening and monitoring). Two independent reviewers screened, extracted data and quality appraised the sources. Results were synthesized narratively. Conclusions: This overview shows that many studies are underway allowing researchers to start building a PTSD digital phenotype using passive data obtained by biometric sensors. Active data obtained from Ecological Momentary Assessment (EMA) could allow clinicians to assess PTSD patients. The place of connected objects, Artificial Intelligence and remote monitoring of patients with psychiatric pathology remains to be defined. These tools must be explained and adapted to the different profiles of physicians and patients. The involvement of patients, caregivers and health professionals is essential to the design and evaluation of these new tools.

show abstract

Section: Resultsmentioning

confidence: 99%

e-PTSD: an overview on how new technologies can improve prediction and assessment of Posttraumatic Stress Disorder (PTSD)

Bourla

Mouchabac

El‐Hage

et al. 2018

European Journal of Psychotraumatology

View full text Add to dashboard Cite

show abstract

“…To answer the question regarding which actions or mini action sequences (i.e., n -grams) are the key factors that distinguish subgroups, we applied a commonly used tool in natural language processing—the chi-square feature selection model (Oakes et al, 2001)—to identify robust classifiers. The chi-square feature selection model is recommended for use in textual analysis due to its high effectiveness in finding robust keywords and for testing the similarity between different text corpora (e.g., Manning and Schütze, 1999; He et al, 2012, 2014, 2017). The definition of “robust” is different from what is defined in statistics; here, robust features are generally defined as the “best” features with high information gain in natural language processing (Joachims, 1998).…”

Section: Methodsmentioning

confidence: 99%

Mapping Background Variables With Sequential Patterns in Problem-Solving Environments: An Investigation of United States Adults’ Employment Status in PIAAC

Liao

Jiao

2019

Front. Psychol.

Self Cite

View full text Add to dashboard Cite

Adult assessments have evolved to keep pace with the changing nature of adult literacy and learning demands. As the importance of information and communication technologies (ICT) continues to grow, measures of ICT literacy skills, digital reading, and problem-solving in technology-rich environments (PSTRE) are increasingly important topics for exploration through computer-based assessment (CBA). This study used process data collected in log files and survey data from the Programme for the International Assessment of Adult Competencies (PIAAC), with a focus on the United States sample, to (a) identify employment-related background variables that significantly related to PSTRE skills and problem-solving behaviors, and (b) extract robust sequences of actions by subgroups categorized by significant variables. We conducted this study in two phases. First, we used regression analyses to select background variables that significantly predict the general PSTRE, literacy, and numeracy skills, as well as the response time and correctness in the example item. Second, we identified typical action sequences by different subgroups using the chi-square feature selection model to explore these sequences and differentiate the subgroups. Based on the malleable factors associated with problem-solving skills, the goal of this study is to provide information for improving competences in adult education for targeted groups.

show abstract

“…In this study, 300 self-narratives, consisting of 150 written by PTSD respondents and 150 written by non-PTSD respondents, were used to develop a screening system. In a follow-up study (He et al, 2017), four machine learning algorithms – including Decision Tree (DT), Naïve Bayes (NB), Support Vector Machine (SVM), and a self-developed alternative, the product score model (PSM) – were employed in conjunction with five data representations – unigrams, bigrams, trigrams, a combination of uni- and bigrams, and a mixture of n-grams. Unigram is the simplest and most commonly used data representation model where each word in a document collection acts as a distinct feature.…”

Section: Methodsmentioning

confidence: 99%

Combining Text Mining of Long Constructed Responses and Item-Based Measures: A Hybrid Test Design to Screen for Posttraumatic Stress Disorder (PTSD)

Veldkamp

Glas

et al. 2019

Front. Psychol.

Self Cite

View full text Add to dashboard Cite

This article introduces a new hybrid intake procedure developed for posttraumatic stress disorder (PTSD) screening, which combines an automated textual assessment of respondents’ self-narratives and item-based measures that are administered consequently. Text mining technique and item response modeling were used to analyze long constructed response (i.e., self-narratives) and responses to standardized questionnaires (i.e., multiple choices), respectively. The whole procedure is combined in a Bayesian framework where the textual assessment functions as prior information for the estimation of the PTSD latent trait. The purpose of this study is twofold: first, to investigate whether the combination model of textual analysis and item-based scaling could enhance the classification accuracy of PTSD, and second, to examine whether the standard error of estimates could be reduced through the use of the narrative as a sort of routing test. With the sample at hand, the combination model resulted in a reduction in the misclassification rate, as well as a decrease of standard error of latent trait estimation. These findings highlight the benefits of combining textual assessment and item-based measures in a psychiatric screening process. We conclude that the hybrid test design is a promising approach to increase test efficiency and is expected to be applicable in a broader scope of educational and psychological measurement in the future.

show abstract

Automated Assessment of Patients’ Self-Narratives for Posttraumatic Stress Disorder Screening Using Natural Language Processing and Text Mining

Cited by 60 publications

References 55 publications

e-PTSD: an overview on how new technologies can improve prediction and assessment of Posttraumatic Stress Disorder (PTSD)

e-PTSD: an overview on how new technologies can improve prediction and assessment of Posttraumatic Stress Disorder (PTSD)

Mapping Background Variables With Sequential Patterns in Problem-Solving Environments: An Investigation of United States Adults’ Employment Status in PIAAC

Combining Text Mining of Long Constructed Responses and Item-Based Measures: A Hybrid Test Design to Screen for Posttraumatic Stress Disorder (PTSD)

Contact Info

Product

Resources

About