Predicting Social Anxiety Treatment Outcome based on Therapeutic Email Conversations

M. Hoogendoorn, Thomas Berger, Ava Schulz, Timo Stolz, Peter Szolovits

Research output: Contribution to JournalArticleAcademicpeer-review

Abstract

Predicting therapeutic outcome in the mental health domain is of utmost importance to enable therapists to provide the most effective treatment to a patient. Using information from the writings of a patient can potentially be a valuable source of information, especially now that more and more treatments involve computer-based exercises or electronic conversations between patient and therapist. In this paper, we study predictive modeling using writings of patients under treatment for a social anxiety disorder. We extract a wealth of information from the text written by patients including their usage of words, the topics they talk about, the sentiment of the messages, and the style of writing. In addition, we study trends over time with respect to those measures. We then apply machine learning algorithms to generate the predictive models. Based on a dataset of 69 patients we are able to show that we can predict therapy outcome with an Area Under the Curve (AUC) of 0.83 halfway through the therapy and with a precision of 0.78 when using the full data (i.e., the entire treatment period). Due to the limited number of participants it is hard to generalize the results, but they do show great potential in this type of information.
Original languageEnglish
Pages (from-to)1449-1459
Number of pages11
JournalJournal of Biomedical and Health Informatics
DOIs
Publication statusPublished - 2016

Fingerprint

Electronic mail
Learning algorithms
Learning systems
Anxiety
Health
Therapeutics
Area Under Curve
Mental Health
Exercise

Cite this

Hoogendoorn, M. ; Berger, Thomas ; Schulz, Ava ; Stolz, Timo ; Szolovits, Peter. / Predicting Social Anxiety Treatment Outcome based on Therapeutic Email Conversations. In: Journal of Biomedical and Health Informatics. 2016 ; pp. 1449-1459.
@article{7818cc309ea94e8996d241112da8d804,
title = "Predicting Social Anxiety Treatment Outcome based on Therapeutic Email Conversations",
abstract = "Predicting therapeutic outcome in the mental health domain is of utmost importance to enable therapists to provide the most effective treatment to a patient. Using information from the writings of a patient can potentially be a valuable source of information, especially now that more and more treatments involve computer-based exercises or electronic conversations between patient and therapist. In this paper, we study predictive modeling using writings of patients under treatment for a social anxiety disorder. We extract a wealth of information from the text written by patients including their usage of words, the topics they talk about, the sentiment of the messages, and the style of writing. In addition, we study trends over time with respect to those measures. We then apply machine learning algorithms to generate the predictive models. Based on a dataset of 69 patients we are able to show that we can predict therapy outcome with an Area Under the Curve (AUC) of 0.83 halfway through the therapy and with a precision of 0.78 when using the full data (i.e., the entire treatment period). Due to the limited number of participants it is hard to generalize the results, but they do show great potential in this type of information.",
author = "M. Hoogendoorn and Thomas Berger and Ava Schulz and Timo Stolz and Peter Szolovits",
year = "2016",
doi = "10.1109/JBHI.2016.2601123",
language = "English",
pages = "1449--1459",
journal = "Journal of Biomedical and Health Informatics",
issn = "2168-2194",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

Predicting Social Anxiety Treatment Outcome based on Therapeutic Email Conversations. / Hoogendoorn, M.; Berger, Thomas; Schulz, Ava; Stolz, Timo; Szolovits, Peter.

In: Journal of Biomedical and Health Informatics, 2016, p. 1449-1459.

Research output: Contribution to JournalArticleAcademicpeer-review

TY - JOUR

T1 - Predicting Social Anxiety Treatment Outcome based on Therapeutic Email Conversations

AU - Hoogendoorn, M.

AU - Berger, Thomas

AU - Schulz, Ava

AU - Stolz, Timo

AU - Szolovits, Peter

PY - 2016

Y1 - 2016

N2 - Predicting therapeutic outcome in the mental health domain is of utmost importance to enable therapists to provide the most effective treatment to a patient. Using information from the writings of a patient can potentially be a valuable source of information, especially now that more and more treatments involve computer-based exercises or electronic conversations between patient and therapist. In this paper, we study predictive modeling using writings of patients under treatment for a social anxiety disorder. We extract a wealth of information from the text written by patients including their usage of words, the topics they talk about, the sentiment of the messages, and the style of writing. In addition, we study trends over time with respect to those measures. We then apply machine learning algorithms to generate the predictive models. Based on a dataset of 69 patients we are able to show that we can predict therapy outcome with an Area Under the Curve (AUC) of 0.83 halfway through the therapy and with a precision of 0.78 when using the full data (i.e., the entire treatment period). Due to the limited number of participants it is hard to generalize the results, but they do show great potential in this type of information.

AB - Predicting therapeutic outcome in the mental health domain is of utmost importance to enable therapists to provide the most effective treatment to a patient. Using information from the writings of a patient can potentially be a valuable source of information, especially now that more and more treatments involve computer-based exercises or electronic conversations between patient and therapist. In this paper, we study predictive modeling using writings of patients under treatment for a social anxiety disorder. We extract a wealth of information from the text written by patients including their usage of words, the topics they talk about, the sentiment of the messages, and the style of writing. In addition, we study trends over time with respect to those measures. We then apply machine learning algorithms to generate the predictive models. Based on a dataset of 69 patients we are able to show that we can predict therapy outcome with an Area Under the Curve (AUC) of 0.83 halfway through the therapy and with a precision of 0.78 when using the full data (i.e., the entire treatment period). Due to the limited number of participants it is hard to generalize the results, but they do show great potential in this type of information.

U2 - 10.1109/JBHI.2016.2601123

DO - 10.1109/JBHI.2016.2601123

M3 - Article

SP - 1449

EP - 1459

JO - Journal of Biomedical and Health Informatics

JF - Journal of Biomedical and Health Informatics

SN - 2168-2194

ER -