Predicting therapy success for treatment as usual and blended treatment in the domain of depression

Ward van Breda, Vincent Bremer, Dennis Becker, Mark Hoogendoorn, Burkhardt Funk, Jeroen Ruwaard, Heleen Riper

Research output: Contribution to JournalArticleAcademicpeer-review

Abstract

In this paper, we explore the potential of predicting therapy success for patients in mental health care. Such predictions can eventually improve the process of matching effective therapy types to individuals. In the EU project E-COMPARED, a variety of information is gathered about patients suffering from depression. We use this data, where 276 patients received treatment as usual and 227 received blended treatment, to investigate to what extent we are able to predict therapy success. We utilize different encoding strategies for preprocessing, varying feature selection techniques, and different statistical procedures for this purpose. Significant predictive power is found with average AUC values up to 0.7628 for treatment as usual and 0.7765 for blended treatment. Adding daily assessment data for blended treatment does currently not add predictive accuracy. Cost effectiveness analysis is needed to determine the added potential for real-world applications.
Original languageEnglish
JournalInternet Interventions
DOIs
Publication statusPublished - 2017

Fingerprint

Depression
Therapeutics
Area Under Curve
Cost-Benefit Analysis
Mental Health
Delivery of Health Care

Keywords

  • Classification
  • Depression
  • E-health
  • Prediction
  • Therapy success

Cite this

van Breda, Ward ; Bremer, Vincent ; Becker, Dennis ; Hoogendoorn, Mark ; Funk, Burkhardt ; Ruwaard, Jeroen ; Riper, Heleen. / Predicting therapy success for treatment as usual and blended treatment in the domain of depression. In: Internet Interventions. 2017.
@article{fa479c8680b44eb996afeace62919759,
title = "Predicting therapy success for treatment as usual and blended treatment in the domain of depression",
abstract = "In this paper, we explore the potential of predicting therapy success for patients in mental health care. Such predictions can eventually improve the process of matching effective therapy types to individuals. In the EU project E-COMPARED, a variety of information is gathered about patients suffering from depression. We use this data, where 276 patients received treatment as usual and 227 received blended treatment, to investigate to what extent we are able to predict therapy success. We utilize different encoding strategies for preprocessing, varying feature selection techniques, and different statistical procedures for this purpose. Significant predictive power is found with average AUC values up to 0.7628 for treatment as usual and 0.7765 for blended treatment. Adding daily assessment data for blended treatment does currently not add predictive accuracy. Cost effectiveness analysis is needed to determine the added potential for real-world applications.",
keywords = "Classification, Depression, E-health, Prediction, Therapy success",
author = "{van Breda}, Ward and Vincent Bremer and Dennis Becker and Mark Hoogendoorn and Burkhardt Funk and Jeroen Ruwaard and Heleen Riper",
year = "2017",
doi = "10.1016/j.invent.2017.08.003",
language = "English",
journal = "Internet Interventions",
issn = "2214-7829",
publisher = "Elsevier BV",

}

Predicting therapy success for treatment as usual and blended treatment in the domain of depression. / van Breda, Ward; Bremer, Vincent; Becker, Dennis; Hoogendoorn, Mark; Funk, Burkhardt; Ruwaard, Jeroen; Riper, Heleen.

In: Internet Interventions, 2017.

Research output: Contribution to JournalArticleAcademicpeer-review

TY - JOUR

T1 - Predicting therapy success for treatment as usual and blended treatment in the domain of depression

AU - van Breda, Ward

AU - Bremer, Vincent

AU - Becker, Dennis

AU - Hoogendoorn, Mark

AU - Funk, Burkhardt

AU - Ruwaard, Jeroen

AU - Riper, Heleen

PY - 2017

Y1 - 2017

N2 - In this paper, we explore the potential of predicting therapy success for patients in mental health care. Such predictions can eventually improve the process of matching effective therapy types to individuals. In the EU project E-COMPARED, a variety of information is gathered about patients suffering from depression. We use this data, where 276 patients received treatment as usual and 227 received blended treatment, to investigate to what extent we are able to predict therapy success. We utilize different encoding strategies for preprocessing, varying feature selection techniques, and different statistical procedures for this purpose. Significant predictive power is found with average AUC values up to 0.7628 for treatment as usual and 0.7765 for blended treatment. Adding daily assessment data for blended treatment does currently not add predictive accuracy. Cost effectiveness analysis is needed to determine the added potential for real-world applications.

AB - In this paper, we explore the potential of predicting therapy success for patients in mental health care. Such predictions can eventually improve the process of matching effective therapy types to individuals. In the EU project E-COMPARED, a variety of information is gathered about patients suffering from depression. We use this data, where 276 patients received treatment as usual and 227 received blended treatment, to investigate to what extent we are able to predict therapy success. We utilize different encoding strategies for preprocessing, varying feature selection techniques, and different statistical procedures for this purpose. Significant predictive power is found with average AUC values up to 0.7628 for treatment as usual and 0.7765 for blended treatment. Adding daily assessment data for blended treatment does currently not add predictive accuracy. Cost effectiveness analysis is needed to determine the added potential for real-world applications.

KW - Classification

KW - Depression

KW - E-health

KW - Prediction

KW - Therapy success

U2 - 10.1016/j.invent.2017.08.003

DO - 10.1016/j.invent.2017.08.003

M3 - Article

JO - Internet Interventions

JF - Internet Interventions

SN - 2214-7829

ER -