Analyzing User Journey Data In Digital Health: Predicting Dropout From A Digital CBT-I Intervention

Publikation: Beiträge in ZeitschriftenKonferenz-Abstracts in FachzeitschriftenForschungbegutachtet

Standard

Analyzing User Journey Data In Digital Health: Predicting Dropout From A Digital CBT-I Intervention. / Bremer, Vincent; Chow, Philip; Funk, Burkhardt et al.
in: Sleep, Jahrgang 43, Nr. Supplement 1, 1204, 27.05.2020, S. A460.

Publikation: Beiträge in ZeitschriftenKonferenz-Abstracts in FachzeitschriftenForschungbegutachtet

Harvard

APA

Vancouver

Bremer V, Chow P, Funk B, Thorndike F, Ritterband L. Analyzing User Journey Data In Digital Health: Predicting Dropout From A Digital CBT-I Intervention. Sleep. 2020 Mai 27;43(Supplement 1):A460. 1204. doi: 10.1093/sleep/zsaa056.1198

Bibtex

@article{8e1794a97dcc4ca8945bb78e569b8b5f,
title = "Analyzing User Journey Data In Digital Health: Predicting Dropout From A Digital CBT-I Intervention",
abstract = "Intervention dropout is an important factor for the evaluation and implementation of digital therapeutics, including in insomnia. Large amounts of individualized data (logins, questionnaires, EMA data) in these interventions can combine to create user journeys - the data generated by the path an individual takes to navigate the digital therapeutic. User journeys can provide insight about how likely users are to drop out of an intervention on an individual level and lead to increased prediction performance. Thus, the goal of this study is to provide a step-by-step guide for the analysis of user journeys and utilize this guide to predict intervention dropout, illustrated with an example from a data in a RCT of digital therapeutic for chronic insomnia, for which outcomes have previously been published.MethodsAnalysis of user journeys includes data transformation, feature engineering, and statistical model analysis, using machine learning techniques. A framework is established to leverage user journeys to predict various behaviors. For this study, the framework was applied to predict dropouts of 151 participants from a fully automated web-based program (SHUTi) that delivered cognitive behavioral therapy for insomnia. For this task, support vector machines, logistic regression with regularization, and boosted decision trees were applied at different points in 9-week intervention. These techniques were evaluated based on their predictive performance.ResultsAfter model evaluation, a decision tree ensemble achieved AUC values ranging between 0.6-0.9 based on application of machine earning techniques. Various handcrafted and theory-driven features (e.g., time to complete certain intervention steps, time to get out of bed after arising, and days since last system interaction contributed to prediction performance.ConclusionResults indicate that utilizing a user journey framework and analysis can predict intervention dropout. Further, handcrafted theory-driven features can increase prediction performance. This prediction of dropout could lead to an enhanced clinical decision-making in digital therapeutics.SupportThe original study evaluating the efficacy of this intervention has been reported elsewhere and was funded by grant R01 MH86758 from the National Institute of Mental Health.",
keywords = "Business informatics, Health sciences",
author = "Vincent Bremer and Philip Chow and Burkhardt Funk and F Thorndike and Lee Ritterband",
note = "Abstract supplement; Annual Meeting of the Associated Professional Sleep Societies 2020 ; Conference date: 27-08-2020 Through 30-08-2020",
year = "2020",
month = may,
day = "27",
doi = "10.1093/sleep/zsaa056.1198",
language = "English",
volume = "43",
pages = "A460",
journal = "Sleep",
issn = "0161-8105",
publisher = "Oxford University Press",
number = "Supplement 1",
url = "https://www.sleepmeeting.org/",

}

RIS

TY - JOUR

T1 - Analyzing User Journey Data In Digital Health: Predicting Dropout From A Digital CBT-I Intervention

AU - Bremer, Vincent

AU - Chow, Philip

AU - Funk, Burkhardt

AU - Thorndike, F

AU - Ritterband, Lee

N1 - Conference code: 34

PY - 2020/5/27

Y1 - 2020/5/27

N2 - Intervention dropout is an important factor for the evaluation and implementation of digital therapeutics, including in insomnia. Large amounts of individualized data (logins, questionnaires, EMA data) in these interventions can combine to create user journeys - the data generated by the path an individual takes to navigate the digital therapeutic. User journeys can provide insight about how likely users are to drop out of an intervention on an individual level and lead to increased prediction performance. Thus, the goal of this study is to provide a step-by-step guide for the analysis of user journeys and utilize this guide to predict intervention dropout, illustrated with an example from a data in a RCT of digital therapeutic for chronic insomnia, for which outcomes have previously been published.MethodsAnalysis of user journeys includes data transformation, feature engineering, and statistical model analysis, using machine learning techniques. A framework is established to leverage user journeys to predict various behaviors. For this study, the framework was applied to predict dropouts of 151 participants from a fully automated web-based program (SHUTi) that delivered cognitive behavioral therapy for insomnia. For this task, support vector machines, logistic regression with regularization, and boosted decision trees were applied at different points in 9-week intervention. These techniques were evaluated based on their predictive performance.ResultsAfter model evaluation, a decision tree ensemble achieved AUC values ranging between 0.6-0.9 based on application of machine earning techniques. Various handcrafted and theory-driven features (e.g., time to complete certain intervention steps, time to get out of bed after arising, and days since last system interaction contributed to prediction performance.ConclusionResults indicate that utilizing a user journey framework and analysis can predict intervention dropout. Further, handcrafted theory-driven features can increase prediction performance. This prediction of dropout could lead to an enhanced clinical decision-making in digital therapeutics.SupportThe original study evaluating the efficacy of this intervention has been reported elsewhere and was funded by grant R01 MH86758 from the National Institute of Mental Health.

AB - Intervention dropout is an important factor for the evaluation and implementation of digital therapeutics, including in insomnia. Large amounts of individualized data (logins, questionnaires, EMA data) in these interventions can combine to create user journeys - the data generated by the path an individual takes to navigate the digital therapeutic. User journeys can provide insight about how likely users are to drop out of an intervention on an individual level and lead to increased prediction performance. Thus, the goal of this study is to provide a step-by-step guide for the analysis of user journeys and utilize this guide to predict intervention dropout, illustrated with an example from a data in a RCT of digital therapeutic for chronic insomnia, for which outcomes have previously been published.MethodsAnalysis of user journeys includes data transformation, feature engineering, and statistical model analysis, using machine learning techniques. A framework is established to leverage user journeys to predict various behaviors. For this study, the framework was applied to predict dropouts of 151 participants from a fully automated web-based program (SHUTi) that delivered cognitive behavioral therapy for insomnia. For this task, support vector machines, logistic regression with regularization, and boosted decision trees were applied at different points in 9-week intervention. These techniques were evaluated based on their predictive performance.ResultsAfter model evaluation, a decision tree ensemble achieved AUC values ranging between 0.6-0.9 based on application of machine earning techniques. Various handcrafted and theory-driven features (e.g., time to complete certain intervention steps, time to get out of bed after arising, and days since last system interaction contributed to prediction performance.ConclusionResults indicate that utilizing a user journey framework and analysis can predict intervention dropout. Further, handcrafted theory-driven features can increase prediction performance. This prediction of dropout could lead to an enhanced clinical decision-making in digital therapeutics.SupportThe original study evaluating the efficacy of this intervention has been reported elsewhere and was funded by grant R01 MH86758 from the National Institute of Mental Health.

KW - Business informatics

KW - Health sciences

UR - https://academic.oup.com/sleep/article-abstract/43/Supplement_1/A460/5846921

U2 - 10.1093/sleep/zsaa056.1198

DO - 10.1093/sleep/zsaa056.1198

M3 - Conference abstract in journal

VL - 43

SP - A460

JO - Sleep

JF - Sleep

SN - 0161-8105

IS - Supplement 1

M1 - 1204

T2 - Annual Meeting of the Associated Professional Sleep Societies 2020

Y2 - 27 August 2020 through 30 August 2020

ER -

DOI

Zuletzt angesehen

Aktivitäten

  1. 1st Global Conference on Research Integration and Implementation - i2S 2013
  2. Exploring Urban Music Studies (Roundtable)
  3. Monomers release from composite materials after halogen and LED curing.
  4. Theoretical Dimensions of Good Practices for Struggling Adolescent Readers
  5. Imagining real utopia: An empirical exploration of organizing alternative projects
  6. Urban spaces of possibility and imaginaries of sustainability
  7. Just why, how and when should more participation lead to better environmental policy outcomes? A causal framework for analysis
  8. Artificial Intelligence in Criminal Law
  9. 19th Annual SemFest
  10. Rational Design of Molecules by Life Cycle Engineering.
  11. International Conference of Mathematical Modelling and Applications - ICTMA 17
  12. Who does take part in which kind of teacher professional development?
  13. Local Interest Representation in Multi-Level Parties
  14. Towards a Better Understanding of the Correlation between Corporate Environmental Sustainability and Financial Performance
  15. Autorschaft
  16. "SIMBA - Social Information Monitoring for Patients with Bipolar Affective Disorder”: A feasibility study on a sensor-based application for smart phones to predict phase transitions in bipolar disorder
  17. Liquidity, Flows, Circulation: The Cultural Logic of Environmentalization (1st part)
  18. Workshop Open Educational Ressourcen für das Sprachenlernen
  19. Touching Land. Creative Practices for Planetary Be/Longings
  20. 5th Int. Summer Academy „Energy and the Environment“ 2008
  21. Göttingen Centre for Gender Studies (GCG) Summer Symposium Reconsidering gender-based violence in the context of displacement and migration
  22. - Keep it simple make it fast
  23. The relationship between intragenerational and intergenerational justice in the use of ecosystems and their services. An ecological-economic mode.
  24. Beyond the New Bentham. Workshop on Current Issues in Bentham Studies 2012
  25. Double Perspective Taking Processes of Primary Children
  26. CES Summer School 2016
  27. AG-Tagung Chemie an AHS 2022
  28. EuroCIS Forum - 2010