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

Publikation: Beiträge in ZeitschriftenKonferenz-Abstracts in FachzeitschriftenForschungbegutachtet

Authors

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.
Methods
Analysis 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.
Results
After 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.
Conclusion
Results 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.
Support
The 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.
OriginalspracheEnglisch
Aufsatznummer1204
ZeitschriftSleep
Jahrgang43
AusgabenummerSupplement 1
Seiten (von - bis)A460
Anzahl der Seiten1
ISSN0161-8105
DOIs
PublikationsstatusErschienen - 27.05.2020
VeranstaltungAnnual Meeting of the Associated Professional Sleep Societies 2020 - VIRTUAL
Dauer: 27.08.202030.08.2020
Konferenznummer: 34
https://www.sleepmeeting.org/

Bibliographische Notiz

Abstract supplement

DOI

Zuletzt angesehen

Publikationen

  1. Recognition and approach responses toward threatening objects
  2. Considerations on efficient touch interfaces - How display size influences the performance in an applied pointing task
  3. What can conservation strategies learn from the ecosystem services approach?
  4. Wavelet functions for rejecting spurious values
  5. Data based analysis of order processing strategies to support the positioning between conflicting economic and logistic objectives
  6. A Multimethod Latent State-Trait Model for Structurally Different and Interchangeable Methods
  7. Guest Editorial Special Issue on Sensors in Machine Vision of Automated Systems
  8. Online-scheduling using past and real-time data
  9. Designing a Thrifty Approach for SME Business Continuity: Practices for Transparency of the Design Process
  10. Using heuristic worked examples to promote solving of reality‑based tasks in mathematics in lower secondary school
  11. Modeling self-determination theory motivation data by using unfolding IRT
  12. The structure of emotions in learning situations
  13. A New Approach for Optimal Solving Cyclic and Non-Cyclic Bus Drvier Rostering Problems
  14. Introduction Mobile Digital Practices. Situating People, Things, and Data
  15. Geometric structures for the parameterization of non-interacting dynamics for multi-body mechanisms
  16. Vergütung, variable
  17. Tuning kalman filter in linear systems
  18. There is no Software, there are just Services: Introduction
  19. Noninteracting optimal and adaptive torque control using an online parameter estimation with help of polynomials in EKF for a PMSM
  20. Other spaces