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

Research output: Journal contributionsConference abstract in journalResearchpeer-review

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.
Original languageEnglish
Article number1204
JournalSleep
Volume43
Issue numberSupplement 1
Pages (from-to)A460
Number of pages1
ISSN0161-8105
DOIs
Publication statusPublished - 27.05.2020
EventAnnual Meeting of the Associated Professional Sleep Societies 2020 - VIRTUAL
Duration: 27.08.202030.08.2020
Conference number: 34
https://www.sleepmeeting.org/

Recently viewed

Researchers

  1. Kerstin Fedder

Publications

  1. Machine Learning and Knowledge Discovery in Databases
  2. The elicitation process in developing of case library for Case-Based Reasoner system whilst consideration for validating electronic communication technologies
  3. There is no Software, there are just Services: Introduction
  4. Mechanism of dynamic recrystallization and evolution of texture in the hot working domains of the processing map for Mg-4Al-2Ba-2Ca Alloy
  5. Geometric structures for the parameterization of non-interacting dynamics for multi-body mechanisms
  6. Monitoring of microbially mediated corrosion and scaling processes using redox potential measurements
  7. Recontextualizing Anthropomorphic Metaphors in Organization Studies
  8. Teachers’ temporary support and worked-out examples as elements of scaffolding in mathematical modeling
  9. Application of feedforward artificial neural network in Muskingum flood routing
  10. Dynamic Semantic Web Content for Museum Guides
  11. Gaining deep leverage? Reflecting and shaping real-world lab impacts through leverage points
  12. Toward a lifespan metric of reading fluency
  13. Consular Assistance: Rights, Remedies, and Responsibility Comments on the ICJ's Judgment in the LaGrand Case
  14. Explaining implementation deficits through multi-level governance in the EU's new member states
  15. Combined MRI-PET dissects dynamic changes in plant structures and functions
  16. University, failed
  17. Precrop functional group identity affects yield of winter barley but less so high carbon amendments in a mesocosm experiment
  18. Modeling a modular omnidirectional AGV developmental platform with integrated suspension and power-plant
  19. An Adaptive Resonance Regulator Design for Motion Control of Intake Valves in Camless Engine Systems
  20. Second-order SMC with disturbance compensation for robust tracking control in PMSM applications
  21. An Experimental Approach to the Optimization of Customer Information at the Point of Sale
  22. Calibrated Passive Sampling - Multi-plot Field Measurements of NH3 Emissions with a Combination of Dynamic Tube Method and Passive Samplers
  23. Trees in the desert
  24. Audiosoftware im Unterricht
  25. Glancing into the Applied Tool Box
  26. Adding the “e-” to Learning for Sustainable Development
  27. Design and evaluation of learning processes in an international sustainability oriented study programme. In search of a new educational quality and assessment method