Challenges of and Solutions for Developing Tailored Video Interventions That Integrate Multiple Digital Assets to Promote Engagement and Improve Health Outcomes: Tutorial
Bibliographic record
Abstract
BACKGROUND: Video is a versatile and popular medium for digital health interventions. As mobile device and app technology advances, it is likely that video-based interventions will become increasingly common. Although clinic waiting rooms are complex and busy environments, they offer the opportunity to facilitate engagement with video-based digital interventions as patients wait to see their providers. However, to increase efficiency in public health, leverage the scalability and low cost of implementing digital interventions, and keep up with rapidly advancing technology and user needs, more design and development guidance is needed for video-based tailored interventions. OBJECTIVE: We provide a tutorial for digital intervention researchers and developers to efficiently design and develop video-based tailored digital health interventions. We describe the challenges and solutions encountered with Positive Health Check (PHC), a hybrid app used to deliver a brief, interactive, individually tailored video-based HIV behavioral counseling intervention. PHC uses video clips and multimedia digital assets to deliver intervention content, including interactive tailored messages and graphics, a repurposed animated video, and patient and provider handouts generated in real time by PHC. METHODS: We chronicle multiple challenges and solutions for the following: (1) using video as a medium to enhance user engagement, (2) navigating the complexity of linking a database of video clips with other digital assets, and (3) identifying the main steps involved in building an app that will seamlessly deliver to users individually tailored messages, graphics, and handouts. RESULTS: We leveraged video to enhance user engagement by featuring "video doctors," full-screen video, storyboards, and streamlined scripts. We developed an approach to link the database of video clips with other digital assets through script coding and flow diagrams of algorithms to deliver a tailored user experience. We identified the steps to app development by using keyframes to design the integration of video and digital assets, using agile development methods to gather iterative feedback from multidisciplinary teams, and creating an intelligent data-driven back-end solution to tailor message delivery to individual users. CONCLUSIONS: Video-based digital health interventions will continue to play an important role in the future of HIV prevention and treatment, as well as other clinical health practices. However, facilitating the adoption of an HIV video intervention in HIV clinical settings is a work in progress. Our experience in designing and developing PHC presented unique challenges due to the extensive use of a large database of videos tailored individually to each user. Although PHC focuses on promoting the health and well-being of persons with HIV, the challenges and solutions presented in this tutorial are transferable to the design and development of video-based digital health interventions focused on other areas of health.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.005 | 0.010 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.004 | 0.006 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.004 | 0.004 |
| Insufficient payload (model declined to judge) | 0.011 | 0.004 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".