Dynamic Personalized Optimization Enables Real-Time Digital Therapeutics
Dohyoung Rim publishes in JMIR Medical Informatics (2026) a conceptual framework called Dynamic Personalized Optimization (DPO) defining AI functions for real-time personalized digital therapeutics. The paper formalizes four data types (user, status, content, feedback), proposes predictive-model approaches to optimize treatment content by predicting feedback or final patient status, and notes LLMs can help process heterogeneous inputs. The framework aims to improve engagement and therapeutic effectiveness.
Key Points
- 1Defines Dynamic Personalized Optimization (DPO) framework using four data types U, M, C, F
- 2Highlights AI-driven content optimization by predicting feedback or final patient status
- 3Enables real-time personalized therapy adjustments improving engagement and potential clinical outcomes
Scoring Rationale
Peer-reviewed, actionable DTx personalization framework drives relevance; limitation is conceptual novelty rather than empirical validation.
Sources
Public references used for this report.
Practice interview problems based on real data
1,625 SQL & Python problems across 15 industry datasets — the exact type of data you work with.
Try 250 free problems
