Uncertainty-Informed Scheduling of Decision Points for Intelligent Mobile Health Interventions

2025-07-14

AI Summary

Most existing mHealth interventions employ fixed-interval decision points, neglecting inter-individual differences in behavioral rhythms—leading to delayed and untimely interventions. To address this, we propose SigmaScheduling, a dynamic decision-point scheduling framework grounded in predictive uncertainty of behavioral timing. SigmaScheduling is the first approach to leverage prediction uncertainty as the primary scheduling criterion; it integrates heterogeneous time-series data (e.g., wearable sensor streams and ecological momentary assessments) to jointly model both the expected occurrence time and its confidence interval for target behaviors. Intervention timing is then adaptively adjusted based on real-time uncertainty estimates. In a real-world study with 68 participants, SigmaScheduling achieved over 70% probability of triggering decision points prior to toothbrushing—significantly improving intervention pre-emption rate and efficacy. This work transcends conventional static scheduling paradigms, establishing a new foundation for personalized, precision-oriented mobile health interventions.

Technology Category

• Planning, Routing, and Scheduling: Scheduling under Uncertainty
• Reasoning under Uncertainty: Sequential Decision Making
• Humans and AI: Planning and Decision Support for Human-Machine Teams

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Timely decision making is critical to the effectiveness of mobile health (mHealth) interventions. At predefined timepoints called "decision points," intelligent mHealth systems such as just-in-time adaptive interventions (JITAIs) estimate an individual's biobehavioral context from sensor or survey data and determine whether and how to intervene. For interventions targeting habitual behavior (e.g., oral hygiene), effectiveness often hinges on delivering support shortly before the target behavior is likely to occur. Current practice schedules decision points at a fixed interval (e.g., one hour) before user-provided behavior times, and the fixed interval is kept the same for all individuals. However, this one-size-fits-all approach performs poorly for individuals with irregular routines, often scheduling decision points after the target behavior has already occurred, rendering interventions ineffective. In this paper, we propose SigmaScheduling, a method to dynamically schedule decision points based on uncertainty in predicted behavior times. When behavior timing is more predictable, SigmaScheduling schedules decision points closer to the predicted behavior time; when timing is less certain, SigmaScheduling schedules decision points earlier, increasing the likelihood of timely intervention. We evaluated SigmaScheduling using real-world data from 68 participants in a 10-week trial of Oralytics, a JITAI designed to improve daily toothbrushing. SigmaScheduling increased the likelihood that decision points preceded brushing events in at least 70% of cases, preserving opportunities to intervene and impact behavior. Our results indicate that SigmaScheduling can advance precision mHealth, particularly for JITAIs targeting time-sensitive, habitual behaviors such as oral hygiene or dietary habits.

Problem

• Dynamic scheduling of decision points for mHealth interventions
• Addressing uncertainty in predicting habitual behavior timing
• Improving intervention timeliness for irregular routines

Innovation

• Dynamic scheduling based on uncertainty predictions
• Adjusts decision points for irregular routines
• Increases timely intervention likelihood effectively