More Modality, More AI: Exploring Design Opportunities of AI-Based Multi-modal Remote Monitoring Technologies for Early Detection of Mental Health Sequelae in Youth Concussion Patients

2025-02-06

AI Summary

Early identification of post-concussion mental health sequelae—including anxiety, depression, and suicidal ideation—in adolescents remains challenging due to insufficient remote monitoring fidelity and delayed clinical decision-making. Method: We developed the first multimodal AI-powered Remote Patient Monitoring (AI-RPM) clinical decision support framework specifically for adolescent concussion patients. Our approach integrates heterogeneous data streams—physiological signals, naturalistic behavioral metrics, and linguistic text—within a semi-structured, clinician-informed design research process, augmented by human-AI collaborative, interpretable interface design adhering to responsible AI principles. Contribution/Results: We identified six core clinical challenges, co-designed and validated a high-usability prototype with multidisciplinary clinical experts, and empirically demonstrated the clinical utility and feasible implementation pathway of multimodal AI-RPM for early mental health screening in this population.

Technology Category

• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Psychology-informed user models and recommender systems
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Anxiety, depression, and suicidality are common mental health sequelae following concussion in youth patients, often exacerbating concussion symptoms and prolonging recovery. Despite the critical need for early detection of these mental health symptoms, clinicians often face challenges in accurately collecting patients' mental health data and making clinical decision-making in a timely manner. Today's remote patient monitoring (RPM) technologies offer opportunities to objectively monitor patients' activities, but they were not specifically designed for youth concussion patients; moreover, the large amount of data collected by RPM technologies may also impose significant workloads on clinicians to keep up with and use the data. To address these gaps, we employed a three-stage study consisting of a formative study, interface design, and design evaluation. We first conducted a formative study through semi-structured interviews with six highly professional concussion clinicians and identified clinicians' key challenges in remotely collecting patient information and accessing patient treatment compliance. Subsequently, we proposed preliminary clinician-facing interface designs with the integration of AI-based RPM technologies (AI-RPM), followed by design evaluation sessions with highly professional concussion clinicians. Clinicians underscored the value of integrating multi-modal AI-RPM technologies to support clinicians' decision-making while emphasizing the importance of customizable interfaces with explainability and multiple responsible design considerations.

Problem

• AI-based multi-modal remote monitoring for youth concussion
• Early detection of mental health sequelae post-concussion
• Reducing clinician workload with customizable AI interfaces

Innovation

• AI-based multi-modal monitoring
• Customizable clinician interfaces
• Explainable AI design integration