Artificial Intelligence-Driven Multi-Modal Sensing Technologies for Pediatric Health Monitoring and Diagnostics

Child health monitoring remains a major challenge, as many pediatric conditions—such as neurodevelopmental disorders, sleep disturbances, obesity, chronic diseases, and neonatal complications like jaundice—often progress silently before becoming clinically evident. For example, neonatal jaundice is one of the most common conditions in early life; timely detection is essential to prevent severe outcomes such as kernicterus, yet current assessments still rely on invasive blood sampling or subjective visual inspection, both of which are limited in accuracy and feasibility for continuous monitoring. More broadly, traditional pediatric health assessments depend on hospital-based visits and resource-intensive procedures, lacking the capacity for real-time and objective tracking of developmental and disease trajectories. Recent advances in artificial intelligence (AI) and multi-modal sensing technologies—including acoustic analysis, EEG/ECG monitoring, motion tracking, infrared thermography, non-invasive bilirubin measurement, and wearable devices—are transforming this field. These tools allow longitudinal, non-invasive data collection, while AI algorithms can identify clinically meaningful patterns that conventional methods cannot capture. However, translation into pediatric practice remains limited, with gaps in validation, multi-modal integration, and practical application. Addressing these challenges could enable earlier detection of developmental delays, safer monitoring of neonatal jaundice, and personalized management of chronic conditions, thereby advancing proactive pediatric care.

The purpose of this Research Topic is to address the urgent need for more accurate, real-time, and non-invasive monitoring methods in pediatrics. Many critical conditions in children—ranging from neonatal jaundice and sleep disturbances to neurodevelopmental and chronic disorders—are currently assessed using subjective or resource-intensive approaches that fail to capture early warning signals. Artificial intelligence (AI) combined with multi-modal sensing technologies offers a transformative opportunity to overcome these limitations. By integrating acoustic, electrophysiological, motion, thermal, biochemical, and wearable data, AI can extract clinically meaningful patterns to enable earlier detection, personalized care, and proactive interventions. This Research Topic aims to bring together interdisciplinary contributions from medicine, engineering, and data science to translate innovative sensing technologies into practical pediatric applications that can improve health outcomes for children worldwide.

This Research Topic seeks contributions that explore the integration of artificial intelligence and multi-modal sensing technologies into pediatric health monitoring and diagnostics. We particularly welcome manuscripts addressing the following themes:

• AI-based analysis of multi-modal pediatric health data (EEG, ECG, motion, acoustic signals).
• Non-invasive monitoring technologies for neonatal care (e.g., jaundice detection, respiratory function, sleep tracking).
• Wearable devices and real-time health alert systems for children.
• Infrared thermography and stress or pain response monitoring.
•Algorithm development and data fusion strategies for early disease detection.
• Clinical validation studies and translation of sensing technologies into pediatric practice.
• Ethical, legal, and privacy considerations in children’s health data.

Keywords: AI-Powered Multi-Modal Sensing for Pediatric Health: Advancing Monitoring, Early Detection, Personalized Care

Important note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.