Apnea of prematurity and the need for immediate cardiopulmonary support at birth remain major causes of neonatal instability, especially in very preterm infants. This review summarizes current advances in technologies for apnea detection and neonatal resuscitation, highlighting the transition from conventional bedside monitoring to integrated, data-driven support systems. Literature relating to impedance pneumography, respiratory inductance plethysmography, non-contact video monitoring, dry-electrode electrocardiography, respiratory function monitoring, T-piece ventilation, and machine-learning-enabled analytics was reviewed. Conventional impedance-based respiratory monitoring remains widely used but is limited by motion artifact, cardiac interference, and frequent false alarms, all of which contribute to alarm fatigue and may mask clinically important apnea events. Emerging technologies improve signal quality, reduce the need for adhesive interfaces, and enable more accurate discrimination of true apnea from artifact or periodic breathing. In the delivery room, dry-electrode electrocardiography provides faster heart-rate acquisition than pulse oximetry, while fixed-pressure ventilation systems and respiratory function monitors improve feedback during positive-pressure ventilation. Artificial intelligence is increasingly used to aggregate multimodal physiologic data, automate event quantification, and support prediction of cardiorespiratory deterioration. However, the implementation of advanced neonatal technologies is constrained by cost, infrastructure dependence, interoperability gaps, maintenance limitations, and training requirements, particularly in low-resource settings. Future progress will depend on rigorous validation, human-centered design, reduced alarm burden, open data standards, and equitable deployment strategies that align innovation with real-world neonatal care needs.
Keywords: Artificial Intelligence, Monitoring, apnea of prematurity, dry-electrode electrocardiography, neonatal resuscitation
