An AIoT-Based Intelligent Neonatal Jaundice Monitoring System with Real-Time Data Validation: Clinical Statistical Analysis of Efficacy and Safety

Abstract

Neonatal jaundice, a common condition requiring prompt and effective  treatment,  often  faces  challenges  such  as  inconsistent therapeutic outcomes and safety risks in traditional phototherapy. This study presents an AIoT-based intelligent neonatal jaundice monitoring  system  designed to  enhance treatment  efficacy  and safety through real-time data validation and dynamic parameter adjustments.  The  system  integrates  artificial  intelligence   (AI) algorithms,  including  Convolutional  Neural  Networks  (CNNs) and  Multilayer  Perceptrons  (MLPs),  with  IoT-enabled  sensors for   continuous   monitoring   of   physiological   parameters   and environmental    conditions    (e.g.,    light     intensity,    incubator temperature).      Clinical      trials      involving      200      neonates demonstrated  significant  reductions  in  serum  bilirubin  levels (from  15  mg/dL  to  5  mg/dL  within  24  hours)  and  treatment duration (18 hours for double-sided phototherapy vs. 24 hours for  single-sided  methods).  Statistical  analysis  revealed  a  90% cure rate in the system group, compared to 78% in the control group   (P=0.021),   alongside   significantly   lower   incidences   of adverse events. The system’s ability to dynamically optimize light distribution   and   intensity   based   on   real-time   data   ensures uniform therapy delivery while prioritizing patient comfort and safety.  These  results  underscore  the  potential  of  AIoT-driven systems   to   revolutionize   neonatal   jaundice   management   by combining precision, adaptability, and clinical reliability.