An intelligent ventilation and oxygenation management system in neonatal intensive care using fuzzy trend template fitting

Physiol Meas. 2005 Aug;26(4):555-70. doi: 10.1088/0967-3334/26/4/019.


This paper describes an open loop feedback intelligent system for neonatal intensive care management. The system provides a tool enabling the user to make the final decision to accept or reject the advice given. The system collects 18 parameters from the bedside monitor and ventilator using a Medical Information Bus (MIB) system. Comparison between the system's recommendations and seven clinical users (three doctors and four nurses) actions was made during monitoring of seven neonates with gestation age of 27-31 weeks for 124.13 h (mu=17.7329, sigma=5.3843 h, range=10.40-23.85 h). The validation process compared the recommendations triggered by the system with the user feedback (agree, disagree, wait). The system made 191 recommendations in total, 33 of which (17%) were for ventilation and 158 (83%) for oxygenation. The clinician agreed with the system ventilation decisions in 30 occasions (91%) and in 148 occasions for the system oxygenation decisions (94%). The overall percentage of the agreement between the system and the clinician was 93%.

MeSH terms

  • Artificial Intelligence
  • Decision Support Systems, Clinical*
  • Diagnosis, Computer-Assisted / methods*
  • Fuzzy Logic
  • Humans
  • Infant, Newborn
  • Intensive Care, Neonatal / methods*
  • Oxygen Inhalation Therapy / methods*
  • Respiration, Artificial / methods*
  • Respiratory Insufficiency / diagnosis*
  • Respiratory Insufficiency / therapy*
  • Therapy, Computer-Assisted / methods*
  • User-Computer Interface