MULTICENTER VALIDATION OF AN INTELLIGENT SYSTEM FOR MANAGING LABOR

Fetal condition during labour is inferred from a continuous visual rec ording of the fetal heart rate and uterine contractions, called the ca rdiotocogram (CTG). Difficulties in CTG interpretation is a major prob lem that can lead to both unnecessary Caesarean sections and damage to the infant. Our group has developed an intelligent system which appli es expert knowledge to support clinical decision making during labour The system was previously found to obtain a performance comparable to local experts in two internal evaluations. This study presents a valid ation of the system which compared its management with 17 experts from 16 leading centres within the U.K. in 50 cases selected from a databa se of 2400 high risk labours. This study found that the majority of ex perts agreed well and were largely consistent in their management of t he cases. The system obtained a performance that was indistinguishable from the experts. Copyright (C) 1996 Elsevier Science Ltd