Conference Paper

A Machine Learning Approach to the Detection of Fetal Hypoxia during Labor and Delivery.

Conference: Proceedings of the Twenty-Second Conference on Innovative Applications of Artificial Intelligence, July 11-15, 2010, Atlanta, Georgia, USA
Source: DBLP


Labor monitoring is crucial in modern health care, as it can be used to detect (and help avoid) significant problems with the fetus. In this article we focus on detecting hypoxia (or oxygen deprivation), a very serious condition that can arise from different pathologies and can lead to lifelong disability and death. We present a novel approach to hypoxia detection based on recordings of the uterine pressure and fetal heart rate, which are obtained using standard labor monitoring devices. The key idea is to learn models of the fetal response to signals from its environment. Then, we use the paraim-, eters of these models as attributes in a binary classification problem. A running count of pathological classifications over several time periods is taken to provide the current label for the fetus. We use a unique database of real clinical recordings, both from normal and pathological cases. Our approach classifies correctly more than half the pathological cases, 1.5 hours before delivery. These are cases that were missed by clinicians; early detection of this type would have allowed the physician to perform a Cesarean section, possibly avoiding the negative outcome. Copyright © 2012 Association for the Advancement of Artificial Intelligence. All rights reserved.

Download full-text


Available from: Robert Edward Kearney, Jan 27, 2014
  • [Show abstract] [Hide abstract]
    ABSTRACT: Soft Computing (SC) techniques are based on exploiting human knowledge and experience and they are extremely useful to model any complex decision making procedure. Thus, they have a key role in the development of Medical Decision Support Systems (MDSS). The soft computing methodology of Fuzzy Cognitive Maps has successfully been used to represent human reasoning and to infer conclusions and decisions in a human-like way and thus, FCM-MDSSs have been developed. Such systems are able to assist in critical decision-making, support diagnosis procedures and consult medical professionals. Here a new methodology is introduced to expand the utilization of FCM-MDSS for learning and educational purposes using a scenario-based learning (SBL) approach. This is particularly important in medical education since it allows future medical professionals to safely explore extensive "what-if" scenarios in case studies and prepare for dealing with critical adverse events.
    No preview · Article · Aug 2014