Research Article
Expert System Design for Automated Prediction of Difficulties in Securing Airway in ICU and OT
@INPROCEEDINGS{10.1007/978-3-030-20615-4_10, author={D. Sreekantha and H. Rachana and Sripada Mehandale and Mohammed Javed and K. Sairam}, title={Expert System Design for Automated Prediction of Difficulties in Securing Airway in ICU and OT}, proceedings={Ubiquitous Communications and Network Computing. Second EAI International Conference, Bangalore, India, February 8--10, 2019, Proceedings}, proceedings_a={UBICNET}, year={2019}, month={5}, keywords={Difficult airway Endotracheal intubation Anaesthesia Laryngoscopy Prediction Intensive Care Unit (ICU) Decision tree Machine learning Expert system and knowledge base}, doi={10.1007/978-3-030-20615-4_10} }- D. Sreekantha
H. Rachana
Sripada Mehandale
Mohammed Javed
K. Sairam
Year: 2019
Expert System Design for Automated Prediction of Difficulties in Securing Airway in ICU and OT
UBICNET
Springer
DOI: 10.1007/978-3-030-20615-4_10
Abstract
The maintenance of uninterrupted patient respiratory passage (airway) and unhindered breathing is the primary duty of an anesthesiologist or other physicians involved in patient care under emergency trauma or surgical procedures in ICU (Intensive Care Unit) and Operation Theatre (OT). Anesthesiologist should ensure the full control over the patient airway management either bypassing an endotracheal tube or any other similar devices. The unanticipated difficulties in airway management are the most important contributors to airway related mishaps, if these are not managed effectively may lead to death or permanent bodily harm to the patient due to inadequate oxygenation. The recent survey reports revealed that 53% of anaesthetic deaths are either airway or respiratory related. Incidence of difficult airway among patients has been predicted to be in the range of 1.1 to 3.8%. This paper aims at identifying all the critical risk parameters contributing to difficult airway and subsequently developing a framework to automate the prediction of difficult airways well in advance. Authors have designed an expert system prototype for predicting the difficulties in airway management and suggesting appropriate remedies using machine learning algorithms.