Artificial Neural Networks in Cancer Diagnosis, Prognosis, and Patient Management
Artificial Neural Networks in Cancer Diagnosis, Prognosis, and Patient Management
The Algorithm for Detecting Critical Conditions During Anesthesia
CBMS '99 Proceedings of the 12th IEEE Symposium on Computer-Based Medical Systems
Estimating the depth of anesthesia using fuzzy soft computation applied to EEG features
Intelligent Data Analysis
ICCRD '10 Proceedings of the 2010 Second International Conference on Computer Research and Development
IEEE Transactions on Information Technology in Biomedicine
Fuzzy Logic-Based Approach to Detecting a Passive RFID Tag in an Outpatient Clinic
Journal of Medical Systems
Robust discrete-time minimum-variance filtering
IEEE Transactions on Signal Processing
Hi-index | 0.00 |
Anaesthesia monitoring involves critical diagnostic tasks carried out amongst lots of distractions. Computers are capable of handling large amounts of data at high speed and therefore decision support systems and expert systems are now capable of processing many signals simultaneously in real time. We have developed two fuzzy logic based anaesthesia monitoring systems; a real time smart anaesthesia alarm system (RT-SAAM) and fuzzy logic monitoring system-2 (FLMS-2), an updated version of FLMS for the detection of absolute hypovolaemia. This paper presents the design aspects of these two systems which employ fuzzy logic techniques to detect absolute hypovolaemia, and compares their performances in terms of usability and acceptability. The interpretation of these two systems of absolute hypovolaemia was compared with clinicians' assessments using Kappa analysis, RT-SAAM K=0.62, FLMS-2 K=0.75; an improvement in performance by FLMS-2.