Related Experiment Video
Updated: Apr 25, 2026
Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
Developing a genetic fuzzy system for risk assessment of mortality after cardiac surgery
Mahyar Taghizadeh Nouei1, Ali Vahidian Kamyad, MahmoodReza Sarzaeem
1Department of Applied Mathematics, School of Mathematical Sciences, Ferdowsi University of Mashhad, International Campus, Mashhad, Iran, M.nouei@yahoo.ca.
Insights
This study introduces an expert system for assessing cardiac surgery mortality risk, achieving 100% sensitivity and 84.7% specificity. This fuzzy logic tool offers a promising alternative to current risk assessment methods.
Area of Science:
- Cardiovascular medicine and artificial intelligence
- Medical expert systems
- Surgical risk assessment
Background:
- Cardiac events are leading global causes of death and increase healthcare costs.
- Despite technological advances, predicting mortality risk after coronary surgery remains challenging.
- Current mortality risk assessment systems often rely on crisp databases, limiting their precision.
Purpose of the Study:
- To develop an expert system for accurate mortality risk assessment following cardiac surgery.
- To improve the prediction and assessment of mortality risk in coronary surgery patients.
- To introduce a fuzzy logic-based tool as a potential alternative to existing risk assessment systems.
Main Methods:
- A three-step approach involving feature selection, fuzzy inference system generation, and hybrid optimization.
- Application of a filtering feature selection method to identify optimal predictive attributes.
- Utilization of a data-driven method to create a preliminary fuzzy inference system, refined by a hybrid optimization technique.
Main Results:
- The developed expert system achieved 100% sensitivity and 84.7% specificity on a dataset of 1,811 samples.
- The system demonstrated superior performance compared to benchmark methods like logistic regression (LR) and multilayer perceptron (MLP) neural networks.
- LR and MLP methods yielded lower sensitivity (65%) and specificity (78.6% and 75.8%, respectively).
Conclusions:
- The developed fuzzy supportive tool shows significant potential as an alternative for cardiac surgery mortality risk assessment.
- The expert system offers a more accurate and sensitive approach compared to traditional methods.
- This advancement could lead to improved patient management and outcomes in cardiac surgery.
Abstract:
Cardiac events could be taken into account as the leading causes of death throughout the globe. Such events also trigger an undesirable increase in what treatment procedures cost. Despite the giant leaps in technological development in heart surgery, coronary surgery still carries the high risk of the mortality. Besides, there is still a long way ahead to accurately predict and assess the mortality risk. This study is an attempt to develop an expert system for the risk assessment of mortality following the cardiac surgery. The developed system involves three main steps. In the first step, a filtering feature selection method is applied to select the best features. In the second step, an ad hoc data-driven method is utilized to generate the preliminary fuzzy inference system. Finally, a hybrid optimization method is presented to select the optimum subset of the rules. The study relies on 1,811 samples to evaluate the diagnosis performance of the proposed system. The obtained classification accuracy is very promising with regard to other benchmark classification methods including binary logistic regression (LR) and multilayer perceptron neural network (MLP) with the same attributes. The developed system leads to 100% sensitivity and 84.7% specificity, while LR and MLP methods statistically come up with lower figures (65, 78.6 and 65%, 75.8%), respectively. Now, a fuzzy supportive tool can be potentially taken as an alternative for the current mortality risk assessment system that are applied in coronary surgeries, and are chiefly based on crisp database.
