Intelligent Postoperative Morbidity Prediction of Heart Disease Using Artificial Intelligence Techniques

Abstract

Endovascular aneurysm repair (EVAR) is an advanced minimally invasive surgical technology that is helpful for reducing patients' recovery time, postoperative morbidity and mortality. This study proposes an ensemble model to predict postoperative morbidity after EVAR. The ensemble model was developed using a training set of consecutive patients who underwent EVAR between 2000 and 2009. All data required for prediction modeling, including patient demographics, preoperative, co-morbidities, and complication as outcome variables, was collected prospectively and entered into a clinical database. A discretization approach was used to categorize numerical values into informative feature space. Then, the Bayesian network (BN), artificial neural network (ANN), and support vector machine (SVM) were adopted as base models, and stacking combined multiple models. The research outcomes consisted of an ensemble model to predict postoperative morbidity after EVAR, the occurrence of postoperative complications prospectively recorded, and the causal effect knowledge by BNs with Markov blanket concept.

An intelligent recommender system based on predictive analysis in telehealthcare environment

“…On other hand, Bayesian classifiers, decision tree, logistic regression and back propagation neural network have been utilized by [4,5,7,13,14] to predict diseases at an early stage for patients. In these studies, effective predictive models have been built to discover different diseases as early as possible in order to treat them effectively.…”

“…Many of these researches have been carried out in data mining and analytic on medical data. The assessment and prediction of various diseases for patients have been widely reviewed by using data mining techniques and statistical tools [4,5,6,7,8,25]. Especially, there have been a number of the predictive models which employ artificial neural network and regressions for predicting medical outcomes in various chronical diseases [25,27,28,31].…”

An Intelligent Recommender System Based on Short-Term Risk Prediction for Heart Disease Patients

“…In these works, laboratory measurements and symptoms were utilized to predict the disease risk. Different predictive data mining techniques such as Bayesian classifiers, decision tree, logistic regression and back propagation neural network have been utilized by [4,5,7,13,14] to predict diseases at early stage for patients. These techniques have been used in building effective predictive models to discover different diseases as early as possible in order to treat them effectively.…”

“…Data mining techniques and statistical tools have been widely used for various diseases prediction [3,4,5,6,7,25]. However, a challenge remains still in securing an effective analytic tool with high accuracy to help support personalized evidence-based decisions.…”

IRS-HD: An Intelligent Personalized Recommender System for Heart Disease Patients in a Tele-Health Environment

“…Today, the survival rates have been increased partially due to technological advancements in disease prediction. Extensive research work has been carried out on data mining and analytic in various medical domains [2].…”