Feature selection and risk prediction for patients with coronary artery disease using data mining

Idris, Nashreen Md; Chiam, Yin Kia; Varathan, Kasturi Dewi; Ahmad, Wan Azman Wan; Chee, Kok Han; Liew, Yih Miin

doi:10.1007/s11517-020-02268-9

Cited by 15 publications

(5 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides, some studies focused on new COVID-19 cases in the future by predicting using the risk factors or the arrivals history. They used different machine learning techniques to predict how many infected cases may occur in future days [16],G. [45,46].…”

Section: Literature Reviewmentioning

confidence: 99%

Simulation of the COVID-19 patient flow and investigation of the future patient arrival using a time-series prediction model: a real-case study

Tavakoli

Tavakkoli–Moghaddam

Mesbahi

et al. 2022

Med Biol Eng Comput

View full text Add to dashboard Cite

COVID-19 looks to be the worst pandemic disease in the last decades due to its number of infected people, deaths, and the staggering demand for healthcare services, especially hospitals. The first and most important step is to identify the patient flow through a certain process. For the second step, there is a crucial need for predicting the future patient arrivals for planning especially at the administrative level of a hospital. This study aims to first simulate the patient flow process and then predict the future entry of patients in a hospital as the case study. Also, according to the system status, this study suggests some policies based on different probable scenarios and assesses the outcome of each decision to improve the policies. The simulation model is conducted by Arena.15 software. The seasonal auto-regressive integrated moving average (SARIMA) model is used for patient's arrival prediction within 30 days. Different scenarios are evaluated through a data envelopment analysis (DEA) method. The simulation model runs for predicted patient's arrival for the least efficient scenario and the outputs compare the base run scenario. Results show that the system collapses after 14 days according to the predictions and simulation and the bottleneck of the ICU and CCU departments becomes problematic. Hospitals can use simulation and also prediction tools to avoid the crisis to plan for the future in the pandemic.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Simulation of the COVID-19 patient flow and investigation of the future patient arrival using a time-series prediction model: a real-case study

Tavakoli

Tavakkoli–Moghaddam

Mesbahi

et al. 2022

Med Biol Eng Comput

View full text Add to dashboard Cite

show abstract

“…Features which attained with 0% importance is neglected for classification [28]. Idris et al [33] created an embedded method DT using RF with the features selected from Gini impurity. 20 features were used for the classification of CAD.…”

Section: Decision Treementioning

confidence: 99%

Potential directions on coronary artery disease prediction using machine learning algorithms: A survey

Vijayaraj,

Pasupathi

2024

IJ-AI

View full text Add to dashboard Cite

<p>Coronary artery disease (CAD) is the most ubiquitous and protuberant cause of fatal death. The hit in mortality rate is because of certain lifestyle variables including unhealthy diet, usage of tobaccos and drugs, physical inactivity, and environmental pollution. Traditional screening tests including computed tomography, angiography, electrocardiography, and magnetic resonance imaging are employed for diagnosis and would necessitate more manpower. Machine learning (ML) has been utilized in healthcare to create early predictions from massive volumes of data. The Scopus, Web of Science databases were exhaustively searched utilizing a search strategy that comprised CAD prediction, cardiac illness detection, and heart disease categorization. After applying the inclusion and exclusion criteria to the 99 articles obtained, the population of the study was composed of 30 articles. This review study offers an organized look at the articles published in ML-based CAD detection and classification models that include clinical variables. The use of ML could produce amazing results in CAD detection, as evidenced by the classifiers random forest, decision tree, and k-nearest-neighbour with accuracy being >90%. The use of ML in CAD diagnosis lowers false-positive, and false-negative errors, and presents a special opportunity by providing patients quick, and affordable diagnostic services.</p>

show abstract

“…In case it fails to work precisely, the psyche and various organs will stop working, and within two or three minutes, the singular will pass on. Dataset azures of patients' data from which to separate valuable information, specialists have been using information mining methodologies to assist health care with caring experts in the determination of coronary disease (Md Idris et al 2020). This research arranged a coronary disease expectation framework to anticipate whether the patient is most likely going not set in stone to have a coronary illness or not utilizing the clinical history of the patient.…”

Section: Introductionmentioning

confidence: 99%

“…An Accurate Classifier Approach for Predicting Heart Disease This research examines how tree approaches are shown in data mining. The gathering tree computations used and attempted in this paper are Decision Stump, Novel Random Forest, and LMT Tree estimation (Md Idris et al 2020). This survey intended to recognize AI classifiers with the most noteworthy accuracy for such symptomatic purposes.…”

Section: Introductionmentioning

confidence: 99%

Prediction Analysis of Novel Random Forest Algorithm and K Nearest Neighbor Algorithm in Heart Disease Prediction with an Improved Accuracy Rate

Poojitha¹,

Mahaveerakannan²

2023

View full text Add to dashboard Cite

Aim: Coronary illness is one of the main sources of mortality in this current world. A basic test in the field of clinical information assessment is the expectation of cardiovascular infection. The fundamental target of this paper is to work on the exactness of the Data mining algorithms being used to improve heart disease prediction. We will be comparing the novel Random forest with K Nearest Neighbor to find out which of these can give us the best accuracy. Material and Methods: The study used 98 samples with Novel Random Forest and K Nearest Neighbor is executed with varying training and testing splits for predicting the accuracy for heart disease prediction with the 80% of G-power value and data about cardiovascular disease was gathered from numerous web sources, including latest research findings and threshold 0.05%, confidence interval 95% mean and standard deviation. The performance of the accuracy rate of the classifiers is examined using the heart disease dataset.. There was a statistical insignificant difference among Innovative Random Forest and K Nearest Neighbor p = 0.484 (p>0.05). Results and Discussion: The accuracy of predicting heart disease in Novel Random Forest 90.16% and K Nearest Neighbor 67.21% is obtained. Conclusion: Prediction of Heart disease using the innovative Random Forest (RF) technique appears to be a significant improvement over the K Nearest Neighbor (KNN) algorithm in terms of accuracy.

show abstract

Feature selection and risk prediction for patients with coronary artery disease using data mining

Cited by 15 publications

References 29 publications

Simulation of the COVID-19 patient flow and investigation of the future patient arrival using a time-series prediction model: a real-case study

Simulation of the COVID-19 patient flow and investigation of the future patient arrival using a time-series prediction model: a real-case study

Potential directions on coronary artery disease prediction using machine learning algorithms: A survey

Prediction Analysis of Novel Random Forest Algorithm and K Nearest Neighbor Algorithm in Heart Disease Prediction with an Improved Accuracy Rate

Contact Info

Product

Resources

About