scholarly journals Towards Designing A Hierarchical Fuzzy System for Early Diagnosis of Heart Disease

2019 ◽  
Vol 4 (2) ◽  
pp. 31-41 ◽  
Author(s):  
Tajul Rosli Razak ◽  
Nurika Filzah Mahadi ◽  
Iman Hazwam Abd Halim ◽  
Muhammad Nabil Fikri Jamaluddin ◽  
Mohammad Hafiz Ismail ◽  
...  
Keyword(s):  
Heart Disease ◽  
Early Diagnosis ◽  
Fuzzy System ◽  
Early Stage ◽  
Heart Diseases ◽  
The Elderly ◽  
Medical Application ◽  
Input Variables ◽  
Hierarchical Fuzzy System ◽  
Hierarchical Fuzzy Systems

Heart disease may represent a range of conditions that affect our heart. Disease under heart diseases umbrella include coronary heart disease, heart attack, congestive heart failure, and congenital heart disease, is the leading cause of death. Mor eover, heart disease not only attacks the elderly. In the present day, lots of younger people might be getting affected by the number of heart diseases. In order to decrease the mortality rate caused by heart disease, it is necessary for the disease, to be diagnosed at an early stage. In this paper, we have proposed the use of hierarchical fuzzy systems (HFSs) for early diagnosis of heart disease. However, to design the HFSs is challenging, especially for the complex system. Therefore, in this paper, we foc us on designing a hierarchical fuzzy system to handle the complex medical application. The designed HFS consists of six key main steps implemented on heart disease. The input variables of heart disease includes shortness of breath, discomfort, pressure, he aviness, or pain in the chest, arm, or below the breastbone, fatigue, nausea, difficulties in climbing stairs, swelling in ankles, difficulty to sleep at night, irregular heartbeats, fullness, sweating, take frequent break during the day, dizzy and depress ed. Additionally, the output of heart disease is to classify whether the patient is healthy or suspecting with heart disease. The study contributes to providing insight into a way of designing the HFSs, particularly for the complex medical application.

Analysis and Application of a Kind of Hierarchical Fuzzy Systems

2011 ◽  
Vol 219-220 ◽  
pp. 1097-1100 ◽  
Author(s):  
Jie Wang ◽  
Xiao Dong Zhu
Keyword(s):  
Structural Analysis ◽  
Fuzzy System ◽  
Fuzzy Systems ◽  
Weight Coefficient ◽  
Oil Drilling ◽  
Analytic Hierarchical Process ◽  
Input Variables ◽  
Hierarchical Fuzzy System ◽  
Hierarchical Fuzzy Systems ◽  
Forewarning System

In this paper a kind of hierarchical fuzzy systems was introduced. The characteristics and structural relation of this hierarchical fuzzy system were analyzed. The sensitivity between the input variables and the output variables and the position of variables in the hierarchical fuzzy system were given according to the importance of variables. The weight coefficient of variables was confirmed applying the methods of analytic hierarchical process (AHP). Then the structural analysis and the weight coefficient were applied to the forewarning system of oil drilling.

scholarly journals Usage of Data Mining Techniques in Predicting the Heart Diseases Decision Tree & Random Forest Algorithm

2019 ◽  
Vol 9 (2) ◽  
pp. 963-967
Keyword(s):  
Data Mining ◽  
Heart Disease ◽  
Random Forest ◽  
Early Diagnosis ◽  
Decision Tree ◽  
Heart Diseases ◽  
Classification Algorithms ◽  
Random Forest Algorithm ◽  
Medical Field ◽  
Data Mining Techniques

Nowadays, heart disease is the main cause of several deaths among all other diseases. Due to the lack of resources in the medical field, the prediction of heart diseases becomes a major problem. For early diagnosis and treatment, some classification algorithms such as Decision Tree and Random Forest Algorithm are used. The data mining techniques compare the accuracy of the algorithm and predict heart diseases. The main aim of this paper is to predict heart disease based on the dataset values. In this paper we are comparing the accuracy of above two algorithms. To implement these methods the following steps are used. In first phase, a dataset of 13 attributes is collected and it was applied on classification techniques using the Decision tree and Random Forest Algorithms. Finally, the accuracy is collected for both the algorithms. In this paper we observed that random forest is generating better results than decision tree in prediction of heart diseases.

scholarly journals An Exploratory Study of Hierarchical Fuzzy Systems Approach in A Recommendation System

2019 ◽  
Vol 14 (2) ◽  
pp. 174-186
Author(s):  
Tajul Rosli Razak ◽  
Iman Hazwam Abd Halim ◽  
Muhammad Nabil Fikri Jamaludin ◽  
Mohammad Hafiz Ismail ◽  
Shukor Sanim Mohd Fauzi
Keyword(s):  
Fuzzy Logic ◽  
Fuzzy Systems ◽  
Recommendation System ◽  
Systems Approach ◽  
Fuzzy Logic Systems ◽  
Input Variables ◽  
Hierarchical Fuzzy System ◽  
Hierarchical Fuzzy Systems ◽  
Insight Into ◽  
Logic System

Recommendation system, also known as a recommender system, is a tool to help the user in providing asuggestion of a specific dilemma. Recently, the interest in developing a recommendation system in manyfields has increased. Fuzzy Logic system (FLSs) is one of the approaches that can be used to model therecommendation systems as it can deal with uncertainty and imprecise information. However, one of thefundamental issues in FLS is the problem of the curse of dimensionality. That is, the number of rules inFLSs is increasing exponentially with the number of input variables. One effective way to overcome thisproblem is by using Hierarchical Fuzzy System (HFSs). This paper aims to explore the use of HFSs forRecommendation system. Specifically, we are interested in exploring and comparing the HFS and FLS forthe Career path recommendation system (CPRS) based on four key criteria, namely topology, the numberof rules, the rules structures and interpretability. The findings suggested that the HFS has advantagesover FLS towards improving the interpretability models, in the context of a recommendation systemexample. This study contributes to providing an insight into the development of interpretable HFSs in theRecommendation systems. Keywords: Fuzzy Logic Systems, Hierarchical Fuzzy Systems, Recommendation Systems

scholarly journals China Registry Study on Cognitive Impairment in the Elderly: Protocol of a Prospective Cohort Study

2021 ◽  
Vol 13 ◽  
Author(s):  
Yingying Zhu ◽  
Dong Pan ◽  
Lei He ◽  
Xiaoming Rong ◽  
Honghong Li ◽  
...  
Keyword(s):  
Cognitive Impairment ◽  
Early Diagnosis ◽  
Cognitive Decline ◽  
Risk Model ◽  
Early Stage ◽  
The Elderly ◽  
Imaging Biomarkers ◽  
Linear Mixed Effect Model ◽  
Registry Study ◽  
Mixed Effect

Introduction: To develop appropriate strategies for early diagnosis and intervention of cognitive impairment, the identification of minimally invasive and cost-effective biomarkers for the early diagnosis of cognitive impairment is crucial and desirable. Therefore, the CHina registry study on cOgnitive imPairment in the Elderly (HOPE) study is designed to investigate the natural course of cognitive decline and explore the clinical, imaging, and biochemical markers for the detection and diagnosis of cognitive impairment on its earliest stage.Methods: Approximately 5,000 Chinese elderly aged more than 50 years were recruited from Sun Yat-sen Memorial Hospital, Sun Yat-sen University in Guangzhou, China by the year 2024. All subjects were invited to complete the clinical assessment, neuropsychological assessment, the biological samples collection (blood and cerebrospinal fluid (CSF)], magnetic resonance imaging (MRI) examination, and optional amyloid and tau PET. The follow-up survey was conducted every 1 year to repeat these assessments for 20 years. To better clarify the relationship between potential risk factors and endpoint events [changes in cognitive score or incidence of mild cognitive impairment (MCI) and/or dementia], appropriate statistical methods were used to analyze the data, including but not limited to, such as linear mixed-effect model, competing risk model, or the least absolute shrinkage and selection operator model.Significance: The CHina registry study on cOgnitive imPairment in the Elderly study is designed to explore the longitudinal changes in characteristics of participants with cognitive decline and to identify potential plasma and imaging biomarkers with cost-benefit and scalability advantages. The results will enable broader clinical access and efficient population screening and then improve the development of treatment and the quality of life for cognitive impairment at the early stage.Trial registration number: NCT04360200.

scholarly journals Early Diagnosis of Congenital Heart Disease Improves Outcome

2020 ◽  
Keyword(s):  
Congenital Heart Disease ◽  
Heart Disease ◽  
Early Diagnosis ◽  
Congenital Heart ◽  
Autosomal Recessive ◽  
Heart Diseases ◽  
Recessive Gene ◽  
Contributory Factor ◽  
Surgical Expertise

Congenital heart disease has an overall incidence of 8-10/1000 live births and is similar across the globe. The incidence may be higher in countries where consanguinity is high, suggesting an autosomal recessive gene as a risk factor. Advances in surgical expertise has improved outcome of simple and complex heart diseases. Early diagnosis and referral to centers caring for such babies is an important contributory factor to a better outcome. This review focuses on early diagnosis of congenital heart disease in neonates and children by Health Care Physicians (General and Family Physicians) and Pediatricians. Careful neonatal and pediatric cardiovascular examination, screening pulse oximetry on all newborns before hospital discharge and an early post natal follow up are important to diagnose CHD.

scholarly journals Recommendation of Attributes for Heart Disease Prediction using Correlation Measure

2019 ◽  
Vol 8 (2S3) ◽  
pp. 870-875
Keyword(s):  
Heart Disease ◽  
Mortality Rate ◽  
Early Stage ◽  
Heart Diseases ◽  
Correct Diagnosis ◽  
Disease Prediction ◽  
Correlation Measure ◽  
Heart Problem ◽  
Correlation Measures ◽  
General Prediction

Heart diseases are the major cause for human mortality rate. Correct diagnosis and treatment at an early stage will save people from heart disease and will decrease mortality rate due to heart problem. Since ten years various data mining techniques have been used to facilitate the prediction of heart diseases .In general prediction algorithms for trained with huge, known dataset to arrive at a classifier which then predicts the diseases for unknown data with the help of classifying attributes. These attributes also called as features. In this work relevant features are determined for heart disease prediction with known dataset using correlation measures. The results are presented.

scholarly journals Computational Learning Model for Prediction of Heart Disease Using Machine Learning Based on a New Regularizer

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Abdulaziz Albahr ◽  
Marwan Albahar ◽  
Mohammed Thanoon ◽  
Muhammad Binsawad
Keyword(s):  
Machine Learning ◽  
Heart Disease ◽  
Standard Deviation ◽  
Early Diagnosis ◽  
Cross Validation ◽  
Heart Diseases ◽  
Computational Learning ◽  
Diagnosis And Prognosis ◽  
Tenfold Cross Validation ◽  
Better Than

Heart diseases are characterized as heterogeneous diseases comprising multiple subtypes. Early diagnosis and prognosis of heart disease are essential to facilitate the clinical management of patients. In this research, a new computational model for predicting early heart disease is proposed. The predictive model is embedded in a new regularization based on decaying the weights according to the weight matrices’ standard deviation and comparing the results against its parents (RSD-ANN). The performance of RSD-ANN is far better than that of the existing methods. Based on our experiments, the average validation accuracy computed was 96.30% using either the tenfold cross-validation or holdout method.

Heart Disease Prediction Using Machine Learning

2021 ◽  
pp. 373-381
Author(s):  
Shiva Shanta Mani B. ◽  
Manikandan V. M.
Keyword(s):  
Machine Learning ◽  
Heart Disease ◽  
Early Stage ◽  
Heart Diseases ◽  
Age Groups ◽  
Disease Prediction ◽  
Learning Approaches ◽  
Health Issues ◽  
Decision Tree Classifier ◽  
Knn Classifier

Heart disease is one of the most common and serious health issues in all the age groups. The food habits, mental stress, smoking, etc. are a few reasons for heart diseases. Diagnosing heart issues at an early stage is very much important to take proper treatment. The treatment of heart disease at the later stage is very expensive and risky. In this chapter, the authors discuss machine learning approaches to predict heart disease from a set of health parameters collected from a person. The heart disease dataset from the UCI machine learning repository is used for the study. This chapter discusses the heart disease prediction capability of four well-known machine learning approaches: naive Bayes classifier, KNN classifier, decision tree classifier, random forest classifier.

scholarly journals Complex Congenital Heart Disease in an Infant - A Case Report and Review

2021 ◽  
Vol 10 (39) ◽  
pp. 3505-3507
Author(s):  
Srinivas Naik ◽  
Sourya Acharya ◽  
Gajendra Agrawal ◽  
Chetan Rathi ◽  
Sunil Kumar
Keyword(s):  
Congenital Heart Disease ◽  
Heart Disease ◽  
Early Diagnosis ◽  
Congenital Heart ◽  
Clinical Presentation ◽  
Heart Diseases ◽  
Diagnosis And Treatment ◽  
Ductus Venosus ◽  
Congenital Heart Diseases ◽  
Life Threatening

Congenital heart disease (CHD) often poses a great diagnostic challenge for physicians. Despite antenatal diagnostic tests advancing to a great level, accurate diagnosis and treatment of congenital heart diseases is mandatory. These diseases range from mild to severe life-threatening scenarios sometimes having vague presentations making diagnosis even more difficult. Early diagnosis and treatment are usually lifesaving.1 Congenital heart diseases can often be classified as cyanotic and acyanotic based on clinical presentation. After birth, fetal structures like foramen ovale, ductus venosus and ductus arteriosus are no longer required for survival and they begin to close.2 Persistence of such structures after birth is a sign of congenital heart diseases. High mortality contributing diseases which require prompt intervention include hypoplastic left heart syndrome (HLHS), coarctation of aorta (COA), interrupted aortic arch (IAA), transposition of the great arteries (TGA), total anomalous pulmonary venous return (TAPVR), critical aortic stenosis (AS) pulmonary atresia (PA) and tricuspid atresia (TA).3 They contribute to significant mortality amongst neonatal age groups. Recognition of congenital heart diseases based on clinical fractures like cyanosis, tachycardia, tachypnoea, irritability, refusal to feed stabilisation and prompt referral to tertiary cardiac centre are critical to improve outcomes in neonates with CHDs, seizures, murmur etc is diagnostically challenging but lifesaving. Life-threatening CHDs may perhaps present with cyanosis, respiratory distress, shock or collapse; all of these are also frequent clinical presentation of various respiratory problems or sepsis in newborn. Early diagnosis and prompt treatment are the only life saving measures.

scholarly journals Rational of Current Practice of Prescribing Statin to Treat Dyslipidaemia as Primary Prevention of Coronary Heart Disease in Elderly People

1970 ◽  
Vol 1 (1) ◽  
pp. 45-55
Author(s):  
Asif Manwar ◽  
Michael Y Henein ◽  
Md Nurul Amin ◽  
Khaled Mohsin
Keyword(s):  
Coronary Heart Disease ◽  
Heart Disease ◽  
Primary Prevention ◽  
Statin Therapy ◽  
Elderly People ◽  
Elderly Population ◽  
Heart Diseases ◽  
The Elderly ◽  
Coronary Heart Diseases

Background: The efficacy of statin therapy in preventing both primary and secondary coronary heart diseases in young and middle aged people is well known and well supported by numbers of landmark clinical trials. Literatures addressing reduction of cholesterol level in elderly (septogenarians & octogenarians) as primary prevention strategy for coronary heart diseases are scarce. The elderly population rarely suffer from primary heart attack and as such routine prescribing of statin to treat dyslipidaemia as primary prevention of coronary heart disease is controversial, particularly when there are reports that statin therapy in elderly population causes cancer, haemorrhagic stroke, dementia and so on. The present study was aimed at answering these questions in order to help formulating a separate guideline for statin therapy in elderly. Methods: The present study reviewed literatures of recent and recent past origin. A systematic literature search of MEDLINE, EMBASE, CINAHL, Web of Science, CANCERLIT and the Cochrane Systematic Review Database have been used to identify randomized clinical trials of statin use with the main focus on primary or secondary end point of CHD, acute coronary syndrome (ACS), cardiac death, overall death, stroke and cancer diagnosis or cancer death. To be included in this review, (1) the entire study subjects or a sub-group were of age 55 years or more (2) had a mean (or median) duration of patient follow-up of at least 1 year, (3) enrolled a minimum of 100 patients, and (4) reported data on the incidence of either cancer diagnosis or cancer death in the elderly population. Conclusions: The study concludes that statin therapy in elderly people may not provide additional benefit in the prevention of primary cardiovascular diseases or death due to primary cardiovascular events. Though most of the studies ruled out excess risk of cancer or other noncardiovascular events, their probability cannot be entirely ignored. However, there is report that addition of statin to the existing drug schedule of elderly subjects does not cause drug interaction. Large-scale, randomized trial on truly representative population with long term follow up will provide authentic data to answer the question whether statin therapy in elderly people with dyslipidaemia can prevent primary heart diseases. Key words: Statin; primary prevention; coronary heart disease; dyslipidemia; elderly people. Ibrahim Card Med J 2011; 1(1):45-55

Sign in / Sign up

Export Citation Format

Share Document