An efficient SKNN based approach for heart disease classification

Ansari, Heena Farheen; Namdeo, Varsha

doi:10.19101/ijatee.2019.650034

Cited by 4 publications

(3 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When it is no longer in the process of finding a new solution, that is, the solution space of the subset is stable, we can say that we have found a local optimal solution or even a global optimal solution. In the application of genetic algorithm, we first take the solution space of binary coding problem and every solution encoded in the space as individuals, and any number of coding individuals as individual genes, and these individuals constitute the whole population [3]. Then we can generate an initial population, based on the principle of evolution, the individual in the population selection, crossover and mutation operation, after the evolution Frontiers in Medical Science Research ISSN 2618-1584 Vol.…”

Section: Overview Of Genetic Algorithmsmentioning

confidence: 99%

The Classification of Heart Disease Based on Artificial Network

2023

FMSR

View full text Add to dashboard Cite

Heart disease is a chronic disease which is not infectious but has high mortality in clinic. It is difficult to be accurately analyzed by traditional medical decision-making and diagnosis methods. With the emergence of a large number of clinical diagnosis, treatment and examination reports and network electronic medical record data, information technology provides a large number of data basis for interventional medical diagnosis and auxiliary medical pathological diagnosis. Based on plenty of data for clinical diagnosis and treatment for effective extraction and processing, machine learning algorithms can make accurate diagnosis for heart diseases, predict the probability of disease disease cases and patients, and combined with relevant professional knowledge, in the field of balancing potential data analysis and processing, in order to get better disease diagnosis, improve disease prevention, diagnosis and research status.

show abstract

Section: Overview Of Genetic Algorithmsmentioning

confidence: 99%

The Classification of Heart Disease Based on Artificial Network

2023

FMSR

View full text Add to dashboard Cite

show abstract

“…The advancement of computing technology has facilitated to healthcare agencies for data collection and archiving efforts to use in clinical decisionmaking [50]. In [51], a combination of ANN and GA was applied on Z-Alizadeh Sani heart diseases dataset, which consisted of fifty-four attributes of 303 patients.…”

Section: 2heart Related Diseasesmentioning

confidence: 99%

Impact of machine and deep learning techniques on diseases classification and prediction: a systematic review

2023

IJATEE

View full text Add to dashboard Cite

Over the past few years, various researchers have applied machine and deep learning (DL) techniques to predict several diseases, including cancer, heart disease, Parkinson's disease, diabetes, asthma, brain tumors, obesity, skin conditions, COVID-19, Alzheimer's disease, pneumonia, and crop diseases.According to the World Health Organization (WHO) statistics, heart or cardiovascular diseases are responsible for more deaths worldwide than any other disease, accounting for 31% of all deaths. In the United States (US), this disease is the cause of one in every four deaths, with one person dying from it every 36 seconds [13]. In India, the number of deaths due to heart diseases reached approximately 4.8 million in 2020, a significant increase from the 2.26 million recorded in 1990. Recent projections indicate that India is on track to become the leader in the incidence of heart diseases [13]. *Author for correspondenceIt's worth noting that advancements in machine and DL techniques have played a crucial role in early detection, risk assessment, and treatment planning for various diseases, including heart disease.Presently, one death out of five in India is due to this disease and in upcoming years, this ratio is expected to reach up to every third death, majority will belong to the younger age groups [1]. Due to expensive diagnosis, about 75% of deaths occur in low-and middle-income countries. According to National Center for Biotechnology Information (NCBI), in every 10 years, mortality rates due to cardiovascular diseases increased about 60% in the US [2]. Deathsrelated to this disease is higher in developing countries as comparison to developed countries [3]. Obesity or overweight are the abnormal or excessive fat accumulation that presents a risk to health. Childhood and teenage obesity are one of the most serious health problems over the globe. It has spread to every country and is now a worldwide crisis in public health. All around the world, childhood and

show abstract

“…Also, it performs better for linearly separable binary classifier when a linear kernel is used. KNN classifier is robust against noisy data Ansari and Namdeo [43]. A DT can handle categorical data well and an RF is an ensemble model with a collection of DT working together in the classification.…”

Section: 4classificationmentioning

confidence: 99%

Role of attribute selection on tuning the learning performance of Parkinson’s data using various intelligent classifiers

Alice¹,

Natesan²,

Dhanalakshmi³

et al. 2021

IJATEE

View full text Add to dashboard Cite

Dr James Parkinson first defined the Parkinson's Disease (PD) as "shaking palsy" in 1817. PD is one of the most common neurological syndromes of the central nervous system. It is a serious disease targeting aged persons above 60 years of age. PD is identified as a brain disorder [1] that causes the nerve cells to be lost or impaired. These impaired or lost nerve cells will stop the dopamine fluid production in the area of Substantia Nigra. Dopamine is an essential chemical fluid in the brain, which makes nerve cells passes the message to other nerve cells. Due to the lack of dopamine, information has to pass to another nerve cell to be stopped.

show abstract

An efficient SKNN based approach for heart disease classification

Cited by 4 publications

References 19 publications

The Classification of Heart Disease Based on Artificial Network

The Classification of Heart Disease Based on Artificial Network

Impact of machine and deep learning techniques on diseases classification and prediction: a systematic review

Role of attribute selection on tuning the learning performance of Parkinson’s data using various intelligent classifiers

Contact Info

Product

Resources

About