Knowledge discovery in medicine: Current issue and future trend

Esfandiari, Nura; Babavalian, Mohammad Reza; Moghadam, Amir Masoud Eftekhari; Tabar, Vahid Kashani

doi:10.1016/j.eswa.2014.01.011

Cited by 209 publications

(119 citation statements)

References 288 publications

Supporting

Mentioning

117

Contrasting

Unclassified

Order By: Relevance

“…DM implementation in healthcare is well documented in the literature [5] [6]. However, the utilisation of the SECI model in the healthcare domain is still deficient.…”

Section: Introductionmentioning

confidence: 99%

Application of the SECI Model Using Web Tools to Support Diabetes Self-Management and Education in the Kingdom of Saudi Arabia

Almuayqil¹,

Atkins²,

Sharp³

2017

IIM

View full text Add to dashboard Cite

The area of knowledge management, the SECI mode in particular, has great value in terms of enriching patients' knowledge about their diseases and its complications. Despite its effectiveness, the application of knowledge management in the healthcare sector in the Kingdom of Saudi Arabia seems deficient, leading to insufficient practice of self-management and education of different prevalent diseases in the Kingdom. Moreover, the SECI model seems to be only focusing in the conversion of human knowledge and ignore knowledge stored in databases and other technological means. In this paper, we propose a framework to support diabetic patients and healthcare professionals in the Kingdom of Saudi Arabia to self-manage their disease. Data mining and the SECI model can provide effective mechanisms to support people with diabetes mellitus. The area of data mining has long been utilised to discover useful knowledge whereas the SECI model facilitates knowledge conversion between tacit and explicit knowledge among different individuals. The paper also investigates the possibilities of applying the model in the web environment and reviews the tools available in the internet that can apply the four modes of the SECI model. This review helps in providing a new median for knowledge management by addressing several cultural obstacles in the Kingdom.

show abstract

“…DM implementation in healthcare is well documented in the literature [5] [6]. However, the utilisation of the SECI model in the healthcare domain is still deficient.…”

Section: Introductionmentioning

confidence: 99%

Application of the SECI Model Using Web Tools to Support Diabetes Self-Management and Education in the Kingdom of Saudi Arabia

Almuayqil¹,

Atkins²,

Sharp³

2017

IIM

View full text Add to dashboard Cite

show abstract

“…Data mining is a powerful tool to extract the knowledge from raw data. In this context, various challenges and techniques have been proposed by different researchers [1,9]. A predictive approach has been developed for human breast and colon cancer with two-stage strategy namely preprocessing stage MT is used to increase the samples of a minority class and balancing the dataset.…”

Section: Literature Surveymentioning

confidence: 99%

Implicating Machine Learning towards Development of Intelligent System for Wart Treatment Therapy Identification

Khatri¹,

Arora²,

Kumar³

2018

IJET

View full text Add to dashboard Cite

Warts are produced on the human body because of contamination caused by Human Papillomavirus (HPV). The most affected areas of warts are hands and feet specifically, which is bit annoying and hard to recover in later stages. After massive literature survey, it is found that different treatments have been suggested for treating this illness. The basic problem found while treating that the treatment given to one patient may or may not be suitable for another patient, so it is hard to detect specific kind of treatment to be followed for faster recovery and effective customized treatment against this viral disease. The objective of this research work is to identify the ideal treatment method for both particular plantar and normal warts, between immunotherapy and cryotherapy treatment methods. Implications of machine learning techniques are now playing a vital role specifically in clinical diagnosis toward identifying different clinical patterns, disease classification and its predictions. In this research, work authors have implemented classifiers like Bayes Net, SVM, Multi-Layer Perceptron, k-NN, FURIA, Random Forest with the help of WEKA tool. The experimentation has been performed on data sets obtained from UCI Machine Learning Repositories. The experimentation was performed with total 180 patient instances having wart illness present in immunotherapy and cryotherapy datasets respectively. The result outcomes have been discussed and compared with existing methodologies mentioned in the literature. It was observed that the decision tree based classifier random forest is having the best classification accuracy among the chosen set of classifiers. The result shows highest classification accuracy in case random forest, 86% and 93% was noted for immunotherapy and cryotherapy treatment methods datasets. This research work is helpful for physicians in selecting the best treatment method for their patient suffering from wart illness in order to reduce overall treatment cost incurred and also improving the quality of treatment given to the patients.

show abstract

“…Among various algorithms in data modeling, decision tree is known as the most popular due to its simplicity and interpretability [5], [6].Now a days more efficient algorithms such as SVM and artificial neural networks have also become popular [7], [4], [8].…”

Section: Introductionmentioning

confidence: 99%

Predicting and Diagnosing of Heart Disease Using Machine Learning Algorithms

Sen¹

2017

ijecs

View full text Add to dashboard Cite

Prediction and diagnosing of heart disease become a challenging factor faced by doctors and hospitals both in India and abroad. In order to reduce the large scale of deaths from heart diseases, a quick and efficient detection technique is to be discovered. Data mining techniques and machine learning algorithms play a very important role in this area. The researchers accelerating their research works to develop a software with the help machine learning algorithm which can help doctors to take decision regarding both prediction and diagnosing of heart disease. The main objective of this research paper is predicting the heart disease of a patient using machine learning algorithms. Comparative study of the various performance of machine learning algorithms is done through graphical representation of the results.

show abstract

Knowledge discovery in medicine: Current issue and future trend

Cited by 209 publications

References 288 publications

Application of the SECI Model Using Web Tools to Support Diabetes Self-Management and Education in the Kingdom of Saudi Arabia

Application of the SECI Model Using Web Tools to Support Diabetes Self-Management and Education in the Kingdom of Saudi Arabia

Implicating Machine Learning towards Development of Intelligent System for Wart Treatment Therapy Identification

Predicting and Diagnosing of Heart Disease Using Machine Learning Algorithms

Contact Info

Product

Resources

About