The impact of data mining techniques on medical diagnostics

Wasan, Siri Krishan; Bhatnagar, Vasudha; Kaur, Harleen

doi:10.2481/dsj.5.119

Cited by 59 publications

(18 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Knowledge discovery in databases (KDD) and data mining are the two terms, which are interchangeable. Process of finding useful information and extracting knowledge is called KDD and data mining respectively [2]. Learning from the learned knowledge Is roughly called Meta-learning.…”

Section: Types Of Liver Infectionmentioning

confidence: 99%

Comparative Analysis of Meta Learning Algorithms for Liver Disease Detection

Pasha¹,

Fatima²

2017

JSW

View full text Add to dashboard Cite

Various kinds of pressure and unbalanced eating behaviors, along with alcohol inhalation and ongoing toxic gases, absorption of tainted nutrients, unnecessary intake of cured food and ingestion of drug, enables patients to increase year by year from liver disease. For this purpose, the type of data mining algorithms can help medical doctors to diagnose patients in hospital. This paper analyzes meta learning algorithms to classify the Indian liver patient dataset. The Data set is attained from UCI repository that contains 583 instances. Adaboost, logitboost, Bagging and Grading meta learning algorithms are applied to this data set. These algorithms are compared on the basis of Correct Classification, Incorrect Classification and Time to build model. Grading is the best algorithm among these meta learning algorithms as it provides highest Correct Classification rate and minimum rate of incorrect classification. Execution time for Grading is less than Adaboost, Logitboost and Bagging. Key role is played by Grading algorithm in shaping enhanced classification accuracy (Correct Classification Rate) of a data set.

show abstract

Section: Types Of Liver Infectionmentioning

confidence: 99%

Comparative Analysis of Meta Learning Algorithms for Liver Disease Detection

Pasha¹,

Fatima²

2017

JSW

View full text Add to dashboard Cite

show abstract

“…Its positive impact is through data cleaning and evidence and negative impact is usually through delays in updating the data ware house and by the limitations of expressing it in the conceptual models, they added. Data mining techniques can create rich knowledge (Wasan et al, 2006). According to Seifert (2004) over the past years there has been a rapid increase in the volume of information collected and stored.…”

Section: Background and Hypothesis Formulationmentioning

confidence: 99%

Marketing Information System (MkIS): Benefits for Small and Medium Enterprises in Fiji

Devi

Singh

Naz

2013

J. Info. Know. Mgmt.

View full text Add to dashboard Cite

The purpose of this paper is to highlight the bene¯ts of using Marketing Information System (MkIS) for Small and Medium Enterprises (SMEs) in Fiji. The paper comprises of quantitative data, which is comprehensively analysed statistically. Structured questionnaire was used to collect data from the SMEs from¯ve major towns in Fiji forming a sample of 96 SMEs. This research has found that, SMEs in Fiji are quite aware of the resulting bene¯ts of MkIS, though the usage rate is low. This has resulted in changes for SMEs' business in terms of growth (sales and pro¯ts), from the time when SMEs started using MkIS or any form of technologies. The importance of MkIS in making extreme decision is also tested and analysed.

show abstract

“…Nowadays many systems in health care domain are of multi-purpose type which support various complex tasks along-with diagnosis and combine more than one AI technique [17]. Medical care could be enhanced and costs could be reduced by means of an automated medical diagnosis system [15]. The importance of the role of data mining techniques in providing better patient care and effective diagnostic capabilities by finding patterns and extracting knowledge increases with the increase in the volume of stored data [16].…”

Section: B Indian Heart Risk Predicting Featuresmentioning

confidence: 99%

A Novel Risk Level Classification of Ischemic Heart Disease using Artificial Neural Network Technique - An Indian Case Study

Rajeswari¹,

Vaithiyanathan²,

Amirtharaj³

2011

IJMLC

View full text Add to dashboard Cite

Abstract-Cardiovascular Diseases (CVD) comprises of a group of diseases of the heart and vascular system. The major conditions include Coronary Heart Disease (CHD) or Ischemic Heart Disease (IHD) which causes 25-30 percent of deaths in most industrialized countries. India is in a risk of developing more death due to CHD. Hence a Decision Support System (DSS) is proposed to identify the level of risk in Ischemic Heart Disease of a Patient. This will help the patients in taking precautionary steps like following a balanced diet and medication which in turn may increase the life time of a patient. The features for prediction are selected after considering Indian conditions from literature and based on the Expert knowledge from Doctors. Framingham Risk score which has five attributes is used for comparison. Our proposed system will have seventeen features to be analyzed according to Indian Conditions. The system proposes implementation of Artificial Neural Network technique to mine the knowledge from Medical data collected.

show abstract

The impact of data mining techniques on medical diagnostics

Cited by 59 publications

References 8 publications

Comparative Analysis of Meta Learning Algorithms for Liver Disease Detection

Comparative Analysis of Meta Learning Algorithms for Liver Disease Detection

Marketing Information System (MkIS): Benefits for Small and Medium Enterprises in Fiji

A Novel Risk Level Classification of Ischemic Heart Disease using Artificial Neural Network Technique - An Indian Case Study

Contact Info

Product

Resources

About