Fuzzy Decision Trees in Medical Decision Making Support Systems

International Journal for Research in Applied Science and Engineering Technology IJRASET, 2020

Now a days, diseases have become one of the major causes of human death. To reduce this rising growth of medical problems, data mining techniques have been popularized on higher scale. It has potentially enhanced the clinical decisions and survival time of patients. But choosing appropriate data mining technique is the main task because accuracy is the main issue. The paper presents an overview of the decision tree technique with its medical aspects of Disease Prediction. Major objective is to evaluate decision tree technique in clinical and health care applications to develop accurate decisions. It uses already existing data in different databases to transform it into new research and accurate results. Managing patient's historical data is also made easy and less complex with less effort. This paper describes health prediction results online using decision tree technique with maximum accuracy and presents a glimpse of how this website will work.

Now-a-day's humankind suffering with many health complications. This century's the people affected by most progressive diseases (like as Heart disease, Diabetes disease, AIDS disease, Hepatitis disease and Fibroid diseases) and its complications. Data mining (also called as knowledge discovery) is the process of summarizing the data into useful information by analyzing data from different perspectives. Data Mining is a technology for processing large volume of data that combines traditional data analysis methods with highly developed algorithms. Data mining techniques can be used to support a wide range of security and business applications such as work flow management, customer profiling and fraud detection. It can be also used to predict the outcome of future observations. The Data mining techniques can be developed by the Decision tree algorithm. According to recent survey of World Health Organization (WHO), all diseases and its complications are problematical health hazards of this century. A better and early diagnosis of disease may improve the lives of all people affected and people may lead healthy life. In this paper, the authors present the Decision tree algorithm for better diagnosis of Diseases using association rule mining. In this computational intelligence techniques the authors tested the performance of the method using disease data sets. The authors presented a better algorithm which is used to calculate sensitivity, specificity comprehensibility and rule length. This gain and gain ratio achieved for promising accuracy.

TJPRC, 2013

The healthcare industry collects a huge amount of data which is not properly mined and not put to the optimum use. Discovery of these hidden patterns and relationships often goes unexploited. Advanced data mining modeling techniques can help overcome this situation. The health-care knowledge management especially in heart disease can be improved through the integration of data mining and decision support. This paper presents a prototype heart disease decision support system that uses two data mining classification modeling techniques, namely, Naïve Bayes and Decision Trees. It extracts hidden knowledge from a database containing information about patients with two important heart diseases in Egypt, namely, AMI (Coronary artery), and HTN (High blood pressure) disease. The models are trained and validated against a test dataset. Lift Chart and Classification Matrix methods are used to evaluate the effectiveness of the models. The results showed that the two models are able to extract patterns in response to the predictable state. Five mining goals are defined based on exploration of the two heart diseases dataset and the objectives of this research. The goals are evaluated against the trained models. The two models could answer complex queries, each with its own strength with respect to ease of model interpretation, access to detailed information and accuracy.

International Journal of Trend in Scientific Research and Development, 2019

Data mining techniques are rapidly developed for many applications. In recent year, Data mining in healthcare is an emerging field research and development of intelligent medical diagnosis system. Classification is the major research topic in data mining. Decision trees are popular methods for classification. In this paper many decision tree classifiers are used for diagnosis of medical datasets. AD Tree, J48, NB Tree, Random Tree and Random Forest algorithms are used for analysis of medical dataset. Heart disease dataset, Diabetes dataset and Hepatitis disorder dataset are used to test the decision tree models.

— Nowadays, the classification represents a significant part of the data mining. The object of the classification is assigned to the new data sample the output property (class label) based on previous, learned experience. In this paper the approach of ordered fuzzy decision tree is considered. The fuzzy logic can reduce the uncertainness of initial data and it is closer to natural way of human thinking. Chosen classification model is evaluated by estimation of error and accuracy of the resulting classification. INTRODUCTION Data mining is the process of analysis of data from the various perspective and summarization the results on useful information [1]. The goal of data mining is to discover salutary knowledge stored in huge databases and repositories [1]. Data mining includes many techniques like prediction, classification, clustering, association rules, estimation and affinity grouping [2]. One of the mentioned data mining tasks is classification. The aim of the classification is to assign the class label for new instance. The popular way of classification is decision tree technique. Nowadays, there are many methods for induction of decision tree. One of the first decision tree technique has been published by J. R. Quinlan in [3]. The main idea of the ID3 algorithm is to choose the associate attribute to each node with minimal entropy or maximal information gain [3]. J. R. Quinlan modified ID3 algorithm in [4]. The modified version is called C4.5. Also C4.5 algorithm deals with information entropy. The splitting criterion is the normalized information gain [4]. Many real words problems are uncertainties and noisy. In this case, the crisp classification can be difficult to perform. The usage of fuzzy sets can be useful to describe real-world problems with higher accuracy [5] and more naturally to the way of human thinking. For this reason, the fuzzy decision trees are considered in this paper. At present time, many algorithms for induction of fuzzy decision tree have been proposed. One popular method has been described by Yuan and Shaw in [6]. The induction is based on the reduction of classification ambiguity with fuzzy evidence. Another way of FDT induction is based on fuzzy rules and published by Xianchang Wang in [7]. In contrast with " traditional " decision trees in which only a single attribute is taken into account at an each node, the node of the proposed decision trees in [7] involves a fuzzy rule which take into account multiple attributes. The next approach has been presented in [8]. This algorithm for Ordered Decision Tree (OFDT) is proposed in [8] and used for needs of this paper. OFDT algorithm takes only one attribute to each level of the decision tree. This feature can be considered as an advantage, because it allows constructing OFDT as a parallel process [5]. The criterion to choose attribute associated with given level is cumulative information estimations of fuzzy sets [9]. The usage of considered classification method has been evaluated on well know public dataset Pima Indians Diabetes Database. The dataset contains medical records of female patients and the goal is to estimate whatever a patient has signs of diabetes or not. Evaluation of OFDT is done by estimation of error and accuracy of the resulting classification.

Decision making is becoming more complex and stressful for individuals and groups especially for medical professionals as a result of huge quantity of data. This paper is on the use of decision tree for treatment options in medical decision support systems. Decision tree was developed and an algorithm to identify optimal choice among complicated options in Surgery (Medical Operation) and Medical management (Drug Prescription) by calculating probabilities of events and incorporating patient evaluations of possible outcomes based on Average Life Year (ALY). This can help the medical professionals in taking decision among the available choices.

Medical datasets have reached enormous capacities. This data may contain valuable information that awaits extraction. The knowledge may be encapsulated in various patterns and regularities that may be hidden in the data. Such knowledge may prove to be priceless in future medical decision making. The data which is analyzed comes from National Breast Cancer Prevention Program. The aim of this thesis is the evaluation of the analytical data from the Program to see if the domain can be a subject to data mining. The next step is to evaluate several data mining methods with respect to their applicability to the given data. This is to show which of the techniques are particularly usable for the given dataset. Finally, the research aims at extracting some tangible medical knowledge from the set. The research utilizes a data warehouse to store the data. The data is assessed via the ETL process. The performance of the data mining models is measured with the use of the lift charts and confusion (classification) matrices. The medical knowledge is extracted based on the indications of the majority of the models. The data mining models were not unanimous about patterns in the data. Thus the medical knowledge is not certain and requires verification from the medical people. However, most of the models strongly associated patient's age, tissue type, hormonal therapies and disease in family with the malignancy of cancers. The next step of the research is to present the findings to the medical people for verification. In the future the outcomes may constitute a good background for development of a Medical Decision Support.

IJSRD, 2013

In this paper, we are proposing a modified algorithm for classification. This algorithm is based on the concept of the decision trees. The proposed algorithm is better then the previous algorithms. It provides more accurate results. We have tested the proposed method on the example of patient data set. Our proposed methodology uses greedy approach to select the best attribute. To do so the information gain is used. The attribute with highest information gain is selected. If information gain is not good then again divide attributes values into groups. These steps are done until we get good classification/misclassification ratio. The proposed algorithms classify the data sets more accurately and efficiently.

International Journal of Computer …, 2011

In data mining, classification is one of the significant techniques with applications in fraud detection, Artificial intelligence, Medical Diagnosis and many other fields. Classification of objects based on their features into predefined categories is a widely studied problem. Decision trees are very much useful to diagnose a patient problem by the physicians. Decision tree classifiers are used extensively for diagnosis of breast tumour in ultrasonic images, ovarian cancer and heart sound diagnosis. In this paper, performance of decision tree induction classifiers on various medical data sets in terms of accuracy and time complexity are analysed.

Lecture Notes in Computer Science, 2009

Decision Tree Induction (DTI), one of the Data Mining classification methods, is used in this research for predictive problem solving in analyzing patient medical track records. In this paper, we extend the concept of DTI dealing with meaningful fuzzy labels in order to express human knowledge for mining fuzzy association rules. Meaningful fuzzy labels (using fuzzy sets) can be defined for each domain data. For example, fuzzy labels poor disease, moderate disease, and severe disease are defined to describe a condition/type of disease. We extend and propose a concept of fuzzy information gain to employ the highest information gain for splitting a node. In the process of generating fuzzy association rules, we propose some fuzzy measures to calculate their support, confidence and correlation. The designed application gives a significant contribution to assist decision maker for analyzing and anticipating disease epidemic in a certain area.