A Case-Based-Reasoning System for Feature Selection and Diagnosing Asthma

A Case-Based-Reasoning System for Feature Selection and Diagnosing Asthma

Somayeh Akhavan Darabi (Azad University of Tehran Shomal, Iran) and Babak Teimourpour (Tarbiat Modares University, Iran)
DOI: 10.4018/978-1-5225-2515-8.ch019
OnDemand PDF Download:


Asthma is a chronic disease of the airways in the lungs. The differentiation between asthma, COPD and bronchiectasis in the early stage of disease is very important for the adoption of appropriate therapeutic measures. In this research, a case-based-reasoning (CBR) model is proposed to assist a physician to therapy. First of all, features and symptoms are determined and patients' data is gathered with a questionnaire, then CBR algorithm is run on the data which leads to the asthma diagnosis. The system was tested on 325 asthmatic and non-asthmatic adult cases and the accuracy was eighty percent. The consequences were promising. This study was performed in order to determine risk factors for asthma in a specific society and the results of research showed that the most important variables of asthma disease are symptoms hyper-responsive, frequency of cough and cough.
Chapter Preview

Literature Review

There are different kinds of studies for Data Mining techniques in medical databases. We identify the following categories:

Key Terms in this Chapter

Data Mining: Data mining, also called knowledge discovery in databases, in computer science, the process of discovering interesting and useful patterns and relationships in large volumes of data. The field combines tools from statistics and artificial intelligence (such as neural networks and machine learning) with database management to analyze large digital collections, known as data sets.

Feature Selection: In machine learning and statistics, feature selection, also known as variable selection, attribute selection or variable subset selection, is the process of selecting a subset of relevant features (variables, predictors) for use in model construction. Feature selection techniques are used for four reasons: Simplification of models to make them easier to interpret by researchers/users, Shorter training times, To avoid the curse of dimensionality, Enhanced generalization by reducing over fitting. AU81: Anchored Object 1

Case-Based Reasoning: Process of arriving at the solution of a new problem on the basis of the solutions of previously-solved similar problems, such as when a doctor, lawyer, or mechanic relies on experience to remedy a current situation. In comparison to rule based systems (see expert system) which are useful where only one or a few solutions to a problem are possible, case based systems are useful in solving complex problems with many alternative solutions.

Differential Diagnosis: The process of weighing the probability of one disease versus that of other diseases possibly accounting for a patient's illness.

Asthma: Asthma is a chronic (long-term) lung disease that inflames and narrows the airways. Asthma causes recurring periods of wheezing (a whistling sound when you breathe), chest tightness, shortness of breath, and coughing. The coughing often occurs at night or early in the morning.

Classification: Classification is a general process related to categorization, the process in which ideas and objects are recognized, differentiated, and understood.

Complete Chapter List

Search this Book: