Abstract
The huge amount of health data attracts machine learning (ML) techniques to medical classification, and, through learning strategies, obtain remarkable results. Some techniques are used to classify and predict data to make accurate decisions, especially case-based reasoning (CBR), which is considered a reasonable technique in medicine, based on past experiences for problem solving. This chapter studies the case-based reasoning approach and its use in the medical field. In the analysis, the authors identify hybridization as a major trend in CBR. Secondly, random forests (RF) as a very popular tool in machine learning is also suggested and is presented as a new way to improve the recall phase of CBR in order to further improve it for medical data. Thus, the authors present hybrid systems between case-based reasoning and random forests. The authors show that combining ideas from some classifiers can lead to better performance.
TopCase Based Reasoning
Case-based reasoning is a problem-solving methodology that relies on the reuse by analogy of past problem solutions called “source cases”. These cases contain knowledge that is useful for solving new problems called “target cases”. The source cases are stored in a memory called “case base (CB)”.To understand how CBR works, different models have been proposed in the literature, among them the most used model according to Amodt and Plaza is made up of four phases (Figure1).
- •
Retrieve: is the process of searching for the most similar cases in a case base, the search is done using different approaches(Yan et al., 2017) such as the nearest neighbor approach(Liao et al., 1998)the knowledge-based approach(Watson & Marir, 1994) and the validated approach(Aamodt & Plaza, 1994) .
- •
Reuse: who is responsible for reusing the solution from the most similar case to the new case?
- •
Revise: implies evaluation, if the solution is correct then the system integrates the success otherwise the system repairs the solution.
- •
Retain: if the case is successfully solved then it can be saved in the case base for future problem solving.
Key Terms in this Chapter
Valvular Heart Disease: This: is any process of cardiovascular disease involving one or more of the four valves of the heart. These conditions are most often due to aging, but can also be the result of congenital (inborn) defects or specific diseases.
Headache: Headaches are a common condition that most people face several times in their lives, with several types including tension headaches.
Chronic Kidney: It is a disease that consists of a weakening of the function of the kidneys, resulting in a harmful accumulation of fluids, electrolytes and waste products in the body. Among the most important risk factors for kidney disease are: diabetes, high blood pressure, and heart disease.
Baging: This is a Machine Learning method that improves the accuracy of machine learning algorithms.
Continuous Glucose Monitoring Systems: CGMS are used to provide detailed information on the variability of glucose in the interstitial fluid on a continuous basis: direction, magnitude, duration and frequency of hypo- or hyperglycemia. This allows the identification of blood glucose trends throughout the day.
Kidney Clear Cell Carcinoma: This is a common malignant kidney tumor that is characterized by a poor prognosis and can be identified using associated molecular analyses by assessing the function and differential expression of specific genes.
Influential Blogger: This is simply someone who can encourage others, provoke their inspiration and determination to pursue what they want to do.