: The medical diagnostic process works very similarly to the Case Based Reasoning (CBR) cycle scheme. CBR is a problem solving approach based on the reuse of past experiences called cases. To improve the performance of the retrieval phase, a Random Forest (RF) model is proposed, in this respect we used this algorithm in three different ways (three different algorithms): Classic Random Forest (CRF) algorithm, Random Forest with Feature Selection (RF_FS) algorithm where we selected the most important attributes and deleted the less important ones and Weighted Random Forest (WRF) algorithm where we weighted the most important attributes by giving them more weight. We did this by multiplying the entropy with the weight corresponding to each attribute.We tested our three algorithms CRF, RF_FS and WRF with CBR on data from 11 medical databases and compared the results they produced. We found that WRF and RF_FS give better results than CRF. The experiemental results show the performance and robustess of the proposed approach.

No 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.

Random Forest (RF) is a popular machine learning algorithm. It is based on the concept of ensemble learning, which is a process of combining several classifiers to solve a complex problem and improve model performance. The random forest allows extending the notions of decision trees (DT) in order to build more stable models. In this work we propose to further improve the predictions of the trees in the forest by a pre-pruning technique, which aims to optimize the performance of the nodes and to minimize the size of the trees. Two experiments are performed to evaluate the performance of the proposed method; in the first experiment we applied the Classical Random Forest algorithm (CRF) with several different trees. While in the second one, a pre-pruning technique is established on the trees in order to define the optimal size of the forest. Finally, we compared the results obtained. The main objective is to produce accurate decision trees with high precision. The effectiveness of the proposed method is validated on five medical databases; the prediction precision will be improved with 83%, 94%, 95%, 97%, and 81% for Diabetes, Hepatitis, SaHeart, EEG-Eye-State, Prostate-cancer databases respectively. The performance results confirm that the proposed method performs better than the classical random forest algorithm.