Classification of Diseases Using Machine Learning Algorithms: A Comparative Study

Abstract

Machine learning in the medical area has become a very important requirement. The healthcare professional needs useful tools to diagnose medical illnesses. Classifiers are important to provide tools that can be useful to the health professional for this purpose. However, questions arise: which classifier to use? What metrics are appropriate to measure the performance of the classifier? How to determine a good distribution of the data so that the classifier does not bias the medical patterns to be classified in a particular class? Then most important question: does a classifier perform well for a particular disease? This paper will present some answers to the questions mentioned above, making use of classification algorithms widely used in machine learning research with datasets relating to medical illnesses under the supervised learning scheme. In addition to state-of-the-art algorithms in pattern classification, we introduce a novelty: the use of meta-learning to determine, a priori, which classifier would be the ideal for a specific dataset. The results obtained show numerically and statistically that there are reliable classifiers to suggest medical diagnoses. In addition, we provide some insights about the expected performance of classifiers for such a task.

Relationship between outpatients’ sociodemographic and belief characteristics and their healthcare-seeking behavioral decision-making: Evidence from Jiaxing city, China

“…The outpatients’ responses regarding their general healthcare-seeking behaviors were classified into groups using a C4.5 classifier to estimate a decision tree model: This type of classifier is among the most commonly used in classifying patterns of machine learning [ 28 ]. Moreover, machine learning is concerned with features and labels.…”

“…Decision tree and logistic regression are two different classification methods. In many studies, with the same datasets, the two classifiers were compared by the sensitivity or specificity to the predictive performance in machine learning [ 28 , 31 ]. Lee Yoonju [ 32 ] also got the common major predictors of suicide attempts in the two methods, showing the robustness of results using the two methods.…”

Feature Selection Approach to Improve Malaria Diagnosis Model for High and Low Endemic Areas of Tanzania

“…Machine learning has been successfully applied in the prediction of various diseases such as cancer, diabetics, typhoid, respiratory tract infection and even covid 19 [20]. In the study done by [21] highlighted that machine learning diagnosis is better that medical doctor's diagnosis and this proves the potential in the used of these algorithms in the diagnosis of diseases.…”

“…The 6 classifiers chosen were: K Nearest Neighbor (KNN), Support Vector Machine (SVM), Naïve Bayes (NB), Logistic Regression (LR), Decision Tree (DT) and Random Forest (RF) classifiers. These were chosen due to their popularity in disease diagnosis [20], [30], [31].…”

Lossless Medical Image Compression by Using Difference Transform

“…For this reason, technology specialists and healthcare professionals have developed computer-aided systems that rely on image processing [ 1 , 2 , 3 , 4 , 5 , 6 ] to give better diagnoses [ 7 , 8 ]. Many machine learning and deep learning researchers base their decisions on image databases and other types of databases that could reveal disease information with the goal of handing tools to healthcare professionals so that they come to better conclusions [ 9 , 10 , 11 , 12 , 13 , 14 , 15 , 16 ].…”