Correct diagnosis in medicine is of great importance as it is one of the most important issues in medicine. Today, researchers have embarked on many new searches to make an accurate medical diagnosis. In order for any disease to be cured, it is necessary to define it precisely early and accurately. In this study, a new method was proposed to make a more accurate medical diagnosis. This method is based on automatically selecting the fold with the best accuracy rate after k-fold crossvalidation is performed in any database. In this way, scientific studies that lead to more accurate results will be carried out by using the fold with the highest accuracy in both classification and medical diagnosis procedures. This method has been applied on two different databases, Ecoli and Wisconsin Breast Cancer Diagnostic (WBCD) databases, which are used in scientific studies by many researchers in the literature. The statistical measurements of each fold values of both databases used have been examined in detail. Diagnostics for these databases were carried out using 7 different Machine Learning Algorithms (MLA), (k nearest neighbor (k-NN), Decision Tree (DT), Random Forest (RF), Multinominal Logistic Regression (MLR), Naive Bayes (NB), Support Vector Machine (SVM), Minumum (Mean) Distance Classifier (MMDC)). In the test procedures for Ecoli dataset, the following accuracy values were obtained for k-NN, DT, RF, MLR, NB, SVM, MMDC, respectively; 0.8485, 0.8358, 0.9848, 0.8182, 0.6667, 0.8636, 0.7424. For the WBCD database, the following accuracy values were obtained for k-NN, DT, RF, MLR, NB, SVM, MMDC, respectively; 0.9856, 0.9568, 0.9784, 0.9856, 0.9856, 0.9856, 0.9784. Other results were given in detail in the experimental studies section. It is of great importance to choose the most accurate MLAs to be used in medical diagnosis for human life. Thus, in the studies to be done with MLAs in medicine or any field in the literature, how the best score that can be obtained from MLAs will be introduced to the literature. In this study, an original study was conducted on how to make the correct medical diagnosis, which is one of the most important issues for human life.

正确的诊断在医学中非常重要，因为它是医学中最重要的问题之一。如今，研究人员已经开始进行许多新的搜索，以做出准确的医学诊断。为了治愈任何疾病，必须尽早、准确地定义它。在这项研究中，提出了一种新方法来做出更准确的医学诊断。该方法基于在任何数据库中执行k次交叉验证后自动选择具有最佳准确率的折叠。这样，在分类和医疗诊断过程中使用最准确的折叠来进行科学研究，将获得更准确的结果。该方法已应用于两个不同的数据库，Ecoli 和威斯康星乳腺癌诊断（WBCD）数据库，文献中许多研究人员将其用于科学研究。所使用的两个数据库的每个折叠值的统计测量都已被详细检查。使用 7 种不同的机器学习算法 (MLA)、(k 最近邻 (k-NN)、决策树 (DT)、随机森林 (RF)、多项 Logistic 回归 (MLR)、朴素贝叶斯 (NB) 对这些数据库进行诊断）、支持向量机（SVM）、最小（平均）距离分类器（MMDC））。在Ecoli数据集的测试过程中，k-NN、DT、RF、MLR、NB、SVM、MMDC分别获得了以下准确度值； 0.8485、0.8358、0.9848、0.8182、0.6667、0.8636、0.7424。对于WBCD数据库，分别针对k-NN、DT、RF、MLR、NB、SVM、MMDC获得以下准确度值； 0.9856、0.9568、0.9784、0.9856、0.9856、0.9856、0.9784。其他结果在实验研究部分详细给出。选择最准确的 MLA 用于人类生命的医学诊断非常重要。因此，在医学或文献中任何领域的 MLA 进行的研究中，如何从 MLA 获得的最佳分数将被引入文献中。在这项研究中，对如何做出正确的医学诊断进行了原创性研究，这是人类生命中最重要的问题之一。