The growing significance of machine learning techniques in medical diagnosis has prompted numerous studies focusing on Chronic Kidney Disease (CKD) detection. This survey paper presents a comprehensive overview of the recent advancements in applying machine learning algorithms for CKD diagnosis. By analyzing a wide array of research articles and studies, this paper aims to provide a holistic understanding of the diverse methodologies employed in CKD detection using machine learning. The survey delves into various machine learning algorithms, such as Logistic Regression, Decision Trees, Support Vector Machines, and K-Nearest Neighbors, highlighting their strengths, limitations, and suitability for CKD detection. The paper also explores the pivotal role of feature selection in diagnosis models. Furthermore, examines the challenges associated with imbalanced datasets, noise, and missing values, and explores how researchers have addressed these issues in their approaches. Through an in-depth analysis of existing literature, this survey paper synthesizes the current state of CKD detection using machine learning and identifies trends, gaps, and possible areas for future research. The ultimate aim is to facilitate a comprehensive understanding of the field, aiding researchers and medical professionals in making informed decisions when developing and applying machine learning-based CKD diagnosis systems.