This paper presents a machine learning (ML)-based e-diagnostic system specifically designed for the early detection of gestational diabetes mellitus (GDM). The study aims to explore the application of the K-nearest neighbors (KNN) algorithm on the Pima Indians Diabetes dataset to predict diabetes diagnosis. The KNN algorithm, a non-parametric instance-based learning method, was used to classify individuals as diabetic or non-diabetic. The research involved data preprocessing, including handling missing values, feature scaling, and splitting the data into training and testing sets. The KNN classifier was trained and tested using these parameters, achieving an accuracy of approximately 0.76 in predicting diabetes diagnosis. The study also discussed the importance of hyperparameter tuning, data preprocessing, and handling imbalanced data to optimize KNN model performance. The findings suggest that KNN can serve as a viable tool for early diabetes detection, paving the way for broader applications in healthcare and predictive modeling. The study evaluated various machine learning approaches, including recall, accuracy, precision, and F1-score, and highlighted the significance of these metrics in assessing the model's performance.This paper presents a machine learning (ML)-based e-diagnostic system specifically designed for the early detection of gestational diabetes mellitus (GDM). The study aims to explore the application of the K-nearest neighbors (KNN) algorithm on the Pima Indians Diabetes dataset to predict diabetes diagnosis. The KNN algorithm, a non-parametric instance-based learning method, was used to classify individuals as diabetic or non-diabetic. The research involved data preprocessing, including handling missing values, feature scaling, and splitting the data into training and testing sets. The KNN classifier was trained and tested using these parameters, achieving an accuracy of approximately 0.76 in predicting diabetes diagnosis. The study also discussed the importance of hyperparameter tuning, data preprocessing, and handling imbalanced data to optimize KNN model performance. The findings suggest that KNN can serve as a viable tool for early diabetes detection, paving the way for broader applications in healthcare and predictive modeling. The study evaluated various machine learning approaches, including recall, accuracy, precision, and F1-score, and highlighted the significance of these metrics in assessing the model's performance.