<![CDATA[Artificial intelligence (AI) application in disease classification is a rapidly growing area of interest for medical practitioners in diagnosing illnesses. This work provides a comprehensive study on the application of AI, particularly Machine Learning (ML) algorithms, for predicting diseases based on symptoms in healthcare. The research wants to improve the diagnosis of illnesses using symptom data by utilizing two popular ML algorithms, the Support Vector Machine (SVM) and the Gradient Boosting Classifier (GBC). The research utilizes a dataset containing 4,921 items, split into 80% for training and 20% for testing. The methodology section includes information on the procedures for collecting and preparing data, such as importing data, handling missing values, categorizing symptom severity, and dividing the data. Subsequently, a range of measurement performances such as F1 score, accuracy, precision, and recall are utilized to evaluate the model technology's effectiveness. The default hyperparameters of the GBC model are used for evaluation, while the SVM model is optimized through parameter adjustments using GridSearchCV. The effectiveness of the GBC model is evaluated utilizing similar metrics, while the SVM model demonstrates high accuracy across different hyperparameter configurations. The research suggests that ML algorithms have the potential to enhance the precision of predicting illnesses, and it also considers the significance of these discoveries within the broader scope of AI in healthcare. The research sets the stage for potential explorations in this field, emphasizing the importance of continual research and enhancement of AI techniques to enhance healthcare outcomes.]]>
Copyrights © 2025
