ABSTRACT
In the face of intricate disease mechanisms and symptoms globally, there is a pressing need for advanced detection methods and treatment strategies. Today's lifestyle and habits contribute significantly to various health issues, underscoring the importance of early identification and prediction to mitigate their severity. Unfortunately, clinicians often struggle with precise diagnosis in the early stages of diseases. To address this challenge, machine learning algorithms offer promising predictive capabilities, assisting healthcare professionals, researchers, and patients alike. This paper proposes a novel approach to forecast chronic illnesses by integrating contextual factors like symptoms and lifestyle choices. It advocates for an interactive interface that engages users with pertinent questions, leveraging machine learning algorithms for prediction. By leveraging diverse datasets, the framework trains and validates models, ensuring accurate disease prognosis. Employing Convolutional Neural Networks for feature extraction, alongside classification models like Support Vector Machine, Naive Bayes, and Random Forest in R programming, ensures robust predictions. The resulting disease prediction system amalgamates these models, promising high accuracy and reliability, facilitating early intervention and enhanced patient outcomes. A user-friendly interface enhances the overall experience, streamlining the input of patient data. The paper provides a comparative analysis of outcomes generated by these algorithms, highlighting their efficacy.
