Medicine Overdose Detection System Using Machine Learning

Computer Science Engineering

Medicine overdose is a significant medical issue affecting individuals of all age groups, often resulting from incorrect dosage, lack of medical supervision, or misinterpretation of drug instructions. This project introduces an intelligent system designed to predict the likelihood of a medicine overdose using two machine learning algorithms: Support Vector Machine (SVM) and Logistic Regression. Users interact with the system through a secure registration and login interface, providing personal and medical information such as age, gender, BMI, medicine type, and dosage. The data undergoes preprocessing including normalization, encoding, and feature extraction to ensure it is suitable for model training. SVM and Logistic Regression are employed to analyze the processed data and classify the risk level associated with the medicine intake. The models generate outputs that categorize the overdose risk as high, moderate, or low, thereby assisting users in identifying potentially harmful dosages. This system is especially beneficial for individuals practicing self-medication and in regions with limited access to healthcare professionals. The comparative analysis of both algorithms allows for validation and improvement of prediction accuracy, ultimately supporting safer medicine usage.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.