OPTIMIZE EMERGENCY MEDICATION DECISIONS THROUGH RANDOM FOREST & ADAPTIVE DECISION SUPPORT SYSTEM FOR A PERSONALIZED DRUG RECOMMENDATION FRAMEWORK

Abstract

In healthcare, prompt and precise medicine recommendations during medical crises may greatly influence patient outcomes. This project introduces a comprehensive "Drug Recommendation System for Medical Emergencies utilizing Machine Learning," developed in Python. The system employs two robust classification algorithms, namely the Random Forest Classifier and the Decision Tree Classifier, achieving exceptional accuracies of 98.6% on both training and test datasets. The dataset used in this research consists of 1200 records, each defined by 30 attributes. These elements include a varied array of medical indicators, offering a comprehensive depiction of patient health. The dataset has 10 unique categories, representing a range of medical conditions: Allergy, Chickenpox, Chronic, Cold, Diabetes, Fungal, GERD, Jaundice, Malaria, and Pneumonia. The Random Forest Classifier, noted for its ensemble learning features, and the Decision Tree Classifier, esteemed for its interpretability, were carefully selected to represent the complex interactions within the dataset. Both algorithms demonstrated outstanding performance, attaining flawless accuracy ratings on both training and test datasets, indicating the effectiveness of the created recommendation system. This study exemplifies the efficacy of machine learning in healthcare applications and highlights the essential need of precise medicine recommendations in emergency medical situations. The attained 98.6% accuracy highlights the system's stability and precision, fostering trust in its prospective use in practical medical environments. This Drug Recommendation System exemplifies the revolutionary influence of machine learning on patient care at the crossroads of technology and healthcare in crucial scenarios.