• Preethika Sequeira
• Shifana Begum

In health-related emergencies, timely and accurate medication recommendations are critical for effective treatment and improved patient outcomes. In order to improve decision-making and automate medicine selection, an ML-Powered Emergency medicine Assistance for Critical Healthcare system that makes use of machine learning techniques was introduced. To provide personalized and trustworthy pharmaceutical recommendations, the system examines patient data, such as symptoms, medical history, and health indicators. The framework guarantees excellent accuracy in forecasting the optimal course of action by using machine learning techniques like Naive Bayes, Random Forest, Decision Tree, Gradient Boosting, and Logistic Regression. In order to deliver a holistic solution that encourages preventative healthcare by recognizing potential dangers and providing customized lifestyle and medication suggestions, the system integrates predictive analytics and classification techniques in addition to emergency treatment. This proactive approach reduces medical errors, bridges gaps, and enhances healthcare delivery in resource-constrained environments. By automating prescription suggestions, the framework lowers human involvement, streamlines decision-making, and supports healthcare practitioners in making decisions.

Machine Learning, Emergency Drug Assistance, Healthcare Decision Support, Personalized Medication Recommendations, Predictive Analytics, Naive Bayes, Random Forest, Logistic Regression, Gradient Boosting.

"ML-POWERED EMERGENCY DRUG ASSISTANCE FOR CRITICAL HEALTHCARE NEEDS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 7, page no.77-83, July-2025, Available :http://www.jetir.org/papers/JETIRGX06015.pdf

"ML-POWERED EMERGENCY DRUG ASSISTANCE FOR CRITICAL HEALTHCARE NEEDS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 7, page no. pp77-83, July-2025, Available at : http://www.jetir.org/papers/JETIRGX06015.pdf