World Journal of Engineering Research and Technology

Dr. Levina Tukram*, Shaik Aman, Nitesh Jha, Bibek Pangeni, Roshan Kumar Mahato

ABSTRACT

Drug overdose, particularly opioid-related cases, has become a global public health crisis, ranking as the leading cause of death for individuals under 50. The challenge in addressing this epidemic lies in the inadequacy of available data, which hinders city officials from fully understanding the scale and distribution of drug-related incidents. Effective intervention requires a comprehensive predictive model capable of estimating drug consumption patterns, identifying high-risk areas, and categorizing the substances involved. Traditional methods of data collection often fail to capture real-time trends, making it difficult to develop timely and targeted prevention strategies. This studyexplores the application of predictive analytics in forecasting drug use and overdose trends by integrating diverse data sources, including sewage-based drug epidemiology, healthcare records, social media analysis, and law enforcement reports. By leveraging machine learning and data mining techniques, the project aims to enhance the accuracy of overdose predictions, enabling authorities to deploy resources efficiently and implement proactive measures. The findings will provide valuable insights for policymakers and healthcare professionals, facilitating data-driven strategies to combat opioid-related fatalities and improve public health outcomes.

[Full Text Article] [Download Certificate]