Abstract: Drug overdose is now the leading cause of death for those under 50 in the World.Inadequate data present a challenge for city officials, which prevents them from investigating the scale of the opioid overdose crisis.Various factors need to be considered in the prediction model for estimating the level of drug consumption, type of drug, and the location of the affected area.The aim of this project is to investigate several prediction and analysis models for forecasting drug use and overdoses by considering diverse data obtained from different sources, including sewage-based drug epidemiology, healthcare data, social networks data mining, and police data.Such analysis will help to formulate more effective policies and programs to combat fatal opioid overdoses.This project aims to explore, develop, and evaluate various prediction and analysis models to forecast drug usage trends and overdose risks by integrating diverse datasets. The data sources include sewage-based drug epidemiology, healthcare records, social media and network data mining, and police and law enforcement reports. Machine learning algorithms and statistical modeling will be employed to estimate the level of drug consumption, identify high-risk substances, and pinpoint geographical regions most affected by the crisis. Index Term: Drug Overdose Prediction, Opioid Crisis, Machine Learning, Predictive Analytics, Sewage-based Epidemiology, Data Mining, Healthcare Data, Social Media Analysis, Law Enforcement Data, Public Health Policy.
Lavanya et al. (Fri,) studied this question.