AI-Powered Pattern Mining for Drug Overdose Insights: Leveraging Apriori and FP-Growth

The increasing rate of accidental drug-related deaths in the United States continues to pose serious public health challenges, especially amid the ongoing opioid crisis. This study uses data mining techniques, specifically the Apriori and FP-Growth algorithms, to analyze drug combinations involved in overdose cases using the “Accidental_Drug_Related_Deaths” dataset. After thorough preprocessing and converting data into transaction format, we spot frequent patterns and associations among commonly used substances. A comparison shows differences in algorithm efficiency and usefulness, with FP-Growth offering better scalability and memory efficiency, while Apriori is simpler for smaller datasets. Our results highlight important drug interaction patterns that could guide clinical actions and policy decisions. This study provides current insights (Patel & Mohammed, 2023; Usmani et al., 2025) into applying association rule mining for public health analytics and overdose prevention in 2025.