Process mining extracts insights about business processes from information system data. However, traditional techniques often assume static processes, which is unrealistic. Detecting process drifts is crucial for accurate analysis, but existing methods lack consistent detection due to parameter sensitivity and a lack of a standard comparison protocol. This paper introduces the Adaptive Interactive Process Drift Detection (IPDD), which applies the ADWIN change detector to process model quality metrics over time. Adaptive IPDD continuously assesses fitness and precision metrics to detect drifts. Results show IPDD’s effectiveness in synthetic datasets, comparable to Apromore in drift detection and outperforming Apromore AWIN in Mean delay. We also highlight that IPDD exhibits stable performance even with low window size values. We also evaluate a real-life event log representing an Italian company’s ticketing management process using Adaptive IPDD. The results demonstrated that the drift analysis for real scenarios can be improved by exploring the user interface of IPDD.