Using process mining algorithms for process improvement in healthcare

Abstract

Healthcare professionals must provide their patients with the best possible service and be well-informed and expert at carrying out complex surgical procedures to fulfill this responsibility. The aim of the medical treatments is fewer complications, shorter hospital stays, and a better patient experience. Through continuous learning and training, medical practitioners trained in up-to-date and state-of-the-art surgical techniques and technologies make productive and effective healthcare systems possible. Healthcare systems often report on problems with surgical processes, skipped procedures, unusual activities during operations, and lengthy transition times. This event log data allows implementing process mining methods to deliver medical professionals with simple and understandable findings using Petri nets for process analysis and enhancement. This study identifies the parallels and discrepancies between the pre-and post-stages and their respective frequency on each typical Central Venous Catheter (CVC) installation activity. The Process Mining for Python (PM4Py) frameworks used four major mining algorithms to view the event log (i.e., alpha miner, directly-follows graph (DFG), heuristic miner, and inductive miner). This study's findings indicate that medical residents are more susceptible to error during pre-operative procedures.