The purpose of this study is twofold: (1) to derive a workflow consensus from multiple clinical activity logs and (2) to detect workflow outliers automatically and without prior knowledge from experts.
Methods
Workflow mining is used in this paper to derive consensus workflow from multiple surgical activity logs using tree-guided multiple sequence alignment. To detect outliers, a global pair-wise sequence alignment (Needleman–Wunsch) algorithm is used. The proposed method is validated for Laparoscopic Cholecystectomy (LAPCHOL).
Results
An activity log is directly derived for each LAPCHOL surgery from laparoscopic video using an already developed instrument tracking tool. We showed that a generic consensus can be derived from surgical activity logs using multi-alignment. In total 26 surgery logs are used to derive the consensus for laparoscopic cholecystectomy. The derived consensus conforms to the main steps of laparoscopic cholecystectomy as described in best practices. Using global pair-wise alignment, we showed that outliers can be detected from surgeries using the consensus and the surgical activity log.
Conclusion
Alignment techniques can be used to derive consensus and to detect outliers from clinical activity logs. Detecting outliers particularly in surgery is a main step to automatically mine and analyse the underlying cause of these outliers and improve surgical practices.
► Defines a workflow mining framework for medical environments such as the OR, ICU, and PACU. ► Derives a surgical consensus from multiple activity logs from those environments. ► Detects outliers using global alignment by comparing new activity logs to the general consensus. ► The proposed algorithm is validated for laparoscopic surgery.
