Clinical interventions subordinate to medical pathways are characterized by patientspecific complications and variability of process durations. At the same time, estimating these durations is critical for developing accurate schedules. However, data of clinical information systems are recorded primarily for reporting, liability, and billing purposes; the systems do not fully capture detailed process information. Very little work has been done on predicting these types of durations for scheduling, other than using experts’ estimates or historical averages. We evaluate how predictive analytics based on patientspecific features can help develop estimates of otherwise unknown process durations, taking infusion chemotherapy as an example. We highlight the challenges of using clinical real-life data and discuss how we plan to address these challenges in the future
Oberste, Luis; Aydingül, Okan; Jussupow, Ekaterina; and Heinzl, Armin, "When Every Minute Matters – Using Predictive Analytics of Intervention Durations to Support Hospital Scheduling" (2021). PACIS 2021 Proceedings. 221.
When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.