A Clinical Pathway Mining Approach to Enable Scheduling of Hospital Relocations and Treatment Services

As discussed in numerous studies, clinical pathways of patients form an appropriate tool for describing hospital processes and thereby provide a basis for increasing the effectiveness of hospitals. Developing pathways led to a considerable research investigating IT-techniques to support pathway generation. However, previous research neglected finding pathways designed to support scheduling of hospital relocations and treatment services. To close this gap, we first introduce a clinical pathway concept consisting of both pathway structure and pathway constraints suitable for scheduling tasks. Second, we provide a pathway mining method for automatically extracting corresponding pathways from standard hospital billing data required for the German §21-KHentgG. Applying our approach to a real world dataset of a university hospital, we illustrate the results using a pathway for malignant neoplasm of prostate containing feasible time windows and precedence relations of treatments, durations at attended wards as well as possible process improvements stimulated from the results.