Assessing the Quality of Care for End Stage Renal Failure Patients by means of Artificial Intelligence Methodologies

End Stage Renal Disease is a severe chronic condition that corresponds to the ¯nal stage of kidney failure. Hemodialysis (HD) is the most widely used treatment method for ESRD. The HD treatment is costly and demanding from an organizational viewpoint, requiring day hospital beds, specialized nurses and periodical visits and exams of out- patients. In order to assess the performance of HD centers, we are developing an auditing system, which resorts to (i) temporal data mining techniques, to discover relationships between the time patterns of the data automat- ically collected during HD sessions and the performance outcomes, and to (ii) case based reasoning (CBR) to retrieve similar time series within the HD data, in order to evaluate the frequency of critical patterns. In particular, as regards temporal data mining, two new methods for asso- ciation rule discovery and temporal rule discovery have been applied to the HD time series. As regards CBR, we have implemented a case-based retrieval system, which resorts to a multi-step architecture, and exploits dimensionality reduction techniques for e±cient time series indexing. The overall approach has demonstrated to be suitable for knowledge dis- covery and critical patterns similarity assessment on real patients' data, and its use in the context of an auditing system for dialysis manage- ment is helping clinicians to improve their understanding of the patients behaviour.