ICDE '95 Proceedings of the Eleventh International Conference on Data Engineering
BIDE: Efficient Mining of Frequent Closed Sequences
ICDE '04 Proceedings of the 20th International Conference on Data Engineering
Mining Sequential Patterns by Pattern-Growth: The PrefixSpan Approach
IEEE Transactions on Knowledge and Data Engineering
Mining Therapeutic Patterns from Clinical Data for Juvenile Diabetes
Fundamenta Informaticae - To Andrzej Skowron on His 70th Birthday
| Hi-index | 0.00 |
Analysing sequential medical data to detect hidden patterns has recently received great attention in a variety of applications. This paper addresses the analysis of patients' exam log data to rebuild from operational data an image of the steps of the medical treatment process. The analysis is performed on the medical treatment of diabetic patients provided by a Local Sanitary Agency in Italy. The extracted knowledge allows highlighting medical pathways typically adopted for specific diseases, as well as discovering deviations with respect to them, which can indicate alternative medical treatments, medical/patient negligence or incorrect procedures for data collection. Detected medical pathways include both the sets of exams which are frequently done together, and the sequences of exam sets frequently followed by patients. The proposed approach is based on the extraction of the frequent closed sequences, which provide, in a compact form, the medical pathways of interest.