Extraction of Medical Pathways from Electronic Patient Records

Extraction of Medical Pathways from Electronic Patient Records

Dario Antonelli (Politecnico di Torino, Italy), Elena Baralis (Politecnico di Torino, Italy), Giulia Bruno (Politecnico di Torino, Italy), Silvia Chiusano (Politecnico di Torino, Italy), Naeem A. Mahoto (Politecnico di Torino, Italy) and Caterina Petrigni (Politecnico di Torino, Italy)
Copyright: © 2013 |Pages: 15
DOI: 10.4018/978-1-4666-2455-9.ch051
OnDemand PDF Download:
No Current Special Offers


With the introduction of electronic medical records, a large amount of patients’ medical data has been available. An actual problem in this domain is to perform reverse engineering of the medical treatment process to highlight medical pathways typically adopted for specific health conditions. This chapter addresses the ability of sequential data mining techniques to reconstruct the actual medical pathways followed by patients. Detected medical pathways are in the form of sets of exams frequently done together, sequences of exam sets frequently followed by patients and frequent correlations between exam sets. The analysis shows that the majority of the extracted pathways are consistent with the medical guidelines, but also reveals some unexpected results, which can be useful both to enrich existing guidelines and to improve the public sanitary service.
Chapter Preview


The use of data mining techniques in healthcare institutes has taken great attention due to the large amount of generated data (Hardin, 2007). A lot of research has been carried out for enhancing and improving medical practices, disease management and resource utilization.

The medical treatment relationships and condition of a patient for a given disease can be extracted by means of data mining techniques (Cerrito, 2007). The decision support tools for clinical healthcare based on data mining techniques are addressed in Siddiq (2009), Kazemazadeh (2006) and Palniappan (2008). However, these works do not exploit real datasets for experiments. In Stoblba (2007), data warehousing and data mining techniques are emphasized essential to provide evidence-based guidelines for clinicians. Health care resources optimal utilization is focused in Dart (2003) and Rossille (2008).

Chen (2007) presents possible side effects of using multiple drugs during pregnancy period with the use of association rule mining approach. The SmartRule technique is used to mine association rules from a saved tabular pregnancy data and finds Maximum Frequent Itemsets (MFI) based on user specified minimum support threshold. The subset of MFIs is selected with targeted attributes by users to derive association rules for a given support and confidence level. The author tries to highlight and warn the drugs that may cause harm to unborn babies.

Complete Chapter List

Search this Book: