A System for Monitoring Nosocomial Infections

In this work, we describe a project, jointly started by DEIS University of Bologna and Dianoema S.p.A., in order to build a system which is able to monitor nosocomial infections. To this purpose, the system computes various statistics that are based on the count of patient infections over a period of time. The precise count of patient infections needs a precise definition of bacterial strains. In order to find bacterial strains, clustering has been applied on the microbiological data collected along two years in an Italian hospital. 1 MICROBIOLOGICAL DATA ANALYSIS A very important problem that arises in hospitals is the monitoring and detection of nosocomial infections. A hospitalacquired or nosocomial infection is a disease that develops after the admission to the hospital, and is the consequence of a treatment, not necessarily a surgical one, or work by the hospital staff. Usually, a disease is considered a nosocomial infection if it develops 72 hours after the admission to the hospital. In Italy, this problem is very serious: actually almost the 15% of patients admitted to hospitals develop a nosocomial infection. In order to monitor nosocomial infections, the results of microbiological analyses must be carefully collected and analysed. In Italy, a great number of hospitals manages analysis results by means of a software system named Italab C/S, developed by Dianoema S.p.A. Italab C/S is a Laboratory Information System based on a Client/Server architecture, which manages all the activities of the various analysis laboratories of the hospital. Italab C/S stores all the information concerning patients, the analysis requests, and the analysis results. In particular, for bacterial infections data includes: • information about the patient: sex, age, hospital unit where the patient has been admitted; • the kind of material (specimen) to be analysed (e.g., blood, urine, saliva, pus, etc.) and its origin (the body part where the specimen was collected); • the date when the specimen was collected (often substituted with the analysis request date); • for every different bacterium identified, its species and its