No abstract

The goals of the MELANIE project are to determine if disease-associated patterns can be detected in high resolution two-dimensional polyacrylamide gel electrophoresis (HR 2D-PAGE) images and if a diagnosis can be established automatically by computer. The ELSIE/MELANIE system is a set of computer programs which automatically detect, quantify, and compare protein spots shown on HR 2D-PAGE images. Classification programs help the physician to find disease-associated patterns from a given set of two-dimensional gel electrophoresis images and to form diagnostic rules. Prototype expert systems that use these rules to establish a diagnosis from new HR 2D-PAGE images have been developed. They successfully diagnosed cirrhosis of the liver and were able to distinguish a variety of cancer types from biopsies known to be cancerous.

BACKGROUND:Methicillin-resistant Staphylococcus aureus (MRSA) is an escalating problem in hospitals worldwide. The hospital reservoir for MRSA includes recognized and unrecognized colonized or infected patients, as well as previously colonized or infected patients readmitted to the hospital. Early and appropriate infection control measures (ICM) are key elements to reduce MRSA transmission and to control the hospital reservoir.OBJECTIVE: To describe the role of an expert system applied to the control of MRSA at a large medical center (1,600 beds) with high endemic rates. METHODS:The University Hospital of Geneva has an extended hospital information system (HIS), DIOGENE, structured with an open distributed architecture. It includes administrative, medical, nursing, and laboratory applications with their relational databases. Among available patient databases, clinical microbiology laboratory and admission-discharge-transfer (ADT) databases are used to generate computer alerts. A laboratory alert (lab alert) is printed daily in the Infection Control Program (ICP) offices, listing all patients with cultures positive for MRSA detected within the preceding 24 hours. Patients might be either newly detected patients colonized or infected with MRSA, or previously recognized MRSA patients having surveillance cultures. The ICP nurses subsequently go to the ward or call the ward personnel to implement ICM. A second alert, the "readmission alert," detects readmission to the hospital of any patient previously colonized or infected with MRSA by periodic queries (q 1 min) to the ADT database. The readmission alert is printed in the ICP offices, but also forwarded with added guidelines to the emergency room.RESULTS: During the first 12 months of application (July 1994 to June 1995), the lab alert detected an average of 4.6 isolates per day, corresponding to 314 hospital admissions (248 patients); the use of this alert saved time for the ICP nurses by improving work organization. There were 438 readmission alerts (1.2 alerts per day) over the study period; of 347 patients screened immediately upon readmission, 114 (33%) were positive for MRSA carriage. Delayed recognition of readmitted MRSA carriers decreased significantly after the implementation of this alert; the proportion of MRSA patients recognized at the time of admission to the hospital increased from 13% in 1993 to 40% in 1995 (P<.001).CONCLUSIONS: Hospital information system-based alerts can play an important role in the surveillance and early prevention of MRSA transmission, and it can help to recognize patterns of colonization and transmission (Infect Control Hosp Epidemiol 1996;17:496-502).

Abstract:For medical records, the challenge for the present decade is Natural Language Processing (NLP) of texts, and the construction of an adequate Knowledge Representation. This article describes the components of an NLP system, which is currently being developed in the Geneva Hospital, and within the European Community’s AIM programme. They are: a Natural Language Analyser, a Conceptual Graphs Builder, a Data Base Storage component, a Query Processor, a Natural Language Generator and, in addition, a Translator, a Diagnosis Encoding System and a Literature Indexing System. Taking advantage of a closed domain of knowledge, defined around a medical specialty, a method called proximity processing has been developed. In this situation no parser of the initial text is needed, and the system is based on semantical information of near words in sentences. The benefits are: easy implementation, portability between languages, robustness towards badly-formed sentences, and a sound representation using conceptual graphs.