S Zubillaga | PubMed Health

PubMed1997

DIAVAL, a Bayesian expert system for echocardiography.

DIAVAL is an expert system for the diagnosis of heart diseases, including several kinds of data, mainly from echocardiography. The first part of this paper is devoted to the causal probabilistic model which constitutes the knowledge base of the expert system in the form of a Bayesian network, emphasizing the importance of the OR gate. The second part deals with the process of diagnosis, which consists of computing the a posteriori probabilities, selecting the most probable and most relevant diagnoses, and generating a written report. It also describes the results of the evaluation of the program.

Artificial Intelligence↗

PubMedDate not supplied

[Randomized study of two different fat emulsions in total parenteral nutrition of malnourished surgical patients;effect of infectious morbidity and mortality].

GOAL: Lipid infusions of a physical mixture of medium-chain triglycerides and long-chain triglycerides (MCT/LCT) used in peri-operative total parenteral nutrition (TPN) have a lower immunosuppressive effect in laboratory studies than emulsions containing only long-chain triglycerides (LCT). The purpose of the present study was to compare the incidence of nosocomial infections and the in-hospital mortality of severely undernourished surgical patients treated with TPN using an MCT/LCT lipid emulsion or with an LCT mixture, administered under a randomized, double blind protocol. PATIENTS AND METHODS: A total of 72 severely undernourished patients subjected to planned or emergency laparotomy were prospectively recruited and stratified by the presence or absence of cancer, on admission to the departments of General Surgery and Intensive Care Medicine at a teaching hospital. The main outcome was the incidence of intra-hospital nosocomial infection and the secondary outcome was mortality. RESULTS: The patients in the study group (MCT/LCT) and the control group (LCT) shared similar characteristics. The patients in the MCT/LCT group had a significantly lower incidence of intra- abdominal abscesses (2/26) than those in the LCT group (10/31) (p < 0.05; RR 0.18; CI 95%; 0.03-0.89). There were no significant differences in the incidence of other infections. Nor was there a difference between the two groups in terms of the intra-hospital mortality (4/26 versus 11/31). In the stratified analysis, patients without cancer treated with MCT/LCT presented significantly fewer intra-abdominal abscesses (2/14) than those with LCT (5/8) (p < 0.05; RR 0.1; CI 95%; 0.01-0.79) and a significantly lower mortality (2/14 versus 5/8; p < 0.05; RR 0.1; CI 95%; 0.01-0.79). CONCLUSIONS: Lipid infusions of MCT/LCT used in peri-operative TPN protect severely undernourished surgical patients against the onset of intra-abdominal abscesses when compared with LCT infusions. Patients without cancer may obtain more benefit from the use of these mixtures.

Aged↗