PubMed Health⌕ Search
Home/Archive/PubMed

PubMed · 7569742

Computational intelligence for laboratory information systems.

P Eklund·J J Forsström
View original source ↗Export metadata ↓

Abstract

Non-linear models, such as given by neural networks and fuzzy logic, have established a good reputation for medical data analysis as computational and logical counterparts to statistical methods. Whereas multilayer perceptrons perform well with large data sets, a combination of neural learning together with fuzzy logical network interpretations provides a network reduction well suited for smaller data sets. The aim of this paper is to present an approach to neural fuzzy systems data analysis and knowledge acquisition in laboratory information systems. We also describe a software system, DiagaiD, which provides an analysis and development workbench involving laboratory data.

Explore related subjects

Clinical Laboratory Information SystemsComputer SystemsData Interpretation, StatisticalFuzzy LogicNeural Networks, ComputerNonlinear DynamicsSoftwareJournal Article

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

P Eklund, J J Forsström. 1995. Computational intelligence for laboratory information systems.. https://doi.org/10.3109/00365519509088447

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related citations

PubMed2002

[Screening and follow-up of nosocomial infections by multiresistant bacteria using the Bacterio software. Microbiology laboratory data].

OBJECTIVE: To study the relationship between the prevalence of multi-resistant bacteria (MRB) and nosocomial MRB infections. METHOD: This work presents the results of a follow up of hospital-acquired infections due to multidrug-resistant bacteria (MRB), based on microbiology detection with the Bacterio software and clinical confirmation. RESULTS: Clinical responses reached 93%. During the year 2000, the incidence of hospital-acquired MRB infections was 1.23 for 1000 hospitalization days and 1.00 for 100 admissions. Ticarcilline-resistant P. aeruginosa were responsible for 32% of hospital-acquired MRB infections. The incidence curve of MRB colonization was parallel with that of hospital-acquired infections. Hence, the incidence of MRB colonization is a rapid and good means of assessing the best probabilistic antibiotherapy especially in intensive care units. COMMENTS: Examination of medical records is however necessary to obtain complementary clinical information on: risk factors, use of medical devices, medical or chirurgical antecedents and prior antibiotherapy. The easiness of detection and management of hospital-acquired infections allowed us to extend its use in 2001 to the follow-up of all hospital-acquired infections, with or without MRB. Bacterio is also able to detect the hospital-acquired infections that, according to the recent decree (No. 2001-671, july 30th, 2001), must be declared to the sanitary authorities. Such suspicions should then be validated by the clinicians and the practising hygienist.

Clinical Laboratory Information Systems↗
PubMed2002

Empowering patients with point-of-care testing.

Point-of-care testing (POCT) is becoming a major force in the future evolution of healthcare. It has the potential to expand further by increasing the accessibility, speed and accuracy of results. New developments in POCT technology will predictably occur in four areas: scope, connectivity, non-invasiveness and miniaturization. POCT test menus will continue to grow, wireless connectivity with automatic data capture will become the norm and non-invasive POCT will evolve into a wide range of sizes, shapes and functionalities.

Clinical Laboratory Information Systems↗