Search

Your search keyword '"Irjala K"' showing total 537 results
Start Over Author "Irjala K"
537 results on '"Irjala K"'

21. Comprehensive real-time epidemiological data from respiratory infections in Finland between 2010 and 2014 obtained from an automated and multianalyte mariPOC (R) respiratory pathogen test

Author

University of Helsinki, Medicum, Gunell, M., Antikainen, P., Porjo, N., Irjala, K., Vakkila, J., Hotakainen, K., Kaukoranta, S. S., Hirvonen, J. J., Saha, K., Manninen, R., Forsblom, B., Rantakokko-Jalava, K., Peltola, V., Koskinen, J. O., Huovinen, P., University of Helsinki, Medicum, Gunell, M., Antikainen, P., Porjo, N., Irjala, K., Vakkila, J., Hotakainen, K., Kaukoranta, S. S., Hirvonen, J. J., Saha, K., Manninen, R., Forsblom, B., Rantakokko-Jalava, K., Peltola, V., Koskinen, J. O., and Huovinen, P.

Abstract

Respiratory viruses cause seasonal epidemics every year. Several respiratory pathogens are circulating simultaneously and typical symptoms of different respiratory infections are alike, meaning it is challenging to identify and diagnose different respiratory pathogens based on symptoms alone. mariPOC (R) is an automated, multianalyte antigen test which allows the rapid detection of nine respiratory infection pathogens [influenza A and B viruses, respiratory syncytial virus (RSV), human metapneumovirus, adenovirus, parainfluenza 1-3 viruses and pneumococci] from a single nasopharyngeal swab or aspirate samples, and, in addition, can be linked to laboratory information systems. During the study period from November 2010 to June 2014, a total of 22, 485 multianalyte respi tests were performed in the 14 participating laboratories in Finland and, in total, 6897 positive analyte results were recorded. Of the tested samples, 25 % were positive for one respiratory pathogen, with RSV (9.8 %) and influenza A virus (7.2 %) being the most common findings, and 0.65 % of the samples were multivirus-positive. Only small geographical variations in seasonal epidemics occurred. Our results show that the mariPOC (R) multianalyte respi test allows simultaneous detection of several respiratory pathogens in real time. The results are reliable and give the clinician a picture of the current epidemiological situation, thus minimising guesswork.

Published
2016

26. Coding drug effects on laboratory tests for health care information systems

Author

Grönroos, P., Irjala, K., and Forsström, J. J.

Subjects
Pharmacology, Drug-Related Side Effects and Adverse Reactions, Clinical Laboratory Techniques, Humans, Classification, Clinical Laboratory Information Systems, Research Article
Abstract

Drugs interfere with laboratory diagnostics. This interference is not only confusing for clinicians but may lead to wrong diagnoses or treatments as well as unnecessary further tests. However, at the moment the drug-laboratory interferences are usually ignored in patient care because clinicians do not know or remember these properties of drugs. In Turku University Central Hospital we are now able to bring this information automatically available for clinicians by using a computerized system for linking individual patient medication data with laboratory information system. For this purpose, we are building a rule base containing the effects of drugs on laboratory tests. In order that the rule base would give the maximum benefit for all users, even other hospitals, the data included have to be classified and coded properly taking into account the various requirements and needs of all users. In this paper we introduce a coding scheme for classification and coding of drug effects on laboratory tests.

Published
1995

39. Using data preprocessing and single layer perceptron to analyze laboratory data

Author

Forsström, J. J., Irjala, K., Selén, Gustaf, Nyström, Mats, Eklund, Patrik, Forsström, J. J., Irjala, K., Selén, Gustaf, Nyström, Mats, and Eklund, Patrik

Abstract

During daily work in hospitals a large amount of clinical data is produced each day. Totally computerized patient records are not yet widely used but a large part of essential information is already stored on computer files. These include laboratory test results, diagnoses, codes for operations, codes of histopathological diagnoses and maybe even the patient's medication. Accordingly, these databases include much clinical knowledge that would be useful for clinicians. Laboratories try to support clinicians by producing reference values for laboratory tests. It is, of course, necessary information but, however, it does not give very much information about the weight of evidence that an abnormal laboratory test will give in special clinical settings. We have developed a software package - DiagaiD - in order to build a smart link between patient databases and clinicians. It utilizes neural network-based machine learning techniques and can produce decision support which meets the special needs of clinicians. From example cases it can learn clinically relevant transformations from original numeric values to logical values. By using data transformation together with a single layer perceptron it is possible to build nonlinear models from a set of preclassified example cases. In this paper, we use two small datasets to show how this scheme works in the diagnosis of acute appendicitis and in the diagnosis of myocardial infarction. Results are compared with those obtained using logistic regression or backpropagation neural networks. The performance of our neuro-fuzzy tool seemed to be slightly better in these two materials but the differences did not reach statistical significance.

Published
1995
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results