Assessments of feline plasma biochemistry reference intervals for three in-house analysers and a commercial laboratory analyser

Abstract

For each species, the manufacturers of in-house analysers (and commercial laboratories) provide standard reference intervals (RIs) that do not account for any differences such as geographical population differences and do not overtly state the potential for variation between results obtained from serum or plasma. Additionally, biases have been demonstrated for in-house analysers which result in different RIs for each different type of analyser. The objective of this study was to calculate RIs (with 90% confidence intervals [CIs]) for 13 biochemistry analytes when tested on three commonly used in-house veterinary analysers, as well as a commercial laboratory analyser. The calculated RIs were then compared with those provided by the in-house analyser manufacturers and the commercial laboratory. Plasma samples were collected from 53 clinically normal cats. After centrifugation, plasma was divided into four aliquots; one aliquot was sent to the commercial laboratory and the remaining three were tested using the in-house biochemistry analysers. The distribution of results was used to choose the appropriate statistical technique for each analyte from each analyser to calculate RIs. Provided reference limits were deemed appropriate if they fell within the 90% CIs of the calculated reference limits. Transference validation was performed on provided and calculated RIs. Twenty-nine of a possible 102 provided reference limits (28%) were within the calculated 90% CIs. To ensure proper interpretation of laboratory results, practitioners should determine RIs for their practice populations and/or use reference change values when assessing their patients' clinical chemistry results.

Figure 1

(a) Histogram of raw data for alkaline phosphatase (ALP) on the Abaxis analyser. Note the left skew (calculated as 1.9, notably greater than the allowable range of –0.5 to 0.5) and the high peakedness (kurtosis); excess kurtosis is any value >0, and this was calculated as 4.9. (b) Histogram of Box–Cox transformed data for ALP on the Abaxis analyser. Note that (compared with [a]) there is no longer any appreciable skew (calculated as –0.02), and excess kurtosis is greatly reduced to 0.5. This histogram was determined to be a normal distribution by both Anderson–Dowling and Shapiro–Wilk techniques