Electrolytes assessed by point-of-care testing - Are the values comparable with results obtained from the central laboratory?

Abstract

Background and aims: When dealing with very sick patients, the speed and accuracy of tests to detect metabolic derangements is very important. We evaluated if there was agreement between whole blood electrolytes measured by a point-of-care device and serum electrolytes measured using indirect ion-selective electrodes.

Materials and methods: In this prospective study, electrolytes were analyzed in 44 paired samples drawn from critically ill patients. Whole blood electrolytes were analyzed using a point-of-care blood gas analyzer and serum electrolytes were analyzed in the central laboratory on samples transported through a rapid transit pneumatic system. Agreement was summarized by the mean difference with 95% limits of agreement (LOA) and Lin's concordance correlation (p(c)).

Results: There was a significant difference in the mean (±standard deviation) sodium value between whole blood and serum samples (135.8 ± 5.7 mmol/L vs. 139.9 ± 5.4 mmol/L, P < 0.001), with the agreement being modest (p(c) = 0.71; mean difference -4.0; 95% LOA -8.78 to 0.65). Although the agreement between whole blood and serum potassium was good (p(c) = 0.96), and the average difference small (-0.3; 95% LOA -0.72 to 0.13), individual differences were clinically significant, particularly at lower potassium values. For potassium values <3.0 mmol/L, the concordance was low (p(c) = 0.53) and the LOA was wide (1.0 to -0.13). The concordance for potassium was good (p(c) = 0.96) for values ≥3.0 (mean difference -0.2; 95% LOA -0.48 to 0.06).

Conclusions: Clinicians should be aware of the difference between whole blood and serum electrolytes, particularly when urgent samples are tested at point of care and routine follow-up electrolytes are sent to the central laboratory. A correction factor needs to be determined at each center.

Keywords: Agreement; bland and altman; concordance; electrolytes; point-of-care testing.

Figure 1

Relationship between serum sodium and whole blood sodium values analyzed for 44 sodium values. (a) Concordance plot showing agreement between serum and whole blood sodium samples (in mmol/L). The solid line indicates the line of perfect concordance and the dotted line indicates the best fitted line for our data. (b) Bland and Altman plot depicting the agreement between serum and whole blood values with 95% LOA (small dotted lines) and the observed average agreement (bold dotted lines). The bold line at y = 0 indicates the line of perfect average agreement

Figure 2

Relationship between serum potassium and whole blood potassium. (a) Concordance plot showing agreement between serum and whole blood potassium samples (in mmol/L). The solid line indicates the line of perfect concordance and the dotted line indicates the best fitted line for our data. (b) Bland and Altman plot depicting the agreement between serum and whole blood values with 95% LOA (small dotted lines) and the observed average agreement (bold dotted lines).The bold line at y = 0 indicates the line of perfect average agreement

Figure 3

Relationship between serum potassium and whole blood potassium analyzed for 11 potassium values <3 mmol/L. (a) Concordance plot showing agreement between serum and whole blood potassium samples <3mmol/L. The solid line indicates the line of perfect concordance and the dotted line indicates the best fitted line for our data. (b) Bland and Altman plot depicting the agreement between serum and whole blood values with 95% LOA (small dotted lines) and the observed average agreement (bold dotted lines).The bold line at y = 0 indicates the line of perfect average agreement