Level of agreement of point-of-care and laboratory HbA1c measurements in the preoperative outpatient clinic in non-diabetic patients who are overweight or obese

Abstract

Implementation of point-of-care HbA1c devices in the preoperative outpatient clinic might facilitate the early diagnosis of glycemic disturbances in overweight or obese patients undergoing surgery, but validation studies in this setting do not exist. We determined the level of agreement between a point-of-care and laboratory HbA1c test in non-diabetic patients visiting the outpatient clinic for preoperative risk profiling. Point-of-care HbA1c levels were measured in whole blood obtained by a finger prick (Siemens DCA Vantage HbA1c analyzer) and in hemolysed EDTA blood in the central laboratory (LAB). Bland Altman and Clarke's error grid analysis were used to analyze the agreement between the point-of-care and laboratory measurements. Patients (n = 49) were 55 ± 11 years old, 47% were male with a body mass index (BMI) of 30.6 ± 3.4 kg/m². The mean HbA1c was 38.1 ± 3.7 mmol/mol or 5.6 ± 0.3%. One patient was diagnosed with a HbA1c indicative for diabetes mellitus (6.7%). Bland Altman analysis revealed a bias of - 0.53 ± 1.81 mmol/mol with limits of agreement of - 4.09 to 3.03 mmol/mol and a bias of - 0.05 ± 0.17% with limits of agreement - 0.39 to 0.28%. The percentage error was 9.2% and 5.9% for HbA1c expressed in mmol/mol and %, respectively. Clarke's error grid analysis showed that 48 out of 49 measurements were located in area A (98%). Point-of-care HbA1c measurements showed a high level of agreement with the laboratory test in the outpatient setting, and may be used for preoperative risk profiling in patients prone to cardiometabolic complications.Trial registration: Netherlands Trial Register NTR3057.

Keywords: Anesthesia; Diabetes; Glucose; Obesity; Preoperative screening.

Fig. 1

Bland Altman analysis for paired point-of-care (POC) or laboratory (LAB) HbA1c measurements in mmol/mol (a) and % (b)

Fig. 2

Clarke’s error grid analysis of for the level of agreement between the POC and LAB HbA1c tests expressed as mmol/mol (a) or % (b). Zone A (green) shows the clinical acceptable area with an acceptance of 10% deviation between the two methods. Zone B (yellow) represents an error > 10% and in this area hyperglycemia is over- or underestimated with possibly changing clinical decision-making. Zone C (red) represents a clinically unsafe zone in which hyperglycemia is severely under- or overestimated with a high risk for inadequate clinical decision-making

Fig. 3

The relative number of patients with normal HbA1c values (≤ 5.5%), prediabetes (5.6–6.4%) and diabetes (≥ 6.5%)according to the laboratory or point-of-care HbA1c test method