Comparison of Methodologies to Detect Low Levels of Hemolysis in Serum for Accurate Assessment of Serum microRNAs

Abstract

microRNAs have emerged as powerful regulators of many biological processes, and their expression in many cancer tissues has been shown to correlate with clinical parameters such as cancer type and prognosis. Present in a variety of biological fluids, microRNAs have been described as a 'gold mine' of potential noninvasive biomarkers. Release of microRNA content of blood cells upon hemolysis dramatically alters the microRNA profile in blood, potentially affecting levels of a significant number of proposed biomarker microRNAs and, consequently, accuracy of serum or plasma-based tests. Several methods to detect low levels of hemolysis have been proposed; however, a direct comparison assessing their sensitivities is currently lacking. In this study, we evaluated the sensitivities of four methods to detect hemolysis in serum (listed in the order of sensitivity): measurement of hemoglobin using a Coulter® AcT diff™ Analyzer, visual inspection, the absorbance of hemoglobin measured by spectrophotometry at 414 nm and the ratio of red blood cell-enriched miR-451a to the reference microRNA miR-23a-3p. The miR ratio detected hemolysis down to approximately 0.001%, whereas the Coulter® AcT diff™ Analyzer was unable to detect hemolysis lower than 1%. The spectrophotometric method could detect down to 0.004% hemolysis, and correlated with the miR ratio. Analysis of hemolysis in a cohort of 86 serum samples from cancer patients and healthy controls showed that 31 of 86 (36%) were predicted by the miR ratio to be hemolyzed, whereas only 8 of these samples (9%) showed visible pink discoloration. Using receiver operator characteristic (ROC) analyses, we identified absorbance cutoffs of 0.072 and 0.3 that could identify samples with low and high levels of hemolysis, respectively. Overall, this study will assist researchers in the selection of appropriate methodologies to test for hemolysis in serum samples prior to quantifying expression of microRNAs.

Fig 1. Sensitivities of four methods to detect hemolysis.

(A) A hemolysis series was prepared by diluting 100% hemolyzed sample with unhemolyzed serum (0%), and the sensitivity of each method determined by its ability to detect hemolysis (indicated by arrows). (B—E) Detection of hemolysis using four methods. For visual inspection, samples were scored from 0 (unhemolyzed sample) to 5 (100% hemolysis). Averages of technical replicates are shown where appropriate. ‘Unhem’ denotes unhemolyzed serum. Absorbance measures (D) and miR ratios (E) are noted on the graphs.

Fig 2. Comparison of methodologies for determining hemolysis in serum samples.

Serum samples (N = 86) categorized by low (miR ratio <5; N = 14), moderate (miR ratio 5–7; N = 41) and severe (miR ratio >7; N = 31) hemolysis. Results of visual inspection are recorded for each category as the proportion of samples that are clear, cloudy or visibly pink. (B) Absorbance at 414 nm and the miR ratio of the cohort (N = 86). The dotted line represents the threshold above which samples are considered to be severely hemolysed according to the miR ratio (>7). Samples are color-coded according to their visual appearance (clear, cloudy or visibly pink).

Fig 3. Identification of samples with low or severe hemolysis by spectrophotometric absorbance.

(A) Cohort (N = 86) is grouped by low (miR ratio <5; N = 14), moderate (miR ratio 5–7; N = 41) and severe (miR ratio >7; N = 31) predicted risk of hemolysis, and absorbance at 414 nm was compared between groups. No significant differences in absorbance of samples were observed between the low and moderate groups; however, both were significantly different to the severe hemolysis group. (B-C) Absorbance of samples with miR ratio >7 was 1.85-fold higher than those with miR ratio <7. ROC analysis suggested that absorbance could predict severely hemolyzed samples (miR ratio >7). The cut-off for absorbance of 0.3 identified by ROC is shown as a dotted red line. (D-E) ROC analysis revealed a cut-off for absorbance of 0.072 (depicted as a dotted red line) below which samples would be predicted to have low levels of hemolysis (miR ratio <5). ** P < 0.001, *** P < 0.0001 and ## Mann-Whitney U test P < 0.001. ‘TPR’ and ‘FPR’ refer to true and false positive rates, respectively.

Fig 4. Hemolysis-sensitive high and low abundant microRNAs are significantly altered between categories defined by the miR ratio.

(A) Levels of hemolysis-sensitive highly abundant serum microRNA miR−16−5p was found to be significantly altered across low, moderate and severely hemolyzed serum samples defined by miR ratios (B) Levels of a hemolysis-sensitive low abundant microRNA miR−15b−3p were also different across all miR ratio categories. (C) miR−23a−3p was present at a similar level amongst three categories, supporting its use as a reference microRNA in determining the miR ratio. * P <0.05, ** P < 0.001 and *** P < 0.0001.

Fig 5. Assessment of hemolysis in serum samples.

All serum samples exhibiting pink discoloration were found to be strongly affected by hemolysis for microRNA profiling according to the miR ratio. After exclusion of the visibly hemolyzed samples, samples with absorbance at 414 nm of >0.3 are also likely to be have miR ratio >7, predicting severe hemolysis. In contrast, samples with an absorbance at 414 nm of <0.072 are predicted to have a miR ratio <5. Samples meeting these criteria may be excluded from miR ratio for the purpose of determining hemolysis; however, the miR ratio should be determined for samples with absorbance between 0.072 and 0.3. PPV and NPV refer to positive and negative predictive values after removal of visibly hemolyzed or cloudy samples, respectively.