Reliability of standard pupillometry practice in neurocritical care: an observational, double-blinded study

Abstract

Background: In critical care units, pupil examination is an important clinical parameter for patient monitoring. Current practice is to use a penlight to observe the pupillary light reflex. The result seems to be a subjective measurement, with low precision and reproducibility. Several quantitative pupillometer devices are now available, although their use is primarily restricted to the research setting. To assess whether adoption of these technologies would benefit the clinic, we compared automated quantitative pupillometry with the standard clinical pupillary examination currently used for brain-injured patients.

Methods: In order to determine inter-observer agreement of the device, we performed repetitive measurements in 200 healthy volunteers ranging in age from 21 to 58 years, providing a total of 400 paired (alternative right eye, left eye) measurements under a wide variety of ambient light condition with NeuroLight Algiscan pupillometer. During another period, we conducted a prospective, observational, double-blinded study in two neurocritical care units. Patients admitted to these units after an acute brain injury were included. Initially, nursing staff measured pupil size, anisocoria and pupillary light reflex. A blinded physician subsequently performed measurement using an automated pupillometer.

Results: In 200 healthy volunteers, intra-class correlation coefficient for maximum resting pupil size was 0.95 (IC: 0.93-0.97) and for minimum pupil size after light stimulation 0.87 (0.83-0.89). We found only 3-pupil asymmetry (≥ 1 mm) in these volunteers (1.5% of the population) with a clear pupil asymmetry during clinical inspection. The mean pupil light reactivity was 40 ± 7%. In 59 patients, 406 pupillary measurements were prospectively performed. Concordance between measurements for pupil size collected using the pupillometer, versus subjective assessment, was poor (Spearmen's rho = 0.75, IC: 0.70-0.79; P < 0.001). Nursing staff failed to diagnose half of the cases (15/30) of anisocoria detected using the pupillometer device. A global rate of discordance of 18% (72/406) was found between the two techniques when assessing the pupillary light reflex. For measurements with small pupils (diameters <2 mm) the error rate was 39% (24/61).

Conclusion: Standard practice in pupillary monitoring yields inaccurate data. Automated quantitative pupillometry is a more reliable method with which to collect pupillary measurements at the bedside.

Keywords: Anisocoria; Neurocritical Care; Neurological examination; Pupillary light reflex; Pupillary reactivity; Pupillary size; Pupillometer.

Fig. 1

NeuroLight Algiscan’s inter-observer variability. Comparison of the maximum resting pupil size a and the minimum pupil size after light stimulation b measured with the NeuroLight Algiscan quantitative pupillometer by two operators in 200 healthy volunteers. CI confidence interval

Fig. 2

Comparison of pupil size obtained with the pupillometer versus subjective estimates. Box plots indicate medians (horizontal line in box), the 25th and 75th percentiles (lower and upper box margins), the 10th and 90th percentiles (lower and upper error bars), and individual patients in the lower 10th percentiles (open squares) for each visual measurement of pupil size. The short box whisker plots for the 1 mm and 6 mm groups suggest a high level of agreement. Box plots for the 2–5 mm groups are stretched by outliers, suggesting a lower level of agreement between the two measurements for each of these groups

Fig. 3

ROC curve analyses for different groups of pupil size as determined visually, and then compared with the electronic pupillometer. These data show the reliability of pupil size measurements for each pupil size group. The closer the curve approaches the 45° diagonal, the less accurate the test

Fig. 4

Detection of anisocoria by nursing staff. White circles represent for each set of paired measurements the mean pupil size according to the left and right pupil size differences measured by the pupillometer. Anisocoria was defined as a pupil size difference of ≥1 mm (red square). Red circles represent anisocoria detected by the nurses. Nursing staff failed to diagnose half of the cases (15/30) of anisocoria detected using the pupillometer device and wrongly detected 16 episodes of anisocoria (Color figure online)

Fig. 5

Assessment of PLR by nursing staff. Percentage agreement (green and light green) or discrepancy (red and orange) in the assessment of PLR either by standard visual examination or using the automated pupillometer. The presence (+) or absence (–) of PLR was evaluated by nurses using a penlight and by physicians using a calibrated light stimulus delivered by the pupillometer. A global rate of discordance (red and orange) of 18 % (72/406) was found between the two techniques when assessing the PLR. For measurements with small pupils (diameters <2 mm) the error rate was at its greatest: 39 % (24/61). (Color figure online)