The agreement and repeatability of tear meniscus height measurement methods

Purpose. This study investigated the agreement and repeatability of five techniques of measuring tear meniscus height (TMH). Methods. Pairs of TMH measurements were obtained from one eye of 25 normal subjects with five techniques: optical coherence tomography in cross-section (OCT) and optical pachymetry in cross-section (PACH), without fluorescein; and 5 minutes after the instillation of fluorescein, optical pachymetry en-face (SL-F) and in cross-section (SL-X), and video capture en-face (VC). These 10 measurements were taken on different days within a period of 21 days. Additionally, immediately successive replicates were taken at the first visit when VC was used, allowing for the separation of technique repeatability from true day-to-day variation in TMH. Results. Ninety-five percent confidence intervals for the mean TMH and 95% repeatability coefficients for repeated testing on separate occasions were: 0.25 to 0.29 mm, 0.14 mm-OCT, 0.30 to 0.36 mm, 0.13 mm-PACH, 0.27 to 0.34 mm, 0.092 mm-SL-F, 0.35 to 0.41 mm, 0.19 mm-SL-X, and 0.30 to 0.38 mm, 0.088 mm-VC. Reported repeatability coefficients are averages because, despite a relatively narrow experimental range, the measurements of low TMH were generally more repeatable than those of large TMH. Ninety-five percent limits of agreement were wide for all pairwise comparisons and included zero, indicating that the methods used in this study are interchangeable when taking single recordings, at least on subjects without dry eye. Conclusions. The average TMH of the five techniques was similar, although OCT and SL-X tended to record lower and higher values, respectively. However, their agreement for single recordings was poor, an inevitable consequence of the low intertest repeatability found for all methods. A much improved repeatability for immediate replicates indicated that this, in turn, was principally caused by a large day-to-day variation in TMH rather than measurement error.