Agreement study on gait assessment using a video-assisted rating method in patients with idiopathic normal-pressure hydrocephalus

Abstract

Gait disturbance is a major symptom of idiopathic normal-pressure hydrocephalus (iNPH) and is assessed by raters of different professions or with different degrees of experience. Agreement studies are usually done by two raters or more, and comparisons among multiple groups of raters are rare. In this study, we aimed to examine the agreement among multiple groups of raters on gait patterns and a grading scale through a video-assisted gait analysis in patients with iNPH. Fifteen participants with iNPH were enrolled. Gait was assessed according to seven patterns, including freezing and wide-based gaits. The levels of severity (evident, mild, none) were rated by three groups of raters (two neurosurgeons [DR2], three experienced physiotherapists [PTe3], and two less experienced physiotherapists [PTl2]) through a simultaneous video viewing session. Severity of gait disturbance (GSg) was rated using the Japanese iNPH grading scaleiNPHGS, and Krippendorff alpha was computed to assess agreement, with alpha ≥0.667 indicating good agreement and alpha ≥0.8 indicating excellent agreement. For group comparisons, 84%, not 95%, confidence intervals were applied. Among the seven gait patterns in the first assessment, excellent agreement was observed in wide-based and short-stepped gaits in only DR2. Good agreement was observed in four patterns, but the agreement by two groups was in shuffling and wide-based gait. There were no gait patterns showing good agreement among three groups. In the second assessment, excellent agreement was observed in three patterns but no gait patterns showed good agreement between two groups or more. Learning effect was observed only for standing difficulty in DR2. In contrast, good or nearly good agreement on GSg was observed among the three groups with excellent agreement in two groups. Agreement on gait patterns among the three groups of raters was not high, but agreement on the iNPHGS was high, indicating the importance of a precise description facilitating differentiation between neighboring grades.

Fig 1. Ratings by seven raters on representative gait patterns and severity of gait disturbance in the first assessment in the homogeneous group.

Each grade by different raters was plotted not to overlap. A: Wide-based gait, B: short-stepped gait, C: festination, D: severity on the gait domain of the iNPH grading scale.

Fig 2. Krippendorff alpha in the first assessment in the homogeneous group.

Dashed line: Krippendorff alpha ≥0.667, dotted line: Krippendorff alpha ≥0.80, longitudinal bar: 84% confidence intervals, DR2: doctor group, PTe3: experienced physiotherapist group, PTl2: less experienced physiotherapist group, *statistically significant difference between two groups.

Fig 3. Krippendorff alpha in the second assessment in the homogeneous group.

Dashed line: Krippendorff alpha ≥0.667, dotted line: Krippendorff alpha ≥0.80, longitudinal bars: confidence intervals, DR2: doctor group, PTe3: experienced physiotherapist group, PTl2: less experienced physiotherapist group, *statistically significant difference between two groups.

Fig 4. Comparison between the first and second assessments in the homogeneous group.

Dashed line: Krippendorff alpha ≥0.667, dotted line: Krippendorff alpha ≥0.80, longitudinal bars: confidential intervals, DR2: doctor group, PTe3: experienced physiotherapist group, PTl2: less experienced physiotherapist group, #statistically significant difference between the first and second assessments.

Fig 5. Comparison between the first and second assessments in the mixed group.

Dashed line: Krippendorff alpha ≥0.667, dotted line: Krippendorff alpha ≥0.80, longitudinal bars: confidence intervals, DR2: doctor group, PTe3: experienced physiotherapist group, PTl2: less experienced physiotherapist group.