Comparison of the Bedside Head-Impulse Test with the Video Head-Impulse Test in a Clinical Practice Setting: A Prospective Study of 500 Outpatients

Abstract

Objectives: The primary aim was to determine the sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of the bedside head-impulse test (bHIT) using the video HIT (vHIT) as the gold standard for quantifying the function of the vestibulo-ocular reflex (VOR). Secondary aims were to determine the bHIT inter-rater reliability and sensitivity in detecting unilateral and bilateral vestibulopathy.

Methods: In this prospective study, 500 consecutive outpatients presenting to a tertiary neuro-otology clinic with vertigo or dizziness of various vestibular etiologies who did not have any of the pre-defined exclusion criteria were recruited. Bedside HITs were done by three experienced neuro-otology clinicians masked to the diagnosis, and the results were compared with the vHIT. The patients were likewise blinded to the bHIT and vHIT findings. Patients with VOR deficits were identified on the vHIT by referencing to the pre-selected "pathological" gain of <0.7. The data were then analyzed using standard statistical methods.

Results: For the primary outcome (vHIT "pathological" VOR gain <0.7), the three-rater mean bHIT sensitivity = 66.0%, PPV = 44.3%, specificity = 86.2%, and NPV = 93.9%. Shifting the "pathological" threshold from 0.6 to 0.9 caused the bHIT sensitivity to decrease while the PPV increased. Specificity and NPV tended to remain stable. Inter-rater agreement was moderate (Krippendorff's alpha = 0.54). For unilateral vestibulopathy, overall bHIT sensitivity = 69.6%, reaching 86.67% for severely reduced unilateral gain. For VOR asymmetry <40% and >40%, the bHIT sensitivity = 51.7 and 83%, respectively. For bilateral vestibulopathy, overall bHIT sensitivity = 66.3%, reaching 86.84% for severely reduced bidirectional gains.

Conclusion: For the primary outcome, the bHIT had moderate sensitivity and low PPV. While the study did not elucidate the best choice for vHIT reference, it demonstrated how the bHIT test properties varied with vHIT thresholds: selecting a lower threshold improved the sensitivity but diminished the PPV, while a higher threshold had the opposite effect. The VOR was most likely normal if the bHIT was negative due to its high NPV. The bHIT was moderately sensitive for detecting unilateral and bilateral vestibulopathy overall, but better for certain subgroups.

Keywords: head-impulse test; negative predictive value; positive predictive value; sensitivity; specificity; vestibulo-ocular reflex.

Figure 1

The distribution of vHIT gains in the study group.

Figure 2

The relationship of the bHIT sensitivity, PPV, specificity and NPV to different vHIT pathological gain thresholds from 0.6 to 0.9. (A) The bHIT sensitivity decreased with increasing vHIT gain setting from 0.6 to 0.9. (B) The bHIT PPV increased with increasing vHIT gain setting from 0.6 to 0.9. (C) The bHIT specificity remains above 76% for vHIT gains 0.6 to 0.9. (D) The NPV remained above 80% until vHIT gain setting was >0.8.

Figure 3

Relationship of bHIT sensitivity to the VOR asymmetry and absolute VOR gains in unilateral vestibulopathy and bilateral vestibulopathy. Subgroup analysis of patients with unilateral vestibulopathy (n = 43) and bilateral vestibulopathy (n = 38). (A) The bHIT sensitivity increased with increasing VOR asymmetry between the 2 labyrinths. (B) The bHIT sensitivity increased with increasing degrees of unilateral hypofunction. (C) When both labyrinths had severe VOR gain reductions, the bHIT had the highest sensitivity. The bHIT sensitivity was most dependent on the VOR asymmetry in the group with dissimilar gains (“all other combinations”).