Improving the Diagnostic Workup of Vertigo: A Multidisciplinary Review

TL;DR

This review explores new methods and tools to improve diagnosing vertigo, aiming to better distinguish between peripheral and central causes.

Contribution

The paper reviews recent advancements in risk stratification, clinical pathways, and AI/ML tools for diagnosing vertigo.

Findings

New tools show potential for accurately distinguishing peripheral from central vertigo.

AI/ML-based models are promising but require further study for implementation in clinical settings.

Recent developments include novel questionnaires and clinical pathways to improve diagnostic accuracy.

Abstract

This Clinical (Narrative) Review addresses potential improvements to the diagnostic workup of vertigo. Despite substantial healthcare expenditures, diagnostic accuracy for vertigo remains suboptimal, and many patients undergo extensive testing without timely identification of the underlying cause. The available literature, with a focus on articles published after 2015, was narratively reviewed for novel risk stratification metrics, clinical pathways, questionnaires, and technological tools that have been developed and studied for improving the diagnostic efficiency and accuracy of vertigo. Recent developments in the workup of vertigo are diverse and show potential for accurately stratifying patients by peripheral versus central etiology. As with any new clinical tools, there are barriers when it comes to implementing them into an emergency or primary care setting. AI/ML-based models are promising; however, further study is needed. These tools may support improved efficiency of the evaluation and management of patients who present with vertigo.