Benign Paroxysmal Positional Vertigo in the Acute Care Setting

Diagnosing the benign paroxysmal positional vertigo via 1D and deep-learning composite model

BACKGROUND

Benign Paroxysmal Positional Vertigo (BPPV) is the leading cause of vertigo, and its characteristic nystagmus induced by positional maneuvers makes it a good model for Artificial Intelligence (AI) diagnosis. However, during the testing procedure, up to 10 min of indivisible long-range temporal correlation data are produced, making the AI-informed real-time diagnosing unlikely in clinical practice.

METHODS

A combined 1D and Deep-Learning (DL) composite model was proposed. Two separate cohorts were recruited, with one for model generation and the other for evaluation of model's real-world generalizability. Eight features, including two head traces and three eye traces and their corresponding slow phase velocity (SPV) value, were served as the inputs. Three candidate models were tested, and a sensitivity study was conducted to determine the saliently important features.

RESULTS

The study included 2671 patients in the training cohort and 703 in the test cohort. A hybrid DL model achieved a micro-area under the receiver operating curve (AUROC) of 0.982 (95% CI 0.965, 0.994) and macro-AUROC of 0.965 (95% CI 0.898, 0.999) for overall classification. The highest accuracy was observed for right posterior BPPV, with an AUROC of 0.991 (95% CI 0.972, 1.000), followed by left posterior BPPV, with an AUROC of 0.979 (95% CI 0.940, 0.998), the lowest AUROC was 0.928 (95% CI 0.878, 0.966) for lateral BPPV. The SPV was consistently identified as the most predictive feature in the models. If the model process is carried out 100 times for a 10-min data, one single running takes 0.79 ± 0.06 s.

CONCLUSION

This study designed DL models which can accurately detect and categorize the subtype of BPPV, enabling a quick and straightforward diagnosis of BPPV in clinical setting. The critical feature identified in the model helps expand our understanding of this disorder.

Risk of benign paroxysmal positional vertigo in patients with depressive disorders: a nationwide population-based cohort study

OBJECTIVE

The association between depression and benign paroxysmal positional vertigo (BPPV) remains debated. This study aimed to investigate the risk of BPPV in patients with depressive disorders.

DESIGN

Longitudinal nationwide cohort study.

SETTING

National health insurance research database in Taiwan.

PARTICIPANTS

We enrolled 10 297 patients diagnosed with depressive disorders between 2000 and 2009 and compared them to 41 188 selected control patients who had never been diagnosed with depressive disorders (at a 1:4 ratio matched by age, sex and index date) in relation to the risk of developing BPPV.

METHODS

The follow-up period was defined as the time from the initial diagnosis of depressive disorders to the date of BPPV, censoring or 31 December 2009. Cox proportional hazard regression analysis was used to investigate the risk of BPPV by sex, age and comorbidities, with HRs and 95% CIs.

RESULTS

During the 9-year follow-up period, 44 (0.59 per 1000 person-years) patients with depressive disorders and 99 (0.33 per 1000 person-years) control patients were diagnosed with BPPV. The incidence rate ratio of BPPV among both cohorts calculating from events of BPPV per 1000 person-years of observation time was 1.79 (95% CI 1.23 to 2.58, p=0.002). Following adjustments for age, sex and comorbidities, patients with depressive disorders were 1.55 times more likely to develop BPPV (95% CI 1.08 to 2.23, p=0.019) as compared with control patients. In addition, hyperthyroidism (HR=3.75, 95% CI 1.67-8.42, p=0.001) and systemic lupus erythematosus (SLE) (HR=3.47, 95% CI 1.07 to 11.22, p=0.038) were potential risk factors for developing BPPV in patients with depressive disorders.

CONCLUSIONS

Patients with depressive disorders may have an increased risk of developing BPPV, especially those who have hyperthyroidism and SLE.

A New Diagnostic Approach to the Adult Patient with Acute Dizziness

BACKGROUND

Dizziness, a common chief complaint, has an extensive differential diagnosis that includes both benign and serious conditions. Emergency physicians must distinguish the majority of patients with self-limiting conditions from those with serious illnesses that require acute treatment.

OBJECTIVE OF THE REVIEW

This article presents a new approach to diagnosis of the acutely dizzy patient that emphasizes different aspects of the history to guide a focused physical examination with the goal of differentiating benign peripheral vestibular conditions from dangerous posterior circulation strokes in the emergency department.

DISCUSSION

Currently, misdiagnoses are frequent and diagnostic testing costs are high. This relates in part to use of an outdated, prevalent, diagnostic paradigm. The traditional approach, which relies on dizziness symptom quality or type (i.e., vertigo, presyncope, or disequilibrium) to guide inquiry, does not distinguish benign from dangerous causes, and is inconsistent with current best evidence. A new approach divides patients into three key categories using timing and triggers, guiding a differential diagnosis and targeted bedside examination protocol: 1) acute vestibular syndrome, where bedside physical examination differentiates vestibular neuritis from stroke; 2) spontaneous episodic vestibular syndrome, where associated symptoms help differentiate vestibular migraine from transient ischemic attack; and 3) triggered episodic vestibular syndrome, where the Dix-Hallpike and supine roll test help differentiate benign paroxysmal positional vertigo from posterior fossa structural lesions.

CONCLUSIONS

The timing and triggers diagnostic approach for the acutely dizzy patient derives from current best evidence and offers the potential to reduce misdiagnosis while simultaneously decreases diagnostic test overuse, unnecessary hospitalization, and incorrect treatments.

Diazepam and Meclizine Are Equally Effective in the Treatment of Vertigo: An Emergency Department Randomized Double-Blind Placebo-Controlled Trial

BACKGROUND

Vertigo is a debilitating disease that is commonly encountered in the emergency department (ED). Diazepam and meclizine are oral medications that are commonly used to alleviate symptoms.

OBJECTIVES

We sought to determine whether meclizine or diazepam is superior in the treatment of patients with peripheral vertigo in the ED.

METHODS

We performed a double-blind clinical trial at a suburban, teaching ED. We randomized a convenience sample of adult patients with acute peripheral vertigo (APV) to diazepam 5 mg or meclizine 25 mg orally. Demographic and historical features were recorded on a standardized data form. Patients recorded their initial level (t0) of vertigo on a 100-mm visual analog scale (VAS) and after 30 min (t30) and 60 min (t60). The primary outcome parameter was the mean change in VAS score from t0 to t60. Differences between groups and 95% confidence intervals were calculated. Our a priori power calculation estimated that a sample size of 20 patients in each group was required to have an 80% power to detect a difference of 20 mm between treatment groups.

RESULTS

There were 20 patients in the diazepam group and 20 in the meclizine group. The two groups were similar with respect to patient demographics and presenting signs and symptoms. At t60, the mean improvements in the diazepam and meclizine groups were 36 and 40, respectively (difference -4; 95% confidence interval -20 to 12; p = 0.60).

CONCLUSION

We found no difference between oral diazepam and oral meclizine for the treatment of ED patients with acute peripheral vertigo.

A New Approach to the Diagnosis of Acute Dizziness in Adult Patients

Dizziness is a common chief complaint in emergency medicine. The differential diagnosis is broad and includes serious conditions, such as stroke, cardiac arrhythmia, hypovolemic states, and acute toxic and metabolic disturbances. Emergency physicians must distinguish the majority of patients who suffer from benign self-limiting conditions from those with serious illnesses that require acute treatment. Misdiagnoses are frequent and diagnostic test costs high. The traditional approach does not distinguish benign from dangerous causes and is not consistent with best current evidence. This article presents a new approach to the diagnosis of acutely dizzy patients that highly leverages the history and the physical examination.

An Abbreviated Diagnostic Maneuver for Posterior Benign Positional Paroxysmal Vertigo

Introduction

Benign paroxysmal positional vertigo (BPPV) secondary to canalolithiasis of the posterior semicircular canal is perhaps the most frequent cause of vertigo and dizziness. One of its properties is a high response rate to canalith repositioning maneuvers. However, delays in the diagnosis and treatment of this entity can range from days to years, depending on the setting. Here, we present an abbreviated variation of the Dix–Hallpike maneuver, which can be used to diagnose this disease. It is similar to the standard maneuver but can be performed without an examination bed/table and requires only a backed chair (a difference that we feel is very important in settings where a clinical bed/table is not readily available).

Methods

A diagnostic assessment study was conducted in 163 patients who presented with vertigo or dizziness.

Results

The abbreviated test had fairly good sensitivity (80%) and high specificity (95%) for diagnosing posterior BPPV.

Discussion

This new diagnostic maneuver may serve as a screening procedure for quickly identifying this pathology. This will allow patients to be more directly treated, without requiring unnecessary referrals or full vestibular testing, and will be especially useful in primary care settings or heavily overloaded otolaryngology or neurology departments.