β-trace protein as a diagnostic marker for perilymphatic fluid fistula: a prospective controlled pilot study to test a sample collection technique

Abstract

Objectives: The diagnosis of perilymphatic fluid (PLF) fistula is still challenging. Perilymphatic fluid fistula is one possible complication after stapedotomy or cochlear implant surgery. We have performed a prospective diagnostic pilot study to further investigate β-trace protein (β-TP) as a marker for PLF fistula. In this pilot study, we tested the sensitivity of the β-TP marker using a simple method for sample collection from the tympanic cavity.

Design: Prospective controlled diagnostic study.

Setting: Two-center tertiary referral hospitals.

Patients: A total of 35 adult patients undergoing ear surgery were included. Subjects were divided into 2 groups: 1) 19 patients undergoing stapedotomy were investigated for PLF fistula in samples obtained from the tympanic cavity and 2) 16 patients undergoing myringoplasty were investigated for PLF fistula in samples from the tympanic cavity. This group served as the control. Mean age +/- SD at surgery was 49.9 +/- 8.0 years in the study group and 39.69 +/- 15.47 years in the control group.

Intervention: β-Trace protein (prostaglandin D synthase) in tympanic cavity samples and serum samples was analyzed. The samples were collected by gradually filling the tympanic cavity with 100 to 200 μl sodium chloride and by immediately collecting a volume of 60 to 100 μl in a mucus specimen set container.

Main outcome measures: The concentration of β-TP was quantified using laser nephelometry.

Results: The median β-TP in the study group was 0.8 mg/L (range, 0.05-4.5 mg/L). In the control group, the median β-TP value was 0.16 mg/L (range, 0.01-0.36 mg/L). Thirty-five percent of the values in the study group were below the highest value in the negative control group. The β-TP values of the tympanic cavity samples were significantly higher in the study group than in controls (p = 0.0001). The serum values were 0.55 +/- 0.18 and 0.53 +/- 0.11 mg/L, respectively.

Conclusion: It may be feasible to test for PLF fistula using β-TP in samples from the tympanic cavity. Our results, however, suggest a relative low diagnostic sensitivity, given a cutoff that is set to obtain a high specificity when using a simple sample collection method. Furthermore, the test does not permit the distinction between PLF fistula and cerebrospinal fluid fistula. Further studies should focus on minimal dilution at sampling and on minimizing sample volumes.