Effects of meteorological factor and air pollution on sudden sensorineural hearing loss using the health claims data in Busan, Republic of Korea.

PURPOSE: Specific meteorological factors, including air pollution in the form of particulate matter (PM), affect the development of otologic disease and have adverse effects on the cardiovascular and respiratory systems. This study investigated relationships between the development of sudden sensorineural hearing loss(SSNHL) and meteorological factor with air pollution including PM. MATERIALS AND METHODS: The daily patient number in 2015 admitted to the hospital with SSNHL were extracted from the Health Insurance Review and Assessment Service Bigdata in Busan. The meteorological factors and air pollution data of Busan area were obtained from meteorological stations in Busan. The relationship between the number of hospitalizations and the climatic factors was checked. RESULTS: SSNHL patient group showed more common in women, and the highest rates were observed in patients in their 50s. The daily mean patient numbers were 2.27. The number of SSNHL patients in spring was statistically significantly higher than that in summer. The mean daily PM10 and PM2.5 concentrations were 48.0 and 29.4 µg/m3, respectively. The mean wind speed, maximum wind speed and daily atmospheric pressure range was weakly positively associated with SSNHL patient number. There were weak negative correlations between maximum PM2.5 and SSNHL admissions. The mean temperature and wind chill index showed non-significantly negative relationships with SSNHL admissions. CONCLUSIONS: In Busan area, statistically significant weak relationships were detected between the daily numbers of patients admitted to the hospital with SSNHL and meteorological data, including PM level. Further investigation of these associations is required.

Hearing recovery prediction and prognostic factors of idiopathic sudden sensorineural hearing loss: a retrospective analysis with a deep neural network model.

OBJECTIVE: Idiopathic Sudden Sensorineural Hearing Loss (ISSHL) is an otologic emergency, and an early prediction of prognosis may facilitate proper treatment. Therefore, we investigated the prognostic factors for predicting the recovery in patients with ISSHL treated with combined treatment method using machine learning models. METHODS: We retrospectively reviewed the medical records of 298 patients with ISSHL at a tertiary medical institution between January 2015 and September 2020. Fifty-two variables were analyzed to predict hearing recovery. Recovery was defined using Siegel's criteria, and the patients were categorized into recovery and non-recovery groups. Recovery was predicted by various machine learning models. In addition, the prognostic factors were analyzed using the difference in the loss function. RESULTS: There were significant differences in variables including age, hypertension, previous hearing loss, ear fullness, duration of hospital admission, initial hearing level of the affected and unaffected ears, and post-treatment hearing level between recovery and non-recovery groups. The deep neural network model showed the highest predictive performance (accuracy, 88.81%; area under the receiver operating characteristic curve, 0.9448). In addition, initial hearing level of affected and non-affected ear, post-treatment (2-weeks) hearing level of affected ear were significant factors for predicting the prognosis. CONCLUSION: The deep neural network model showed the highest predictive performance for recovery in patients with ISSHL. Some factors with prognostic value were identified. Further studies using a larger patient population are warranted. LEVEL OF EVIDENCE: Level 4.

Hearing recovery prediction and prognostic factors of idiopathic sudden sensorineural hearing loss: a retrospective analysis with a deep neural network model

Abstract Objective Idiopathic Sudden Sensorineural Hearing Loss (ISSHL) is an otologic emergency, and an early prediction of prognosis may facilitate proper treatment. Therefore, we investigated the prognostic factors for predicting the recovery in patients with ISSHL treated with combined treatment method using machine learning models. Methods We retrospectively reviewed the medical records of 298 patients with ISSHL at a tertiary medical institution between January 2015 and September 2020. Fifty-two variables were analyzed to predict hearing recovery. Recovery was defined using Siegel's criteria, and the patients were categorized into recovery and non-recovery groups. Recovery was predicted by various machine learning models. In addition, the prognostic factors were analyzed using the difference in the loss function. Results There were significant differences in variables including age, hypertension, previous hearing loss, ear fullness, duration of hospital admission, initial hearing level of the affected and unaffected ears, and post-treatment hearing level between recovery and non-recovery groups. The deep neural network model showed the highest predictive performance (accuracy, 88.81%; area under the receiver operating characteristic curve, 0.9448). In addition, initial hearing level of affected and non-affected ear, post-treatment (2-weeks) hearing level of affected ear were significant factors for predicting the prognosis. Conclusion The deep neural network model showed the highest predictive performance for recovery in patients with ISSHL. Some factors with prognostic value were identified. Further studies using a larger patient population are warranted. Level of evidence: Level 4.