Sleep postures monitoring systems in the hospital aim at transforming sensing signals into quantitative data to characterize the sleep behaviors of the patient. However, a home-care sleep posture monitoring system needs to be user friendly. In this paper, we present iSleePost - a user-friendly home-care intelligent sleep posture monitoring system. We address the labor-intensive labeling issue of traditional machine learning approaches in the training phase. Our proposed mobile health (mHealth) system leverages the communications and computation capabilities of mobile phones for provisioning a continuous sleep posture monitoring service. Our experiments show that iSleePost can achieve 90 percent accuracy in recognizing sleep postures. More importantly, iSleePost demonstrates that an easily-wear wrist sensor can accurately quantify sleep postures.

Background: Autoimmune inner ear disease (AIED) is a rare autoimmune condition characterized by progressive sensorineural hearing loss with hearing fluctuations over weeks to months, presenting significant challenges in both diagnosis and treatment. Due to its rarity, treatment responses and prognosis in AIED remain poorly understood. Methods: This study reviewed medical records from Taipei Medical University Hospital documented between August 2016 and August 2021. Among 67 patients experiencing fluctuating hearing loss, 11 met the diagnostic criteria for AIED and underwent regular follow-up assessments within a 5-year timeframe. ROC curve was used to discriminate the power of these prognostic parameters. Results: In this study, several factors including younger age, milder initial hearing loss, meeting criteria for bilateral Meniere's disease (MD), having an ascending audiogram pattern, longer time interval between hearing impairment attacks in contralateral ears and responding well to steroids were associated with better prognosis. ROC curve demonstrated the diagnostic value of specific parameters such as the presence of bilateral MD (AUC 0.825, 95% CI 0.640–1.000), pretreatment HI ≤ 45 dB HL (AUC 0.808, 95% CI 0.610–1.000), response to steroids (AUC 0.800, 95% CI 0.595–1.000), and ascending audiogram (AUC 0.858, 95% CI 0.683–0.858). Conclusions: This study identified key prognostic factors for AIED, providing valuable insights for predicting AIED prognosis and facilitating personalized patient management.