Efficacy and safety of digital therapeutic application of Sleep Index-Based Treatment for Insomnia (dSIBT-I): a pilot study.

The aim of this study was to evaluate the safety and efficacy of digital therapeutic application of Sleep Index-Based Treatment for Insomnia (dSIBT-I) and compare them with those of digital application of Cognitive Behavioural Therapy for Insomnia (dCBT-I). This randomised prospective pilot study was conducted at the Asan Medical Center. A total of 50 patients with insomnia were recruited between December 2022 and January 2023 and randomly allocated to the dSIBT-I or dCBT-I group. The study was carried out for one month. The primary outcome was the significant reduction in Insomnia Severity Index score at Week 4 compared to baseline, while the secondary outcome was proportion of participants whose Insomnia Severity Index scores were reduced to <15 at Week 4. We performed linear mixed model and generalised estimating equation analyses. Both dSIBT-I and dCBT-I groups showed significant improvements in Insomnia Severity Index scores at Week 4. There was no significant difference between two groups in terms of Insomnia Severity Index scores at Week 4 (group × time effect, F = 1.07, p = 0.382) and proportion of participants whose Insomnia Severity Index scores were reduced to <15 at Week 4 (group × time effects, F = 1.80, p = 0.615). However, at Week 2, the dSIBT-I group showed better results than the dCBT-I group in terms of both Insomnia Severity Index scores (p = 0.044) and proportion of participants whose Insomnia Severity Index scores were reduced to <15 (82.6% vs. 48.0%, p = 0.017). No treatment-emergent adverse events were reported in either group. The dSIBT-I is a safe and effective therapy for insomnia, with rapid treatment effects.

Validation Study on Automated Sleep Stage Scoring Using a Deep Learning Algorithm.

Background and Objectives: Polysomnography is manually scored by sleep experts. However, manual scoring is a time-consuming and labor-intensive task. The goal of this study was to verify the accuracy of automated sleep-stage scoring based on a deep learning algorithm compared to manual sleep-stage scoring. Materials and Methods: A total of 602 polysomnography datasets from subjects (Male:Female = 397:205) aged 19 to 65 years (mean age, 43.8, standard deviation = 12.2) were included in the study. The performance of the proposed model was evaluated based on kappa value and bootstrapped point-estimate of median percent agreement with a 95% bootstrap confidence interval and R = 1000. The proposed model was trained using 482 datasets and validated using 48 datasets. For testing, 72 datasets were selected randomly. Results: The proposed model exhibited good concordance rates with manual scoring for stages W (94%), N1 (83.9%), N2 (89%), N3 (92%), and R (93%). The average kappa value was 0.84. For the bootstrap method, high overall agreement between the automated deep learning algorithm and manual scoring was observed in stages W (98%), N1 (94%), N2 (92%), N3 (99%), and R (98%) and total (96%). Conclusions: Automated sleep-stage scoring using the proposed model may be a reliable method for sleep-stage classification.