Objectives: To evaluate the efficacy of ear molding across various initial ages and analyze challenges encountered by infants beyond the optimal treatment age window. Methods: A retrospective review of 331 infants (527 ears) treated with EarWell was conducted over 5 years from January 2017 to March 2022 at a single center. The treatment duration of the ear molding, success rate, recurrence rate, and complication rate were analyzed among the 3 age groups. Concentrate on evaluating treatment outcomes for infants with an initial age exceeding 42 days. Results: The mean age at initial treatment was 25±28 days. In addition, it includes a child with cryptotia who is 3.5 years old (1278 d). The mean duration of treatment was 7±5 weeks. In the long-term follow-up, the overall treatment success rate was 92%, with 467 ears (88.6%) showing improvement without recurrence, 30 ears (5.7%) experiencing varying degrees of recurrence, and 30 ears (5.7%) showing no improvement or complete recurrence. A total of 20 infants (3%) developed mild skin complications during treatment. Conclusions: Ear molding is a safe and effective option for the treatment of congenital ear anomalies, with a low recurrence rate during long-term follow-up. For infants with congenital auricular anomalies aged over 42 days, ear molding remains a viable option. Treatment success may be influenced by the age at treatment, the subtype of anomalies, and relies on the assessment of a specialized otologist, expert procedural techniques, as well as thorough understanding and cooperation from parents.
Reliable respiratory phase sensing is important for respiratory-synchronized hypoglossal nerve stimulation (HGNS), but conventional sensing approaches may impose additional burden. This pilot study investigated whether a surface triaxial accelerometry sensor (TAS) could detect thoracic respiratory inductance plethysmography (RIP) troughs, which were used as operational phase landmarks representing the transition from end expiration to subsequent inspiration, rather than as directly established physiological respiratory onsets. Ten participants underwent synchronized overnight polysomnography and surface TAS recording, providing 5377.3 min of analyzable data and 75,499 automatically generated RIP landmarks. Two complementary Conformer models were trained using Gaussian weak labels and combined using multi-offset dual-conformer fusion. Generalization was evaluated using outer leave-one-subject-out validation, with fusion weights and event thresholds selected from training-side validation data. At a ±1.0 s matching tolerance, the fusion achieved participant-mean precision, recall, and F1 scores of 0.78, 0.82, and 0.80, respectively, with a 95% confidence interval of 0.75–0.85 for the mean F1 score. It outperformed each component model in 9 of 10 participants; however, its F1 gain over otherwise identical single-grid fusion was 0.0036, below the prespecified exploratory advancement margin. These findings provide preliminary evidence that surface TASs can recover an RIP-trough-derived operational phase landmark in unseen same-center participants. Independent multimodal adjudication, external replication, and full-night causal testing are required before clinical or respiratory-synchronized HGNS applications.