Purpose: A large portion of the adult population is thought to suffer from obstructive sleep apnoea syndrome (OSAS), a sleep-related breathing disorder associated with increased morbidity and mortality. International guidelines include the polysomnography and the cardiorespiratory monitoring (CRM) as diagnostic tools for OSAS, but they are unfit for a large-scale screening, given their invasiveness, high cost and lengthy process of scoring. Current screening methods are based on self-reported questionnaires that suffer from lack of objectivity. On the contrary, commercial smartbands are wearable devices capable of collecting accelerometric and photoplethysmographic data in a user-friendly and objective way. We questioned whether machine-learning (ML) classifiers trained on data collected through these wearable devices would help predict OSAS severity. Patients and Methods: Each of the patients (n = 78, mean age ± SD: 57.2 ± 12.9 years; 30 females) underwent CRM and concurrently wore a commercial wrist smartband. CRM’s traces were scored, and OSAS severity was reported as apnoea hypopnoea index (AHI). We trained three pairs of classifiers to make the following prediction: AHI < 5 vs AHI ≥ 5, AHI < 15 vs AHI ≥ 15, and AHI < 30 vs AHI ≥ 30. Results: According to the Matthews correlation coefficient (MCC), the proposed algorithms reached an overall good correlation with the ground truth (CRM) for AHI < 5 vs AHI ≥ 5 (MCC: 0.4) and AHI < 30 vs AHI ≥ 30 (MCC: 0.3) classifications. AHI < 5 vs AHI ≥ 5 and AHI < 30 vs AHI ≥ 30 classifiers’ sensitivity, specificity, positive predictive values (PPV), negative predictive values (NPV) and diagnostic odds ratio (DOR) are comparable with the STOP-Bang questionnaire, an established OSAS screening tool. Conclusion: Machine learning algorithms showed an overall good performance. Unlike questionnaires, these are based on objectively collected data. Furthermore, these commercial devices are widely distributed in the general population. The aforementioned advantages of machine-learning algorithms applied to smartbands’ data over questionnaires lead to the conclusion that they could serve a population-scale screening for OSAS.

: OBJECTIVES: The goal of this study was to analyse the outcomes in 53 patients with thymoma, 34 of whom had myasthenia gravis (MG), who were treated with robotic surgery. The oncological outcomes of the whole series of patients were analysed. Furthermore, because consistent data are not yet available in the literature, the main focus was the analysis of the neurological results of the patients affected by MG and thymoma.METHODS: The clinical outcomes of 53 patients with a diagnosis of thymoma who underwent robotic thymectomy between January 2014 and December 2019 in our institution were collected and evaluated; 34 of these patients had a concomitant diagnosis of MG. The neurological status of the patients was determined from a clinical evaluation according to the Osserman classification and on pre- and post-surgery Myasthenia Gravis Composite scores, whereas neurological clinical outcomes were assessed using the Myasthenia Gravis Foundation of America Post-Intervention Score. Reduction of steroid therapy was also considered. The recurrence rate, adjuvant radiotherapy and overall survival of the patients with a thymoma were evaluated.RESULTS: Neurological outcomes: improvement of the clinical conditions was obtained in 26 patients (76.5%) following the operation: complete stable remission was observed in 5 patients (14.7%), pharmacological remission in 10 (29.4%) and minimal manifestation in 11 (32.3%). Four patients (11.8%) exhibited no substantial change from the pretreatment clinical manifestations or reduction in MG medication and 4 (11.8%) patients experienced worsening of clinical conditions. In 21 patients (61.7%) a reduction of the dosage of steroid therapy was obtained. Oncological outcomes: at an average follow-up of 36 months, the overall survival was 96%, 4 patients (7.5%) had pleural relapses and 12 patients (22.6%) underwent postoperative radiotherapy, according to their stage. In accordance with Masaoka staging, 34% were in stage I, 56.6% in stage II and 9.4% in stage IIICONCLUSIONS: Our results suggest that robotic surgical treatment of patients with thymoma and concomitant MG is effective in improving the neurological outcomes. Moreover, the oncological results obtained in this series confirm the efficacy of robotic surgery for the treatment of thymic malignancies, with results in line with those of open surgery. However, due to the indolent growth of thymomas, further observations with longer follow-up are necessary.