Actigraphic and self-reported characterization of sleep in systemic lupus erythematosus patients

OBJECTIVES

In a cross-sectional study, we explored possible differences in sleep parameters between SLE patients and age- and gender-matched healthy controls through actigraphic and self-reported measures. Furthermore, we aimed to identify possible predictors of such disturbances in the patient cohort.

METHODS

Participants' sociodemographic data and sleep parameters were collected. Sleep parameters were evaluated through the Pittsburgh Sleep Quality Index, the Insomnia Severity Index and 7-day actigraphic monitoring. The 10-item Perceived Stress Scale was used to investigate stress. Disease activity and daily glucocorticoid dose were assessed in SLE patients. Possible predictors of the SLE group were explored through two binomial logistic models. Within the SLE group, possible predictors of sleep parameters were tested estimating multiple linear regression models.

RESULTS

A total of 40 SLE patients and 33 controls were included in the study. The SLE group showed worse sleep maintenance actigraphic parameters (i.e. sleep efficiency and wake after sleep onset), higher total sleep time and higher perceived stress. Within the SLE cohort, the daily glucocorticoids dose was associated with an impairment in sleep maintenance despite no reduction in sleep duration, typical of normal sleep duration insomnia, whereas perceived stress was associated with short sleep duration insomnia.

CONCLUSION

Compared with healthy controls, SLE patients showed worse sleep quality and greater perceived stress severity. As glucocorticoids and perceived stress are associated with different types of insomnia in these patients, a multidimensional approach to both sleep characterization and therapy might be preferred.

Obstructive Sleep Apnoea Syndrome Screening Through Wrist-Worn Smartbands: A Machine-Learning Approach

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.