Search

Background: The past few years have seen a rapid emergence of artificial intelligence (AI)-enabled technology in the field of sleep medicine. AI refers to the capability of computer systems to perform tasks conventionally considered to require human intelligence, such as speech recognition, decision-making, and visual recognition of patterns and objects. The practice of sleep tracking and measuring physiological signals in sleep is widely practiced. Therefore, sleep monitoring in both the laboratory and ambulatory environments results in the accrual of massive amounts of data that uniquely positions the field of sleep medicine to gain from AI. Method: The purpose of this article is to provide a concise overview of relevant terminology, definitions, and use cases of AI in sleep medicine. This was supplemented by a thorough review of relevant published literature. Results: Artificial intelligence has several applications in sleep medicine including sleep and respiratory event scoring in the sleep laboratory, diagnosing and managing sleep disorders, and population health. While still in its nascent stage, there are several challenges which preclude AI's generalizability and wide-reaching clinical applications. Overcoming these challenges will help integrate AI seamlessly within sleep medicine and augment clinical practice. Conclusion: Artificial intelligence is a powerful tool in healthcare that may improve patient care, enhance diagnostic abilities, and augment the management of sleep disorders. However, there is a need to regulate and standardize existing machine learning algorithms prior to its inclusion in the sleep clinic. [ABSTRACT FROM AUTHOR]

Purpose: To examine associations between objectively measured sleep duration and sleep timing with odds of completion of an in vitro fertilization (IVF) cycle. Methods: This prospective cohort study enrolled 48 women undergoing IVF at a large tertiary medical center between 2015 and 2017. Sleep was assessed by wrist-worn actigraphy, 1–2 weeks prior to initiation of the IVF cycle. Reproductive and IVF cycle data and demographic and health information were obtained from medical charts. Sleep duration, midpoint, and bedtime were examined in relation to IVF cycle completion using logistic regression models, adjusted for age and anti-Müllerian hormone levels. A sub-analysis excluded women who worked non-day shifts to control for circadian misalignment. Results: The median age of all participants was 33 years, with 29% of women >35 years. Ten women had an IVF cycle cancelation prior to embryo transfer. These women had shorter sleep duration, more nocturnal awakenings, lower sleep efficiency, and later sleep timing relative to those who completed their cycle. Longer sleep duration was associated with lower odds of uncompleted IVF cycle (OR = 0.88; 95%CI 0.78, 1.00, per 20-min increment of increased sleep duration). Women with later sleep midpoint and later bedtime had higher odds of uncompleted cycle relative to those with earlier midpoint and earlier bedtime; OR = 1.24; 95%CI 1.09, 1.40 and OR = 1.33; 95%CI 1.17, 1.53 respectively, for 20-min increments. These results were independent of age, anti-Müllerian hormone levels, or sleep duration, and remained significant after exclusion of shift-working women. Conclusions: Shorter sleep duration and later sleep timing increase the odds of uncompleted cycles prior to embryo transfer. [ABSTRACT FROM AUTHOR]

Circadian clocks control the timing of many physiological events in the 24-h day. When individuals undergo an abrupt external shift (e.g., change in work schedule or travel across multiple time zones), circadian clocks become misaligned with the new time and may take several days to adjust. Chronic circadian misalignment, e.g., as a result of shift work, has been shown to lead to several physical and mental health problems. Despite the serious health implications of circadian misalignment, relatively little is known about how genetic variation affects an individual's ability to entrain to abrupt external changes. Accordingly, we used the one-hour advance from the onset of daylight saving time (DST) as a natural experiment to comprehensively study how individual heterogeneity affects the shift of sleep/wake cycles in response to an abrupt external time change. We found that individuals genetically predisposed to a morning tendency adjusted to the advance in a few days, while genetically predisposed evening-inclined individuals had not shifted. Observing differential effects by genetic disposition after a one-hour advance underscores the importance of heterogeneity in adaptation to external schedule shifts. These genetic differences may affect how individuals adjust to jet lag or shift work as well. [ABSTRACT FROM AUTHOR]

While 24-h total sleep time (TST) is established as a critical driver of major depression, the relationships between sleep timing and regularity and mental health remain poorly characterized because most studies have relied on either self-report assessments or traditional objective sleep measurements restricted to cross-sectional time frames and small cohorts. To address this gap, we assessed sleep with a wearable device, daily mood with a smartphone application and depression through the 9-item Patient Health Questionnaire (PHQ-9) over the demanding first year of physician training (internship). In 2115 interns, reduced TST (b = −0.11, p < 0.001), later bedtime (b = 0.068, p = 0.015), along with increased variability in TST (b = 0.4, p = 0.0012) and in wake time (b = 0.081, p = 0.005) were associated with more depressive symptoms. Overall, the aggregated impact of sleep variability parameters and of mean sleep parameters on PHQ-9 were similar in magnitude (both r2 = 0.01). Within individuals, increased TST (b = 0.06, p < 0.001), later wake time (b = 0.09, p < 0.001), earlier bedtime (b = − 0.07, p < 0.001), as well as lower day-to-day shifts in TST (b = −0.011, p < 0.001) and in wake time (b = −0.004, p < 0.001) were associated with improved next-day mood. Variability in sleep parameters substantially impacted mood and depression, similar in magnitude to the mean levels of sleep parameters. Interventions that target sleep consistency, along with sleep duration, hold promise to improve mental health. [ABSTRACT FROM AUTHOR]

Purpose: Home sleep apnea tests (HSATs) are an alternative to attended polysomnograms (PSGs) when the pre-test probability for moderate to severe OSA is high. However, insurers often mandate use anytime OSA is suspected regardless of the pre-test probability. Our objective was to determine the ability of HSATs to rule in OSA when the pre-test probability of an apnea hypopnea index (AHI) in the moderate to severe range is low.Methods: Patients who underwent HSATs were characterized as low or high pre-test probability based on the presence of two symptoms of the STOP instrument plus either BMI > 35 or male gender. The odds of HSAT diagnostic for OSA dependent on pre-test probability was calculated. Stepwise selection determined predictors of non-diagnostic HSAT. As PSG is performed after HSATs that do not confirm OSA, false negative results were assessed.Results: Among 196 individuals, pre-test probability was low in 74 (38%) and high in 122 (62%). A lower percentage of individuals with a low versus high pre-test probability for moderate to severe OSA had HSAT results that confirmed OSA (61 versus 84%, p = 0.0002) resulting in an odds ratio (OR) of 0.29 for confirmatory HSAT in the low pre-test probability group (95% CI [0.146, 0.563]). Multivariate logistic regression demonstrated that age ≤ 50 (OR 3.10 [1.24-7.73]), female gender (OR 3.58[1.50-8.66]), non-enlarged neck circumference (OR 11.50 [2.50-52.93]), and the absence of loud snoring (OR 3.47 [1.30-9.25]) best predicted non-diagnostic HSAT. OSA was diagnosed by PSG in 54% of individuals with negative HSAT which was similar in both pre-test probability groups.Conclusion: HSATs should be reserved for individuals with high pre-test probability for moderate to severe disease as opposed to any individual with suspected OSA. [ABSTRACT FROM AUTHOR]

With the growth of the 24-hour global marketplace, a substantial proportion of workers are engaged in nontraditional work schedules and frequent jet travel across multiple time zones. Thus, shift work disorder and jet lag are prevalent in our 24/7 society and have been associated with significant health and safety repercussions. In both disorders, treatment strategies are based on promoting good sleep hygiene, improving circadian alignment, and targeting specific symptoms. Treatment of shift work must be tailored to the type of shift. For a night worker, circadian alignment can be achieved with bright light exposure during the shift and avoidance of bright light (with dark or amber sunglasses) toward the latter portion of the work period and during the morning commute home. If insomnia and/or excessive sleepiness are prominent complaints despite behavioral approaches and adequate opportunity for sleep, melatonin may be administered prior to the day sleep period to improve sleep, and alertness during work can be augmented by caffeine and wake-promoting agents. For jet lag, circadian adaptation is suggested only for travel greater than 48 h, with travel east more challenging than travel west. Although advancing sleep and wake times and circadian timing for eastward travel with evening melatonin and morning bright light several days prior to departure can help avoid jet lag at the new destination, this approach may be impractical for many people, Therefore, strategies for treatment at the destination, such as avoidance of early morning light and exposure to late-morning and afternoon light alone or in conjunction with bedtime melatonin, can accelerate re-entrainment following eastward travel. For westward travel, a circadian delay can be achieved after arrival with afternoon and early-evening light with bedtime melatonin. Good sleep hygiene practices, together with the application of circadian principles, can improve sleep quality, alertness, performance, and safety in shift workers and jet travelers. However, definitive multicenter randomized controlled clinical trials are still needed, using traditional efficacy outcomes such as sleep and performance as well as novel biomarkers of health. [ABSTRACT FROM AUTHOR]