RESUMEN
Predicting vigilance impairment in high-risk shift work occupations is critical to help to reduce workplace errors and accidents. Current methods rely on multi-night, often manually entered, sleep data. This study developed a machine learning model for predicting vigilance errors based on a single prior sleep period, derived from an under-mattress sensor. Twenty-four healthy volunteers (mean [SD] age = 27.6 [9.5] years, 12 male) attended the laboratory on two separate occasions, 1 month apart, to compare wake performance and sleep under two different lighting conditions. Each condition occurred over an 8 day protocol comprising a baseline sleep opportunity from 10 p.m. to 7 a.m., a 27 h wake period, then daytime sleep opportunities from 10 a.m. to 7 p.m. on days 3-7. From 12 a.m. to 8 a.m. on each of days 4-7, participants completed simulated night shifts that included six 10 min psychomotor vigilance task (PVT) trials per shift. Sleep was assessed using an under-mattress sensor. Using extra-trees machine learning models, PVT performance (reaction times <500 ms, reaction, and lapses) during each night shift was predicted based on the preceding daytime sleep. The final extra-trees model demonstrated moderate accuracy for predicting PVT performance, with standard errors (RMSE) of 19.9 ms (reaction time, 359 [41.6]ms), 0.42 reactions/s (reaction speed, 2.5 [0.6] reactions/s), and 7.2 (lapses, 10.5 [12.3]). The model also correctly classified 84% of trials containing ≥5 lapses (Matthews correlation coefficient = 0.59, F1 = 0.83). Model performance is comparable to current fatigue prediction models that rely upon self-report or manually entered data. This efficient approach may help to manage fatigue and safety in non-standard work schedules.
RESUMEN
BACKGROUND: Irregularities in sleep duration and sleep timing have emerged as potential risk factors for hypertension. This study examined associations between irregularity in sleep duration and timing with hypertension in a large, global sample over multiple months. METHODS: Data from 12 287 adults, who used an under-mattress device to monitor sleep duration and timing and also provided blood pressure recordings on ≥5 separate occasions, were analyzed. Sleep duration irregularity was assessed as the SD in total sleep time across the ≈9-month recording period. Sleep timing irregularity was assessed as SDs in sleep onset time, sleep midpoint, and sleep offset time. Logistic regressions were conducted to investigate associations between sleep irregularity and hypertension, defined as median systolic blood pressure ≥140 mm Hg or median diastolic blood pressure ≥90 mm Hg. RESULTS: Participants were middle-aged (mean±SD, 50±12 years), mostly men (88%) and overweight (body mass index, 28±6 kg/m-2). Sleep duration irregularity was consistently associated with an ≈9% to 17% increase in hypertension independently of the total sleep time. A ≈34-minute increase in sleep onset time irregularity was associated with a 32% increase in hypertension (1.32 [1.20-1.45]). A 32-minute increase in sleep midpoint irregularity was associated with an 18% increase in hypertension (1.18 [1.09-1.29]), while a 43-minute increase in sleep offset time irregularity was associated with an 8.9% increase in hypertension (1.09 [1.001-1.18]). CONCLUSIONS: These findings support that sleep irregularity, both in duration and timing, is a risk marker for poor cardiovascular health. Further mechanistic investigations of temporal relationships between day-to-day fluctuations in sleep duration and timing, next-day blood pressure, and other cardiovascular outcomes are warranted.
