Big Monkey| Sleep Shift Scheduling Tool
Sleep Shift Scheduling Tool
Sleepy Monkey
Summary
Sleepy Monkey aims to bring precision and scientific knowledge to the traveler and shift worker's sleep schedule. We have created a platform that utilizes phase response curves for several variables that affect sleep and wake times, such as drugs, exercise, light exposure and ambient temperature. Our shift calculating functions, regressed from reputable scientific sources, can inform a user as to when a certain activity among the above mentioned should be undertaken to achieve a desired shift in the circadian clock. Additionally, the tool also optimizes for sleep quality, using information about individual sleep and daily habits to improve sleep onset and reduce latency
How We Addressed This Challenge
We developed and app that calculates optimal times for exercise, drugs and light as to shift or improve one's circadian rhythm. Our project brings scientific precision to the domain of sleep-enhancement technologies, recommending the exact timing of certain stimuli to achieve desired shifts in the phase of the circadian clock oscillator. The app should also be able to time stimuli (food, exercise, drug consumption) to enhance sleep instead of just shifting the period to compensate for jet lag. Right now the user must set the target sleep time by themselves, but a future version will predict the target sleep time automatically according to the traveler's current sleep time and the target timezone. The algorithm uses a single variable, work_time, to encapsulate the working hours, departure, arrival and docking periods with the purpose of avoiding recommending routines during these periods. Current drugs with coded phase response curves are PF670462 and exogenous melatonin.
How We Developed This Project
Our inspiration was
For the complete development of this project, several technologies were needed. The platform used Javascript (NodeJS for the back-end and React for the front-end), but in order to make the sleep schedule phase response algorithms function, they had to be regressed from Phase Response Curve research data available online. With that in mind, we used NumPy to regress polynomials that matched the individual phase responses of variables. In the phase 2 of the project, the evaluation of sleep quality, we pretend to calculate data with neural networks that output sleep onset, latency and wakefulness according to daily behavior and stimuli. The data used will mainly come from the Nature Microgravity article, as it is most suited for the calculation of microgravity sleep quality. Other sources for nutrition and exercise had to be taken in account to enable sleep quality prediction engines better latency regression.
One relevant problem was acquiring reputable sources to back our calculations. Most datasets in the sleep field are quite small, only comprising of a few dozens of individuals. Simple regression algorithms were used for the Phase Response Curves, but the sleep quality indices required more advanced prediction.
Another problem was calculating sleep time shifts when the most optimal shift for the user was within work time, i.e. finding the best time under a restriction
How We Used Space Agency Data in This Project
During part 2 of algorithm development, optimization of sleep quality based on docking, caffeine and lighting, we used {Flynn-Evans, E., Barger, L., Kubey, A. et al. Circadian misalignment affects sleep and medication use before and during spaceflight. npj Microgravity2, 15019 (2016). https://doi.org/10.1038/npjmgrav.2015.19} as a reference to help calculate the influence of each variable on sleep quality
Project Demo
https://docs.google.com/presentation/d/1EG8pzNeyuiZ_lw8azsHzHxph5t_EBtV7/edit#slide=id.p1
Project Code
Data & Resources
Flynn-Evans, E., Barger, L., Kubey, A. et al. Circadian misalignment affects sleep and medication use before and during spaceflight. npj Microgravity2, 15019 (2016). https://doi.org/10.1038/npjmgrav.2015.19
Burgess HJ, Eastman CI. Short nights reduce light-induced circadian phase delays in humans. Sleep. 2006;29(1):25-30. doi:10.1093/sleep/29.1.25
Burgess HJ, Revell VL, Molina TA, Eastman CI. Human phase response curves to three days of daily melatonin: 0.5 mg versus 3.0 mg. J Clin Endocrinol Metab. 2010;95(7):3325-3331. doi:10.1210/jc.2009-2590
St Hilaire MA, Gooley JJ, Khalsa SB, Kronauer RE, Czeisler CA, Lockley SW. Human phase response curve to a 1 h pulse of bright white light. J Physiol. 2012;590(13):3035-3045. doi:10.1113/jphysiol.2012.227892
Khalsa SB, Jewett ME, Cajochen C, Czeisler CA. A phase response curve to single bright light pulses in human subjects. J Physiol. 2003;549(Pt 3):945-952. doi:10.1113/jphysiol.2003.040477
Revell VL, Molina TA, Eastman CI. Human phase response curve to intermittent blue light using a commercially available device. J Physiol. 2012;590(19):4859-4868. doi:10.1113/jphysiol.2012.235416
Youngstedt SD, Elliott JA, Kripke DF. Human circadian phase-response curves for exercise. J Physiol. 2019;597(8):2253-2268. doi:10.1113/JP276943
Okamoto-Mizuno K, Mizuno K. Effects of thermal environment on sleep and circadian rhythm. J Physiol Anthropol. 2012;31(1):14. Published 2012 May 31. doi:10.1186/1880-6805-31-14
Fairbrother K, Cartner B, Alley JR, et al. Effects of exercise timing on sleep architecture and nocturnal blood pressure in prehypertensives. Vasc Health Risk Manag. 2014;10:691-698. Published 2014 Dec 12. doi:10.2147/VHRM.S73688
Lindseth G, Murray A. Dietary Macronutrients and Sleep. West J Nurs Res. 2016;38(8):938-958. doi:10.1177/0193945916643712
Badura, Lori, et al. "An inhibitor of casein kinase Iϵ induces phase delays in circadian rhythms under free-running and entrained conditions." Journal of Pharmacology and Experimental Therapeutics 322.2 (2007): 730-738.