20th Annual Sleep and Health Benefit

A classification approach to predicting human circadian phase from actigraphy data

Lindsey Brown, SM

Harvard John A. Paulson School of Engineering and Applied Sciences

If the PDF viewer does not appear initially, please reload the page to refresh your browser. 

Clinical Implications
Chronotherapeutic approaches require the ability to assess an individual’s circadian phase. The current gold standard approach for assessing human circadian phase, dim light melatonin onset, is limited in utility for this purpose because it is time and resource intensive. The approach to predicting phase detailed here provides a noninvasive approach which generalizes well to cases when circadian and rest-activity rhythms are well aligned. Thus, this approach provides an alternative method for circadian phase assessment and suggests the limitations of the use of actigraphy measures in misaligned cases.
Research Narrative

Dim light melatonin onset, or DLMO, is the gold standard for circadian phase assessment in humans, but it is limited in being time and resource intensive. Numerous studies have attempted to predict circadian phase from actigraphy data with some success in more controlled populations, where mean errors are reported between .5 and 1 hours. We find that such algorithms are less successful in predicting DLMO in a population of college students with more irregular schedules, where mean errors in predicting DLMO directly are approximately 1.5 hours. By reframing the problem of predicting DLMO as a classification problem, where we use a neural network to predict whether a timepoint falls before or after DLMO, we find high classification accuracy of about 90%, which decreases the mean error to approximately 1.2 hours. To test the generalizability of this approach, we apply the same neural network to data from forced desynchrony studies. In the participants on the forced desynchrony protocol, classification accuracy drops to 55-65%. We find that this accuracy is highly dependent upon the phase angle between DLMO and sleep onset with highest accuracy at normal phase angles: ranging between 20 and 80% depending upon the phase angle. This suggests that the method is valid when circadian phase and sleep-wake with its associated behaviors are appropriately aligned. More work should be done in cases of circadian misalignment with rest-activity rhythms.

Research Category
Explore Other Posters

10:00 – 11:30 AM ET
HMS DSM Annual Faculty Meeting

10:00 – 11:30 AM ET
Mary A. Carskadon, PhD Introductory Meeting with HMS DSM Trainees

12:00 – 1:15 PM ET
Division of Sleep Medicine Annual Prize Lecture by Mary A. Carskadon, PhD

1:15 – 1:30 PM ET
Awarding of 2020 Harvard Medical School Division of Sleep Medicine Prize to Mary A. Carskadon, PhD

3:00 – 4:30 PM ET
Poster Session

4:30 – 5:30 PM ET

6:00 – 7:00 PM ET
Evening Public Lecture by Mary A. Carskadon, PhD

“Changes in Sleep Biology Create a Perfect Storm Affecting Teen Health and Well-Being”