Assaf Glazer, Natalie Barnett, Tor Ivry, Yanai Ankri, Shaked Dovrat, Haviva Veler
Presented at 9th Biennial Conference on Pediatric Sleep Medicine, Nov 2017.
Abstract
Objectives
Nanit has developed a new system for monitoring infant sleep. This system is based on a video camera that is installed above the baby’s crib with a computerized system of identifying sleep and wakefulness. Nanit implements machine learning and advanced camera sensors to measure and understand a baby's sleep cycles. It tells caregivers how long a baby slept, analyzes sleep patterns, keeps track of nighttime visits, plus delivers summaries of day and night sleep. Nanit is the first Baby-Safe smart monitor that utilizes the most advanced and secure camera technology available.
With the development of Nanit, we hope to more accurately and very inexpensively measure sleep parameters without the need for parental reporting or the use of an actigraph or manual video annotation. The objective of this study was to establish an initial proof of concept for Nanit as a replacement of the actigraph as the gold standard of in-home sleep monitoring.
Methods
Three normal babies (aged 5, 8 and 10 months) wore the Motionlogger® Micro Watch Actigraph on their ankle for a cumulative total of eight nights at the same time as they used the Nanit camera above the crib. The actigraph and the Nanit both measure sleep/awake states. The results were analyzed using the Sadeh Infant algorithm. The video from the nanit camera was then manually scored for asleep or awake states by trained personnel with a resolution of 30 seconds epochs. In total, 204131 sleep and 13712 awake epochs were collected.
Results
For the eight nights that were available for analysis, while the overall agreement and sensitivity were similar for both Actigraph and Nanit (around 97% agreement, 98% sensitivity), Nanit outperforms Actigraph on specificity (85% and 70%, respectively). These preliminary results demonstrate the superiority of Nanit to classify awake states at high precision. In addition, the Nanit was also able to provide information on the number of times a caregiver approached the crib and interacted with the baby and the number of times the baby was taken from the crib.
Conclusions
These preliminary results establish proof of concept. We hope the Nanit camera will be able to replace the actigraph as the gold standard of in-home sleep monitoring to provide an inexpensive, accurate way to measure sleep parameters. Nanit also has the potential to revolutionize other fields of research, where diseases could possibly be detected and treated earlier.
More work needs to be done to verify these results with a larger cohort.
We welcome contact by collaborators who may see an opportunity to use Nanit in their research.
Acknowledgment:
This study was conducted under the supervision and advisory support of Prof. Avi Sadeh at TAU.
Disclosure Statement:
This study was funded by Nanit, Inc. Natalie Barnett, Haviva Veler and Avi Sadeh served as consultants for Nanit. Assaf Glazer, Tor Ivry, Yanai Ankri, and Shaked Dovrat are employees of Nanit.
About the Researchers
The researchers included Assaf Glazer, Natalie Barnett, Tor Ivry, Yanai Ankri, Shaked Dovrat, Haviva Veler.
- Dr. Natalie Barnett serves as VP of Clinical Research at Nanit. Natalie initiated sleep research collaborations at Nanit and in her current role, Natalie oversees collaborations with researchers at hospitals and universities around the world who use the Nanit camera to better understand pediatric sleep and leads the internal sleep and development research programs at Nanit. Natalie holds a Ph.D. in Genetics from the University of New England in Australia and a Postgraduate Certificate in Pediatric Sleep Science from the University of Western Australia. Natalie was an Assistant Professor in the Neurogenetics Unit at NYU School of Medicine prior to joining Nanit. Natalie is also the voice of Nanit's science-backed, personalized sleep tips delivered to users throughout their baby's first few years.