SleepFit SG app for iPhone and iPad

SleepFit SG gives you unparalleled insights into your health through sleep biomarkers. We track and analyze your vitals like heartbeats, respiration, temperature, and movements up to a thousand times every second while you sleep to extract incredible insights into your physical and mental well-being. We use sleep as a portal to understand your present and future health and provide specific actions to improve it.

The data collected is processed by Neurobit’s proprietary AI called Z3Pulse which is backed by decades of research and is trained on trillions of health data points allowing it to understand you both in reference to the general population as well as “you” as a unique person. We strive to continuously add new insights and measurements backed by research and clinical data to better understand yourself and help you and your family lead a healthier and happier life.

Take control of your health through personalized AI-driven recommendations tailored just for you!

DISCLAIMER:

The SleepFit SG app provides you with the analysis of the data collected through the SleepFit sensor. The information presented within the APP or associated report is not intended to diagnose, treat, cure or prevent any disease. All information presented within the APP and the reports are not meant as a substitute for or alternative to information from healthcare practitioners. You may use it as a starting point for any conversation you may have with your doctor.


Clinical Validations*:


Pini, N., Ong, J. L., Yilmaz, G., Chee, N. I., Siting, Z., Awasthi, A., ... & Lucchini, M. (2021). An automated heart rate-based algorithm for sleep stage classification: validation using conventional PSG and innovative wearable ECG device. medRxiv.


Chen, Y. J., Siting, Z., Kishan, K., & Patanaik, A. (2021). Instantaneous Heart Rate-based sleep staging using deep learning models as a convenient alternative to Polysomnography.


Siting, Z., Chen, Y. J., Kishan, K., & Patanaik, A. (2021). Automated sleep apnea detection from instantaneous heart rate using deep learning models.