We make a software service called EnsoSleep that automates the scoring and analysis of sleep studies using machine learning. Our product saves sleep centers potentially hundreds of hours per month automating one of the most arduous and repetitive data annotation tasks in healthcare; sleep study scoring. More specifically, EnsoSleep saves time by fully automating the process of identifying all of the neural and cardiopulmonary patterns that are necessary to diagnose sleep disorders, and providing a summary report that sleep physicians use to assist diagnosis. Our software integrates with the most popular sleep testing devices and viewers, and requires no user interaction to facilitate end-to-end automated analysis and report generation. Sleep centers currently pay sleep technologists $30-$40 per hour for 1-2 hours for this analysis per patient, so our service is 100x faster, providing results in minutes versus hours, at less than half the cost and greater reliability. With more than 29 m...
We make a software service called EnsoSleep that automates the scoring and analysis of sleep studies using machine learning. Our product saves sleep centers potentially hundreds of hours per month automating one of the most arduous and repetitive data annotation tasks in healthcare; sleep study scoring. More specifically, EnsoSleep saves time by fully automating the process of identifying all of the neural and cardiopulmonary patterns that are necessary to diagnose sleep disorders, and providing a summary report that sleep physicians use to assist diagnosis. Our software integrates with the most popular sleep testing devices and viewers, and requires no user interaction to facilitate end-to-end automated analysis and report generation. Sleep centers currently pay sleep technologists $30-$40 per hour for 1-2 hours for this analysis per patient, so our service is 100x faster, providing results in minutes versus hours, at less than half the cost and greater reliability. With more than 29 million Americans estimated to suffer from sleep apnea, and 50-70 million with a sleep disorder, there is a massive opportunity to deliver cost and time savings to sleep centers and health systems at scale.

It's important to note that we view EnsoSleep as the first of many products built on our core machine learning technology. Our true vision is to become the leading machine learning and artificial intelligence engine for all health signal data. Put simply, we've implemented hundreds of thousands of lines of code to build custom machine learning algorithms that are massively parallelized both across CPU/GPU and distributed cloud systems, capable of running optimizations on terabytes of healthcare data daily. This system has immediate applications for event detection in conditions like Epilepsy, Cardiology (e.g. CHF, atrial fibrillation, arrhythmia), ICU physiological monitoring for decompensation, home health monitoring for chance patients, and a broad variety of other medical, diagnostic, therapeutic, and EMR data sources. Similar to sleep, our goal is to provide artificial intelligence powered software services that create massive cost and time savings for frontline clinicians, allowing them to spend more time with patients and less time with data; improving both patient and provider satisfaction, and patient outcomes.
More information

Investors

Recommendations

Maggie Brickerman

I can't recommend the EnsoData team more highly. In addition to being technical ninjas, they are collaborative, persistent, and highly emotionally intelligent -- all the things you want in a group of founders. It is teams like EnsoData that will change the future of health care.

Ryne Natzke

The EnsoData team has fully immersed themselves in the sleep medicine world as they look to match up their data science/machine learning expertise with making the lives of sleep clinicians and their patients better. After watching sleep technicians spend an hour or more manually scoring complicated test results consisting of dozens of wave forms, Chris and Sam made it their focus to get the clinicians away from the computer and back with the patients. They have very quickly been able to replicate the quality of manual scoring while cutting the time needed per test by about 90%.

They are hungry to get their product through the required regulatory hurdles and into the hands of sleep clinicians, while also keeping an eye on the next opportunity where their platform can analyze and create actionable insights from the exponentially increasing amount of healthcare data being collected by wearables, bedside devices, and EMRs.