EMFIT QS for Academic Research
Emfit QS + Research
Several academic researchers are using EMFIT QS to collect vitals data during sleep. Our API allows autonomous and automatic data collection for medical insights and discoveries. Cellular network connectivity (3G version) enables hassle-free home installation for research participant. That, and being contact-free under mattresses installed, ensures best possible user adherence. These features make it easier to enroll participants and conduct studies.
The Sleep Period API
The SleepPeriod API is “push API” where all sleep period data is pushed to a given endpoint URL after a period has ended. It provides heart rate, breathing rate, and movement activity data by every 4 seconds. Sleep staging every 30 seconds and HRV RMSSD every 3 minutes. Research potential of this high-frequency and high quality calculated data is vast.
Band-Pass-filtered Sensor Signal API
Optionally the band-pass-filtered sensor signal is available as “get API”. The low band 0,07 – 3 Hz is sampled at 25 Hz. The high band is either 1 – 35 Hz band and sampled at 100 Hz, or 1 – 85 Hz band and sampled at 200 Hz. Both high band options show clearly both ballistocardiogram and breathing, and the later also snoring. The amount of data collected — and the insight gained — is groundbreaking.
Samuel Eving, EngD
Major pharmaceutical company
EMFIT QS enables high adherence to data capture processes
Could you please introduce yourself?
I’m Sam Ewing, Doctor of Engineering and I lead sensor assessment and selection for a major pharmaceutical company.
Could you tell us a little bit about your digital health research projects?
We are using Emfit sleep sensors in a number of our clinical research programs ranging from neurodevelopmental disorders to cardiovascular diseases. Our research covers the breadth of indications for digital health monitoring solutions, from symptom progression and remote disease monitoring to clinical trial endpoint development and drug efficacy in clinical trials.
What do you think are today’s biggest challenges in your area of research?
The biggest challenge in the application of consumer sensor technologies is the volatility of the enormous technology space: the number of vendors marketing a technology solution for a sensor/measurement modality is vastly greater than the number of sensor technologies themselves with vendors appearing and disappearing over short timescales. Even the product life cycles of relatively mature technologies from massive suppliers are extremely short compared with the timescale of clinical development requiring digital biomarker strategies to continuously evolve. Monitoring this landscape is intensive and providing continuity of our research deliverables over the lifetime of clinical development is extremely challenging.
Has EMFIT QS helped you with these challenges and if it has, how?
Emfit haven’t necessarily addressed this challenge yet. However, I expect that as the wearable sensor field matures that we will see a number of mergers, acquisitions and vendor-shutdowns that will consolidate this technology space and reduce the complexity. Having assessed the hardware available in this space, I am confident that Emfit will weather this and continue to provide high-quality sleep sensors that I can rely on in the years to come.
Have you been happy with the technology and quality of service of Emfit?
I am very satisfied with my experience with Emfit sensors and the support I have received from the Emfit team. I look forward to continuing to work with Emfit in the future.
What do you think are the strengths of EMFIT QS for research use?
Emfit’s solution for capturing sleep data is unobtrusive, easy-to-use and transparent to our study participants. The 3G solution fits into our strategy of deploying devices that require the minimum possible effort on behalf of study participants. The device, being essentially plug-and-play, is invisible to our participants enabling high adherence to our data capture processes.