Research - EnsoData

Treatment for Obstructive Sleep Apnea by Area Socioeconomic Deprivation in Six Million Adults

This study assesses the rate of treatment for Obstructive Sleep Apnea analyzed through a lens of socioeconomic demographic data.

REM Behavior Disorder Explainability in EEG via Spectral Band Cluster Prevalence

This study demonstrates potential to improve identification of RBD and RBD subtype-specific EEG biomarkers associated with synucleinopathy and PTSD/TASD.

Narcolepsy Disorders Explainability in EEG via Spectral Band Cluster Prevalence

This study features novel analytic methods for explainability, SBCP (spectral band cluster prevalence), with potential applications to Narcolepsy disorder-specific EEG biomarkers and AI understandability.

Relationship Between RDW and Disease Burden in Obstructive Sleep Apnea

This study highlights the relationship between RDW and Disease Burden in OSA, presented by Northwell Health, Donald and Barbara Zucker School of Medicine at Hofstra/Northwel, and EnsoData Research.

Utilizing machine learning based on multi-modal data to predict PAP adherence in patients with OSA

This study highlights the use of machine learning based on multi-modal data to predict PAP adherence in patients with OSA, presented by Kaiser Permanente and EnsoData Research.

Sleep Architecture Associations with Brain Age: A Multi-Site Model Validation

This research study evaluates large multi-site datasets and assesses the relationship of N3/REM sleep duration with the predicted brain age.

Deep Learning to Predict PAP Adherence in Obstructive Sleep Apnea

In this study, EnsoData shows how ML algorithms based on PAP usage can predict future adherence, offering potential for personalized treatment decisions and preemptive interventions when upcoming non-adherence is predicted.

Artificial Intelligence to Aid in Diagnosis of Type I Narcolepsy

This research study demonstrated that Machine Learning methods can automatically detect Type I Narcolepsy using in PSG-EEG with promising degrees of accuracy.

Use of Artificial Intelligence for Early Characterization of Patients with RBD

This study demonstrates the ability of AI approaches produced high specificity and moderate sensitivity for REM Behavior Disorder and the potential to expand early detection and diagnosis of RBD.