CPAP Adherence Assessment via Gaussian Mixture Modeling of Telemonitored Apnea Therapy

Sleep disorders pose serious cardiovascular threats if not treated effectively. However, adherence to Continuous Positive Airway Pressure (CPAP), the most recommended therapy, is known to be challenging to monitor. Telemonitored CPAP equipment has improved the follow-up of CPAP adherence (hours of use per night) by producing far larger amounts of data collected daily. The analysis of such data have relied on averaging the entire therapeutic history and interpreting it without a proper reference concerning the level of adherence. By contrast, we contribute with an unsupervised machine-learning methodology that (i) translates the adherence data to a scale of discrete numbers that hold correspondence to the most usual 30-day-long patterns as observed in a real-word database; (ii) avoids the loss of information aggregation problem by creating summaries of the time series that capture the dynamic nature of the everyday-use CPAP. Our experiments have detected eight particular adherence behaviors validated with information-oriented statistical criteria; we successfully applied them to the time series of a French hospital to produce summaries that reflect the adherence of any 30 days of interest. Our method can aid physicians in more precisely evaluating the therapy adherence, as well as fostering systems to alert of problems in the treatment automatically.

Automated summary

This research introduces an unsupervised machine-learning methodology that translates CPAP therapy adherence data into discrete numbers corresponding to 30-day patterns and captures the dynamic nature of CPAP through time series summaries. The method allows for more precise evaluation of therapy adherence and early identification of treatment issues.