automatic support for improving management and treatment of patients with obtrusive sleep apnea...

9
Automatic Support for Improving Management and Treatment of Patients with Obstructive Sleep Apnea Syndrome Xavier Rafael Palou; Cecilia Turino; Alexander Steblin; Alejandro Lopera; Ferran Peña; Ana Mayoral; Manuel Sánchez de la Torre; Ferran Barbe; Jordi Blanco; Eloisa Vargiu

Upload: eloisa-vargiu

Post on 22-Jan-2018

113 views

Category:

Healthcare


0 download

TRANSCRIPT

Automatic Support for Improving Management and Treatment of Patients with Obstructive Sleep

Apnea SyndromeXavier Rafael Palou; Cecilia Turino; Alexander Steblin; Alejandro Lopera; Ferran Peña; Ana Mayoral; Manuel Sánchez de la Torre; Ferran Barbe;

Jordi Blanco; Eloisa Vargiu

Research Objective

To develop new ICT tools and remote clinical follow-up methods to allow the creation of continuous integrated services for the treatment of Obstructive Sleep Apnea (OSA)

To improve patients’ compliance and achieve better follow-up in using continuous positive airway pressure (CPAP) at home

2

Motivation

Currently in Spain, after a visit with a pulmonologist,patients suffering from severe OSA are treated with aCPAP machine at their home

Pulmonologists and CPAP providers guide patients onhow to use the device properly and prescribe them touse the machine at least 4 hours daily in order to benefitthe therapy

From that moment on, the medical protocol states thefollowing visits after 1, 3, 6 and 12 months and then oncea year

3

MethodsPatient’s home: CPAP machine

connected to Internet (3G connectivity) and a smartphone with the app.

Hospital: pulmonologists are provided with a web-application that summarizes relevant information and gives also a support in medical decisions

MyOSA platform: installed in the cloud, it connects all the devices for data exchanging

4

Methods

The core of the proposed solution is the Intelligent Monitoring System It is composed of a set of intelligent algorithms aimed at predicting the

expected adherence level to the therapy by a given patient

Three predictive models have been built: at day enrollment time, at month 1,and at month 3. All predictions regard compliance at month 6

To provide personalized recommendations to patients according to theiradherence, clustering has been used to identify similar users

5

Results

Through the web application pulmonologists may access to patients’ data Usage

Adherence

Number of leaks

Statistics

They also receive a prediction of how patients will follow the therapy

6

Results

Through the myOSA app patients may access to their data Usage

Adherence

Number of leaks

Statistics

They may also receive three kinds of recommendations Awards

Feedback

Alerts7

Final Remarks

The trials just started and a total of 60 patients will participate in the study

We will improve the system by relying with more data and getting direct feedback from patients

We will also work together with pulmonologists to improve and extend the set of recommendations

8

[email protected]

consortium

The study was funded by the Spanish Ministry of Economy and Competitiveness in the framework of the call \Collaboration Challenges" in the State Program for Research, Development and Innovation Oriented to Societal Challenges" (Project myOSA, RTC-2014-3138-1).

Contact