PRESENTED BY: APRA GUPTA

SleepApSleepAp: An Automated Obstructive Sleep

Apnoea Screening Application for Smartphones

OSA is the intermittent cessation of airflow at the nose and mouth during sleep.

It is a type of sleep disorder characterized by pauses in breathing or instances of shallow or infrequent breathing during sleep.

Each pause in breathing, called an apnea and can last for several seconds to several minutes, and may occur 5 to 30 times or more in an hour.

 Similarly, each abnormally shallow breathing event is called a hypopnea. 

What is OSA?

High blood pressure Stroke Heart failure, irregular heart beats, and heart attack Diabetes Depression Worsening of ADHD (Attention-deficit/hyperactivity disorder) Headaches In addition, untreated sleep apnea may be responsible for poor

performance in everyday activities, such as at work and school, motor vehicle crashes, and academic underachievement in children and adolescents.

Effects of Sleep Apnea?

Polysomnography = a detailed overnight sleep study with recordings of features like:

Actigrapghy and body position Audio PPG (Plethysmography) Demographics Questionare

Diagnostic tests

Application of accelerometers using miniature

motion sensors to study the macro and micro

activities associated with human motion has

been termed actigraphy.

Record the patient’s movement over the night

Actigraphy

Body position can be computed on a mobile phone by taking

complimentary measures from two sensors commonly found in

smartphones: an accelerometer and a geomagnetic field sensor

Body position

In this work, audio signals of 145 patients with obstructive sleep apnea were recorded (more than 1000 hours) in a sleep laboratory and analyzed. The method is based on the assumption that during sleep the respiratory efforts are more periodically patterned and consistent relative to a waking state; furthermore, the sound intensity of those efforts is higher, making the pattern more noticeable relative to the background noise level. 

Recorded audio of the patient’s breathing during sleep is an efficient tool forOSAdiagnosis. Snoring sounds

from healthy and sleep apnoea patients have significant

differences and may be used alone to provide accurate classification

between these two groups

Audio

A PPG is often obtained by using a pulse oximeter which illuminates the skin and measures changes in light absorption.A conventional pulse oximeter monitors the perfusion of blood to the dermis and subcutaneous tissue of the skin.

Gives a recorded saturation level of Oxygen.

PPG

Demographics Demographics are the quantifiable statistics of a given

population. Demographics are also used to identify the study of quantifiable subsets within a given population which characterize

that population at a specific point in time.

Questions for Sleep Apnea1. Do you snore more than three nights a week?

 Yes (2 points) No

2. Is your snoring loud (can it be heard through a door or wall)?

 Yes (2 points) No

3. Has anyone ever told you that you briefly stop breathing or gasp when you are asleep?

 Never Occasionally (3 points) Frequently (5 points)

4. What is your collar size? Men: Less than 17 inches 17 inches or greater (5 points)Women: Less than 16 inches 16 inches or greater (5 points)

5. Have you had high blood pressure, or are you being treated for it?

 Yes (2 points) No

6. Do you ever doze or fall asleep during the day when you are not busy or active?

 Yes (2 points) No

7. Do you ever doze or fall asleep during the day when you are driving or stopped at a light?

 Yes (2 points) No

.

The method of multiscale entropy (MSE) analysis is useful for investigating complexity in physiologic signals and other series that have correlations at multiple (time) scales.

MSE

In machine learning, support vector machines (SVMs, also support vector networks[1]) are supervised learning models with associated learningalgorithms that analyze data and recognize patterns, used for classification andregression analysis. The classifier is a separating hyperplane.

Most “important” training points are support vectors; they define the hyperplane.

1. Maximizing the margin is good according to intuition and PAC theory

2. Implies that only support vectors are important; other training examples are ignorable.

3. Empirically it works very very well.

SVM

The recent increase in adoption of smartphones along withthe inclusion of high-quality internal sensors has led to the proliferationof sleep screening smartphone applications

SleepAp