An m-health application for cerebral stroke detection and monitoring using cloud services

Highlights

• We propose a cerebral stroke detection solution that employs the cloud.

• The proposal allows storing and analyzing data to provide statistics to public institutions.

• The system is based on the three most important symptoms of cerebral strokes.

• Several tests have been performed in order to verify the application.

Abstract

Over 25 million people suffered from cerebral strokes in a span of 23 years. Many systems are being developed to monitor and improve the life of patients that suffer from different diseases. However, solutions for cerebral strokes are hard to find. Moreover, due to their widespread utilization, smartphones have presented themselves as the most appropriate devices for many e-health systems. In this paper, we propose a cerebral stroke detection solution that employs the cloud to store and analyze data in order to provide statistics to public institutions. Moreover, the prototype of the application is presented. The three most important symptoms of cerebral strokes were considered to develop the tasks that are conducted. Thus, the first task detects smiles, the second task employs voice recognition to determine if a sentence is repeated correctly and, the third task determines if the arms can be raised. Several tests were performed in order to verify the application. Results show its ability to determine whether users have the symptoms of cerebral stroke or not.

Introduction

Ischaemic strokes are one of the most common diseases in the world. From 1990 to 2013, 6.3 million people died from this type of stroke. Although the numbers are alarming, 25.7 million people were able to survive (Meschia & Brott, 2017). However, surviving a cerebral stroke does not guarantee a prompt recovery or a life exempt of the side effects caused by the lack of blood in the area of the brain affected during the stroke. Moreover, the fastest the stroke is detected, the least sequels the patient will have. The aftereffects of a cerebral stroke include a deterioration of cognitive and motor functions (Tatemichi et al., 1994). Memory loss, difficulties in speech, short attention spans, poor visuospatial skills or lack of orientations are some of the cognitive functions that can be impaired. Mobility in arms and legs is impaired as well resulting in an increased probability of falls (Langhorne et al., 2000). Pain can also be present after the discharge from the hospital. Psychologically, patients may suffer from anxiety and depression. Numerous people do not know how to identify a cerebral stroke and many patients may spend more time than they should waiting for a family member or a person close to them to realize that they are having a stroke. Because of that reason, countless campaigns have been promoted by both hospitals and governments. However, as new platforms are available, the number of campaigns and solutions designed for mobile phones is increasing.

Early disease diagnose of different diseases is increasingly being done utilizing Wireless Sensor Networks (WSN) (Chung, Lee, & Toh, 2008). They provide a great help to people who do not know the symptoms of a disease but suspect that they are having health related problems. Some countries experience overcrowded waiting rooms in hospitals (Firdaus & Samadhi, 2014). Thus, these types of solutions may reduce the number of people that go to the emergency room as they may be advised by the application to go to a regular medical practice. Moreover, one of the areas that has had a greater growth in health-related technologies for health monitoring and prevention is Ambient Assisted Living (AAL) (Lloret, Canovas, Sendra, & Parra, 2015). It provides varied features that allow to make the life of its user more comfortable such as turning on the lights when the user is approaching an area, turning off the television or other electronic devices and closing blinds or curtains at night. Furthermore, AAL in utilized as well to notify a trusted person or emergencies if the user is currently impaired. Falls, shouts or abnormal behavior can trigger the alarm system that contact the necessary parties (Rghioui, Sendra, Lloret, & Oumnad, 2016). Cloud solutions are often necessary in order to manage the vast volume of data generated by these applications (Cuong, Solanki, Thang, & Thuy, 2017). Many providers have addressed this necessity and are now offering competitive services for IoT (Internet of Things) systems. The devices deployed at the house gather data through sensors and forward the information to a database. However, many health problems can also happen when being outside of home.

Smartphones provide a wide variety of sensors integrated in one device, allowing monitoring and measuring health at any place and any time. Multimedia sensors like the microphone and the camera integrated in smartphones allow to employ this device in a wide variety of e-health applications (Parra, Sendra, Jiménez, & Lloret, 2016). As a matter of fact, smartphone cameras were employed on a 67% of the e-health applications developed between 2010 and 2014, and 33% of these applications employed the microphone. On the one hand, cameras can be employed for measuring heart rate, determine the emotions (Lakens, 2013), detecting obstacles and diagnosing retinal and skin diseases. On the other hand, the microphone has been utilized to monitor nasal symptoms like sneezing, monitor sleep apnea, performing a spirometry or detecting stress. Non-multimedia sensors deployed in smartphones are employed for e-health applications as well. The accelerometer has also been widely utilized for e-health solutions. Body postures (Patel, Bhatt, & Patel, 2017), falls (Li et al., 2009) or activity recognition (Ugulino et al., 2012) are some of the activities that are usually monitored employing accelerometers. The conjunction of all these sensors are indicated for cerebral stroke detection as they allow developing the functionalities suitable for its symptoms.

In this paper, a mobile phone application for cerebral stroke detection is proposed. It allows to determine if the symptoms of cerebral strokes are being suffered by users. The application is able to contact a designated person by sending an SMS. Medical emergencies are also contacted in order to reduce the time the user is having a cerebral stroke without being treated. Moreover, demographic information on the user can be stored and analyzed in the cloud in order to provide statistics on the incidence of cerebral strokes. The contributions of this paper are:

• The proposal of a framework for our cerebral stroke detection system that employs cloud to store and analyze the data.

• An implementation of the prototype application which has allowed performing tests and evaluating the response of the user to the proposed application.

The rest of the paper is organized as follows. Section 2 depicts the related work. The proposal is described in Section 3. Section 4 discusses the results. Finally, the conclusion and future work is presented in Section 5.