A Novel AI-enabled Framework to Diagnose Coronavirus COVID 19 using Smartphone Embedded Sensors: Design Study (2003.07434v2)

Abstract: Coronaviruses are a famous family of viruses that cause illness in both humans and animals. The new type of coronavirus COVID-19 was firstly discovered in Wuhan, China. However, recently, the virus has widely spread in most of the world and causing a pandemic according to the World Health Organization (WHO). Further, nowadays, all the world countries are striving to control the COVID-19. There are many mechanisms to detect coronavirus including clinical analysis of chest CT scan images and blood test results. The confirmed COVID-19 patient manifests as fever, tiredness, and dry cough. Particularly, several techniques can be used to detect the initial results of the virus such as medical detection Kits. However, such devices are incurring huge cost, taking time to install them and use. Therefore, in this paper, a new framework is proposed to detect COVID-19 using built-in smartphone sensors. The proposal provides a low-cost solution, since most of radiologists have already held smartphones for different daily-purposes. Not only that but also ordinary people can use the framework on their smartphones for the virus detection purposes. Nowadays Smartphones are powerful with existing computation-rich processors, memory space, and large number of sensors including cameras, microphone, temperature sensor, inertial sensors, proximity, colour-sensor, humidity-sensor, and wireless chipsets/sensors. The designed AI enabled framework reads the smartphone sensors signal measurements to predict the grade of severity of the pneumonia as well as predicting the result of the disease.

• The paper introduces an innovative framework that leverages smartphone sensors like temperature, audio, and inertial data for COVID-19 diagnosis.
• It employs advanced machine learning techniques, including CNNs and RNNs, to analyze sensor data and detect symptoms such as fever and cough.
• The approach offers a scalable, low-cost alternative to traditional diagnostics, potentially expanding rapid COVID-19 screening in resource-limited settings.

An AI-Enabled Framework for Diagnosis of COVID-19 via Smartphone Sensors

The paper presents a novel framework designed to address the urgent need for efficient and cost-effective COVID-19 diagnostic tools. The authors propose an innovative approach leveraging the ubiquity and technological capabilities of modern smartphones. The framework utilizes built-in smartphone sensors to diagnose COVID-19 by analyzing sensor data such as temperature, microphone audio, and accelerometer readings, among others. This approach seeks to alleviate the burden on healthcare systems exacerbated by the COVID-19 pandemic, especially where access to medical resources like CT imaging and nucleic acid tests (NAT) is constrained.

In the backdrop of limited healthcare resources and the risks posed by prolonged exposure environments like hospitals, there is a pressing need for alternative diagnostic methods, particularly during pandemics. Traditional diagnostics, including CT scans and RT-PCR tests, pose limitations due to high costs and the requirement of technical expertise. The proposed smartphone-based method stands out as an accessible and low-cost alternative that might democratize field-based testing. By enabling private individuals and radiologists to conduct preliminary diagnoses using their smartphones, the framework could potentially facilitate widespread and scalable dissemination of diagnostic capabilities.

Technical Contributions

The framework introduced in the paper centers on the exploitation of smartphones' computational capability and their embedded sensors. The paper outlines the development of algorithms that analyze sensor signals to identify COVID-19 symptoms. Specifically, the framework leverages the following:

• Temperature Sensors: Smartphones estimate body temperature through capacitive touch and thermal sensors, potentially identifying fever, a common COVID-19 symptom.
• Microphone: Audio analysis for cough detection, differentiated by sound characteristics unique to respiratory illness.
• Inertial Sensors: Utilized to assess fatigue levels by monitoring user movements, including gait analysis.
• Camera: Provides the capability of capturing CT or X-ray images directly through the phone, aiding in the visualization and assessment of chest abnormalities.

These diagnostic aspects are processed through a comprehensive multi-layered framework featuring sensor data acquisition, preprocessing, symptoms evaluation, and final disease prediction via machine learning techniques. The framework notably combines convolutional neural networks (CNNs) and recurrent neural networks (RNNs), exploiting CNNs for image processing, and RNNs for analyzing time-series sensor data.

Implications and Future Directions

This framework could significantly impact public health by offering a mobile platform for rapid COVID-19 screening. The reliance on smartphones extends diagnostic capabilities to populations with limited access to traditional healthcare. It also presents an opportunity for data collection and aggregation on a massive scale, potentially enhancing epidemiological models and public health strategies.

Future work could explore improvements in algorithmic accuracy and integration with centralized health systems for real-time analytics. The authors have highlighted potential for transfer learning approaches that leverage shared data across devices to refine and enhance diagnostic models, thereby augmenting prediction reliability. Additionally, expanding this framework for detecting other respiratory illnesses could enhance its robustness and applicability beyond COVID-19, rendering it a versatile tool in infectious disease management.

This research signifies a step forward in AI-integrated mobile health solutions and paves the way for innovative, accessible, and cost-effective disease management strategies. Further empirical validation and field studies could consolidate its utility in real-world scenarios, fostering a bridge between technology and global health.