Towards Multimodal Equipment to Help in the Diagnosis of COVID-19 Using Machine Learning Algorithms

COVID-19 occurs due to infection through respiratory droplets containing the SARS-CoV-2 virus, which are released when someone sneezes, coughs, or talks. The gold-standard exam to detect the virus is Real-Time Polymerase Chain Reaction (RT-PCR); however, this is an expensive test and may require up to 3 days after infection for a reliable result, and if there is high demand, the labs could be overwhelmed, which can cause significant delays in providing results. Biomedical data (oxygen saturation level—SpO2, body temperature, heart rate, and cough) are acquired from individuals and are used to help infer infection by COVID-19, using machine learning algorithms. The goal of this study is to introduce the Integrated Portable Medical Assistant (IPMA), which is a multimodal piece of equipment that can collect biomedical data, such as oxygen saturation level, body temperature, heart rate, and cough sound, and helps infer the diagnosis of COVID-19 through machine learning algorithms. The IPMA has the capacity to store the biomedical data for continuous studies and can be used to infer other respiratory diseases. Quadratic kernel-free non-linear Support Vector Machine (QSVM) and Decision Tree (DT) were applied on three datasets with data of cough, speech, body temperature, heart rate, and SpO2, obtaining an Accuracy rate (ACC) and Area Under the Curve (AUC) of approximately up to 88.0% and 0.85, respectively, as well as an ACC up to 99% and AUC = 0.94, respectively, for COVID-19 infection inference. When applied to the data acquired with the IMPA, these algorithms achieved 100% accuracy. Regarding the easiness of using the equipment, 36 volunteers reported that the IPMA has a high usability, according to results from two metrics used for evaluation: System Usability Scale (SUS) and Post Study System Usability Questionnaire (PSSUQ), with scores of 85.5 and 1.41, respectively. In light of the worldwide needs for smart equipment to help fight the COVID-19 pandemic, this new equipment may help with the screening of COVID-19 through data collected from biomedical signals and cough sounds, as well as the use of machine learning algorithms.

[1]  K. Umapathy,et al.  Audio texture analysis of COVID-19 cough, breath, and speech sounds , 2022, Biomedical Signal Processing and Control.

[2]  T. Bastos-Filho,et al.  Molecular dynamics of the COVID-19 pandemic in Espirito Santo (Brazil) and border States , 2022, Revista do Instituto de Medicina Tropical de Sao Paulo.

[3]  Rossana Castaldo,et al.  The use of artificial intelligence systems in diagnosis of pneumonia via signs and symptoms: A systematic review , 2022, Biomed. Signal Process. Control..

[4]  Nizar Al Bassam,et al.  Prediction and evaluation of healthy and unhealthy status of COVID-19 patients using wearable device prototype data , 2022, MethodsX.

[5]  Cecilia Mascolo,et al.  Sounds of COVID-19: exploring realistic performance of audio-based digital testing , 2021, npj Digital Medicine.

[6]  R. Khouri,et al.  A Potential SARS-CoV-2 Variant of Interest (VOI) Harboring Mutation E484K in the Spike Protein Was Identified within Lineage B.1.1.33 Circulating in Brazil , 2021, bioRxiv.

[7]  Teodiano Freire Bastos Filho,et al.  Towards the Use of Artificial Intelligence Techniques in Biomedical Data from an Integrated Portable Medical Assistant to Infer Asymptomatic Cases of COVID-19 , 2021, ICITS.

[8]  N. Akilli,et al.  Prevalence of Asymptomatic SARS-CoV-2 Infection , 2021, Annals of Internal Medicine.

[9]  Nuno R. Faria,et al.  Resurgence of COVID-19 in Manaus, Brazil, despite high seroprevalence , 2021, The Lancet.

[10]  David Atienza,et al.  The COUGHVID crowdsourcing dataset, a corpus for the study of large-scale cough analysis algorithms , 2020, Scientific Data.

[11]  Loris Nanni,et al.  An Ensemble of Convolutional Neural Networks for Audio Classification , 2020, Applied Sciences.

[12]  A. C. Villa-Parra,et al.  Prototype of a Device for the Automatic Measurement of Physiological Signals to Assist the Diagnosis and Monitoring of Patients with Covid-19 , 2022 .

[13]  E. Topol Is my cough COVID-19? , 2020, The Lancet.

[14]  Tao Wang,et al.  Pre-symptomatic detection of COVID-19 from smartwatch data , 2020, Nature Biomedical Engineering.

[15]  Brian Subirana,et al.  COVID-19 Artificial Intelligence Diagnosis Using Only Cough Recordings , 2020, IEEE Open Journal of Engineering in Medicine and Biology.

[16]  Ester Cerdeira Sabino,et al.  SARS-CoV-2 and the COVID-19 disease: a mini review on diagnostic methods , 2020, Revista do Instituto de Medicina Tropical de Sao Paulo.

[17]  Cecilia Mascolo,et al.  Exploring Automatic Diagnosis of COVID-19 from Crowdsourced Respiratory Sound Data , 2020, KDD.

[18]  Srikanth Raj Chetupalli,et al.  Coswara - A Database of Breathing, Cough, and Voice Sounds for COVID-19 Diagnosis , 2020, INTERSPEECH.

[19]  Zhenhua Zhang,et al.  The establishment of reference sequence for SARS‐CoV‐2 and variation analysis , 2020, Journal of medical virology.

[20]  Sridhar Krishnan,et al.  Trends in audio signal feature extraction methods , 2020 .

[21]  Kin-Man Lam,et al.  Histogram-based local descriptors for facial expression recognition (FER): A comprehensive study , 2018, J. Vis. Commun. Image Represent..

[22]  William Robson Schwartz,et al.  Human Activity Recognition Based on Wearable Sensor Data: A Standardization of the State-of-the-Art , 2018, ArXiv.

[23]  James R. Lewis,et al.  The System Usability Scale: Past, Present, and Future , 2018, Int. J. Hum. Comput. Interact..

[24]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[25]  J. B. Brooke,et al.  SUS: a retrospective , 2013 .

[26]  辛 太廣,et al.  Johns Hopkins University , 1895, The Biblical World.

[27]  J. B. Brooke,et al.  SUS: A 'Quick and Dirty' Usability Scale , 1996 .

[28]  D. Phillips,et al.  Accuracy of automated finger blood pressure devices. , 1996, Family medicine.

[29]  James R. Lewis,et al.  IBM computer usability satisfaction questionnaires: Psychometric evaluation and instructions for use , 1995, Int. J. Hum. Comput. Interact..

[30]  Jakob Nielsen,et al.  A mathematical model of the finding of usability problems , 1993, INTERCHI.