Italiano Inglese

CovidDeep: SARS-CoV-2/COVID-19 Test Based on Wearable Medical Sensors and Efficient Neural Networks

Shayan Hassantabar, Novati Stefano, Vishweshwar Ghanakota, Alessandra Ferrari, Gregory N. Nicola, Raffaele Bruno, Ignazio R. Marino, Niraj K. Jha

The novel coronavirus (SARS-CoV-2) has led to a pandemic. Due to its highly contagious nature, it has spread rapidly, resulting in major disruption to public health. In addition, it has also had a severe negative impact on the world economy. As a result, it is widely recognized now that widespread testing is key to containing the spread of the disease and opening up the economy. However, the current testing regime has been unable to keep up with testing demands. Hence, there is a need for an alternative approach for repeated large-scale testing of COVID-19. The emergence of wearable medical sensors (WMSs) and novel machine learning methods, such as deep neural networks (DNNs), points to a promising approach to address this challenge. WMSs enable continuous and user-transparent monitoring of the physiological signals. However, disease detection based on WMSs/DNNs and their deployment on resource-constrained edge devices remain challenging problems. In this work, we propose CovidDeep, a framework that combines efficient DNNs with commercially available WMSs for pervasive testing of the coronavirus. We collected data from 87 individuals, spanning four cohorts including healthy, asymptomatic (but SARS-CoV-2-positive) as well as moderately and severely symptomatic COVID-19 patients. We trained DNNs on various subsets of the features extracted from six WMS and questionnaire categories to perform ablation studies to determine which subsets are most efficacious in terms of test accuracy for a four-way classification. The highest test accuracy obtained was 99.6%. Since different WMS subsets may be more accessible (in terms of cost, availability, etc.) to different sets of people, we hope these DNN models will provide users with ample flexibility. The resultant DNNs can be easily deployed on edge devices, e.g., smartwatch or smartphone, which also has the benefit of preserving patient privacy.

View full article in PDF


Il coronavirus ha portato a una pandemia con gravissime conseguenze per la salute pubblica, un'enorme perdita di vite umane e un forte impatto negativo sull'economia mondiale. E' ampiamente riconosciuto che la diffusione dei test di screening è la chiave per contenere la diffusione della malattia e per riavviare l'economia. C'è la necessità di un approccio alternativo ai test finora disponibili. L'emergere di sensori medici indossabili (WMS) e nuovi metodi di machine learning attraverso l’Artificial Intelligence, come le reti neurali profonde (DNN), indicano un approccio promettente per affrontare questo problema. I WMS consentono un monitoraggio continuo e trasparente dei segnali fisiologici da parte dell'utente. Nel nostro studio abbiamo proposto un framework chiamato CovidDeep che combina DNN efficienti con WMS disponibili in commercio. Abbiamo raccolto dati da 87 individui, suddivisi in quattro coorti, compresi soggetti sani e asintomatici (ma SARS-CoV-2-positivo), nonché pazienti COVID-19 moderatamente e gravemente sintomatici. 
Il test ha dimostrato un'accuratezza del 99,6%. Poiché diversi sottoinsiemi del WMS possono essere più accessibili (in termini di costi, disponibilità, ecc.) a diversi gruppi di persone, ci auguriamo che questi modelli DNN offrano agli utenti un'ampia flessibilità. Si tratta di una vera rivoluzione nello screening dei pazienti.

I DNN risultanti possono essere facilmente implementati su dispositivi come smartwatch o smartphone, preservando la privacy dei pazienti.

Articolo completo in PDF