AI Is Being Used To Screen For Covid By Identifying Its Unique Cough Patterns

Research is revealing that Covid has unique cough patterns which, if identified early enough in potential patients could help screen them for the virus.

AI is being trained on those Covid cough data so that it can test people early in the infection process. JL

AIthority reports:

To use  AI technology to help predict whether people are showing symptoms of COVID-19 infection, one capability involves using crowdsourcing to collect cough sounds from a large number of volunteers and then analyzing that data combined with other datasets from the consortium using AI analytics to identify the unique cough patterns associated with COVID-19 infections. Early published results suggest using AI to identify coughs as a COVID-19 screening mechanism has significant potential, as the pathomorphology of the disease is distinctive from that of other respiratory diseases.

SensiML Corporation, a leading developer of AI tools for building intelligent IoT endpoints, announced that it is collaborating on an effort to use its AI technology to help predict whether people are showing symptoms of COVID-19 infection.  One such capability involves using crowdsourcing to collect cough sounds from a large number of volunteers and then analyzing that data combined with other datasets from the consortium using the SensiML Analytics Toolkit to identify the unique cough patterns associated with COVID-19 infections.  The goal of the initiative is to give businesses, governments, healthcare, and other public facilities access to multi-sensor pre-diagnostic screening mechanisms to help slow the spread of the disease.

The initiative is supported by a consortium of companies, universities, and health organizations including Asymmetric Return Capital, SkyWater Technology, and Upward Health, an in-home and virtual care medical provider. In addition to its work with the consortium to build an enhanced screening application, SensiML plans to open-source its own crowdsourced cough sound dataset for researchers at large to access.

The concept of utilizing AI for pre-diagnostic screening of cough acoustic samples has been studied and validated in recently published academic research and is supported by ongoing projects at multiple esteemed universities.  Early published results suggest that using AI to identify coughs as a COVID-19 screening mechanism has significant potential, as the pathomorphology of the disease is distinctive from that of other respiratory diseases.

“There is tremendous need for better pre-diagnostic screening tools as return-to-work measures are put into place across the US and worldwide.  The entire SensiML team is excited by the prospect that our edge AI technology can potentially make a positive contribution to the global efforts to combat this pandemic,” said Chris Rogers, SensiML CEO.

Data Collection

To support the crowdsourcing effort, the company has set up a web-based data collection page which explains the contribution process and includes a brief (voluntary) questionnaire.  No user-identifying information is collected and all data submitted is anonymous.  Those interested in contributing a cough sample for the initiative (healthy individuals, those having other respiratory conditions, and those suspected or confirmed to have an active COVID-19 infection are encouraged to contribute) can visit:  https://sensiml.com/covid-19/.  Readers and contributors are encouraged to share the link through their own social media channels, as collecting more data will help to make the results more accurate.