MIT Claims AI Model Can Detect Asymptomatic COVID-19 By Sound of Cough

Three MIT researchers recently published a paper in the IEEE Journal of Engineering in Medicine & Biology reporting their AI model could detect asymptomatic cases of COVID-19 just by listening to a person’s cough.

According to the paper’s abstract,

We hypothesized that COVID-19 subjects, especially including asymptomatics, could be accurately discriminated only from a forced-cough cell phone recording using Artificial Intelligence. To train our MIT Open Voice model we built a data collection pipeline of COVID-19 cough recordings through our website (opensigma.mit.edu) between April and May 2020 and created the largest audio COVID-19 cough balanced dataset reported to date with 5,320 subjects. Methods: We developed an AI speech processing framework that leverages acoustic biomarker feature extractors to pre-screen for COVID-19 from cough recordings, and provide a personalized patient saliency map to longitudinally monitor patients in real-time, non-invasively, and at essentially zero variable cost. Cough recordings are transformed with Mel Frequency Cepstral Coefficient and inputted into a Convolutional Neural Network (CNN) based architecture made up of one Poisson biomarker layer and 3 pre-trained ResNet50’s in parallel, outputting a binary pre-screening diagnostic. Our CNN-based models have been trained on 4256 subjects and tested on the remaining 1064 subjects of our dataset. Transfer learning was used to learn biomarker features on larger datasets, previously successfully tested in our Lab on Alzheimer’s, which significantly improves the COVID-19 discrimination accuracy of our architecture. Results: When validated with subjects diagnosed using an official test, the model achieves COVID-19 sensitivity of 98.5% with a specificity of 94.2% (AUC: 0.97). For asymptomatic subjects it achieves sensitivity of 100% with a specificity of 83.2%. Conclusions: AI techniques can produce a free, non-invasive, real-time, any-time, instantly distributable, large-scale COVID-19 asymptomatic screening tool to augment current approaches in containing the spread of COVID-19. Practical use cases could be for daily screening of students, workers, and public as schools, jobs, and transport reopen, or for pool testing to quickly alert of outbreaks in groups.

Trump Again Repeats Nonsensical Conspiracy Theory That Doctors Get Paid For COVID-19 Deaths

The President’s Idiot Son: COVID-19 Deaths Are “Almost Nothing”

While daily COVID-19 cases are spiking to new record levels in the United States, and daily deaths once again trend upwards to more than 839 per day, Donald Trump Jr. went on Fox News to say that COVID-19 deaths are “almost nothing.”

What’s hundreds of thousands of dead Americans when Daddy’s re-election is on the line?

National Center for Disaster Preparedness Report Says 130,000-210,000 US COVID-19 Deaths Were Avoidable

Columbia University’s National Center for Disaster Preparedness released a report arguing that 130,000-210,000 COVID-19 deaths in the United States were avoidable had the national and state governments responded tot he pandemic appropriately.

When comparing U.S. fatalities with other high-income countries, the contrast becomes particularly stark. Beyond the total deaths of U.S. citizens – which officially stands at 217,717 but is likely much higher7 – one informative way to compare total fatalities is using the proportional measure of the number of deaths per 100,000 people.

The United States currently has the 9th highest proportional mortality rate globally, with some 66 deaths
per 100,000 population. It is behind only Peru, Belgium, Bolivia, Brazil, Ecuador, Chile, Spain, and Mexico in this statistic.

. . .

By failing to implement the type of response strategies employed in the six comparison countries, our analysis shows that the United States may have incurred at least 130,000 avoidable deaths. . . . if the U.S. had followed Canadian policies and protocols, there might have only been 85,192 U.S. deaths – making more than 132,500 American deaths “avoidable.” If the U.S. response had mirrored that of Germany, the U.S. may have only had 38,457 deaths – leaving 179,260 avoidable deaths. And in the unique case of South Korea — which had one of the quickest and most robust intervention strategies – the U.S. might have seen just 2,799 deaths, leaving nearly 215,000 deaths avoidable.