App That Listens to Coughing Developed to Tell if People Have COVID-19

If this app works effectively, it will be very important in allowing people to group up more freely again.

As millions of people worldwide battle the symptoms of COVID-19, a group of “silent patients” may not even know they’re sick and spreading the virus. Asymptomatic people, by definition, have no physical symptoms of the illnesses they carry.

Researchers at the Massachusetts Institute of Technology (MIT) however, say they may be showing symptoms after all — in the sound of their cough. Their study has created an artificial intelligence program that can identify if someone has coronavirus by the way their coughing sounds. Researchers programmed their AI model with thousands of different recorded coughs from both healthy and sick volunteers. When they fed in recordings of new patients, the system accurately detected 98.5 percent of coughs coming from people with a confirmed case of COVID-19. AI also successfully picked out 100 percent of asymptomatic cases from volunteers who reported not having any symptoms but tested positive for the virus.

The team is now working on turning their model into a user-friendly app. If approved by the Food and Drug Administration, the app would give people a non-invasive and quick way to screen themselves during the pandemic daily.

“The effective implementation of this group diagnostic tool could diminish the spread of the pandemic if everyone uses it before going to a classroom, a factory, or a restaurant,” says co-author Brian Subirana in a university release.

The MIT team notes researchers have been working on audio-based medical screenings since before the coronavirus emergency began. Their group in particular originally created this AI model to screen for Alzheimer’s disease.

Although the degenerative neurological condition is mostly associated with memory loss, it also affects the muscles and vocal cords. With this knowledge, researchers trained a general machine-learning algorithm called ResNet50 to detect changes in vocal cord strength. Subirana taught the neural network using an audiobook collection with over 1,000 hours of speech files. The AI model could eventually tell the difference between similar worlds like “them” and “the” or “then.”

The system can also read the emotions of the speaker based on the tone of their voice. The team says this is a key in Alzheimer’s detection because patients tend to display more frustration when they try to get words out. The program learned to assess these moods and put them into categories including neutral, calm, happy, and sad.

Finally, the team turned to coughing. Using recordings of patients coughing, the AI model could analyze the lung and respiratory performance of the cougher. An algorithm to detect muscular degradation was also added to help AI distinguish strong coughs from weaker ones.

With all of this data, study authors discovered that the technology could effectively screen for Alzheimer’s based on a patient’s vocal cord strength, sentiment, lung performance, and muscular degradation.

Once the pandemic began, the team at MIT changed gears and started looking at their model to see if it could detect COVID. Researchers say there is growing evidence coronavirus patients also suffer from neurological symptoms and temporary muscular impairment.

“The sounds of talking and coughing are both influenced by the vocal cords and surrounding organs. This means that when you talk, part of your talking is like coughing, and vice versa. It also means that things we easily derive from fluent speech, AI can pick up simply from coughs, including things like the person’s gender, mother tongue, or even emotional state. There’s in fact sentiment embedded in how you cough,” Subirana explains. “So we thought, why don’t we try these Alzheimer’s biomarkers [to see if they’re relevant] for COVID.”

The team created a website to collect audio samples from volunteers, including many with coronavirus. From nearly 200,000 forced-cough audio samples, the group was able to find 2,500 recordings that came from confirmed COVID-19 patients. Many of these patients were also asymptomatic. After adding more random samples to act as a control, the team chose 4,000 coughing samples to train their AI model to screen for the virus.

Along with amazing accuracy in detecting coronavirus patients, researchers say the tests reveal “a striking similarity between Alzheimer’s and COVID discrimination.” They add that the same four biomarkers for detecting Alzheimer’s effectively screen out the virus as well.

“We think this shows that the way you produce sound, changes when you have Covid, even if you’re asymptomatic,” the research scientist in MIT’s Auto-ID Laboratory adds.

Subirana and his team stress that their AI system is not meant to diagnose what illness you may have; whether it be the flu, asthma, or COVID-19. The tool, instead, works by screening out who is healthy from who is asymptomatic but carrying an illness.

The MIT team is now partnering with several hospitals to collect more coughing samples to refine the system’s accuracy. Their hope is to introduce a free pre-screening app to the public which can cut down on clinical testing delays.

“Pandemics could be a thing of the past if pre-screening tools are always on in the background and constantly improved,” the study authors contend.

The study appears in the IEEE Journal of Engineering in Medicine and Biology.

Will Trump Win Again?

American president Donald Trump will not be victorious in the popular vote — that is certain. He will probably lose the popular vote by an even higher margin than what Hillary Clinton beat him with in 2016. That said, the Electoral College is what determines presidential outcomes, and there are factors that may allow Trump to win the Electoral College again.

A poll credited with predicting Trump’s Electoral College win in 2016 — the IBD/TIPP Poll — shows Trump with a 0.7 point lead among Hispanics and a 3 point lead in the Midwest. The Midwest is particularly important to win due to having swing states such as Michigan, Ohio, Wisconsin, and Pennsylvania. Most polls show that Trump has maintained a multiple percentage point lead in the state of Ohio, a state that seems to have largely been neglected by the national media outlets based in coastal areas such as California and New York. (The people working for those coastal media outlets have been increasingly seen as out of touch with the realities of wage stagnation, drug epidemics, and deindustrialization that has taken place place in much of America.) Whoever wins Ohio has won the presidency every year since 1964 — a record of over half a century that makes it stand out even among the other swing states.

Much of my own family supports Trump, something that continues to disturb and disappoint me in 2020. That being said, something people don’t always realize is that much of the population is struggling to an absurd degree in what has long been world history’s wealthiest nation. A CNBC article from before the pandemic found that 78 percent of people were living paycheck to paycheck, a number that can only have grown worse with what is essentially now an economic depression during the pandemic. Many people are therefore too stressed and too busy to consistently study politics effectively, and the American formal education overall does a terrible job at giving people a decent political education. It doesn’t help that there is so much disinformation now that it takes a fair amount of intelligence to see through it, and too many people in America have suffered cognitive problems for reasons such as growing up in extreme poverty, being subjected to abuse generated in their family members by America’s flawed society, and even — as seen in Flint, Michigan — drinking lead in their water supply. The Flynn Effect is a phenomenon recounting how average IQ scores have gone up as factors such as nutrition have improved. It’s been apparent for all of us since our days in school that high general intelligence is somewhat rare, but many people are not as smart as they would otherwise be growing up in healthier environments. Since democracy is about making choices based on information, democracy suffers when the general capacity of the population to make intelligent decisions is reduced. America would look different if the average IQ was 10 points higher than what it is today.

One of the worst things that Trump has said is encouraging his supporters to vote twice — once by mail and once at the polls. This is encouraging his supporters to commit voter fraud, a felony punishable by up to 5 years in prison. With so many people in my family that support Trump, I have spent a considerable amount of time thinking about and reading the more scientific reasoning about why they support him. One of the reasons is that Trump speaks with short sentences that are easier to understand, at what was once evaluated as a speaking level lower than many other politicians. In association with that, Trump is an accomplished con man, seen through the history of his fraudulent for-profit college and his casino bankruptcies, and he is good at making his supporters feel good. He’s an incredibly charismatic politician — the people who deny this are delusional to what his supporters and many others feel. In getting a bit more anecdotal here, even people who know me and don’t particularly like me (i.e., some people in my family) admit that I am perceptive and by nature feel certain things many others don’t. This doesn’t mean I am a sensitive snowflake — I am not and I hate the amount of our discourse taken up by identity politics rather than focus on people’s material interest. In any case, I always seem to feel when someone is charismatic, no matter how vile that person is. Trump is charismatic. The other main reasons are that Trump is an authoritarian, something much of the population identifies with, and — my biggest takeaway from seeing so much of my family support Trump — is that support of Trump is something for people to come together on. American society has become broken, divisive, run-down, and incredibly politically polarized for much of the population, and support of Trump presents an opportunity for what is arguably one of the few ways for Trump supporters to have meaningful positive interactions with each other. Politics is not like talking about the weather or other small talk subjects — it presents a much greater opportunity than those subjects to have more valuable and fulfilling conversations, even if the people discussing the politics are wrong about what issues to support to benefit the majority of the population. The desire to have these fulfilling social conversations, I posit, is an integral part of human social contact, and one that was increasingly fading in the device-driven world before the pandemic and the term social distancing became a widely used term.

In addressing Trump’s perceived strength, the idea that Trump had a significant positive impact on the economy is a joke. The biggest positive factor on the economy in the last decade was probably the appointment of Janet Yellen and her low interest rate policies at the Federal Reserve, and that allowed the unemployment rate to drop low and it therefore also allowed some of the only minor wage growth for low-wage workers in the last 50 years. To his credit, Trump appointed Jerome Powell, who largely continued the policies of Janet Yellen by not raising interest rates and thus allowing the unemployment rate to remain low before the pandemic hit. Trump also refused to go along with the terrible Trans-Pacific Partnership trade agreement, and the tax cuts mainly for the wealthy and corporations that he pressed for did have a slight boost in demand for the economy. If Trump had done well on other major economic things I would give him credit for them, and it’s clear from these points that he did some decent things for the economy while in office. The decent things he did for the economy are heavily outweighed by the flaws of his governing, such as his illogical trade war and his failure on managing the pandemic. The result of his impact on the economy is a net negative effect, one that may prove to be far more net negative later on as the impacts of those policies are felt for years, but many left-wingers don’t admit the very few things he did that were decent. I consider Trump the worst president by far in modern history, but I consider it important to tell the truth about matters such as these and give credit where it’s due. Trump is stunningly ignorant of most important political issues, and he doesn’t talk about it anymore like he did in 2016, but he does seem to understand that trade deficits in America are bad, and that’s part of why in 2016 he won over so many Rust Belt workers who have been screwed by trade policy. The trade deficit increased under Trump however, despite his having the ability to decrease it through policy, and this was before the pandemic. The reason that trade deficits for the U.S. are bad is that it decreases demand in the economy, and we generally have needed more demand to help workers in the last 50 years. On another note, I read an article by a former Republican governor endorsing Joe Biden, and I read it looking for positive things he had to say about Trump. Essentially the most he said that was good about Trump are some regulatory changes. That was all. In conducting surveys of Americans, I would venture a guess that few are fond of the deregulations that allow more coal debris and pollutants to be deposited in streams near residential water supplies and the deregulation that allows imported meat to claim to be made in America. It is rather incredible that so many continue to support Trump despite him not enacting policies that benefit their material interest. The vast majority of the Trump tax cuts go to the richest people in America, not middle-income or low-wage workers. Trump blocked the Post Office from sending out masks to hundreds of millions of Americans because he “didn’t want to create a panic.” There is audio of Trump with Bob Woodward where Trump back in February acknowledges that COVID-19 is far more deadly than the flu, but then he lies to the public in trying to downplay its severity and holds mass gatherings of people close together where many of them don’t wear masks. Trump’s campaign recently had an event in Nebraska where people caught hypothermia and were left out in the cold due to a lack of transportation provided by the campaign. I scanned social media when this happened and I didn’t find any defense of this from the Trump supporters. Trump is a con man that has successfully deceived millions of people, and that includes many things such as his lies about the pandemic, his lies about stopping the wars overseas and his lies about bringing many manufacturing jobs back. If American society was a more rational place, the CNBC program American Greed that focuses on corporate crime would have had an episode on Trump where they focus on his immoral business dealings and damage to much of the population. There’s a long list of how Trump has negatively impacted the public, but I chose to focus more on the economic conditions since that’s more concrete than focus on controversial issues such as abortion and religion.

All of this said, even as a president with an awful track record, Trump may still win the Electoral College. It looks unlikely by polling and the history of presidents losing when they in power during awful economic conditions, but there are variables present in this pandemic election year that normally haven’t been present in past elections. One is that many more Democrats than Republicans will vote by mail, and a considerable percentage of these mail-in ballots won’t be counted. This isn’t a conspiratorial claim — it’s the state of the voter suppression in American politics. In the 2016 election, Greg Palast — author of the book titled “How Trump Won 2020” — found that 141,000 ballots were thrown out after a challenge due to their signatures. He found that there weren’t any voters arrested for forgery because of this. Additionally, Palast said recently that “Once a year, secretaries of state can literally wipe off the voter rolls those voters they think shouldn’t vote. And not surprisingly, these hacks tend to remove people of color where they can, where Republicans control the state. So for example, in Georgia, as you just heard, the Secretary of State [Raffensperger] removed 198,000 voters illegally on false information. Almost all of them [were] black voters, young voters, including Martin Luther King’s 92-year-old cousin.” Palast also said that “In 2016, 5.8 million ballots were cast and never counted. By the way, that’s an official number from the EAC [Election Assistance Commission], from our federal agency; 5.8 million votes cast not counted.” Most disturbingly, Palast mentioned the study finding that “According to MIT [Massachusetts Institute of Technology], 22%, [i.e.,] one in 5 million mail-in ballots, is never counted.”

If 22 percent of mail-in ballots aren’t counted in 2020, that combined with the voter suppression of other people likely to vote for Joe Biden may hand Trump another Electoral College victory. Again, there is a far higher percentage of Republicans going to the polls to vote for Trump than there is Democrats going to the polls to vote for Biden, and this may culminate in not only Trump eventually winning the Electoral College yet again but it may make Trump have an overall lead today on election day before more mail-in ballots are counted. This may then devolve into a scenario where the contested election is taken to the 6-3 conservative majority on the Supreme Court, where the results of the election that are not favorable to Trump may be thrown out.

America will suffer further harm from another four years of Trump. I dislike Biden and consider him to be a politician with a long record of terrible policies, but after years of Trump, it’s apparent that another four years of Trump will continue to have the sort of vast consequences and immense damage seen during the pandemic. In any case, with either person winning the presidency, I would encourage people to try to make the most of what they have even if it’s not that good. A year from now may be an even worse time than today, and now is already bad for so many of us. That’s just the realistic view of things. Exercise and a healthy diet (including plenty of vitamin D to protect against COVID-19 problems) will help us stay strong, and staying strong will remain important when life is tough.

WHO Warns Society is on a Path Towards a Global Pandemic

If there is a global pandemic, hindsight will really be 20/20 on what could have been done to prevent or mitigate it. Cutting the CDC’s budget is particularly horrible — that’s the exact opposite of what should be done.

We have a problem. A serious one. At any moment, a life-threatening global pandemic could spring up and wipe out a significant amount of human life on this planet.

The death toll would be catastrophic; one disease could see as many as 100 million dead.

It sounds like a horrifying dream. It sounds like something that can’t possibly be true. But it is. The information comes from Tedros Adhanom, Director General of the World Health Organization.

He spoke today at the World Government Summit in Dubai, and according to his assessment, things are not looking good.

“This is not some future nightmare scenario,” said Tedros (as he prefers to be called by Ethiopian tradition).

“This is what happened exactly 100 years ago during the Spanish flu epidemic.” A hush fell across the audience as he noted that we could see such devastation again, perhaps as soon as today.

Tedros was equal parts emphatic and grave as he spoke: “A devastating epidemic could start in any country at any time and kill millions of people because we are still not prepared. The world remains vulnerable.”

What is the cause of this great vulnerability? Is it our inability to stave off Ebola? Rising incidents of rabies in animal populations? An increased number of HIV and AIDS cases?

No. According to Tedros, the threat of a global pandemic comes from our apathy, from our staunch refusal to act to save ourselves – a refusal that finds its heart in our indifference and our greed.

“The absence of universal health coverage is the greatest threat to global health,” Tedros proclaimed.

As the audience shifted in their seats uncomfortably, he noted that, despite the fact that universal health coverage is “within reach” for almost every nation in the world, 3.5 billion people still lack access to essential health services.

Almost 100 million are pushed into extreme poverty because of the cost of paying for care out of their own pockets.

The result? People don’t go to the doctor. They don’t seek treatment. They get sicker. They die. And thus, as Tedros explained, “the earliest signals of an outbreak are missed.”

[…]

And in the United States, which is presently enduring a flu season of record-breaking severity, the Centers for Disease Control and Prevention (CDC) recently announced they would be cutting their epidemic prevention programs back by 80 percent.

Programs for preventing infectious diseases, such as Ebola, are being scaled back in 39 of the 49 countries they’ve been employed in, according to The Washington Post.

The reason? Quite simply, governments are pulling money from these programs, and it’s not clear whether any more will ever be allocated – at least, not in the US during the current administration.

It might seem a bit obtuse. But, as Tedros pointed out, too often we “see health as a cost to be contained and not an investment to be nurtured.”

Aside from the obvious – avoiding a global pandemic that ravages humanity – healthy societies are advantageous for reasons that are more economic than epidemiological.

“The benefits of universal health coverage go far beyond health,” Tedros said. “Strong health systems are essential to strong economies.”

We know that the quality of pre- and post-natal care a person receives when a child is born has a direct impact on how soon they’re able to return to work (if they choose to).

If we want our children to grow up healthy enough to become functioning, contributing members of society, then the quality of care they receive from birth throughout childhood can’t be underestimated.