{"id":599141,"date":"2023-01-19T07:00:00","date_gmt":"2023-01-19T13:00:00","guid":{"rendered":"https:\/\/news.sellorbuyhomefast.com\/index.php\/2023\/01\/19\/how-scientists-trained-computers-to-forecast-covid-19-outbreaks-weeks-ahead\/"},"modified":"2023-01-19T07:00:00","modified_gmt":"2023-01-19T13:00:00","slug":"how-scientists-trained-computers-to-forecast-covid-19-outbreaks-weeks-ahead","status":"publish","type":"post","link":"https:\/\/newsycanuse.com\/index.php\/2023\/01\/19\/how-scientists-trained-computers-to-forecast-covid-19-outbreaks-weeks-ahead\/","title":{"rendered":"How scientists trained computers to forecast COVID-19 outbreaks weeks ahead"},"content":{"rendered":"
\n

Imagine a time when your virus-blocking face covering is like an umbrella. Most days, it stays in your closet or is stowed somewhere in your car. But when a COVID-19 outbreak is in the forecast, you can put it to use.<\/p>\n

Beyond that, an inclement viral forecast might induce you to choose an outdoor table when meeting a friend for coffee. If catching the coronavirus is likely to make you seriously ill, you might opt to work from home or attend church services online until the threat has passed.<\/p>\n

Such a future assumes that Americans will heed public health warnings about the pandemic virus \u2014 and that is a big if<\/i>. It also assumes the existence of a system that can reliably predict imminent outbreaks with few false alarms, and with enough timeliness and geographic precision that the public will trust its forecasts.<\/p>\n

A group of would-be forecasters says it\u2019s got the makings for such a system. Their proposal<\/a> for building a viral weather report was published this week in the journal Science Advances.<\/p>\n

\n
\n

Get our free Coronavirus Today newsletter<\/p>\n<\/p><\/div>\n

Sign up for the latest news, best stories and what they mean for you, plus answers to your questions.<\/p>\n

You may occasionally receive promotional content from the Los Angeles Times.<\/p>\n<\/ps-newsletter-module> <\/div>\n

Like the meteorological models that drive weather forecasts, the system to predict COVID-19 outbreaks emerges from a river of data fed by hundreds of streams of local and global information. They include time-stamped internet searches for symptoms such as chest tightness, loss of smell or exhaustion; geolocated tweets that include terms like \u201ccorona,\u201d \u201cpandemic,\u201d or \u201cpanic buying\u201d; aggregated location data from smartphones that reveal how much people are traveling; and a decline in online requests for directions, indicating that fewer folks are going out.<\/p>\n

The resulting volume of information is far too much for humans to manage, let alone interpret. But with the help of powerful computers and software trained to winnow, interpret and learn from the data, a map begins to emerge.<\/p>\n

If you check that map against historical data \u2014 in this case, two years of pandemic experience in 93 counties \u2014 and update it accordingly, you may have the makings of a forecasting system for disease outbreaks.<\/p>\n

That\u2019s exactly what the team led by a Northeastern University computer scientist<\/a> has done. In their bid to create an early-warning system for COVID-19 outbreaks, the study authors built a \u201cmachine learning\u201d system capable of chewing through millions of digital traces, incorporating new local developments, refining its focus on accurate signals of illness, and generating timely notices of impending local surges of COVID-19.<\/p>\n

Among the many internet searches it scoured, one proved to be a particularly good warning sign of an impending outbreak: \u201cHow long does COVID last?\u201d <\/p>\n

When tested against real-world data, the researchers\u2019 machine-learning method anticipated upticks of local viral spread as many as six weeks in advance. Its alarm bells would go off roughly at the point where each infected person was likely to spread the virus to at least one more person. <\/p>\n

Put to the test of anticipating 367 actual county-wide outbreaks, the program provided accurate early warnings of 337 \u2014 or 92% \u2014 of them. Of the remaining 30 outbreaks, it recognized 23 just as they would have become evident to human health officials.<\/p>\n

Once the Omicron variant began to circulate widely in the United States, the early-warning system was able to detect early evidence of 87% of outbreaks at the county level.<\/p>\n

A predictive system with these capabilities might prove useful for local, state and national public health officials who need to plan for COVID-19 outbreaks and warn vulnerable citizens that the coronavirus is threatening an imminent local resurgence.<\/p>\n

But \u201cwe\u2019re looking beyond\u201d COVID, said Mauricio Santillana<\/a>, who directs Northeastern\u2019s Machine Intelligence Group for the Betterment of Health and the Environment<\/a>.<\/p>\n

\u201cOur work is aimed at documenting what techniques and approaches might be useful not just for this, but for the next pandemic,\u201d he said. \u201cWe\u2019re gaining trust from public health officials so they won\u2019t need more convincing\u201d when another disease begins spreading across the country.<\/p>\n

That may not be an easy sell to state public health agencies and the Centers for Disease Control and Prevention, all of which struggled to keep up with pandemic data and incorporate new methods of tracking the virus\u2019 spread. The CDC\u2019s inability to adapt and communicate effectively during the pandemic led to some \u201cpretty dramatic, pretty public mistakes,\u201d Dr. Rochelle Walensky, the agency\u2019s director, has acknowledged<\/a>. Only \u201cchanging culture\u201d will prepare the federal agency for the next pandemic, she warned.<\/p>\n

The CDC\u2019s lackluster efforts to develop prediction tools have not paved the way to easy acceptance either. A 2022 assessment<\/a> of forecasting efforts used by the CDC concluded that most \u201chave failed to reliably predict rapid changes\u201d in COVID-19 cases and hospitalizations. The authors of that assessment warned that the systems developed to date \u201cshould not be relied upon for decisions about the possibility or timing of rapid changes in trends.\u201d <\/p>\n

Anasse Bari<\/a>, an expert in machine learning at New York University, called the new early-warning system \u201cvery promising,\u201d though \u201cstill experimental.\u201d<\/p>\n

\u201cThe machine learning methods presented in the paper are good, mature and very well studied,\u201d said Bari, who was not involved in the research. But he cautioned that in a once-in-a-lifetime emergency such as the pandemic, it would be risky to rely heavily on a new model to predict events. <\/p>\n

For starters, Bari noted, this coronavirus\u2019 first encounter with humankind has not produced the long historical record needed to fully test the model\u2019s accuracy. And the pandemic\u2019s three-year span has provided little time for researchers to recognize the \u201cnoise\u201d that comes when so much data are thrown into a pot. <\/p>\n

The CDC and state health departments have only begun to use epidemiological techniques such as phylodynamic genetic sequencing <\/a>and wastewater surveillance<\/a> to monitor the spread of the coronavirus. Using machine learning to forecast the location of coming viral surges may take another leap of imagination for these agencies, Santillana said.<\/p>\n

Indeed, accepting early-warning tools such as the one developed by Santillana\u2019s group could require some leaps of faith as well. As computer programs digest vast troves of data and begin to discern patterns that could be revealing, they often generate surprising \u201cfeatures\u201d \u2014 variables or search terms that help foretell a significant event, such as a viral surge.<\/p>\n

Even if these apparent signposts prove to accurately predict such an event, their relevance to a public-health emergency may not be immediately clear. A surprising signal may be the first sign of some new trend \u2014 a previously unseen symptom caused by a new variant, for instance. But it also might seem so random to public health officials that it casts doubt on a program\u2019s ability to predict an impending outbreak. <\/p>\n

Santillana, who also teaches at Harvard\u2019s School of Public Health, said that reviewers of his group\u2019s early work<\/a> responded with some skepticism to a few of the signals that emerged as warning signs of a coming outbreak. One of them \u2014 tweets referring to \u201cpanic buying\u201d \u2014 seemed like an errant signal from machines that had latched onto a random event and infused it with meaning, Santillana said.<\/p>\n

He defended the inclusion of the \u201cpanic buying\u201d signal as a revealing sign of an impending local outbreak. (After all, the initial days of the pandemic were marked by shortages of staple items<\/a> including rice and toilet paper<\/a>.) But he acknowledged that an early-warning system that is too \u201cblack-boxy\u201d could meet with resistance from the public health officials who need to trust its predictions.<\/p>\n

\u201cI think the fears of decision-makers is a legitimate concern,\u201d Santillana said. \u201cWhen we find a signal, it\u2019s got to be a reliable one.\u201d<\/p>\n<\/div>\n

Read More<\/a>
\n Melissa Healy<\/p>\n","protected":false},"excerpt":{"rendered":"

Imagine a time when your virus-blocking face covering is like an umbrella. Most days, it stays in your closet or is stowed somewhere in your car. But when a COVID-19 outbreak is in the forecast, you can put it to use. Beyond that, an inclement viral forecast might induce you to choose an outdoor table […]<\/p>\n","protected":false},"author":1,"featured_media":599142,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[534,3807,29751],"tags":[],"class_list":["post-599141","post","type-post","status-publish","format-standard","has-post-thumbnail","category-financial","category-scientists","category-trained"],"aioseo_notices":[],"_links":{"self":[{"href":"https:\/\/newsycanuse.com\/index.php\/wp-json\/wp\/v2\/posts\/599141","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/newsycanuse.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/newsycanuse.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/newsycanuse.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/newsycanuse.com\/index.php\/wp-json\/wp\/v2\/comments?post=599141"}],"version-history":[{"count":0,"href":"https:\/\/newsycanuse.com\/index.php\/wp-json\/wp\/v2\/posts\/599141\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/newsycanuse.com\/index.php\/wp-json\/wp\/v2\/media\/599142"}],"wp:attachment":[{"href":"https:\/\/newsycanuse.com\/index.php\/wp-json\/wp\/v2\/media?parent=599141"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/newsycanuse.com\/index.php\/wp-json\/wp\/v2\/categories?post=599141"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/newsycanuse.com\/index.php\/wp-json\/wp\/v2\/tags?post=599141"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}