{"id":4104,"date":"2020-12-08T02:40:41","date_gmt":"2020-12-08T02:40:41","guid":{"rendered":"https:\/\/techclot.com\/index.php\/2020\/12\/08\/mit-machine-learning-reveals-covid-19-vaccines-may-be-less-effective-for-racial-minorities\/"},"modified":"2020-12-08T02:40:41","modified_gmt":"2020-12-08T02:40:41","slug":"mit-machine-learning-reveals-covid-19-vaccines-may-be-less-effective-for-racial-minorities","status":"publish","type":"post","link":"https:\/\/techclot.com\/index.php\/2020\/12\/08\/mit-machine-learning-reveals-covid-19-vaccines-may-be-less-effective-for-racial-minorities\/","title":{"rendered":"MIT Machine Learning Reveals COVID-19 Vaccines May Be Less Effective for Racial Minorities"},"content":{"rendered":"

MIT Machine Learning Reveals COVID-19 Vaccines May Be Less Effective for Racial Minorities<\/a><\/p>\n

\n <\/div>\n

The last month has been filled with incredible news on COVID-19 vaccines following an astonishing, year-long global effort that has shattered records for vaccine development. Three companies \u2013 Pfizer, Moderna, and AstraZeneca \u2013 have all announced vaccines with shockingly high efficacy rates.<\/span><\/p>\n

Sadly \u2013 at least as it stands \u2013 some of those efficacy rates might not be evenly distributed among populations.<\/span><\/p>\n

In a new paper, researchers at MIT\u2019s Computer Science and Artificial Intelligence Lab (CSAIL)<\/a> combined machine learning and data analytics to show that race may be a strong determinant in the efficacy of vaccines like those touted by Pfizer and Moderna. <\/span><\/p>\n

The researchers started with antigen data from convalescent COVID-19 patients, measured by the Multiplexed Identification of T-cell Receptor Antigen (MIRA) specificity assay. They then combined that data with machine learning predictions, resulting in a combined model that predicts which peptides proved immunogenic for which patients. They then used that model to examine a form of COVID-19 vaccine similar to Pfizer and Moderna\u2019s vaccines.<\/span><\/p>\n

The results revealed a startling disparity. While white populations were projected to see just 0.04% vaccine inefficacy, black populations were projected to see 1.2% inefficacy (30 times higher than white populations) and Asian-American populations were projected to see 10% inefficacy (250 times higher).<\/span><\/p>\n

\u201cThere are obviously many other factors to consider, but our preliminary results suggest that, on average, people of Black or Asian ancestry could have a slightly increased risk of vaccine ineffectiveness,\u201d says MIT professor David Gifford, senior author of the paper. \u201cOur work shows that clinical trials need to carefully consider ancestry in their study designs to ensure that efficacy is measured across an appropriate population.\u201d<\/span><\/p>\n

While the model still anticipates that the vaccine will be broadly effective across all populations (90% efficacy, after all, is an impressive result for any vaccine), the inequity of the disparity led the researchers to hunt for a solution to this projected problem. <\/span><\/p>\n

<\/a><\/p>\n

Improvements in vaccine efficacy across populations by adding more peptides. Image courtesy of MIT.<\/p>\n<\/div>\n

Gifford worked with a couple of PhD students \u2013 Ge Liu and Brandon Carter \u2013 to develop a promising approach. The trio found that by just adding 5 to 20 additional peptides to each vaccine dose, the vaccine\u2019s projected efficacy rose to nearly 100 percent in all populations.<\/span><\/p>\n

The results, Gifford says, are not a reason to halt the vaccines that are already in the later stages of development, but do provide an important cautionary note for future vaccine development.<\/span><\/p>\n

\u201cWhile we should proceed with the current vaccines,\u201d he said, \u201cthere needs to be further research and planning if they are not as effective or durable as expected in all populations.\u201d<\/span><\/p>\n

For its part, Pfizer reports<\/a> that 42% of its trial participants had diverse racial backgrounds, including 10% black and 5% Asian participants. And, the company reported last month, \u201cefficacy was consistent across age, gender, race and ethnicity demographics.\u201d<\/p>\n

To read the paper, click <\/span>here<\/span><\/a>.<\/span><\/p>\n

<\/span> <\/p>\n

Published at Mon, 07 Dec 2020 22:52:30 +0000<\/p>\n

MIT Machine Learning Reveals COVID-19 Vaccines May Be Less Effective for Racial Minorities<\/a><\/p>\n

\n <\/div>\n

The last month has been filled with incredible news on COVID-19 vaccines following an astonishing, year-long global effort that has shattered records for vaccine development. Three companies \u2013 Pfizer, Moderna, and AstraZeneca \u2013 have all announced vaccines with shockingly high efficacy rates.<\/span><\/p>\n

Sadly \u2013 at least as it stands \u2013 some of those efficacy rates might not be evenly distributed among populations.<\/span><\/p>\n

In a new paper, researchers at MIT\u2019s Computer Science and Artificial Intelligence Lab (CSAIL)<\/a> combined machine learning and data analytics to show that race may be a strong determinant in the efficacy of vaccines like those touted by Pfizer and Moderna. <\/span><\/p>\n

The researchers started with antigen data from convalescent COVID-19 patients, measured by the Multiplexed Identification of T-cell Receptor Antigen (MIRA) specificity assay. They then combined that data with machine learning predictions, resulting in a combined model that predicts which peptides proved immunogenic for which patients. They then used that model to examine a form of COVID-19 vaccine similar to Pfizer and Moderna\u2019s vaccines.<\/span><\/p>\n

The results revealed a startling disparity. While white populations were projected to see just 0.04% vaccine inefficacy, black populations were projected to see 1.2% inefficacy (30 times higher than white populations) and Asian-American populations were projected to see 10% inefficacy (250 times higher).<\/span><\/p>\n

\u201cThere are obviously many other factors to consider, but our preliminary results suggest that, on average, people of Black or Asian ancestry could have a slightly increased risk of vaccine ineffectiveness,\u201d says MIT professor David Gifford, senior author of the paper. \u201cOur work shows that clinical trials need to carefully consider ancestry in their study designs to ensure that efficacy is measured across an appropriate population.\u201d<\/span><\/p>\n

While the model still anticipates that the vaccine will be broadly effective across all populations (90% efficacy, after all, is an impressive result for any vaccine), the inequity of the disparity led the researchers to hunt for a solution to this projected problem. <\/span><\/p>\n

<\/a><\/p>\n

Improvements in vaccine efficacy across populations by adding more peptides. Image courtesy of MIT.<\/p>\n<\/div>\n

Gifford worked with a couple of PhD students \u2013 Ge Liu and Brandon Carter \u2013 to develop a promising approach. The trio found that by just adding 5 to 20 additional peptides to each vaccine dose, the vaccine\u2019s projected efficacy rose to nearly 100 percent in all populations.<\/span><\/p>\n

The results, Gifford says, are not a reason to halt the vaccines that are already in the later stages of development, but do provide an important cautionary note for future vaccine development.<\/span><\/p>\n

\u201cWhile we should proceed with the current vaccines,\u201d he said, \u201cthere needs to be further research and planning if they are not as effective or durable as expected in all populations.\u201d<\/span><\/p>\n

For its part, Pfizer reports<\/a> that 42% of its trial participants had diverse racial backgrounds, including 10% black and 5% Asian participants. And, the company reported last month, \u201cefficacy was consistent across age, gender, race and ethnicity demographics.\u201d<\/p>\n

To read the paper, click <\/span>here<\/span><\/a>.<\/span><\/p>\n

<\/span> <\/p>\n

Published at Mon, 07 Dec 2020 22:52:30 +0000<\/p>\n","protected":false},"excerpt":{"rendered":"

MIT Machine Learning Reveals COVID-19 Vaccines May Be Less Effective for Racial Minorities The last…<\/p>\n","protected":false},"author":3,"featured_media":4102,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_jetpack_newsletter_access":"","_jetpack_dont_email_post_to_subs":false,"_jetpack_newsletter_tier_id":0,"_jetpack_memberships_contains_paywalled_content":false,"_jetpack_memberships_contains_paid_content":false,"footnotes":""},"categories":[3],"tags":[],"class_list":["post-4104","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-artificial-intelligence"],"jetpack_featured_media_url":"https:\/\/i0.wp.com\/techclot.com\/wp-content\/uploads\/2020\/12\/3RAfWb.jpg?fit=200%2C86&ssl=1","jetpack_sharing_enabled":true,"jetpack_shortlink":"https:\/\/wp.me\/p3orZX-14c","jetpack-related-posts":[],"_links":{"self":[{"href":"https:\/\/techclot.com\/index.php\/wp-json\/wp\/v2\/posts\/4104","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/techclot.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/techclot.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/techclot.com\/index.php\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/techclot.com\/index.php\/wp-json\/wp\/v2\/comments?post=4104"}],"version-history":[{"count":0,"href":"https:\/\/techclot.com\/index.php\/wp-json\/wp\/v2\/posts\/4104\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/techclot.com\/index.php\/wp-json\/wp\/v2\/media\/4102"}],"wp:attachment":[{"href":"https:\/\/techclot.com\/index.php\/wp-json\/wp\/v2\/media?parent=4104"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/techclot.com\/index.php\/wp-json\/wp\/v2\/categories?post=4104"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/techclot.com\/index.php\/wp-json\/wp\/v2\/tags?post=4104"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}