The National Institutes of Health began the ambitious “All of Us” research project in 2018 with the goal of enrolling at least a million people in the world’s most diverse health database. Officials saw it as an antidote to medical research that traditionally has skewed heavily white, well-off and male.

Amid a wavering federal response that has allowed staggering levels of disease to sweep the country, the NIH program is a potential bright spot. About 350,000 people have consented to be part of the project, and more than 270,000 of them have shared their electronic health records and submitted blood or DNA samples. Of the latter, more than half are members of minority groups, and 81% are from traditionally underrepresented groups in terms of socioeconomic background, sexual identity or other categories, according to NIH.

NIH researchers are trying to get a better sense of how socioeconomic factors like income, family structure, diet and access to health care affect COVID infections and outcomes. The hope is to come up with insights that will better prepare the country, especially its Black and Hispanic communities, for the next pandemic.

The participants’ blood and DNA samples, and access to their electronic health records, offer researchers a trove of data about the pandemic’s effect on minorities. As part of the program, NIH has promised to return research results to all participants in plain language.

In a sense, “All of Us was designed for COVID-19,” said Hugo Campos, a program participant and ambassador who lives in Oakland, California. “If we can’t deliver value to participants now, we might as well just forget it.”

The NIH constructed All of Us with the expectation “that something like COVID-19 could come,” said Josh Denny, the project’s chief executive officer.

All of Us, started by NIH Director Francis Collins under President Barack Obama, aims to answer questions that will allow health care to be tailored to individuals based on their unique genetics, environmental exposures, socioeconomics and other determinants of health. Now, scientists are tapping into its database to ask how factors like isolation, mental health, insurance coverage and work status affect COVID-19 infections and outcomes.

The first NIH study employing the database, already underway, will conduct antibody testing on the blood of at least 10,000 program volunteers, starting with those who joined most recently and going back in time to determine when COVID-19 entered the U.S.

Beginning in early May, All of Us has distributed monthly surveys to participants, via email or text, inquiring about stress levels associated with social distancing, work habits and environments, mask-wearing and hand-washing. It’s also asking whether participants have had COVID-19 symptoms or have been tested, and includes queries about insurance coverage, drug use and mental health status.

Another study will provide researchers with de-identified data, including antibody test results and digital health information, to study whether symptoms vary among people who have tested positive for COVID-19 depending on their ethnicity, socioeconomic status and other categories.

shows that Black seniors have been four times as likely, and Latino seniors twice as likely, to be hospitalized with COVID-19 as white seniors. It’s understood that structural racism and socioeconomic differences contribute to this gap, but All of Us hopes to help pinpoint reasons and potential solutions.

The minorities who’ve experienced the poorest COVID-19 outcomes are well represented in the All of Us research cohort, said Denny. “We will really be able to layer a number of kinds of information on what’s happening to different populations and try to drive at some of that ‘Why?’ Are there genetic differences, differences in prior medical history, timing of testing?”

One of the precepts of All of Us is to share the results of its studies with participants as well as involve them in study designs. NIH hired leaders of churches, community organizations and other grassroots groups to spread the word on the program.

The largely Spanish-speaking clientele at San Ysidro Health, a federally qualified health center based in San Diego, has been eager to participate in the COVID-19 research, said Fatima Muñoz, the health system’s director of research and health promotion. Most of the All of Us participants she helped recruit prefer in-person interactions, but they are adapting to the pandemic’s online requirements, she said.

“There is historically a well-founded mistrust amongst some diverse populations and communities of color in biomedical research,” said Denny. “We can’t control history but can try to engage authentically going forward.”

The Black Lives Matter protest movement has pushed the program’s leaders to do more for its diverse participants, Denny said.

“It’s caused us to think more of how we can promote diversity in researchers, which had not been as much of a focus,” he said. “It has heightened some of the urgency and importance of what we’re doing. It’s a great call to action.”

The All of Us program is funded with $1.5 billion over 10 years through the 21st Century Cures Act of 2016. Denny said he expects results from the antibody testing, an $850,000 project that was contracted out to Quest Diagnostics, to be published this year, with insights from the surveys published after that.

The All of Us database provides unparalleled access to information on research groups whose level of harm by the virus would have been hard to predict, said Dr. Elizabeth Cohn, a professor of nursing at Hunter College in New York. Cohn is a community engagement lead for All of Us and chairs its publications committee.

“This is the demonstration of why we built this platform,” said Cohn. “This is a big moment for All of Us because this is what it was built to do.”

The pandemic has made it even clearer why it’s necessary to have a multicultural base for health research, said Dr. Randall Morgan, executive director of the W. Montague Cobb/National Medical Association Health Institute, an All of Us partner.

“When we get to 1 million, we hope to still have that level of representation,” he said.

This <a target="_blank" href="/public-health/nih-project-homes-in-on-covid-racial-disparities/">article</a&gt; first appeared on <a target="_blank" href="">KFF Health News</a> and is republished here under a <a target="_blank" href=" Commons Attribution-NonCommercial-NoDerivatives 4.0 International License</a>.<img src="/wp-content/uploads/sites/8/2023/04/kffhealthnews-icon.png?w=150&quot; style="width:1em;height:1em;margin-left:10px;">

This <a target="_blank" href="/public-health/coronavirus-tests-the-value-of-artificial-intelligence-in-medicine/">article</a&gt; first appeared on <a target="_blank" href="">KFF Health News</a> and is republished here under a <a target="_blank" href=" Commons Attribution-NonCommercial-NoDerivatives 4.0 International License</a>.<img src="/wp-content/uploads/sites/8/2023/04/kffhealthnews-icon.png?w=150&quot; style="width:1em;height:1em;margin-left:10px;">

The National Institutes of Health began the ambitious “All of Us” research project in 2018 with the goal of enrolling at least a million people in the world’s most diverse health database. Officials saw it as an antidote to medical research that traditionally has skewed heavily white, well-off and male.

Amid a wavering federal response that has allowed staggering levels of disease to sweep the country, the NIH program is a potential bright spot. About 350,000 people have consented to be part of the project, and more than 270,000 of them have shared their electronic health records and submitted blood or DNA samples. Of the latter, more than half are members of minority groups, and 81% are from traditionally underrepresented groups in terms of socioeconomic background, sexual identity or other categories, according to NIH.

NIH researchers are trying to get a better sense of how socioeconomic factors like income, family structure, diet and access to health care affect COVID infections and outcomes. The hope is to come up with insights that will better prepare the country, especially its Black and Hispanic communities, for the next pandemic.

The participants’ blood and DNA samples, and access to their electronic health records, offer researchers a trove of data about the pandemic’s effect on minorities. As part of the program, NIH has promised to return research results to all participants in plain language.

In a sense, “All of Us was designed for COVID-19,” said Hugo Campos, a program participant and ambassador who lives in Oakland, California. “If we can’t deliver value to participants now, we might as well just forget it.”

The NIH constructed All of Us with the expectation “that something like COVID-19 could come,” said Josh Denny, the project’s chief executive officer.

All of Us, started by NIH Director Francis Collins under President Barack Obama, aims to answer questions that will allow health care to be tailored to individuals based on their unique genetics, environmental exposures, socioeconomics and other determinants of health. Now, scientists are tapping into its database to ask how factors like isolation, mental health, insurance coverage and work status affect COVID-19 infections and outcomes.

The first NIH study employing the database, already underway, will conduct antibody testing on the blood of at least 10,000 program volunteers, starting with those who joined most recently and going back in time to determine when COVID-19 entered the U.S.

Beginning in early May, All of Us has distributed monthly surveys to participants, via email or text, inquiring about stress levels associated with social distancing, work habits and environments, mask-wearing and hand-washing. It’s also asking whether participants have had COVID-19 symptoms or have been tested, and includes queries about insurance coverage, drug use and mental health status.

Another study will provide researchers with de-identified data, including antibody test results and digital health information, to study whether symptoms vary among people who have tested positive for COVID-19 depending on their ethnicity, socioeconomic status and other categories.

shows that Black seniors have been four times as likely, and Latino seniors twice as likely, to be hospitalized with COVID-19 as white seniors. It’s understood that structural racism and socioeconomic differences contribute to this gap, but All of Us hopes to help pinpoint reasons and potential solutions.

The minorities who’ve experienced the poorest COVID-19 outcomes are well represented in the All of Us research cohort, said Denny. “We will really be able to layer a number of kinds of information on what’s happening to different populations and try to drive at some of that ‘Why?’ Are there genetic differences, differences in prior medical history, timing of testing?”

One of the precepts of All of Us is to share the results of its studies with participants as well as involve them in study designs. NIH hired leaders of churches, community organizations and other grassroots groups to spread the word on the program.

The largely Spanish-speaking clientele at San Ysidro Health, a federally qualified health center based in San Diego, has been eager to participate in the COVID-19 research, said Fatima Muñoz, the health system’s director of research and health promotion. Most of the All of Us participants she helped recruit prefer in-person interactions, but they are adapting to the pandemic’s online requirements, she said.

“There is historically a well-founded mistrust amongst some diverse populations and communities of color in biomedical research,” said Denny. “We can’t control history but can try to engage authentically going forward.”

The Black Lives Matter protest movement has pushed the program’s leaders to do more for its diverse participants, Denny said.

“It’s caused us to think more of how we can promote diversity in researchers, which had not been as much of a focus,” he said. “It has heightened some of the urgency and importance of what we’re doing. It’s a great call to action.”

The All of Us program is funded with $1.5 billion over 10 years through the 21st Century Cures Act of 2016. Denny said he expects results from the antibody testing, an $850,000 project that was contracted out to Quest Diagnostics, to be published this year, with insights from the surveys published after that.

The All of Us database provides unparalleled access to information on research groups whose level of harm by the virus would have been hard to predict, said Dr. Elizabeth Cohn, a professor of nursing at Hunter College in New York. Cohn is a community engagement lead for All of Us and chairs its publications committee.

“This is the demonstration of why we built this platform,” said Cohn. “This is a big moment for All of Us because this is what it was built to do.”

The pandemic has made it even clearer why it’s necessary to have a multicultural base for health research, said Dr. Randall Morgan, executive director of the W. Montague Cobb/National Medical Association Health Institute, an All of Us partner.

“When we get to 1 million, we hope to still have that level of representation,” he said.

This <a target="_blank" href="/public-health/nih-project-homes-in-on-covid-racial-disparities/">article</a&gt; first appeared on <a target="_blank" href="">KFF Health News</a> and is republished here under a <a target="_blank" href=" Commons Attribution-NonCommercial-NoDerivatives 4.0 International License</a>.<img src="/wp-content/uploads/sites/8/2023/04/kffhealthnews-icon.png?w=150&quot; style="width:1em;height:1em;margin-left:10px;">

The researchers quickly deployed the application, which dots X-ray images with spots of color where there may be lung damage or other signs of pneumonia. It has now been applied to more than 6,000 chest X-rays, and it’s providing some value in diagnosis, said Hsiao, the director of UCSD’s augmented imaging and artificial intelligence data analytics laboratory.

His team is one of several around the country that has pushed AI programs developed in a calmer time into the COVID-19 crisis to perform tasks like deciding which patients face the greatest risk of complications and which can be safely channeled into lower-intensity care.

The machine-learning programs scroll through millions of pieces of data to detect patterns that may be hard for clinicians to discern. Yet few of the algorithms have been rigorously tested against standard procedures. So while they often appear helpful, rolling out the programs in the midst of a pandemic could be confusing to doctors or even dangerous for patients, some AI experts warn.

“AI is being used for things that are questionable right now,” said Dr. Eric Topol, director of the Scripps Research Translational Institute and author of several books on health IT.

Topol singled out a system created by , a major vendor of electronic health records software, that predicts which coronavirus patients may become critically ill. Using the tool before it has been validated is “pandemic exceptionalism,” he said.

Epic said the company’s model had been validated with data from more 16,000 hospitalized COVID-19 patients in 21 health care organizations. No research on the tool has been published, but, in any case, it was “developed to help clinicians make treatment decisions and is not a substitute for their judgment,” said James Hickman, a software developer on Epic’s cognitive computing team.

Others see the COVID-19 crisis as an opportunity to learn about the value of AI tools.

“My intuition is it’s a little bit of the good, bad and ugly,” said Eric Perakslis, a data science fellow at Duke University and former chief information officer at the Food and Drug Administration. “Research in this setting is important.”

Nearly $2 billion poured into companies touting advancements in health care AI in 2019. Investments in the first quarter of 2020 totaled $635 million, up from $155 million in the first quarter of 2019, according to digital health technology funder .

At least three health care AI technology companies have made funding deals specific to the COVID-19 crisis, including , an AI-powered lung-imaging analysis company, according to Rock Health.

Overall, AI’s implementation in everyday clinical care is less common than hype over the technology would suggest. Yet the coronavirus crisis has inspired some hospital systems to accelerate promising applications.

UCSD sped up its AI imaging project, rolling it out in only two weeks.

Hsiao’s project, with research funding from Amazon Web Services, the University of California and the National Science Foundation, runs every chest X-ray taken at its hospital through an AI algorithm. While no data on the implementation has been published yet, doctors report that the tool influences their clinical decision-making about a third of the time, said Dr. Christopher Longhurst, UC San Diego Health’s chief information officer.

“The results to date are very encouraging, and we’re not seeing any unintended consequences,” he said. “Anecdotally, we’re feeling like it’s helpful, not hurtful.”

AI has advanced further in imaging than other areas of clinical medicine because radiological images have tons of data for algorithms to process, and more data makes the programs more effective, said Longhurst.

But while AI specialists have tried to get AI to do things like predict sepsis and acute respiratory distress — researchers at Johns Hopkins University  to use it to predict heart damage in COVID-19 patients — it has been easier to plug it into less risky areas such as hospital logistics.

In New York City, two major hospital systems are using AI-enabled algorithms to help them decide when and how patients should move into another phase of care or be sent home.

´¡³ÙÌý, an artificial intelligence algorithm pinpoints which patients might be ready to be discharged from the hospital within 72 hours, said Robbie Freeman, vice president of clinical innovation at Mount Sinai.

Freeman described the AI’s suggestion as a “conversation starter,” meant to help assist clinicians working on patient cases decide what to do. AI isn’t making the decisions.

 has developed a similar AI model. It predicts whether a COVID-19 patient entering the hospital will suffer adverse events within the next four days, said , who leads NYU Langone’s predictive analytics team.

The model will be run in a four- to six-week trial with patients randomized into two groups: one whose doctors will receive the alerts, and another whose doctors will not. The algorithm should help doctors generate a list of things that may predict whether patients are at risk for complications after they’re admitted to the hospital, Aphinyanaphongs said.

Some health systems are leery of rolling out a technology that requires clinical validation in the middle of a pandemic. Others say they didn’t need AI to deal with the coronavirus.

 is not using AI to manage hospitalized patients with COVID-19, said , the center’s medical informatics director for AI clinical integration. The San Francisco Bay Area  who would have provided the mass of data needed to make sure AI works on a population, he said.

Outside the hospital, AI-enabled risk factor modeling is being used to help health systems track patients who aren’t infected with the coronavirus but might be susceptible to complications if they contract COVID-19.

At Scripps Health in San Diego, clinicians are stratifying patients to assess their risk of getting COVID-19 and experiencing severe symptoms using a risk-scoring model that considers factors like age, chronic conditions and recent hospital visits. When a patient scores 7 or higher, a triage nurse reaches out with information about the coronavirus and may schedule an appointment.

Though emergencies provide unique opportunities to try out advanced tools, it’s essential for health systems to ensure doctors are comfortable with them, and to use the tools cautiously, with extensive testing and validation, Topol said.

“When people are in the heat of battle and overstretched, it would be great to have an algorithm to support them,” he said. “We just have to make sure the algorithm and the AI tool isn’t misleading, because lives are at stake here.”

This <a target="_blank" href="/public-health/coronavirus-tests-the-value-of-artificial-intelligence-in-medicine/">article</a&gt; first appeared on <a target="_blank" href="">KFF Health News</a> and is republished here under a <a target="_blank" href=" Commons Attribution-NonCommercial-NoDerivatives 4.0 International License</a>.<img src="/wp-content/uploads/sites/8/2023/04/kffhealthnews-icon.png?w=150&quot; style="width:1em;height:1em;margin-left:10px;">