Connect with us

Health

Every day use of AI for health diagnoses still years away

Published

on

Back before coronavirus took over the headlines, every week seemed to bring another report about artificial intelligence besting human doctors at everything from diagnosing skin cancer to spotting pneumonia on chest X-rays.

But these artificial intelligence, or AI, tools — computer programs that get better at performing a task by being “trained” on the right kind of data — are years away from being used to help diagnose real-life patients, according to the doctors helping to develop and test them.

“We still have a lot of unknowns in terms of generalizing and validation of these systems before we can start using them as standard of care,” said Dr. Matthew Hanna, a pathologist at Memorial Sloan Kettering Cancer Center in New York City.

Generalizing means building an AI tool that can be used in multiple hospitals, and validation involves testing and adjusting an AI tool to ensure it’s accurate.

“These are the types of studies we need to do to make sure these models are performing properly and not potentially harming patients,” Hanna explained.

Meanwhile, humans are in no rush to swap their doctor for an AI diagnosis.

In a 2019 New York University-Harvard study, business school students said they’d be OK with getting poorer quality health care as long as it was provided by a human instead of AI.

People resisted AI, the study authors found, because they felt it would not take their “idiosyncratic characteristics and circumstances” into account.

Research vs. the real world

Whether people like it or not, AI will increasingly play a supporting role in medicine, helping doctors work more efficiently and consistently.

The U.S. Food and Drug Administration has approved dozens of AI platforms for applications including monitoring patients remotely, identifying brain bleeding on a CT scan, recognizing abnormal heart rhythms based on Apple Watch recordings, and even diagnosing autism.

All of these available tools are supervised, meaning they don’t go off and learn things on their own. Think of them as trusted assistants working behind the scenes, offering suggestions but not making decisions.

AI tools are being developed to speed up cancer diagnosis and treatment, for example, by helping radiologists with jobs that they now must do by hand, such as “contouring,” or manually drawing the boundary line between a tumor and normal tissue on multiple images.

“What we really want to do is, in a structured way, teach an algorithm to find lung nodules, characterize them according to the standard classification schema, and then help radiologists put them into a useful report,” explained Dr. Bibb Allen Jr., chief medical officer of the American College of Radiology’s Data Science Institute.

“AI is all about information and bringing information as appropriate to the physicians that are taking care of the patient,” Allen added. “We have an explosion of data around our patients, but it’s hard to access.”

‘Greater efficiencies’

Radiologists made the switch from reading X-ray films on light boxes to interpreting images on computer screens decades ago. But digitalization is not as far along for pathologists, many of whom are still peering through microscopes at thin slices of biopsied tissue fixed on glass slides.

Even when reviewing slides on a computer, “it can be time-consuming for pathologists to manually review images of all lymph node specimens to identify potential metastatic disease,” Hanna noted. “If an AI model is trained to detect the presence or absence of metastatic breast cancer, this automated screening could help triage cases for pathologists — bringing specific cases to their attention.”

AI won’t replace pathologists, who report multiple other diagnostic findings for each specimen they review, Hanna added. “But AI could create greater efficiencies to potentially shave off hours, or even days, so that pathology reports may be finalized sooner for patients,” he said.

“We have a very large shortage predicted in pathologists in the U.S., and we also have a vastly increased workload, so I think these machine learning models will be a necessity in the future,” Hanna explained.

Allen pointed out that “it’s not going to happen overnight. Every year, we’re just going to put more and more AI tools into the way we care for patients. It’s going to do things that are just going to, over time, improve the way we take care of patients. It’s not going to be, ‘Oh, we flipped a switch and we’ve got AI,'” he added.

“Patients need to understand that their physician will be there helping them and they will be using AI to help their patients, but not as a tool to give to patients to replace their physicians,” Allen said.

Copyright 2020 HealthDay. All rights reserved.



Source link

Health

Study: People in U.S. exercising more, but less intensely, during pandemic

Published

on

In the face of pandemic-mandated gym closings and significant limits on movement outside the home, a new survey suggests that Americans are spending more time exercising while dialing back the intensity of their workouts.

The survey of nearly 900 Americans across the country, conducted between May and June, used as its benchmark World Health Organization recommendations that all adults between 18 and 64 get a minimum of 150 minutes of moderate-intensity exercise a week.

“The COVID-19 restrictions imposed early in the pandemic created a unique, unprecedented environment, including restricted access to resources and, in some cases, increased unstructured time,” said study author Mary Stenson.

“We were curious how these changes might impact physical activity patterns in the U.S. during the shutdowns, but also if these shifts would remain in the long term,” said Stenson, an associate professor of exercise science and sport studies at College of Saint Benedict/Saint John’s University in St. Joseph, Minn.

In Stenson’s study, more than 85% of those polled were women and nearly 90% were white, with an average age of almost 39.

The findings: By June, just over 60% of those surveyed said they were meeting the WHO threshold, representing a nearly 8% jump from pre-pandemic routines.

Investigators also found a more than 11% jump in the number of people who were actually exceeding that threshold.

The number of days per week spent exercising also went up notably, from 3.75 days to more than 4.25 days.

Time spent per exercise session, however, stayed more or less stable, at just under an hour. And exercise intensity decreased “significantly,” the researchers found, with respondents attributing the drop to an inability to access gym equipment and classes and a shift to more outdoor walking.

“The increased activity and lower intensity were in line with what we expected,” said Stenson, who said the findings likely reflect the loss of performance “accountability” that comes with the cancellation of group exercise, organized sports and trainer sessions.

But Stenson said she was surprised by an additional observation that nearly three-quarters of those surveyed said they were likely or very likely to stick with their pandemic exercise habits post-pandemic.

And nearly 94% of those who had increased their activity levels since March said they planned to continue with their new routines over the coming year.

“We hope to find this is true next spring when we follow up,” said Stenson.

The plan is to re-survey the same people next June. In the meantime, she said her team is “hopeful that some individuals realized how much they can be active with limited resources, and that they will maintain their increased activity in the coming months.”

That thought was seconded by Dr. Beatrice Alexandra Golomb, a professor of medicine with the University of California San Diego’s School of Medicine.

“Fitness is tied to better health outcomes, and fewer COVID high-risk factors like hypertension [high blood pressure], obesity and diabetes,” said Golomb, who wasn’t part of the study. “Thus, exercise in the time of COVID remains important.”

“[And] it is a time of opportunity to discover new ways to exercise,” Golomb added. “There are a plethora of online exercise video options, possible parks or trails to investigate, and creative ways to repurpose your home or apartment. Chair, beds, the floor or vacuum cleaners can be conscripted for use. Remember: any movement is better than no movement.”

That becomes all the more important during a time of increased eating and sedentary behavior, said Lona Sandon, program director of the Department of Clinical Nutrition in the School of Health Professions at UT Southwestern Medical Center in Dallas.

“I know from my own experience,” said Sandon, who had no part in the study. “I sit more during the day when working at home. When I am in the office, I move around a lot more, get up out of my desk to talk to people at the other end of the hall, [and] run up the stairs to do something in the lab.”

And because what you eat is as important as exercise, Sandon has some advice: “Think realistically about calorie balance. We tend to underestimate the calories we eat and overestimate the calories we use. If over the past five or six months your clothes have been tightening, take a look at where you might be getting a few extra calories. Are you eating more desserts than you used too? Are you having a few more beers or glasses of wine? Or simply eating out of boredom or stress and depression?”

Stenson and her colleagues presented their findings last week at the virtual annual meeting of the American Physiological Society. Research presented at meetings are considered preliminary until published in a peer-reviewed journal.

More information

There’s more information on the WHO exercise recommendations at World Health Organization.

Copyright 2020 HealthDay. All rights reserved.



Source link

Continue Reading

Health

FDA issues emergency authorization for first at-home COVID-19 test

Published

on

Nov. 18 (UPI) — The U.S. Food and Drug Administration has issued an emergency authorization for the first rapid coronavirus test that can be administered at home.

The agency announced the authorization for the all-in-one test kit late Tuesday in response to a request by Kelly Lewis Brezoczky of Lucira Health, the California-based company that developed the test.

In a letter to Brezoczky, the FDA said the test meets the criteria for an emergency use authorization as there are no available alternatives and the product’s benefits outweigh its known and potential risks.

The test has been authorized for use with samples collected from the nasal cavity of those age 14 years and older whose doctors suspect they have been infected with the coronavirus. Use in doctor’s offices, hospitals, urgent care centers and emergency rooms has been approved for all ages.

While there have been other products approved for collecting samples at home, the Lucira product is the first to be fully self-administered and to provide results without a physician’s assistance.

The company’s website said the test is intended to cost under $50 and is designed to provide results within 30 minutes.

“Today’s authorization for a complete at-home test is a significant step toward FDA’s nationwide response to COVID-19,” Jeff Shuren, director of the FDA’s Center for Devices and Radiological Health, said in a statement.

FDA Commissioner Stephen M. Hahn said the development of a COVID-19 test that can be administered outside a healthcare setting has been a major priority for the FDA, and now that there is one more people who suspect that they may have been infected with the virus can take immediate action to protect themselves and their community.

“We look forward to proactively working with test developers to support the availability of more at-home test options,” he said.

The FDA approval was issued as the nation deals with a growing widespread outbreak. According to data collected by Johns Hopkins University, the United States has recorded more than 150,000 case a day in five of the last six days.

The United States has reported more than 11.3 million infections and nearly 250,000 deaths, making it by far the sickest country to the pandemic.



Source link

Continue Reading

Health

Antidepressant might help prevent severe COVID-19

Published

on

The antidepressant drug fluvoxamine — best known by the brand name Luvox — may help prevent serious illness in COVID-19 patients who aren’t yet hospitalized, a new study finds.

The study included 152 patients infected with mild-to-moderate COVID-19. Of those, 80 took fluvoxamine and 72 took a placebo for 15 days.

By the end of that time, none of the patients who took the drug had seen their infection progress to serious illness, compared with six (8.3%) of the patients who took the placebo, according to researchers at Washington University School of Medicine in St. Louis.

“The patients who took fluvoxamine did not develop serious breathing difficulties or require hospitalization for problems with lung function,” said first author Dr. Eric Lenze, professor of psychiatry.

“Most investigational treatments for COVID-19 have been aimed at the very sickest patients, but it’s also important to find therapies that prevent patients from getting sick enough to require supplemental oxygen or to have to go to the hospital. Our study suggests fluvoxamine may help fill that niche,” Lenze noted in a university news release.

Fluvoxamine — widely used to treat depression, obsessive-compulsive disorder and social anxiety disorder — is a type of drug called a selective serotonin-reuptake inhibitor (SSRI). This class of drugs also includes medicines such as Prozac, Zoloft and Celexa.

But unlike other SSRIs, fluvoxamine has a strong interaction with a protein called the sigma-1 receptor, which helps regulate the body’s inflammatory response.

“There are several ways this drug might work to help COVID-19 patients, but we think it most likely may be interacting with the sigma-1 receptor to reduce the production of inflammatory molecules,” explained study senior author Dr. Angela Reiersen, associate professor of psychiatry.

“Past research has demonstrated that fluvoxamine can reduce inflammation in animal models of sepsis, and it may be doing something similar in our patients,” she said in the release.

By reducing inflammation, fluvoxamine may prevent a hyperactive immune response in COVID-19 patients. That, in turn, may decrease their risk of serious illness and death, Reiersen said.

“Our goal is to help patients who are initially well enough to be at home and to prevent them from getting sick enough to be hospitalized,” Dr. Caline Mattar, assistant professor of medicine in the Division of Infectious Diseases, said in the release. “What we’ve seen so far suggests that fluvoxamine may be an important tool in achieving that goal.”

Dr. Amesh Adalja is a senior scholar at the Johns Hopkins Center for Health Security in Baltimore. He wasn’t involved in the study, but said the research is “notable not only because of its positive outcome — we desperately need a medication that keeps COVID patients out of the hospital — but also because of the manner in which it was conducted.”

But Adalja stressed that a larger trial is needed “to see if the promising findings hold up.”

The researchers said they plan to begin such a study in the next few weeks and it will include patients from across the United States.

The preliminary study was published online Nov. 12 in the Journal of the American Medical Association.

More information

For more on COVID-19, go to the U.S. Centers for Disease Control and Prevention.

SOURCES: Amesh Adalja, M.D., senior scholar, Johns Hopkins Center for Health Security, Baltimore; Washington University in St. Louis, news release, Nov. 12, 2020

Copyright 2020 HealthDay. All rights reserved.



Source link

Continue Reading

Trending