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

Asthma may not boost risk for severe COVID-19, study says

Published

on

New research may have people with asthma breathing a little easier: Doctors found the airway disease doesn’t raise the risk of being hospitalized due to COVID-19.

The researchers also noted that people with asthma weren’t more likely than people without it to need a ventilator to help them breathe.

“A lot of people with asthma think they have a predisposition to severe COVID, and they worry a lot about going out. They should take precautions like using their masks, but they may not need to worry so much,” said study author Dr. Fernando Holguin. He’s director of the Asthma Clinical and Research Program at the University of Colorado Anschutz Medical Campus, in Aurora.

Holguin said the proportion of hospitalized COVID-19 patients with asthma was around 6%.

“For most places, that’s an asthma prevalence that is at or lower than the asthma prevalence in the general population. To compare, with influenza [flu], we typically see about a quarter of those in the hospital have asthma,” he said.

When the pandemic first began, the U.S. Centers for Disease Control and Prevention suggested that people with asthma had a higher risk of hospitalization and other severe outcomes. People with asthma do have a significantly higher risk of complications with flu, another viral infection.

In the new study, the researchers reviewed 15 studies on COVID-19 infections to see how many people hospitalized had asthma.

They also looked at more than 400 patients treated for COVID-19 at the University of Colorado Hospital, to see whether the rates of ventilator use were different in people with asthma.

“The message from our study is not to be cavalier about COVID, but individuals with asthma won’t do worse than people without it,” Holguin said.

Other research also points to the same conclusion. A June study in the Journal of Allergy and Clinical Immunology of more than 1,500 people — 220 with asthma — who had COVID-19 found that people with asthma weren’t more likely to be hospitalized. They also didn’t have a higher risk of death.

Holguin said the researchers have a theory as to why COVID-19 infections don’t seem to lead to worse outcomes in people with asthma.

“Allergic asthma is associated with lower numbers of ACE2 receptors. These are the receptors the virus uses to anchor itself to cells,” he said. That means people with allergic asthma may have less area for the virus to attach to. Holguin added that people who use inhaled corticosteroids (an asthma treatment) also have fewer ACE2 receptors.

The new findings were published Aug. 31 in the Annals of the American Thoracic Society.

Dr. Charles Fishman, a pulmonologist with the NewYork-Presbyterian Medical Group Westchester, in New York City, said, “This study’s findings are consistent with what we’ve seen clinically. The original concern was that since people with asthma are disproportionately hospitalized with flu, that they might also have bad outcomes with coronavirus. But that doesn’t seem to be the case with coronavirus.”

Fishman said it’s probably too soon to know why people with asthma are faring better than expected.

“There so much that’s still unknown. It’s important in drawing conclusions that we really rely on good science,” he added.

In the meantime, like Holguin, he advised, “People with asthma should exercise the exact same caution as people without asthma. They don’t need to be increasingly concerned, but should have a healthy respect for what this virus can do. Until a vaccine is available and the population is fully protected, continue to do those things that protect you from the virus [such as wearing a mask, washing your hands frequently and keeping safe distances from others].”

More information

Learn more about asthma from the American College of Allergy, Asthma, and Immunology.

Copyright 2020 HealthDay. All rights reserved.



Source link

Continue Reading

Health

COVID-19 may cause long-term heart problems in children, researchers say

Published

on

Sept. 4 (UPI) — Children who suffer heart damage caused by COVID-19 may need lifelong care and treatment, according to a review of existing research published Friday by EClinicalMedicine.

Young people who develop multisystem inflammatory syndrome after being infected with the new coronavirus may experience heart-related symptoms similar to those seen with two rare, but serious, conditions called Kawasaki disease and toxic shock syndrome, the researchers said.

In some, this may include a reduced ability for the heart to pump oxygenated blood to the tissues of the body or development of a heart aneurysm.

“This is a new childhood disease that is believed to be associated with [COVID-19], and it can be lethal because it affects multiple organ systems [including] the heart and the lungs, gastrointestinal system or neurologic system,” neonatologist Alvaro Moreira said in a statement.

“Children might have no symptoms, no one knew they had the disease, and a few weeks later, they may develop this exaggerated inflammation in the body,” said Moreira, an assistant professor of pediatrics at The University of Texas Health Science Center at San Antonio.

Moreira and his colleagues reviewed 662 of multisystem inflammatory syndrome cases reported worldwide between Jan. 1 and July 25. Almost half of patients who had it also had an underlying medical condition. Of those, half were obese or overweight.

Seventy-one percent of the children who developed the condition after being infected with COVID-19 were admitted to intensive care units, and 60% had symptoms of shock, the data showed.

More than half — 54% — had abnormal findings on echocardiograms of their hearts, suggesting damage. Roughly one in five required mechanical ventilation to maintain breathing, and 11 died in the hospital, researchers said.

The damage spotted on EKGs included dilation of coronary blood vessels, a phenomenon also seen in Kawasaki disease, and depressed ejection fraction, which indicates a reduced ability for the heart to pump oxygenated blood to the rest of the body.

In addition, almost 10% of children had an aneurysm of a coronary vessel, or a ballooning of the blood vessel that can be measured on an ultrasound of the heart, which places them at high risk for future heart-health problems, Moreira said.

“These are children who are going to require significant observation and follow-up with multiple ultrasounds to see if this is going to resolve or if this is something they will have for the rest of their lives, and that’s catastrophic to a parent who had a previously healthy child,” he said.

Most of the 662 children suffered cardiac involvement as indicated by elevated levels of a protein that regulates muscle contraction called troponin — up to 50 times higher than normal — which is used with great accuracy in adults to diagnose heart attacks.

On the positive side, children who develop multisystem inflammatory syndrome seem to respond well to treatments typically used in Kawasaki disease, including imunoglobulin and glucocorticosteroids.

“Evidence suggests that [these] children … have immense inflammation and potential tissue injury to the heart, and we will need to follow [them] closely to understand what implications they may have in the long term,” Moreira said.



Source link

Continue Reading

Health

Kids’ ‘green’ time reduces adverse effects of ‘screen’ time on behavior, learning

Published

on

Sept. 4 (UPI) — More time spent outdoors — and less in front of a screen — leads to improved mental health in children and adolescents, according to an analysis of existing research published Friday by the journal PLOS ONE.

Based on data from 186 previously published studies, researchers determined that young people who spent more time on handheld games and devices, television and computers were more likely to have behavior and emotional problems and display symptoms of aggression and attention deficit-hyperactivity disorder.

The young people also were more likely to have learning or social difficulties.

Conversely, children who spent more time outdoors and who had increased access to “green” spaces for play and learning were less likely to have these undesirable traits.

“Overall, the studies showed that high levels of screen time were associated with poorer psychological well-being, while more green time was associated with better psychological well-being,” co-author Tassia Oswald told UPI.

“While a lot more work needs to be done in this field to help us understand why this is the case, it is important that [technology] doesn’t become the only thing young people do in their leisure time,” said Oswald, a doctoral student in public health at the University of Adelaide in Australia.

The prevalence of mental health illness among children and adolescents is increasing globally, according to Oswald and her colleagues.

In the United States, roughly 7%, or 4.5 million, of children ages 3 to 17 have been diagnosed with a behavioral problem, the Centers for Disease Control and Prevention estimates.

On average, American children and adolescents spent between four and six hours per day watching or uses devices with screens, and may be exposed to violence and misleading or inaccurate information, among other potentially problematic content, according to the American Academy of Child and Adolescent Psychiatry.

A separate study of 1,239 8- to 9-year-olds in Melbourne, Australia, published earlier this week by PLOS ONE, found that watching two or more hours of television per day at that age was associated with lower reading performance compared to peers two years later.

In addition, using a computer for more than one hour per day was linked to a similar reduction in their ability to understand and work with numbers.

However, no links were found between the use of video games and academic performance, the analysis showed.

Preliminary evidence suggests that green time potentially could limit the effects of high screen time, meaning nature may be an under-utilized public health resource to promote youth psychological well-being in a high-tech era, according to Oswald and her colleagues.

“Monitoring screen time can be difficult for parents — especially at the moment when many children have transitioned to online learning due to COVID-19 lockdowns,” Oswald said.

“Trying to encourage a balance of activities is good — so if a child spends an hour on a video game, encourage them to get outside for an hour.”



Source link

Continue Reading

Trending