Study finds ChatGPT fails at heart risk assessment

 Despite ChatGPT's reported ability to pass medical exams, new research indicates it would be unwise to rely on it for some health assessments, such as whether a patient with chest pain needs to be hospitalized.

In a study involving thousands of simulated cases of patients with chest pain, ChatGPT provided inconsistent conclusions, returning different heart risk assessment levels for the exact same patient data. The generative AI system also failed to match the traditional methods physicians use to judge a patient's cardiac risk. The findings were published in the journal PLOS ONE.

"ChatGPT was not acting in a consistent manner," said lead author Dr. Thomas Heston, a researcher with Washington State University's Elson S. Floyd College of Medicine. "Given the exact same data, ChatGPT would give a score of low risk, then next time an intermediate risk, and occasionally, it would go as far as giving a high risk."

The authors believe the problem is likely due to the level of randomness built into the current version of the software, ChatGPT4, which helps it vary its responses to simulate natural language. This same randomness, however, does not work well for health care uses that require a single, consistent answer, Heston said.

"We found there was a lot of variation, and that variation in approach can be dangerous," he said. "It can be a useful tool, but I think the technology is going a lot faster than our understanding of it, so it's critically important that we do a lot of research, especially in these high-stakes clinical situations."

Chest pains are common complaints in emergency rooms, requiring doctors to rapidly assess the urgency of a patient's condition. Some very serious cases are easy to identify by their symptoms, but lower risk ones can be trickier, Heston said, especially when determining whether someone should be hospitalized for observation or sent home and receive outpatient care.

Currently medical professionals often use one of two measures that go by the acronyms TIMI and HEART to assess heart risk. Heston likened these scales to calculators with each using a handful of variables including symptoms, health history and age. In contrast, an AI neural network like ChatGPT can assess billions of variables quickly, meaning it could potentially analyze a complex situation faster and more thoroughly.

For this study, Heston and colleague Dr. Lawrence Lewis of Washington University in St. Louis first generated three datasets of 10,000 randomized, simulated cases each. One dataset had the seven variables of the TIMI scale, the second set included the five HEART scale variables and a third had 44 randomized health variables.

On the first two datasets, ChatGPT gave a different risk assessment 45% to 48% of the time on individual cases than a fixed TIMI or HEART score. For the last data set, the researchers ran the cases four times and found ChatGPT often did not agree with itself, returning different assessment levels for the same cases 44% of the time.

Despite the negative findings of this study, Heston sees great potential for generative AI in health care—with further development.

For instance, assuming privacy standards could be met, entire medical records could be loaded into the program, and an in an emergency setting, a doctor could ask ChatGPT to give the most pertinent facts about a patient quickly. Also, for difficult, complex cases, doctors could ask the program to generate several possible diagnoses.

"ChatGPT could be excellent at creating a differential diagnosis and that's probably one of its greatest strengths," said Heston.

"If you don't quite know what's going on with a patient, you could ask it to give the top five diagnoses and the reasoning behind each one. So it could be good at helping you think through a problem, but it's not good at giving the answer."

More information: Thomas F. Heston et al, ChatGPT provides inconsistent risk-stratification of patients with atraumatic chest pain, PLOS ONE (2024). DOI: 10.1371/journal.pone.0301854

https://medicalxpress.com/news/2024-05-chatgpt-heart.html

Study sheds light on debate on 2 types of shoulder replacement surgery for osteoarthritis

 

Anatomical and reverse total shoulder replacements. Anatomical total shoulder replacement—prosthetic ball and socket replacement that matches normal ball and socket anatomy of shoulder joint. Reverse total shoulder replacement—prosthetic ball and socket replacement that reverses normal ball and socket anatomy of shoulder joint. Credit: BMJ (2024) DOI: 10.1136/bmj-2023-077939

A new study has provided valuable insights into the ongoing debate surrounding two types of shoulder replacement surgery: reverse total shoulder replacement and anatomical total shoulder replacement as a treatment for patients with osteoarthritis.

The research, led by the University of Oxford and involving researchers from the University of Bristol, has found that reverse total shoulder replacements (RTSR) provide similar long-term outcomes to traditional anatomical total shoulder replacements (TSR) for patients aged 60 years or older with osteoarthritis (OA) and intact rotator cuff tendons.

The study was published in the BMJ.

Shoulder OA is a common and debilitating condition, and shoulder replacement surgery is an effective treatment option for end-stage disease. TSR has long been considered the gold standard for treating patients with OA and intact rotator cuff tendons. However, the RTSR has surged in popularity since 2008 in the UK. Originally designed for a completely different surgical indication, it is now often used instead of TSR in this patient group.

This shift in practice is growing despite a lack of supporting evidence, and in 2020, the National Institute for Health and Care Excellence (NICE) identified this as a key research priority. Researchers from NDORMS, University of Oxford, and involving experts from the University of Bristol set out to provide high-quality evidence to help address this uncertainty.

Epaminondas Markos Valsamis, NIHR Doctoral Research Fellow at the University of Oxford and lead author, explained, "In recent years, the use of RTSR has increased, even for patients with intact rotator cuffs—a group traditionally treated with TSR. But treatment choices are being made without any good evidence, leading to concerns from health care agencies and patients about which procedure is the safest and most effective option."

Dr. Adrian Sayers, Senior Research Fellow in the Bristol Medical School: Translational Health Sciences (THS) and co-author, added, "This work shows the tremendous potential of routinely collected data in answering questions that are important to patients in a timely manner.

"It is reassuring for patients and surgeons to know that either reverse or traditional anatomic shoulder replacement for osteoarthritis is a safe and effective procedure. This question was asked and answered in a fraction of the time and cost of conventional randomized clinical studies."

The research team conducted a population-based cohort study using linked data from the National Joint Registry and NHS Hospital Episode Statistics for England. Over 12,000 patients aged 60 years or older who underwent RTSR or TSR for OA with intact rotator cuff tendons between 2012 and 2020 were included in the study.

The researchers compared the outcomes of patients for each of the two types of procedures, focusing on factors such as revision surgery, serious adverse events, reoperations, hospital stay duration, and lifetime costs to the health care system.

The findings revealed that while TSR had a higher risk of revision surgery in the first three years after surgery, there was no important difference in the longer term, and both procedures were equally safe for patients.

"By the end of the study period we found no 'clinically important' difference in any outcome," said Epaminondas. "This provides reassurance to patients and surgeons that RTSR is an acceptable alternative for this patient group, and we found no evidence to change the growing surgical trend of offering RSTR to them."

While further research is needed to explore functional outcomes and to inform a full cost-effectiveness comparing RTSR and TSR, this study provides valuable insights that can help guide clinical practice by supporting patients and surgeons to make more informed decisions about the best treatment options in order to optimize patient outcomes.

More information: E M Valsamis et al, Reverse total shoulder replacement versus anatomical total shoulder replacement for osteoarthritis: population based cohort study using data from the National Joint Registry and Hospital Episode Statistics for England. BMJ (2024) DOI: 10.1136/bmj-2023-077939. www.bmj.com/content/385/bmj-2023-077939

https://medicalxpress.com/news/2024-05-debate-shoulder-surgery-osteoarthritis.html

'Ethical use of video technology to support patients at risk of falls'

 Video-enabled glasses have the potential to support patients at risk of falls by allowing medical staff to monitor how they move around their homes and their community. However, with privacy concerns at the forefront of this new technology, academics at Northumbria University have carried out a cutting-edge study into the ethical use of AI to ensure video footage can be obscured to ensure patient privacy.

Traditionally, patients at risk of falls have been assessed based on information they provide themselves in diaries or during short in-clinic observation appointments. However, these do not provide clinical teams with objective, digital data on how patients move around outdoors and in their home environments—the areas in which they are most likely to have a fall.

Trials of inertial wearable technology worn on the lower back—similar to that used in a smart watch—to track patients' walking movements, known as gait, are proving valuable but there are still pitfalls due to a lack of contextual information around where a patient is, who they are walking with and what activities they are carrying out.

In a bid to both improve, and personalize, patient care for those at risk of falls through illness or age, experts have been keen to explore how they can improve assessments and gain a fuller picture of what might be contributing to any abnormal gait data captured by the wearable devices.

Asking patients to also wear video-enabled glasses will provide much more accurate information on how they move depending on their surroundings, including obstacles and other hazards, where they are at the time and what might be putting them at increased risk of falls.

However, although the use of video technology has many potential benefits, patients wearing these video-enabled glasses—and their families—must be able to maintain their privacy.

To test how these privacy concerns could be overcome, a group of computing and digital health experts ran a technology pilot to test the application of new AI software that can blur personal data and information captured by video glasses—for example photographs around the home, footage of children or confidential paperwork.

They found that the AI software could successfully analyze the raw video footage and detect and blur details such as faces, letters and laptop or phone screens, ensuring patient privacy could be maintained.

Their research has now been published in npj Digital Medicine.

Dr. Alan Godfrey, Associate Professor in Computer and Information Sciences at Northumbria University, said, "As you can imagine the variability in how people move when they're completing different tasks is enormous.

"The data or information provided from an inertial wearable device attached to someone when they're wandering around their house will inevitably differ from the same person when they're outdoors or walking more quickly to get somewhere or to keep up with someone. This means that while the use of an inertial wearable alone is helpful, it tells us nothing about the context in which a fall may occur.

"Having absolute clarity about the environment and what people are doing is key."

He added, "We wanted to assess how new developments in AI would allow us to provide video-enabled glasses that would allow medical staff to observe patients' movements in real environments over a longer time period without invading their privacy."

The paper demonstrates that by combining information from the wearable device that records gait data with footage captured by video glasses which is obscured where necessary thanks to the ethical use of AI, clinicians have a much more comprehensive picture of how patients' move in their own surroundings.

This could lead to significant improvements in the accuracy of patient fall risk assessment and in the decision-making process around patient care.

Speaking on the study, lead researcher and Ph.D. student Jason Moore, from the Department of Computer and Information Sciences at Northumbria University, said, "Traditionally the use of video within the home has caused some apprehension among patient populations as a result of privacy concerns owing to what else may be captured on camera.

"However, through the use of AI software that can identify and obscure personal or sensitive information we can effectively capture the contextual information that will allow us to better understand abnormal gait data, while overcoming the concerns patients may have around the use of video technology in their own homes.

"The benefit of providing this contextual information is that clinicians will have a fuller picture for each individual patient which could ultimately allow them to provide more informed care plans and potentially keep more patients in their own homes for longer."

The research involved experts from Northumbria's departments of Computer and Information Sciences; Nursing, Midwifery and Health; and Sport, Exercise and Rehabilitation, as well as representatives from Northumbria Healthcare NHS Foundation Trust, and the Cumbria, Northumberland and Tyne & Wear NHS Trust.

Dr. Godfrey continued, "The suggested application of this technology is unique. The way it works means that the raw footage would never be seen by clinicians; however, the contextual information it could provide when it comes to identifying potential reasoning for abnormal variability or asymmetry in gait—effectively the way patients carry themselves and move around which are signs of elevated fall risk—is invaluable.

"Without this context patients with numerous clinical conditions, for example, Parkinson's, those who've suffered strokes or even just those who are suffering from frailty, could find themselves being classed as high risk for falls and ultimately face difficult decisions around moving out of their own environment earlier than necessary. It also alleviates the pressures on patients to travel to bespoke clinics for monitoring replacing this with a community-based approach."

"It could go a long way to help us truly understand the fall risk of a patient and to provide personalized care solutions that are most appropriate to the individual and their needs."

Following on from this initial research paper, the team will examine habitual fall risk in people with Parkinson's disease and are now recruiting people with Parkinson's to wear the technology in their homes and local communities. This will enable the research team to refine and improve their AI algorithms and in the future help inform personalized approaches to reduce fall risk in those living with Parkinson's.

Speaking on the project, co-author and Consultant Physician at Northumbria Healthcare NHS Foundation Trust, Professor Richard Walker, said, "People with Parkinson's have increasing mobility issues as their Parkinson's progresses. Falls can lead to major injuries, such as hip fractures, so anything we can do to try and prevent them would be of great benefit.

"This new technology will hopefully provide us with unique information around the circumstances of falls in order to help us advise on the most appropriate preventive measures."

More information: Jason Moore et al, Contextualizing remote fall risk: Video data capture and implementing ethical AI, npj Digital Medicine (2024). DOI: 10.1038/s41746-024-01050-7

https://medicalxpress.com/news/2024-05-ai-experts-explore-ethical-video.html

Neuroscientists: integrity of white brain matter in superagers does not deteriorate, explains sharp memory

 A team of neuroscientists from Universidad Politécnica de Madrid and Queen Sofia Foundation Alzheimer Center, both in Spain, has found that so-called superagers maintain memory as they grow older because they do not experience a decline in the integrity of their white brain matter.

In their study, published in The Journal of Neuroscience, the group conducted multiple tests with 100 octogenarian volunteers over a 10-year span.

Prior research and anecdotal evidence suggest that as people grow older, they tend to lose neurological function—thinking skills decline, as does memory retention and retrieval. But people known as superagers remain cognitively sharp and their memory skills do not deteriorate.

For this new study, the team in Spain evaluated the brains of these people and compared them with non-superagers to find out what was behind such differences.

The researchers recruited 64 superager volunteers and 55 non-superagers who periodically received brain scans and blood draws, took memory tests and completed multiple types of questionnaires over 10-year periods. The tests were designed to learn more about their lifestyles, behavior and how well their brains were holding up as they grew older.

The researchers found differences in the integrity of white brain matter. For superagers, there was little to no loss. More specifically, they found little loss in the mass of white brain matter in the entorhinal cortex and hippocampus, two parts of the brain that are heavily involved in memory processing and retention. They also found few signs of Alzheimer's disease.

Unfortunately, the research team found no evidence that could explain why some people are superagers, though they did note some minor differences in lifestyle choices—people in better health overall tended to have better mental health, as well.

The team also noted that superagers did not smoke or drink less, eat better, or exercise or sleep more. They also were no smarter or less intelligent than average and did not do any better or worse in their professional life prior to the onset of old age.

More information: Marta Garo-Pascual et al, Superagers resist typical age-related white matter structural changes, The Journal of Neuroscience (2024). DOI: 10.1523/JNEUROSCI.2059-23.2024

https://medicalxpress.com/news/2024-04-neuroscientists-white-brain-superagers-deteriorate.html

RFK Jr. offers Biden wacky ‘no spoiler’ deal in desperate bid to battle Trump for White House

 Independent presidential candidate Robert F. Kennedy Jr. needled President Biden Wednesday, offering a zany “no spoiler” agreement that whichever of the two candidates is least likely to defeat Donald Trump drops out of the race in October.

During a news conference in Brooklyn, the 70-year-old RFK Jr. proposed that he and Biden co-fund a 50-state poll of at least 30,000 likely voters to determine which candidate is the true “spoiler” who would ensure a victory for the 45th president by continuing to campaign.

“Ultimately, I think what we all want in this election is [for] Americans not to feel like they have to vote out of fear,” Kennedy told reporters. “That they feel like they can vote out of hope. And that is only going to happen if there’s a two-way race between me and President Trump or me and President Biden.”

4

Independent presidential candidate Robert F. Kennedy Jr. in a suit, holding a microphone at a press conference in Brooklyn, New York, May 1, 2024AFP via Getty Images

The poll would measure the likelihood both of Kennedy defeating Trump, 77, in a head-to-head race and Biden, 81, repeating his 2020 victory over his Republican rival.

The Democratic National Committee quickly pooh-poohed the proposal from Kennedy, claiming he was there as a Trump ally.

“Robert F. Kennedy Jr is a spoiler-  recruited by the MAGA GOP and propped up by Trump’s largest donor. His ‘Veep’-like performance today does nothing to dispel that notion- it only reinforces how deeply unserious his campaign is,” DNC spokesperson Matt Corridoni told The Post in a statement.

But polls do show that Kennedy has significant support against Biden, the presumptive Democratic nominee.

At Wednesday’s event, the Kennedy campaign cited a 50-state poll conducted by John Zogby Strategies that indicated the independent would win a two-way race against Biden and Trump.

In the survey, which polled over 26,000 people, Kennedy won 367 electoral votes to Biden’s 171. Against Trump, RFK Jr. barely obtained the magic number of 270 electoral votes.

In the widely expected Trump-Biden rematch, the 45th president knocked off his successor by 294 electoral votes to 244, according to Zogby.

4

A map posted by Kennedy’s campaign depicting Trump beating out Biden in the Electoral College.kennedy24.com

4

The largest 50-state poll of the 2024 cycle indicates Robert F. Kennedy Jr. is the only alternative to four more years of Donald Trump.kennedy24.com

4

A map of the United States illustrating the results of a 50-state poll for the 2024 election cycle, suggesting Robert F. Kennedy Jr. as the main alternative to Donald Trump.kennedy24.com

RFK Jr. campaign manager Amaryllis Kennedy had stronger words urging Biden to bow out, saying the incumbent “can not win” Nov. 5, “not in a two-way [race], not in a three-way [race],”

Jeremy Zogby, managing partner of John Zogby Strategies, told The Post that “the numbers speak for themselves” and that Kennedy has been polling well “going back over a year.”

“I’ve conducted 30 something polls and I’ve seen him consistently draw from both parties, equally… When you put it all together he’s polling pretty equally,” Zogby added.

“He’s building a pretty substantial coalition of a mosaic of the political landscape.”

https://nypost.com/2024/05/01/us-news/rfk-jr-offers-biden-wacky-no-spoiler-deal-with-chance-of-october-dropout/

Walmart closing down health centers. What that mean for Amazon, Walgreens, CVS

 A look at whether rival retailers should be worried or encouraged by Walmart shuttering its health centers

Walmart Inc. (WMT) announced Tuesday it's closing its 51 health centers after the retail giant admitted the business had not seen sustainable profits since its inception in 2019.

Walmart's announcement emphasizes the difficulty some retailers have come across as they attempt to enter the primary-care and healthcare markets.

Other retailers who have made moves to provide people with healthcare in recent years include Amazon, CVS (CVS), Walgreens (WBA) and Costco (COST). Amazon acquired One Medical for $3.9 billion last year to bolster its in-person and remote primary-care services. CVS has continued to expand its retail locations. Walgreens introduced several new primary-care locations after a string of acquisitions, including VillageMD, Summit Health and CareCentrix. And Costco began offering its members access to medical care in 2023 through the Sesame platform, which includes $29 virtual primary-care visits.

Some of those companies experienced headwinds related to the healthcare aspects of their business. Amazon (AMZN) had to shut down one iteration of its primary-care service, Amazon Care, in 2022, and Walgreens reported a second-quarter loss partially due to a $5.8 billion charge associated with its primary-care business.

"Retail health presents tremendous opportunities, but also challenges. There's high operating costs, regulatory challenges, and disparities in reimbursement," Natalie Schibell, the vice president of marketing strategy, intelligence and insights at the health platform Zyter|TruCare, told MarketWatch about the Walmart announcement.

Compared with other similar retail stores, Walmart stores tend to be more prevalent in rural areas. And because people living in rural parts of the U.S. often have fewer primary-care options than others, Schibell was optimistic about Walmart Health.

"I had high hopes for retail health clinics, especially those in rural areas to help bring those barriers to access," she said. Some of those barriers include staffing issues, travel-time issues (Americans in rural areas travel an average of 30 minutes or longer for medical appointments) and reimbursement rates.

"Our belief is that the closure of Walmart Health, while it shuts the door on clinics, provides the opportunity to focus on leveraging existing assets in pharmacy, optical, & OTC. We think the new private label brand should help to further bolster market share gains ahead," analysts at Jefferies said in a research note.

But if a company as big as Walmart - with its $485 billion market cap - had a difficult time making substantial profit from ITS retail health offerings, should other companies offering relatively similar services be worried?

"If you look at Walmart's strategy, they're strategically located versus their competitors in more rural areas. And if they're relying heavily on insurance payment being their operations, those little reimbursement rates in rural areas could really impact their profitability," Schibell said.

Walmart's store locations led to a few challenges for the profitability of its primary-care business, an issue that other brands in urban or suburban areas may not experience.

Despite future challenges, some brands are pushing forward with expansion.

"We're still opening 50 to 60 clinics next year," CVS chief executive officer Karen S. Lynch said shortly after the company reported fourth-quarter earnings in February. "All is working well."

CVS's stock tumbled nearly 20% on Wednesday after the healthcare-services brand fell short of first-quarter expectations. CVS cited "elevated medical cost trends" as the reason for cutting its full-year outlook, and showed a 9.7% decrease in year-over-year revenue in its "health services" segment, which includes but is not limited to its medical clinics.

And though Walgreens closed 160 of its VillageMD clinics in March, it's optimistic about a new way forward.

"During the first half of fiscal '24, we have seen positive financial impacts from the recent actions taken by VillageMD management team to accelerate profitability. We believe the focused approach on improving performance in core markets as well as rightsizing the cost structure will provide VillageMD a platform for future growth," Walgreens Chief Executive Tim Wentworth said during the company's second-quarter earnings call.

Amazon's One Medical has 240 primary-care office locations in the U.S. and is looking to expand, particularly in major cities.

"We look at MSA (metropolitan statistical areas) specific needs and try to meet our members where they are in terms of their desire for access and convenience," One Medical CEO Trent Green recently said in an interview with Forbes. "We're sustaining and we are intentionally expanding our physical footprint."

However, healthcare has still proven to be a difficult industry to navigate for retailers.

"[Retailers] are going to need to sharpen their pencil and be more strategic," Schibell concluded.

Walmart said its health centers and telehealth services didn't have a "sustainable business model for us to continue," citing the insurance-reimbursement environment and rising operating costs that hurt profitability.

Walmart's optical business, which includes more than 3,000 vision centers, as well as its 4,600 pharmacies, will continue to operate normally.

Americans spent a total of $4.4 trillion, or $13,493 per capita, on their health in 2022, according to the American Medical Association. Health spending made up 17.3% of the country's GDP that year.

https://www.morningstar.com/news/marketwatch/20240501830/walmart-is-closing-down-its-health-centers-what-does-that-mean-for-amazon-walgreens-and-cvs