Anatomic pathologists understand that, along with breast cancer, diagnostic testing for prostate cancer accounts for a high volume of clinical laboratory tests. Thus, a recent study indicating that a new artificial intelligence (AI)-based software tool can dramatically improve physicians’ ability to identify the extent of these cancers will be of interest.
“The study found that Unfold AI’s patient-specific encapsulation confidence score (ECS), which is generated based on multiple patient data points, including MRI scans, biopsy results, PSA [prostate-specific antigen] data, and Gleason scores, is critical for predicting treatment success,” an Avenda press release states. “These findings emphasize the importance of Unfold AI’s assessment of tumor margins in predicting treatment outcomes, surpassing the predictive capability of conventional parameters.”
“Unfold AI’s ability to identify tumor margins and provide the ECS will improve treatment recommendations and allow for less-invasive interventions,” said study co-author Wayne Brisbane, MD, a urologic oncologist and UCLA medical professor, in another press release. “This more comprehensive approach enhances our ability to predict treatment outcomes and tailor interventions effectively to individual patient needs.”
“This study is important because it shows the ability of AI to not only replicate expert physicians, but to go beyond human ability,” said study co-author Wayne Brisbane, MD (above), a urologic oncologist and UCLA medical professor, in a press release. “By increasing the accuracy of cancer identification in the prostate, more precise and effective treatment methods can be prescribed for patients.” Clinical laboratories that work with anatomic pathologists to diagnose prostate and other cancers may soon have a new AI testing tool. (Photo copyright: UCLA.)
How Unfold AI Works
To gauge the extent of prostate tumors, surgeons typically evaluate results from multiple diagnostic methods such as PSA tests and imaging scans such as MRIs, according to a UCLA press release. However some portions of a tumor may be invisible to an MRI, causing doctors to underestimate the size.
Unfold AI, originally known as iQuest, was designed to analyze data from PSA, MRI, fusion biopsy, and pathology testing, according to a company brochure. From there, it generates a 3D map of the cancer. Avenda’s website says the technology provides a more accurate representation of the tumor’s extent than conventional methods.
“Accurately determining the extent of prostate cancer is crucial for treatment planning, as different stages may require different approaches such as active surveillance, surgery, focal therapy, radiation therapy, hormone therapy, chemotherapy, or a combination of these treatments,” Brisbane said in the UCLA press release.
Putting AI to the Test
In the new study, the UCLA researchers enlisted seven urologists and three radiologists to review 50 prostate cancer cases. Each patient had undergone prostatectomy—surgical removal of all or part of the prostate—but might have been eligible for focal therapy, a less-aggressive approach that uses heat, cryotherapy, or electric shocks to attack cancer cells more selectively.
The physicians came from five hospitals and had a wide range of clinical experience from two to 23 years, the researchers noted in The Journal of Urology.
They reviewed clinical data and examined MRI scans of each patient, then “manually drew outlines around the suspected cancerous areas, aiming to encapsulate all significant disease,” the press release states. “Then, after waiting for at least four weeks, they reexamined the same cases, this time using AI software to assist them in identifying the cancerous areas.”
The researchers analyzed the physicians’ work, evaluating the accuracy of the cancer margins and the “negative margin rate,” indicating whether the clinicians had identified all of the cancerous tissue. Using conventional approaches, “doctors only achieved a negative margin 1.6% of the time,” the press release states. “When assisted by AI the number increased to 72.8%.”
The clinicians’ accuracy was 84.7% when assisted by AI versus 67.2% to 75.9% for conventional techniques.
They also found that clinicians who used the AI software were more likely to recommend focal therapy over more aggressive forms of treatment.
“We saw the use of AI assistance made doctors both more accurate and more consistent, meaning doctors tended to agree more when using AI assistance,” said Avenda Health co-founder and CEO Shyam Natarajan, PhD, who was senior author of the study.
“These results demonstrate a marked change in how physicians will be able to diagnose and recommend treatment for prostate cancer patients,” said Natarajan in a company press release. “By increasing the confidence in which we can predict a tumor’s margins, patients and their doctors will have increased certainty that their entire tumor is treated and with the appropriate intervention in correlation to the severity of their case.”
UCLA’s study found that AI can outperform doctors both in sensitivity (a higher detection rate of positive cancers) and specificity (correctly detecting the sample as negative). That’s relevant and worth watching for further developments.
Pathologists and clinical laboratory managers should consider this use of AI as one more example of how artificial intelligence can be incorporated into diagnostic tests in ways that allow medical laboratory professionals to diagnose disease earlier and more accurately. This will improve patient care because early intervention for most diseases leads to better outcomes.
Pathologists and clinical laboratory managers will want to stay alert to the concerns voiced by tech experts about the need to exercise caution when using generative AI to assist medical diagnoses
GPTs are an integral part of the framework of a generative artificial intelligence that creates text, images, and other media using generative models. These neural network models can learn the patterns and structure of inputted information and then develop new data that contains similar characteristics.
Through their proposal, the AMA has developed principles and recommendations surrounding the benefits and potentially harmful consequences of relying on AI-generated medical advice and content to advance diagnoses.
“We’re trying to look around the corner for our patients to understand the promise and limitations of AI,” said Alexander Ding, MD (above), AMA Trustee and Associate Vice President for Physician Strategy and Medical Affairs at Humana, in a press release. “There is a lot of uncertainty about the direction and regulatory framework for this use of AI that has found its way into the day-to-day practice of medicine.” Clinical laboratory professionals following advances in AI may want to remain informed on the use of generative AI solutions in healthcare. (Photo copyright: American Medical Association.)
Preventing Spread of Mis/Disinformation
GPTs are “a family of neural network models that uses the transformer architecture and is a key advancement in artificial intelligence (AI) powering generative AI applications such as ChatGPT,” according to Amazon Web Services.
In addition to creating human-like text and content, GPTs have the ability to answer questions in a conversational manner. They can analyze language queries and then predict high-quality responses based on their understanding of the language. GPTs can perform this task after being trained with billions of parameters on massive language datasets and then generate long responses, not just the next word in a sequence.
“AI holds the promise of transforming medicine,” said diagnostic and interventional radiologist Alexander Ding, MD, AMA Trustee and Associate Vice President for Physician Strategy and Medical Affairs at Humana, in an AMA press release.
“We don’t want to be chasing technology. Rather, as scientists, we want to use our expertise to structure guidelines, and guardrails to prevent unintended consequences, such as baking in bias and widening disparities, dissemination of incorrect medical advice, or spread of misinformation or disinformation,” he added.
The AMA plans to work with the federal government and other appropriate organizations to advise policymakers on the optimal ways to use AI in healthcare to protect patients from misleading AI-generated data that may or may not be validated, accurate, or relevant.
Advantages and Risks of AI in Medicine
The AMA’s proposal was prompted by AMA-affiliated organizations that stressed concerns about the lack of regulatory oversight for GPTs. They are encouraging healthcare professionals to educate patients about the advantages and risks of AI in medicine.
“AI took a huge leap with large language model tool and generative models, so all of the work that has been done up to this point in terms of regulatory and governance frameworks will have to be treated or at least reviewed with this new lens,” Sha Edathumparampil, Corporate Vice President, Digital and Data, Baptist Health South Florida, told Healthcare Brew.
According to the AMA press release, “the current limitations create potential risks for physicians and patients and should be used with appropriate caution at this time. AI-generated fabrications, errors, or inaccuracies can harm patients, and physicians need to be acutely aware of these risks and added liability before they rely on unregulated machine-learning algorithms and tools.”
According to the AMA press release, the organization will propose state and federal regulations for AI tools at next year’s annual meeting in Chicago.
In a July AMA podcast, AMA’s President, Jesse Ehrenfeld, MD, stressed that more must be done through regulation and development to bolster trust in these new technologies.
“There’s a lot of discomfort around the use of these tools among Americans with the idea of AI being used in their own healthcare,” Ehrenfeld said. “There was a 2023 Pew Research Center poll [that said] 60% of Americans would feel uncomfortable if their own healthcare provider relied on AI to do things like diagnose disease or recommend a treatment.”
WHO Issues Cautions about Use of AI in Healthcare
In May, the World Health Organization (WHO) issued a statement advocating for caution when implementing AI-generated large language GPT models into healthcare.
A current example of such a GPT is ChatGPT, a large language-based model (LLM) that enables users to refine and lead conversations towards a desired length, format, style, level of detail and language. Organizations across industries are now utilizing GPT models for Question and Answer bots for customers, text summarization, and content generation and search features.
“Precipitous adoption of untested systems could lead to errors by healthcare workers, cause harm to patients, erode trust in AI, and thereby undermine (or delay) the potential long-term benefits and uses of such technologies around the world,” commented WHO in the statement.
WHO’s concerns regarding the need for prudence and oversight in the use of AI technologies include:
Data used to train AI may be biased, which could pose risks to health, equity, and inclusiveness.
LLMs generate responses that can appear authoritative and plausible, but which may be completely incorrect or contain serious errors.
LLMs may be trained on data for which consent may not have been given.
LLMs may not be able to protect sensitive data that is provided to an application to generate a response.
LLMs can be misused to generate and disseminate highly convincing disinformation in the form of text, audio, or video that may be difficult for people to differentiate from reliable health content.
Tech Experts Recommended Caution
Generative AI will continue to evolve. Therefore, clinical laboratory professionals may want to keep a keen eye on advances in AI technology and GPTs in healthcare diagnosis.
“While generative AI holds tremendous potential to transform various industries, it also presents significant challenges and risks that should not be ignored,” wrote Edathumparampil in an article he penned for CXOTECH Magazine. “With the right strategy and approach, generative AI can be a powerful tool for innovation and differentiation, helping businesses to stay ahead of the competition and better serve their customers.”
GPT’s may eventually be a boon to healthcare providers, including clinical laboratories, and pathology groups. But for the moment, caution is recommended.
Experts advise clinical laboratories to prepare now for a marked increase in demand for RSV, COVID-19, and influenza testing
Are the COVID-19 lockdowns responsible for the increase in cases of respiratory syncytial virus (RSV)? Some physicians believe that may be the case and it has hospitals, clinical laboratories, and pathology groups scrambling to prepare for a possible “tripledemic,” according to UC Davis Health.
The addition of RSV as we move into what is predicted to be a bad influenza (flu) season has prompted the Centers for Disease Control and Prevention (CDC) to issue a Health Alert Network (HAN) advisory which states, “Co-circulation of respiratory syncytial virus (RSV), influenza viruses, SARS-CoV-2, and others could place stress on healthcare systems this fall and winter.” This is especially true of clinical laboratories that still struggle to keep pace with demand for COVID-19 testing.
“COVID cases are expected to rise during the winter. This will be occurring at the same time we expect to see influenza rates increase while we are already seeing an early start to RSV season,” said Dean Blumberg, MD (above), chief of pediatric infectious diseases at UC Davis Children’s Hospital. “With all three viruses on the rise, we are worried about an increase in the rates of viral infection that may lead to an increase in hospitalizations.” Clinical laboratories should prepare for a marked increase in demand for RSV testing, as well as COVID-19 and influenza. (Photo copyright: UC Davis Health.)
Masking, Lockdowns, and Social Distancing Could be Responsible
Every winter in the United States, outbreaks of the flu and RSV occur. However, this year the RSV outbreak appears to be more serious. The CDC warns that “surveillance has shown an increase in RSV detections and RSV-associated emergency department visits and hospitalizations in multiple US regions, with some regions nearing seasonal peak levels.”
The current spread of RSV infections taking place in the US varies from prior outbreaks in notable ways:
Incidents are happening in the fall, whereas RSV outbreaks usually peak starting in late December.
Older children as well as infants are being hospitalized.
Current cases appear to be more severe.
Episodes are rising at a time when pediatric hospitalizations are already higher than usual due to other illnesses like COVID-19, influenza, and biennial enteroviruses.
Some experts believe that masking and social distancing due to the COVID-19 pandemic resulted in a respite of RSV infections in 2020. However, cases intensified in 2021, most likely a result of fewer young children being exposed to RSV during the previous year.
Most children typically have had at least one RSV infection before the age of two and the illness becomes less troublesome as children get older.
“The theory is that everyone’s now back together and this is a rebound phenomenon,” Jeffrey Kline, MD, Associate Chair of Research, Wayne State University School of Medicine in Detroit, told MarketWatch. “If we think about the relative increase—ninefold increase—that’s not nothing, especially in the pediatric [emergency departments]. Holy mackerel.”
Most RSV Infected Children Require Hospitalization
Kline is in charge of a surveillance network that aggregates information regarding incidents of viral infections from 70 US hospitals. The data shows that more children are being hospitalized with COVID-19 than with RSV, but that 5% of children are testing positive for both illnesses. About 60% of children in that group require hospitalization.
According to the CDC, individuals with RSV will typically begin to experience symptoms within four to six days after getting infected. Symptoms of RSV, which tend to appear in stages, include:
Runny nose
Decrease in appetite
Coughing
Sneezing
Fever
Wheezing
“RSV causes a mild cold illness in most people. But it can be very dangerous for very young children and older adults. And young infants are usually the most at risk of hospitalizations in what physicians would call their first RSV season,” said Andrea Garcia, JD, Vice President, Medicine and Public Health, American Medical Association (AMA), in a November 2 AMA update on the current flu season.
“In a pre-pandemic year,” she added, “we would see 1% to 2% of babies younger than six months with an RSV infection maybe needing to be hospitalized. And virtually all children have gotten an RSV infection by the time they’re two-years-old.”
Infants are at a much higher risk of experiencing severe disease due to RSV because their immune systems are not fully developed, and those under six months old are unable to breathe through their mouths if they are congested.
Mejias is studying whether prior exposure to COVID-19 alters how a baby’s immune system reacts to RSV, and if it may lead to more severe illness in those babies.
“That is something to work on and understand,” she said.
Comorbidities and Compromised Immune Systems also a Factor
Older adults and adults with weakened immune systems are predisposed to RSV infections, but there are things people can do to mitigate their chances of becoming ill from RSV.
“[RSV] is spread through contact with droplets from the nose and throat of infected people when they cough or sneeze. It can also be spread through respiratory secretions on surfaces,” said Garcia in the AMA update. “So, it’s a really good idea to clean and disinfect surfaces, especially in areas where young children are constantly touching things. Handwashing is always important. And if you are sick, please stay home.”
She added, “Premature infants, children with certain medical conditions, are also eligible to take a monthly monoclonal antibody treatment during RSV season, and that can help them stay out of the hospital.”
Most RSV infections typically go away on their own within a week or two. But such infections can lead to more severe illnesses, such as bronchiolitis and pneumonia. The more serious cases may require hospitalization with additional oxygen, IV fluids, and even intubation with mechanical ventilation. In most cases, hospitalization only lasts a few days, according to the CDC.
Be Prepared for a Tripledemic
“Health officials are concerned that this could be a sign of what’s to come,” stated Garcia in the AMA update. “A difficult winter, with multiple respiratory viruses circulating.”
For clinical laboratory managers, the early arrival of RSV cases at the front end of this influenza season provides an opportunity to position their labs to better meet the demand for RSV testing. They should also advise their client physicians that there may be a surge of respiratory illnesses during this flu season.
Medical laboratories and anatomic pathologists may need to squeeze into narrow networks to be paid under value-based schemes, especially where Medicare Advantage is concerned
Pathologists have likely heard the arguments in favor of value-based payment versus fee-for-service (FFS) reimbursement models: FFS encourages providers to order medically unnecessary procedures and lab tests. FFS removes incentives for providers to order patient services more carefully. Fraudsters can generate huge volumes of FFS claims that take payers months/years to recognize and stop.
Studies that favor value-based payment schemes support these claims. But do hospitals and other healthcare providers also accept them? And how is value-based reimbursement really doing?
To find out, Chicago-based thought leadership and advisory company 4Sight Health culled data from various organizations’ reports that suggest value-based reimbursement shows signs of growth as well as signs of stagnation.
Value-Based Payment Has Its Ups and Downs
Healthcare journalist David Burda is News Editor and Columnist at 4Sight Health. In his article, “Is Value-Based Reimbursement Mostly Dead or Slightly Alive?” Burda commented on data from various industry reports that indicated value-based reimbursement shows “signs of life.” For example:
More doctors are accepting pay-for-performance payments: 44.5% in 2020, up from 42.3% in 2018, according to an American Medical Association (AMA) biennial report on physician participation in value-based reimbursement, titled, “Policy Research Perspectives: Payment and Delivery in 2020.”
On the other hand, Burda reported that value-based reimbursement also has these declining indicators:
39.3% of provider payments “flowed” through FFS plans in 2020 with no link to cost or quality. This was unchanged since 2019. (HCPLAN report)
19.8% of FFS payments to providers in 2020 were linked to cost or quality, down from 22.5% in 2019. (HCPLAN report)
88% of doctors reported accepting FFS payments in 2019, an increase from 87% in 2018. (AMA report)
Does Today’s Healthcare Industry Support Value-based Care?
A survey of 680 physicians conducted by the Deloitte Center for Health Solutions suggests the answer could be “not yet.” In “Equipping Physicians for Value-Based Care,” Deloitte reported:
“Physician compensation continues to emphasize volume more than value.
“Availability and use of data-driven tools to support physicians in practicing value-based care continue to lag.
“Existing care models do not support value-based care.”
Deloitte analysts wrote, “Physicians increasingly recognize their role in improving the affordability of care. We repeated a question we asked six years ago and saw a large increase in the proportion of physicians who say they have a prominent role in limiting the use of unnecessary treatments and tests: 76% in 2020 vs. 57% in 2014.
“Physicians also recognize that today’s care models are not geared toward value,” Deloitte continued. “They see many untapped opportunities for improving quality and efficiency. They estimate that even today, sizable portions of their work can be performed by nonphysicians (30%) in nontraditional settings (30%) and/or can be automated (18%), creating opportunities for multidisciplinary care teams and clinicians to work at the top of their license.”
Hospital CFOs Also See Opportunities for Value-based Care
This could be problematic for clinical laboratories, according to Robert Michel, Editor-in-Chief of Dark Daily and our sister publication The Dark Report. According to Guidehouse, “Nearly 60% of health systems plan to advance into risk-based Medicare Advantage models in 2022.”
Medicare Advantage (MA) enrollments have escalated over 10 years: 26.4 million people of the 62.7 million eligible for Medicare chose MA in 2021, noted a Kaiser Family Foundation brief that also noted MA enrollment in 2021 was up by 2.4 million beneficiaries or 10% over 2020.
The graph above is taken from the Kaiser Family Foundation report, “Medicare Advantage in 2021: Enrollment Update and Key Trends.” According to the KFF, “In 2021, more than four in 10 (42%) Medicare beneficiaries—26.4 million people out of 62.7 million Medicare beneficiaries overall—are enrolled in Medicare Advantage plans; this share has steadily increased over time since the early 2000s.” Since MA employs narrow networks for its healthcare providers, it’s likely this trend will continue to affect clinical laboratories that may find it difficult to access these providers. (Graphic copyright: Kaiser Family Foundation.)
“The shift from Medicare Part B—where any lab can bill Medicare on behalf of patients for doctor visits and outpatient care, including lab tests—to Medicare Advantage is a serious financial threat for smaller and regional labs that do a lot of Medicare Part B testing. The Medicare Advantage plans often have networks that exclude all but a handful of clinical laboratories as contracted providers,” Michel cautioned. “Moving into the future, it’s incumbent on regional and smaller clinical laboratories to develop value-added services that solve health plans’ pain points and encourage insurers to include local labs in their networks.”
Medical laboratories and anatomic pathology groups need to be aware of this trend. Michel says value-based care programs call on clinical laboratories to collaborate with healthcare partners toward goals of closing care gaps.
“Physicians and hospitals in a value-based environment need a different level of service and professional consultation from the lab and pathology group because they are being incented to detect disease earlier and be active in managing patients with chronic conditions to keep them healthy and out of the hospital,” he added.
Value-based reimbursement may eventually replace fee-for-service contracts. The change, however, is slow and clinical laboratories should monitor for opportunities and potential pitfalls the new payment arrangements might bring.
The No Surprises Act, passed as part of the COVID-19 relief package, ensures patients do not receive surprise bills after out-of-network care, including hospital-based physicians such as pathologists
Consumer demand for price transparency in healthcare has been gaining support in Congress after several high-profile cases involving surprise medical billing received widespread reporting. Dark Daily covered many of these cases over the years.
Now, after initial opposition and months of legislative wrangling, organizations representing medical laboratories and clinical pathologists have expressed support for new federal legislation that aims to protect patients from surprise medical bills, including for clinical pathology and anatomic pathology services.
The new law Congress passed is known as the No Surprises Act (H.R.3630) and is part of the $900 billion COVID relief and government funding package signed by President Trump on December 27.
The law addresses the practice of “balance billing,” in which patients receive surprise bills for out-of-network medical services even when they use in-network providers. An ASCP policy statement noted that “a patient (consumer) may receive a bill for an episode of care or service they believed to be in-network and therefore covered by their insurance, but was in fact out-of-network.” This, according to the ASCP, “occurs most often in emergency situations, but specialties like pathology, radiology, and anesthesiology are affected as well.”
Most portions of the No Surprises Act take effect on January 1, 2022. The law prohibits balance billing for emergency care, air ambulance transport, or, in most cases, non-emergency care from in-network providers. Instead, if a patient unknowingly receives services from an out-of-network provider, they are liable only for co-pays and deductibles they would have paid for in-network care.
New Law Bars Pathologists from Balance Billing without Advance Patient Consent
The law permits balance billing under some circumstances, but only if the patient gives advance consent. And some specialties, including pathologists, are barred entirely from balance billing.
The law also establishes a process for determining how healthcare providers are reimbursed when a patient receives out-of-network care. The specifics of that process proved to be a major sticking point for providers. In states that have their own surprise-billing protections, payment will generally be determined by state law. Otherwise, payers and providers have 30 days to negotiate payment. If they can’t agree, payment is determined by an arbiter as part of an independent dispute resolution (IDR) process.
Early Proposal Drew Opposition
An early proposal to prohibit surprise billing drew opposition from a wide range of medical societies, including the ASCP, CAP, and the American Medical Association (AMA).
All were signatories to a July 29, 2020, letter sent to leaders of the US Senate and House of Representatives urging them to hold off from enacting surprise billing protections as part of COVID relief legislation. Though the groups agreed in principle with the need to protect patients from surprise billing, they contended that the proposed legislation leaned too heavily in favor of insurers, an ASCP news release noted.
“Legislative proposals that would dictate a set payment rate for unanticipated out-of-network care are neither market-based nor equitable, and do not account for the myriad inputs that factor into payment negotiations between insurers and providers,” the letter stated. “These proposals will only incentivize insurers to further narrow their provider networks and would also result in a massive financial windfall for insurers. As such, we oppose the setting of a payment rate in statute and are particularly concerned by proposals that would undermine hospitals and front-line caregivers during the COVID-19 pandemic.”
On December 11, leaders of key House and Senate committees announced agreement on a bipartisan draft of the bill that appeared to address these concerns, including establishment of the arbitration process for resolving payment disputes.
However, in a letter sent to the committee chairs and ranking members, the AHA asked for changes in the dispute-resolution provisions, including a prohibition on considering Medicare or Medicaid rates during arbitration. “We are concerned that the IDR process may be skewed if the arbiter is able to consider public payer reimbursement rates, which are well known to be below the cost of providing care,” the association stated. However, legislators agreed to the change after last-minute negotiations.
“The AHA is pleased that Congress rejected approaches that would impose arbitrary rates on providers, which could have significant consequences far beyond the scope of surprise medical bills and impact access to hospital care,” AHA President and CEO Rick Pollack (above) said in a statement. “We also applaud Congress for rejecting attempts to base rates on public payers.” (Photo copyright: American Hospital Association.)
Dispute Resolution for Pathologists
The CAP also expressed support for the final bill. In a statement, CAP noted that “As the legislation evolved during the 116th Congress, CAP members met with their federal lawmakers to discuss the CAP’s policy priorities.
“Through the CAP’s engagement and collaboration with other physician associations, the legislation improved drastically,” the CAP stated. “Specifically, the CAP lobbied Congress to hold patients harmless, establish a fair reimbursement formula for services provided, deny insurers the ability to dictate payment, create an independent dispute resolution (IDR) process that pathologists can participate in, and require network adequacy standards for health insurers.”
As laboratory testing was identified by thousands of respondents to the University of Chicago survey as the top surprise bill, it is likely that billing and transparency in charges for clinical pathologist and anatomic pathologist will continue to be scrutinized by law makers and healthcare associations.
