Organizations representing clinical laboratories and other critical healthcare providers urged Congress to pass the Saving Access to Laboratory Services Act by January 1, 2023, to prevent deep cuts in reimbursements
Lessons about the essential role of clinical laboratories during a pandemic was the central theme in a significant publication released recently. The authors were the presidents of two of the nation’s largest healthcare companies and their goal was to connect the value clinical labs delivered during the COVID-19 pandemic to the financial threat labs face should the Protecting Access to Medicare Act of 2014 (PAMA) fee cuts coming to the Medicare Part B Clinical Laboratory Fee Schedule (CLFS) be implemented.
In an article for RealClearPolicy, healthcare executives William G. Morice II, MD, PhD (left), CEO/President, Mayo Clinic Laboratories, and Matt Sause (right), President of Roche Diagnostics North America wrote, “Without PAMA reform, labs could face drastically reduced reimbursement for commonly performed lab tests for a host of diseases.” (Photo copyrights: Mayo Clinic Laboratories/Roche Diagnostics.)
IVD Companies and Clinical Laboratories Sound Alarm
Morice and Sause warn that—without PAMA reform—the nation’s vital medical laboratories will face “drastically reduced reimbursement” for commonly performed lab tests for diseases, including diabetes, heart disease, and cancer. Reimbursement cuts may cause clinical labs serving “the most vulnerable and homebound” to reduce services or close, they noted.
“To emerge from nearly three years of a pandemic by sending the signal that austerity is our nation’s health policy when it comes to testing and diagnostics would be a significant mistake,” they wrote.
“If the proposed cuts to reimbursements for diagnostic tests are allowed to take effect, disparities caused by challenges with accessing diagnostic tests will likely grow even further,” the authors continued.
However, they added, “The Saving Access to Laboratory Services Act [SALSA] would reform PAMA to require accurate and representative data from all laboratory segments that serve Medicare beneficiaries to be collected to support a commonsense Medicare fee schedule that truly represents the market.”
How PAMA Affects Clinical Laboratory Reimbursements
PAMA, which became law in 2014, was aimed at marrying Medicare Part B Clinical Laboratory Fee Schedule (CLFS) reimbursement rates to rates medical laboratories receive from private payers, the National Independent Laboratory Association (NILA) explained in a news release.
But from the start, in its implementation of the PAMA statute, the methods used by the federal Centers for Medicare and Medicaid Services (CMS) to collect data on lab test prices paid by private payers—which were the basis for calculating new lab test prices for the Medicare program—were criticized by many laboratory professionals and other health experts.
Critics frequently pointed out that several types of clinical laboratories were excluded from reporting their private payer lab test prices. Thus, the data collected and used by CMS did not accurately represent the true range of prices paid for clinical lab tests by private health insurance plans, said lab industry groups.
CMS regulations “exclude most hospital outreach laboratories and physician office laboratories from data collection. This approach depresses median prices and has led to deep cuts to lab reimbursement. Many tests were cut up to 30% in 2018 when the new system went into effect,” the America Association for Clinical Chemistry (AACC) noted in a statement.
On September 8, just weeks after publication of the article authored by Morice and Sause, 26 organizations representing clinical laboratories and diagnostics manufacturers sent a letter to Congressional leaders. In it they described the financial impact on labs due to the current law’s omission of some outreach and physician office lab testing, and they urged the passage of the SALSA legislation.
“The significant under-sampling led to nearly $4 billion in cuts to those labs providing the most commonly ordered test services for Medicare beneficiaries,” the organizations wrote in their letter. “For context, the total CLFS spend for 2020 was only $8 billion.”
Reimbursement Cuts to Lab Tests are Coming if SASLA Not Passed
“Without Congressional action, beginning on Jan. 1, 2023, laboratories will face additional cuts of as much as 15% to some of the most commonly ordered laboratory tests,” the NILA said.
“Enactment of the Saving Access to Laboratory Services Act (SALSA/H.R. 8188/S.4449) is urgently needed this year, to allow laboratories to focus on providing timely, high quality clinical laboratory services for patients, continuing to innovate, and building the infrastructure necessary to protect the public health,” NILA added.
In an editorial she wrote for Clinical Lab Products, titled, “Be a Labvocate: Help Pass SALSA Legislation,” Kristina Martin, Clinical Pathology Operations Director, Department of Pathology, University of Michigan Medicine said, “The SALSA legislation provides a permanent, pragmatic approach to evaluating the CLFS, eliminating huge swings, either positive or negative as it pertains to Medicare reimbursement. It also allows for a more comprehensive evaluation of data to be collected from a broader sampling of laboratory sectors.”
Uses statistical sampling for widely available tests performed by a “representative pool of all clinical laboratory market segments.”
Introduces annual “guardrails” aimed at creating limits for reductions as well as increases in CLFS rates.
Excludes Medicaid managed care rates since they are not true “market rates.”
Gives labs the option to exclude mailed remittances from reporting if less than 10% of claims.
Eases clinical labs’ reporting requirements by changing data collection from three years to four.
Make Your Views Known
Proponents urge Congress to act on SALSA before the end of the year. Clinical laboratory leaders and pathologists who want to express their views on SALSA, test reimbursement, and the importance of access to medical laboratory testing can do so through Stop Lab Cuts.org. The website is sponsored by the ACLA.
Goal is to demonstrate how whole human genome sequencing of newborns can deliver important diagnostic findings associated with 250 genetic conditions
Clinical laboratory testing and genetics are moving closer to the delivery room than ever before. In the largest study of its kind in North America, genomic scientists plan to supplement traditional screening for inherited diseases—traditionally performed on a blood sample taken shortly after birth—with whole genome sequencing (WGS) on 100,000 newborns in New York City during their first five years of life, LifeSciencesIntelligence reported.
Conducted by genetic scientists at NewYork-Presbyterian (NYP) and Columbia University, in collaboration with genetic company GeneDx, a wholly-owned subsidiary of health intelligence company Sema4 (NASDAQ:SMFR), the genetic research study, called GUARDIAN (Genomic Uniform-screening Against Rare Diseases In All Newborns), will screen newborn babies for 250 rare diseases that are generally not tested for.
The GUARDIAN program will “drive earlier diagnosis and treatment to improve the health of the babies who participate, generate evidence to support the expansion of newborn screening through genomic sequencing, and characterize the prevalence and natural history of rare genetic conditions,” according to a Sema4 news release.
“The appetite for this is growing. The awareness of this is growing. We all see it as inevitable,” medical geneticist Robert Green, MD, at Brigham and Women’s Hospital and Harvard Medical School told USA Today. “We are grossly underutilizing the life-saving benefits of genetics and we have to get past that.” Clinical laboratory leaders understand the value of early detection of disease and subsequent early treatment. (Photo copyright: Harvard Medical School.)
Improving Health of Babies Through Early Detection of Disease
GUARDIAN aims to use WGS to identify conditions at birth that can affect long-term health and subsequently enhance treatment options and possibly prevent disability or death.
The 250 different diseases GUARDIAN will be screening for typically strike young children. They are mostly rare conditions that:
have an onset before five years of age,
have a greater than 90% probability of the condition developing based on the genetic result,
have effective approaches and treatments that are already available, and/or
have a well-established natural history of the condition.
“We’re entering the therapeutic era and leaving the diagnostic era,” Paul Kruszka, MD, Chief Medical Officer at GeneDx told USA Today. “This potentially has the opportunity to change the way we practice medicine, especially in rare disease.”
Some Parents Reluctant to Agree to Genetic Testing
Green and his research team first began analyzing the genetic sequences of newborns back in 2013. They believe the costs of performing infant WGS is worthwhile because it can improve lives. However, Green also recognizes that some parents are reluctant to agree to this type of genetic testing due to concerns regarding privacy and the fear of discovering their baby may have an illness.
“You’ve gone through all this pregnancy and you’re sitting there with a healthy baby (and I’m) offering you the opportunity to find out something that’s devastating and terrifying,” he told USA Today. “How fun is that?”
Green continued. “We can respect people who don’t want to know, but also respect people who do want to know. Some families will say ‘I treasure the precious ignorance.’ Others will say ‘If I could have known, I would have poured my heart and soul into clinical trials or spent more time with the child when she was healthy.’”
WGS Screening Identifies Undiagnosed Illnesses in Newborn’s Family
The scientists also found that performing WGS in newborns can detect diseases in the infants as well as unknown illnesses in the families of those babies. According to Kruszka, many parents often seek a diagnosis for a rare disease present in their children for several years. Since many common diseases develop as a result of certain combinations of genes, if illnesses are diagnosed at birth, it could extradite the treatment process, prevent complications, and provide better health outcomes for patients.
“We are relentlessly focused on accelerating the adoption and use of genomic information to impact the lives of as many people as possible, particularly newborns and children,” said Katherine Stueland, President and CEO, Sema4, in the Sema4 news release. “As the first commercial laboratory to launch a rapid whole genome sequencing offering, to address broad unmet needs for early diagnosis, participation in this study is an important step forward for healthcare and in delivering on our goal to sequence once, analyze forever.”
The study is open to all babies in New York City who are born in a health system that participates in the GUARDIAN program, regardless of their race, income, or health insurance coverage.
“The results from this study will help us understand the true impact sequencing at birth can have on newborns and their families in comparison to the current standard of care, particularly as we’ll evaluate clinical outcomes in addition to the psychosocial effect on families,” said Kruszka in the Sema4 news release.
Anything that improves the health of newborn babies is a good thing. Regardless of the cost, if DNA analysis can give newborns and their families a better chance at detecting inherited diseases early while clinical laboratory treatment could make a difference, it is worth pursuing.
Experts cite high vaccination rates and behavioral changes among at-risk groups, but warn about complacency; clinical laboratories should remain vigilant
In July, Scott Gottlieb, MD, Commissioner of the US Food and Drug Administration (FDA) from May 2017 to April 2019, wrote an op-ed in The New York Times titled, “Monkeypox Is About to Become the Next Public Health Failure.” In it, he wrote, “Our country’s response to monkeypox has been plagued by the same shortcomings we had with COVID-19.” But has it improved? Clinical laboratory leaders and pathology group managers will find it informative to find out what has taken place since Gottlieb made his stark prediction.
The global monkeypox outbreak that emerged last spring appears to have subsided in the US and Europe, though it remains to be seen if the disease can be completely eradicated, according to multiple media reports. As of Oct. 26, 2022, the Centers for Disease Control and Prevention (CDC) reported a 7-day rolling average of 30 cases per day in the US, down from a peak of nearly 440/day in early August.
Cases are also down in cities that earlier reported heavy outbreaks. For example, the New York City Health Department reported a 7-day average of just two cases per day on Oct. 25, compared with 73/day on July 30.
And the San Francisco Department of Public Health announced on Oct. 20 that it would end the city’s public health emergency on monkeypox (MPX) effective on Oct. 31. “MPX cases have slowed to less than one case per day and more than 27,000 San Franciscans are now vaccinated against the virus,” the agency stated in a press release.
“Once again, we caution that a declining outbreak can be the most dangerous outbreak, because it can tempt us to think that the crisis is over and to let down our guard,” said World Health Organization (WHO) Director-General Tedros Adhanom Ghebreyesus, PhD, in an Oct. 12 global press briefing. “That’s not what WHO is doing. We are continuing to work with countries around the world to increase their testing capacity, and to monitor trends in the outbreak.” Clinical laboratories should not assume the outbreak has passed but continue to be vigilant and prepared for increased demand in monkeypox testing. (Photo copyright: ITU Pictures.)
Changing Behavior Lowers Infection Rates
In addition to high vaccination rates, public health experts have attributed the decline to behavioral changes among at-risk groups. “There were really substantial changes among men who have sex [with] men,” infectious disease physician Shira Doron, MD, of Tufts Medical Center in Boston, told ABC News.
On September 2, the CDC published the results of a survey indicating that about half of men who have sex with men “reported reducing their number of sex partners, one-time sexual encounters, and use of dating apps because of the monkeypox outbreak.”
Another likely factor is the disease’s limited transmissibility. “Initially, there was a lot of concern that monkeypox could spread widely at daycares or in schools, but, overall, there has been very little spread among children,” NPR reported.
But citing multiple studies, the NPR story noted “that often there isn’t very much virus in the upper respiratory tract,” where it might spread through talking or coughing. “Instead, the highest levels of virus occur on sores found on the skin and inside the anus.”
These studies, along with earlier research, “explain why monkeypox is spreading almost exclusively through contact during sex, especially anal and oral sex, during the current outbreak,” NPR reported.
Monkeypox Could Mutate, experts say
Despite the promising numbers, public health experts are warning that monkeypox could remain as a long-term threat to public health. According to an article in Nature, “At best, the outbreak might fizzle out over the next few months or years. At worst, the virus could become endemic outside Africa by reaching new animal reservoirs, making it nearly impossible to eradicate.”
In addition to the limited transmissibility of the virus, Nature noted that the outbreak stems from a relatively mild form of the pathogen and is rarely fatal. As of Oct. 28, the CDC reported a total of just six confirmed deaths in the US out of a total of 28,302 confirmed cases since the first infections were reported in May.
It is possible that the virus could mutate into a more contagious form, but Nature noted that monkeypox is a DNA virus, and that they tend to mutate more slowly than RNA viruses such as SARS-CoV-2 and HIV. Nevertheless, University of Alabama at Birmingham School of Medicine bioinformatician Elliot Lefkowitz, PhD, warned that a “worrisome mutation” could arise if the outbreak continues for much longer.
“I have no confidence that all the people who need to be tested are being tested,” she told Nature. She expressed concerns that people could resume risky behavior if they think the danger has passed.
Another question is whether currently available vaccines offer long-lasting protection. And though reported case numbers are down in the US and Europe, they are rising in parts of Africa and South America, Nature noted.
Gottlieb’s Dire Prediction
The decline in new infections followed dire warnings last summer about the possible consequences of the outbreak. In his New York Times op-ed, former Gottlieb criticized the CDC for being slow to test for the virus. He wrote, “[I]f monkeypox gains a permanent foothold in the United States and becomes an endemic virus that joins our circulating repertoire of pathogens, it will be one of the worst public health failures in modern times not only because of the pain and peril of the disease but also because it was so avoidable.”
At the time of his writing, Gottlieb was right to be concerned. On July 29, the CDC reported a seven-day moving average of 390 reported cases per day. According to the federal agency, a reported case “Includes either the positive laboratory test report date, CDC call center reporting date, or case data entry date into CDC’s emergency response common operating platform, DCIPHER.”
Quashing the outbreak, Gottlieb estimated, would have required about 15,000 tests per week among people presenting symptoms resembling monkeypox. But between mid-May and the end of June, he noted, the CDC had tested only about 2,000 samples, according to the federal agency’s July 15 Morbidity and Mortality Weekly Report (MMWR).
As a remedy, Gottlieb called on the Biden administration to re-focus the CDC’s efforts more on disease control “by transferring some of its disease prevention work to other agencies,” including the FDA.
Regulators and lawmakers are considering proposed changes to CLIA and PAMA involving medical laboratory services
Clinical laboratories and pathology groups should monitor a series of federal regulatory developments underway this fall. The proposals and documents will potentially affect how lab managers and staff do their jobs and how much Medicare reimbursement medical laboratories receive for certain diagnostic tests next year.
Among the initiatives under consideration are the following:
Below are details about these laboratory-related federal bills and regulatory documents that observant laboratory managers will want to track in the coming months.
“Clinical laboratories need to make sure that they have proper requisitions and documentation for genetic testing that involves telemedicine.” Danielle Tangorre, JD (above), a partner at law firm Robinson and Cole LLP in Albany, NY, told Dark Daily. (Photo copyright: Robinson and Cole LLP.)
CLIA Fee Increases and Testing Personnel Changes
The federal Centers for Medicare and Medicaid Services (CMS) is examining fee and personnel changes for CLIA. Officials from CMS are reviewing public comments on the proposal ahead of publishing a final rule.
Among other changes, the proposal would:
Institute a 20% across-the-board increase on existing fees.
Establish a biennial increase of CLIA fees for follow-up surveys, substantiated complaint surveys, and revised certificates.
Add doctoral, master’s, and bachelor’s degrees in nursing to qualify testing personnel for high and moderate complexity testing.
“The Practitioner does not have sufficient contact with or information from the purported patient to meaningfully assess the medical necessity of the items or services ordered or prescribed.
“The Telemedicine Company compensates the Practitioner based on the volume of items or services ordered or prescribed, which may be characterized to the Practitioner as compensation based on the number of purported medical records that the Practitioner reviewed.
“The Telemedicine Company only furnishes items and services to Federal health care program beneficiaries and does not accept insurance from any other payor.
“The Telemedicine Company does not expect Practitioners (or another Practitioner) to follow up with purported patients nor does it provide Practitioners with the information required to follow up with purported patients (e.g., the Telemedicine Company does not require Practitioners to discuss genetic testing results with each purported patient).”
And more.
“In the telehealth space, the issue the OIG has flagged is that genetic tests are being ordered without patient interaction or with only brief telephonic conversations,” Danielle Tangorre, JD, a partner at law firm Robinson & Cole LLP in Albany, N.Y., told Dark Daily.
New Bill May Eliminate 2023 Medical Laboratory Payment Cuts Under PAMA
Medical labs and pathology groups face payment cuts of up to 15% for 800 lab tests on the Medicare Clinical Lab Fee Schedule (CLFS) on Jan. 1, 2023, as part of PAMA.
The bill proposes to move regulatory oversight of LDTs from CLIA to the federal Food and Drug Administration (FDA). Champions of the bill argue that FDA regulation is needed for in vitro clinical tests (IVCTs) because they are similar to medical devices and bring with them patient safety concerns.
The bill seemed ready for a Senate vote over the summer but stalled. On Sept. 30, Congress passed a short-term resolution to keep the federal government funded. During negotiation, the VALID Act was removed from the larger spending package, according to Boston law firm Ropes and Gray.
Expect discussion to renew in Congress about the VALID Act after the mid-term elections.
Clinical laboratory leaders and pathology group managers will want to closely monitor the progress of these four federal legislative and regulatory developments. Each of the possible actions described above would significantly change the status quo in the compliance requirements and reimbursement arrangements for both clinical laboratory testing and anatomic pathology services.
There was cautious optimism about the ability of Canada’s medical laboratories to innovate in ways that advance patient care, while recognizing the ongoing challenge of adequate lab staffing and budget constraints
TORONTO, ONTARIO, CANADA—This week, more than 150 leaders representing clinical laboratories, anatomic pathology labs, in vitro diagnostics (IVD) companies, and provincial health officials gathered for the first “Canadian Diagnostic Executive Forum” (CDEF) since 2019. It would be apt to say that the speakers objectively addressed all the good, the bad, and the ugly of Canada’s healthcare system and its utilization of medical laboratory testing services.
Over the two days of the conference, speakers and attendees alike concurred that the two biggest issues confronting clinical laboratories in Canada were inadequate staffing and an unpredictable supply chain. There also was agreement that the steady increase in prices, fueled by inflation, is exacerbating continuing cost increases in both lab salaries and lab supplies.
Canada’s Health System Has Several Unique Attributes
Canada’s healthcare system has two unique attributes that differentiate it from those of other nations. First, healthcare is mandated by a federal law, but generally each of Canada’s 13 provinces and territories operates its own health plan. Thus, the health system in each province and territory may cover a different mix of clinical services, therapeutic drugs, and medical procedures. The federal government typically pays 40% of a province’s health costs and the province funds the balance.
Second, it is a fact that 90% of the Canadian population lives within 150 miles of the United States border. Yet there are provinces with large populations that have geography that ranges from the US border to north of the Arctic Circle. These provinces have a major challenge to ensure equal access to healthcare regardless of where their citizens live.
During day one of the conference, several presentations addressed innovations that supported those labs’ efforts to deliver value and timely insights during the COVID-19 pandemic. For example, a lab team in Alberta launched a research study involving SARS-CoV-2 virus surveillance from the earliest days of the outbreak. This study was presented by Mathew Diggle, PhD, FRCPath, Associate Professor and Program Lead for the Public Health Laboratory (ProvLab) Medical-Scientific Staff at Alberta Precision Laboratories in Edmonton, Alberta.
Study Designed to Identify Coinfections with COVID-19
While performing tens of thousands of COVID-19 tests from the onset of the pandemic, and identifying the emergence of variants, the ProvLab team also tracked co-infection involving other respiratory viruses.
“This is one of the largest eCoV [endemic coronavirus] studies performed during the COVID-19 pandemic,” Diggle said. “This broad testing approach helped to address a pivotal diagnostic gap amidst the emergence of a novel pathogen: cross-reactivity with other human coronaviruses that can cause similar clinical presentations. This broad surveillance enabled an investigation of cross-reactivity of a novel pathogen with other respiratory pathogens that can cause similar clinical presentations.
“Fewer than 0.01% of specimens tested positive for both SARS-CoV-2 and an eCoV,” he explained. “This suggested no significant cross-reactivity between SARS-CoV-2 and eCoVs on either test and provided a SARS-CoV-2 negative predictive value over 99% from an eCoV-positive specimen … The data we collected was highly compelling and the conclusion was that there was no coinfection.”
Chairing the two days of presentations at this weeks’ Canadian Diagnostic Executive Forum was Kevin D. Orr (above), Senior Director of Hospital Business at In-Common Laboratories. He also served on the program for this national conference serving clinical laboratories, anatomic pathology labs, and in vitro diagnostics (IVD) companies throughout Canada. This was the first gathering of this conference since 2019. Attendees were enthusiastic about the future of medical laboratory services in Canada, despite lab staffing shortages and rising costs due to inflation. (Photo copyright The Dark Report.)
Clinical Laboratory Regionalization in Quebec
One of Canada’s largest projects to regionalize and harmonize clinical laboratory services is proceeding in Quebec. Leading this effort is Ralph Dadoun, PhD, Project Director for OPTILAB Montreal, which is part of the Ministry of Health and Social Services in Quebec. The ambitious goal for this project is to move the 123 clinical laboratories within the province into 12 clusters. Initial planning was begun in 2013, so this project is in its ninth year of implementation.
During his presentation, Dadoun explained that the work underway in the 12 clusters involves creating common factors in these categories:
Implementation consistent with and respecting ISO-15189 criteria.
Another notable achievement in Quebec is the progress made to implement a common laboratory information system (LIS) within all 12 clusters. The first three laboratory clusters are undergoing their LIS conversions to the same platform during the next 180 days. The expectation is that use of a common LIS across all clinical laboratory sites in Quebec will unlock benefits in a wide spectrum of lab activities and work processes.
The 2022 CDEF featured speakers from most of the provinces. The common themes in these presentations were the shortage of lab personnel across all technical positions, disruptions in lab supplies, and the need to support the usual spectrum of lab testing services even as lab budgets are getting squeezed.
At the same time, there was plenty of optimism. Presentations involving adoption of digital pathology, advances in early disease detection made possible by new diagnostic technologies, and the expansion of precision medicine showed that clinical laboratories in Canada are gaining tools that will allow them to contribute to better patient care while helping reduce the downstream costs of care.
The Canadian Diagnostics Executive Forum is organized by a team from In-Common Laboratories in North York, Toronto, Ontario. Founded in 1967, it is a private, not-for-profit company that works with public hospitals and laboratory medicine providers. Information about CDEF can be found at its website, where several of this year’s presentations will be available for viewing.
Proof-of-concept study ‘highlights that using AI to integrate different types of clinically informed data to predict disease outcomes is feasible’ researchers say
Artificial intelligence (AI) and machine learning are—in stepwise fashion—making progress in demonstrating value in the world of pathology diagnostics. But human anatomic pathologists are generally required for a prognosis. Now, in a proof-of-concept study, researchers at Brigham and Women’s Hospital in Boston have developed a method that uses AI models to integrate multiple types of data from disparate sources to accurately predict patient outcomes for 14 different types of cancer.
The process also uncovered “the predictive bases of features used to predict patient risk—a property that could be used to uncover new biomarkers,” according to Genetic Engineering and Biotechnology News (GEN).
Should these research findings become clinically viable, anatomic pathologists may gain powerful new AI tools specifically designed to help them predict what type of outcome a cancer patient can expect.
“Experts analyze many pieces of evidence to predict how well a patient may do. These early examinations become the basis of making decisions about enrolling in a clinical trial or specific treatment regimens,” said Faisal Mahmood, PhD (above) in a Brigham press release. “But that means that this multimodal prediction happens at the level of the expert. We’re trying to address the problem computationally,” he added. Should they be proven clinically-viable through additional studies, these findings could lead to useful tools that help anatomic pathologists and clinical laboratory scientists more accurately predict what type of outcomes cancer patient may experience. (Photo copyright: Harvard.)
AI-based Prognostics in Pathology and Clinical Laboratory Medicine
The team at Brigham constructed their AI model using The Cancer Genome Atlas (TCGA), a publicly available resource which contains data on many types of cancer. They then created a deep learning-based algorithm that examines information from different data sources.
Pathologists traditionally depend on several distinct sources of data, such as pathology images, genomic sequencing, and patient history to diagnose various cancers and help develop prognoses.
For their research, Mahmood and his colleagues trained and validated their AI algorithm on 6,592 H/E (hematoxylin and eosin) whole slide images (WSIs) from 5,720 cancer patients. Molecular profile features, which included mutation status, copy-number variation, and RNA sequencing expression, were also inputted into the model to measure and explain relative risk of cancer death.
The scientists “evaluated the model’s efficacy by feeding it data sets from 14 cancer types as well as patient histology and genomic data. Results demonstrated that the models yielded more accurate patient outcome predictions than those incorporating only single sources of information,” states a Brigham press release.
“This work sets the stage for larger healthcare AI studies that combine data from multiple sources,” said Faisal Mahmood, PhD, Associate Professor, Division of Computational Pathology, Brigham and Women’s Hospital; and Associate Member, Cancer Program, Broad Institute of MIT and Harvard, in the press release. “In a broader sense, our findings emphasize a need for building computational pathology prognostic models with much larger datasets and downstream clinical trials to establish utility.”
Future Prognostics Based on Multiple Data Sources
The Brigham researchers also generated a research tool they dubbed the Pathology-omics Research Platform for Integrative Survival Estimation (PORPOISE). This tool serves as an interactive platform that can yield prognostic markers detected by the algorithm for thousands of patients across various cancer types.
The researchers believe their algorithm reveals another role for AI technology in medical care, but that more research is needed before their model can be implemented clinically. Larger data sets will have to be examined and the researchers plan to use more types of patient information, such as radiology scans, family histories, and electronic medical records in future tests of their AI technology.
“Future work will focus on developing more focused prognostic models by curating larger multimodal datasets for individual disease models, adapting models to large independent multimodal test cohorts, and using multimodal deep learning for predicting response and resistance to treatment,” the Cancer Cell paper states.
“As research advances in sequencing technologies, such as single-cell RNA-seq, mass cytometry, and spatial transcriptomics, these technologies continue to mature and gain clinical penetrance, in combination with whole-slide imaging, and our approach to understanding molecular biology will become increasingly spatially resolved and multimodal,” the researchers concluded.
Anatomic pathologists may find the Brigham and Women’s Hospital research team’s findings intriguing. An AI tool that integrates data from disparate sources, analyzes that information, and provides useful insights, could one day help them provide more accurate cancer prognoses and improve the care of their patients.
