Single genetic test can identify multiple pathogens and can be used by the UCSF clinical laboratory team to help physicians identify difficult to diagnose diseases
Continuing improvements in gene sequencing technologies and analytical software tools are enabling clinical laboratorians to diagnosis patients who have challenging symptoms. One such example is a new genomic test developed by researchers at University California, San Francisco (UCSF). The single test analyzes both RNA and DNA to detect almost any type of pathogen that may be the cause of specific illnesses.
The test uses a genomic sequencing technique known as metagenomics next-generation sequencing (mNGS). It works by sequencing genetic material found in blood, tissue, or body fluid samples and compares the sequenced data against a broad database of known pathogens to seek a match. Instead of looking for just one pathogen at a time, mNGS analyzes all of the nucleic acids, RNA, and DNA present in a sample simultaneously to detect nearly all pathogens, including viruses, bacteria, fungi, and parasites.
The mNGS test is not intended to replace existing clinical laboratory tests, but to help physicians diagnose an illness in cases where patients are experiencing severe symptoms, and where initial, commonplace tests are ineffective. In such cases, medical professionals require additional information to achieve a proper diagnosis.
“Our technology is deceptively simple,” said Charles Chiu, MD, PhD (above), professor of laboratory medicine and infectious diseases at UCSF and senior author of the studies in a news release. “By replacing multiple tests with a single test, we can take the lengthy guesswork out of diagnosing and treating infections.” The new technology may help physicians diagnose patients who have challenging symptoms and where current clinical laboratory testing is ineffective at identifying specific pathogens. (Photo copyright: University California San Francisco.)
Diagnostic Armamentarium for Physicians
According to an article published by the American Society for Microbiology (ASM) titled, “Metagenomic Next Generation Sequencing: How Does It Work and Is It Coming to Your Clinical Microbiology Lab?” mNGS is “running all nucleic acids in a sample, which may contain mixed populations of microorganisms, and assigning these to their reference genomes to understand which microbes are present and in what proportions. The ability to sequence and identify nucleic acids from multiple different taxa [plural for taxon] for metagenomic analysis makes this a powerful new platform that can simultaneously identify genetic material from entirely different kingdoms of organisms.”
The researchers developed the mNGS test years ago and it has produced promising results, including:
Diagnosing cases of encephalitis in transplant recipients to yellow fever in their organ donors.
Helping to identify the cause of a meningitis outbreak in Mexico among surgical patients.
Detecting a case of leptospirosis in a patient who was in a medically induced coma, which prompted doctors to prescribe penicillin and resulted in the full recovery of the patient.
Identifying the cause of neurological infections such as meningitis and encephalitis. The test successfully diagnosed 86% of neurological infections in more than 4,800 spinal fluid samples.
“Our mNGS test performs better than any other category of test for neurologic infections,” said Charles Chiu, MD, PhD, professor of laboratory medicine and infectious diseases at UCSF and senior author of the two studies, in a UCSF news release. “The results support its use as a critical part of the diagnostic armamentarium for physicians who are working up patients with infectious diseases.”
FDA Breakthrough Device Designation
The UCSF test has not yet been approved by the federal Food and Drug Administration (FDA), but it was granted a “breakthrough device” designation by the agency. This classification authorizes labs to use the test as a valid diagnosis method due to its potential ability to benefit patients.
Chiu told NBC News that the test costs about $3,000 per sample and fewer than 10 labs routinely use it due to several issues.
“Traditionally, it’s been used as a test of last resort, but that’s primarily because of issues involving, for instance, the cost of the test, the fact that it’s only available in specialized reference laboratories, and it also is quite laborious to run,” he said.
This type of lab testing is not feasible for most hospitals as it is costly and complicated, and because physicians may need assistance from clinical laboratory personnel who have the appropriate expertise to properly read test results.
“This just is not something that a clinical lab will be doing until somebody commercially puts it in a box with an easy button,” Susan Butler-Wu, PhD, associate professor of clinical pathology at the University of Southern California (USC), told NBC News. “It’s not a one-stop shop. It just can be helpful as an additional tool.”
Although the technology has some limitations, Chiu says the research performed by his team “raises the possibility that we perhaps should be considering running this test earlier” in symptomatic patients. He hopes the test will be used on a widespread basis in hospitals to diagnose various illnesses in the future.
“We need to get the cost down and we need to get the turnaround times down as well,” he told NBC.
Definitive Tool for Pathogen Detection
To increase access to the technology, Chiu and his colleagues founded Delve Bio, which is now the exclusive provider of the mNGS tool created at UCSF. In December, the company announced the commercial launch of Delve Detect, a metagenomic test for infectious diseases. According to its website, Delve Detect “offers genomic testing of cerebrospinal fluid (CSF) for more than 68,000 pathogens, with 48-hour turnaround time and metagenomics experts readily available to discuss results.”
“These findings support including mNGS as a core tool in the clinical workup for CNS [central nervous system] infections,” said Steve Miller, MD, PhD, UCSF volunteer clinical professor, laboratory medicine, and chief medical officer of Delve Bio in the UCSF news release. “mNGS offers the single most unbiased, complete and definitive tool for pathogen detection. Thanks to its ability to quickly diagnose an infection, mNGS helps guide management decisions and treatment for patients with meningitis and encephalitis, potentially reducing healthcare costs down the line.”
This mNGS test may prove to have the potential to greatly improve medical care for some infections and possibly expedite the detection of new viral threats. It is probable that clinical laboratories will soon be learning about and performing more tests of this nature in the future.
New guidelines come on the heels of recommendations covering post-market modifications to AI products, including those incorporated into systems used by clinical laboratories
Artificial intelligence (AI) is booming in healthcare, and as the technology finds its way into more medical devices and clinical laboratory diagnostic test technologies the US Food and Drug Administration (FDA) has stepped up its efforts to provide regulatory guidance for developers of these products. This guidance will have an impact on the development of new lab test technology that uses AI going forward.
In December, the FDA issued finalized recommendations for submitting information about planned modifications to AI-enabled healthcare products. Then, in January, the federal agency issued draft guidance that covers product management and marketing submission more broadly. It is seeking public comments on the latter document through April 7.
“The FDA has authorized more than 1,000 AI-enabled devices through established premarket pathways,” said Troy Tazbaz, director of the Digital Health Center of Excellence at the FDA’s Center for Devices and Radiological Health, in a press release announcing the draft guidance.
This guidance “would be the first to provide total product life cycle recommendations for AI-enabled devices, tying together all design, development, maintenance and documentation recommendations, if and when finalized,” Healthcare IT News reported.
“Today’s draft guidance brings together relevant information for developers, shares learnings from authorized AI-enabled devices, and provides a first point-of-reference for specific recommendations that apply to these devices, from the earliest stages of development through the device’s entire life cycle,” said Troy Tazbaz (above), director of the Digital Health Center of Excellence at the FDA Center for Devices and Radiological Health, in a press release. The new guidance will likely affect the development of new clinical laboratory diagnostic technologies that use AI. (Photo copyright: LinkedIn.)
Engaging with FDA
One key takeaway from the guidance is that manufacturers “should engage with the FDA early to ensure that the testing to support the marketing submission for an AI-enabled device reflects the agency’s total product lifecycle, risk-based approach,” states an analysis from consulting firm Orrick, Herrington and Sutcliffe LLP.
Another key point is transparency, Orrick noted. For example, manufacturers should be prepared to offer details about the inputs and outputs of their AI models and demonstrate “how AI helps achieve a device’s intended use.”
Manufacturers should also take steps to avoid bias in data collection for these models. For example, they should gather evidence to determine “whether a device benefits all relevant demographic groups similarly to help ensure that such devices are safe and effective for their intended use,” Orrick said.
New Framework for AI in Drug Development
On the same day that FDA announced the device guidelines, the agency also proposed a framework for regulating use of AI models in developing drugs and biologics.
“AI can be used in various ways to produce data or information regarding the safety, effectiveness, or quality of a drug or biological product,” the federal agency stated in a press release. “For example, AI approaches can be used to predict patient outcomes, improve understanding of predictors of disease progression and process, and analyze large datasets.”
The press release noted that this is the first time the agency has proposed guidance on use of AI in drug development.
These include “bias and reliability problems due to variability in the quality, size, and representativeness of training datasets; the black-box nature of AI models in their development and decision-making; the difficulty of ascertaining the accuracy of a model’s output; and the dangers of data drift and a model’s performance changing over time or across environments. Any of these factors, in FDA’s thinking, could negatively impact the reliability and relevancy of the data sponsors provide FDA.”
The FDA also plans to participate in direct testing of AI-enabled healthcare tools. In October, the FDA and the Department of Veterans Affairs (VA) announced that they will launch “a joint health AI lab to evaluate promising emerging technologies,” according to Nextgov/FCW.
Elnahal said the facility will allow federal agencies and private entities “to test applications of AI in a virtual lab environment.” The goal is to ensure that the tools are safe and effective while adhering to “trustworthy AI principles,” he said.
“It’s essentially a place where you get rapid but effective evaluation—from FDA’s standpoint and from VA’s standpoint—on a potential new application of generative AI to, number one, make sure it works,” he told Nextgov/FCW.
He added that the lab will be set up with safeguards to ensure that the technologies can be tested safely.
“As long as they go through the right security protocols, we’d essentially be inviting parties to test their technology with a fenced off set of VA data that doesn’t have any risk of contagion into our actual live systems, but it’s still informative and simulated,” he told Nextgov/FCW.
There has been an explosion in the use of AI, machine learning, deep learning, and natural language processing in clinical laboratory diagnostic technologies. This is equally true of anatomic pathology, where AI-powered image analysis solutions are coming to market. That two federal agencies are motivated to establish guidelines on working relationships for evaluating the development and use of AI in healthcare settings tells you where the industry is headed.
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.
These advances in the battle against cancer could lead to new clinical laboratory screening tests and other diagnostics for early detection of the disease
As Dark Daily reported in part one of this story, the World Economic Forum (WEF) has identified 12 new breakthroughs in the fight against cancer that will be of interest to pathologists and clinical laboratory managers.
As we noted in part one, the WEF originally announced these breakthroughs in an article first published in May 2022 and then updated in October 2024. According to the WEF, the World Health Organization (WHO) identified cancer as a “leading cause of death globally” that “kills around 10 million people a year.”
The WEF is a non-profit organization base in Switzerland that, according to its website, “engages political, business, academic, civil society and other leaders of society to shape global, regional and industry agendas.”
Monday’s ebrief focused on four advances identified by WEF that should be of particular interest to clinical laboratory leaders. Here are the others.
Personalized Cancer Vaccines in England
The National Health Service (NHS) in England, in collaboration with the German pharmaceutical company BioNTech, has launched a program to facilitate development of personalized cancer vaccines. The NHS Cancer Vaccine Launch Pad will seek to match cancer patients with clinical trials for the vaccines. The Launch Pad will be based on messenger ribonucleic acid (mRNA) technology, which is the same technology used in many COVID-19 vaccines.
The BBC reported that these cancer vaccines are treatments, not a form of prevention. BioNTech receives a sample of a patient’s tumor and then formulates a vaccine that exposes the cancer cells to the patient’s immune system. Each vaccine is tailored for the specific mutations in the patient’s tumor.
“I think this is a new era. The science behind this makes sense,” medical oncologist Victoria Kunene, MBChB, MRCP, MSc (above), trial principal investigator from Queen Elizabeth Hospital Birmingham (QEHB) involved in an NHS program to develop personalized cancer vaccines, told the BBC. “My hope is this will become the standard of care. It makes sense that we can have something that can help patients reduce their risk of cancer recurrence.” These clinical trials could lead to new clinical laboratory screening tests for cancer vaccines. (Photo copyright: Queen Elizabeth Hospital Birmingham.)
Seven-Minute Cancer Treatment Injection
NHS England has also begun treating eligible cancer patients with under-the-skin injections of atezolizumab, an immunotherapy marketed under the brand name Tecentriq, Reuters reported. The drug is usually delivered intravenously, a procedure that can take 30 to 60 minutes. Injecting the drug takes just seven minutes, Reuters noted, saving time for patients and cancer teams.
The drug is designed to stimulate the patient’s immune system to attack cancer cells, including breast, lung, liver, and bladder cancers.
AI Advances in India
One WEF component—the Center for the Fourth Industrial Revolution (C4IR)—aims to harness emerging technologies such as artificial intelligence (AI) and virtual reality. In India, the organization says the Center is seeking to accelerate use of AI-based risk profiling to “help screen for common cancers like breast cancer, leading to early diagnosis.”
Researchers are also exploring the use of AI to “analyze X-rays to identify cancers in places where imaging experts might not be available.”
Using AI to Assess Lung Cancer Risk
Early-stage lung cancer is “notoriously hard to detect,” WEF observed. To help meet this challenge, researchers at Massachusetts Institute of Technology (MIT) developed an AI model known as Sybil that analyzes low-dose computed tomography scans to predict a patient’s risk of getting the disease within the next six years. It does so without a radiologist’s intervention, according to a press release.
Using Genomics to Identify Cancer-Causing Mutations
In what has been described as the “largest study of whole genome sequencing data,” researchers at the University of Cambridge in the UK announced they have discovered a “treasure trove” of information about possible causes of cancer.
Using data from England’s 100,000 Genomes Project, the researchers analyzed the whole genome sequences of 12,000 NHS cancer patients.
This allowed them “to detect patterns in the DNA of cancer, known as ‘mutational signatures,’ that provide clues about whether a patient has had a past exposure to environmental causes of cancer such as smoking or UV light, or has internal, cellular malfunctions,” according to a press release.
The researchers also identified 58 new mutational signatures, “suggesting that there are additional causes of cancer that we don’t yet fully understand,” the press release states.
The study appeared in April 2022 in the journal Science.
Validation of CAR-T-Cell Therapy
CAR-T-cell therapy “involves removing and genetically altering immune cells, called T cells, from cancer patients,” WEF explained. “The altered cells then produce proteins called chimeric antigen receptors (CARs), which can recognize and destroy cancer cells.”
The therapy appeared to receive validation in 2022 when researchers at the University of Pennsylvania published an article in the journal Nature noting that two early recipients of the treatment were still in remission after 12 years.
However, the US Food and Drug Administration (FDA) announced in 2023 that it was investigating reports of T-cell malignancies, including lymphoma, in patients who had received the treatment.
WEF observed that “the jury is still out as to whether the therapy is to blame but, as a precaution, the drug packaging now carries a warning.”
Breast Cancer Drug Repurposed for Prevention
England’s NHS announced in 2023 that anastrozole, a breast cancer drug, will be available to post-menopausal women to help reduce their risk of developing the disease.
“Around 289,000 women at moderate or high risk of breast cancer could be eligible for the drug, and while not all will choose to take it, it is estimated that if 25% do, around 2,000 cases of breast cancer could potentially be prevented in England, while saving the NHS around £15 million in treatment costs,” the NHS stated.
The tablet, which is off patent, has been used for many years to treat breast cancer, the NHS added. Anastrozole blocks the body’s production of the enzyme aromatase, reducing levels of the hormone estrogen.
Big Advance in Treating Cervical Cancer
In October 2024, researchers announced results from a large clinical trial demonstrating that a new approach to treating cervical cancer—one that uses currently available therapies—can reduce the risk of death by 40% and the risk of relapsing by 36%.
“This is the biggest improvement in outcome in this disease in over 20 years,” said Mary McCormack, PhD, clinical oncologist at the University College London and lead investigator in the trial.
The scientists published their findings in The Lancet.
Pathologists and clinical lab managers will want to keep track of these 12 breakthrough advancements in the diagnosis and treatment of cancer highlighted by the WEF. They will likely lead to new screening tests for the disease and could save many lives.
Clinical laboratory executives and pathology leaders may want to develop strategies for supporting the growing numbers of at-home screening and diagnostic test users
Findings of a national poll conducted by the University of Michigan (U-M) exploring consumers’ purchases suggests seniors are becoming more comfortable with ordering and using at-home medical testing. Their choice of tests and opinions may be of interest to clinical laboratory executives, pathologists, and primary care physicians considering programs to support self-test purchasers.
The researchers found that 48% of adults, ages 50 to 80, purchased at least one at-home medical test, and that 91% of the buyers indicated intentions to purchase another test in the future, according to a U-M news release.
In their paper, they note that “validity, reliability, and utility of at-home tests is often uncertain.” Further, understanding and responding to test results—especially since caregivers may not have ordered them—could lead to “a range of unintended consequences,” they wrote.
“As a primary care doctor, I would want to know why my patient chose to take an at-home test that I didn’t order for them. We also need to understand in greater detail why folks use at-home tests instead of traditional means, beyond convenience,” said the U-M study’s lead author Joshua Rager, MD, a research scientist at William M. Tierney Center for Health Services Research at Regenstrief Institute, who is now an assistant professor of medicine, Indiana University, in a news release. The findings of the U-M study will be of interest to clinical laboratory executives and pathology leaders. (Photo copyright: Regenstrief Institute.)
Free COVID-19 Tests Ignite At-Home Testing
In their Journal of Health Care paper, the U-M researchers speculate that curiosity in at-home testing may have been propelled by the offer of free COVID-19 tests by the US government starting in 2021 during the pandemic.
They also noted the different ways at-home test kits are performed by healthcare consumers. Some, such as COVID-19 rapid antigen tests, return results to users in a few moments similar to pregnancy tests. Others involve self-collecting specimens, such as a stool sample, then sending the specimen to a clinical laboratory for analysis and results reporting to physicians.
Of those older adults who participated in U-M’s National Poll on Healthy Aging study, the following bought at-home medical tests online or from pharmacies and supermarkets, according to U-M’s paper:
As to perceptions of at-home medical testing by users, when polled on their test experience, the surveyed seniors reported the following:
75.1% perceived at-home medical tests to be more convenient than conventional medical tests.
59.9% believe the tests “can be trusted to give reliable results.”
54.8% believe the tests “are regulated by government.”
66% called them a “good value.”
93.6% indicated results “should be discussed with my doctor.”
Inconsistency in how people shared test results with their healthcare providers was a concern voiced by the researchers.
“While nearly all patients who had bought an at-home cancer screening test shared the results with their primary care provider, only about half of those who tested for an infection other than COVID-19 had. This could have important clinical implications,” the researchers wrote in their paper.
Confusion over Government Regulation
The U-M study also revealed consumer misunderstanding about government regulation of at-home clinical laboratory tests purchased over-the-counter.
The US Food and Drug Administration (FDA) cleared “some diagnostic at-home tests for over-the counter use. But many tests on the market are unregulated or under-regulated,” the authors wrote, adding, “Our results suggest, however, that patients generally believe at-home tests are regulated by government, but a substantial minority did not, which may reflect public confusion in how at-home testing is regulated.”
Women, College-Educated Buy More At-Home Tests
Purchase of at-home tests varies among groups, as follows, the news release noted:
56% and 61% of older adults with a college degree or household income above $100,000, respectively, were “much more likely” to buy at-home tests than people in other income and education brackets.
87% of women would buy at-home tests again compared with 76% of men.
89% of college-educated people would purchase the tests again, compared with 78% of people with high school educations or less.
Future U-M research may explore consumers’ awareness/understanding concerning federal regulations of at-home testing, Rager noted.
“At-home tests could be used to address disparities in access to care. We hope these findings will inform regulators and policymakers and spark future research on this topic,” he said in the news release.
The U-M Institute for Healthcare Policy and Innovation survey results confirm that the country’s senior generations are becoming comfortable with at-home and self-testing options. As Dark Daily has previously suggested, clinical laboratories may want to develop service offerings and a strategy for supporting patients who want to perform their own lab tests at home.
