Two studies show the accuracy of perception-based systems in detecting disease biomarkers without needing molecular recognition elements, such as antibodies
Researchers from multiple academic and research institutions have collaborated to develop a non-conventional machine learning-based technology for identifying and measuring biomarkers to detect ovarian cancer without the need for molecular identification elements, such as antibodies.
Traditional clinical laboratory methods for detecting biomarkers of specific diseases require a “molecular recognition molecule,” such as an antibody, to match with each disease’s biomarker. However, according to a Lehigh University news release, for ovarian cancer “there’s not a single biomarker—or analyte—that indicates the presence of cancer.
“When multiple analytes need to be measured in a given sample, which can increase the accuracy of a test, more antibodies are required, which increases the cost of the test and the turnaround time,” the news release noted.
Unveiled in two sequential studies, the new method for detecting ovarian cancer uses machine learning to examine spectral signatures of carbon nanotubes to detect and recognize the disease biomarkers in a very non-conventional fashion.
“Carbon nanotubes have interesting electronic properties,” said Daniel Heller, PhD (above), in the Lehigh University news release. “If you shoot light at them, they emit a different color of light, and that light’s color and intensity can change based on what’s sticking to the nanotube. We were able to harness the complexity of so many potential binding interactions by using a range of nanotubes with various wrappings. And that gave us a range of different sensors that could all detect slightly different things, and it turned out they responded differently to different proteins.” This method differs greatly from traditional clinical laboratory methods for identifying disease biomarkers. (Photo copyright: Memorial Sloan-Kettering Cancer Center.)
Perception-based Nanosensor Array for Detecting Disease
In the Science Advances paper, the researchers described their development of “a perception-based platform based on an optical nanosensor array that leverages machine learning algorithms to detect multiple protein biomarkers in biofluids.
“Perception-based machine learning (ML) platforms, modeled after the complex olfactory system, can isolate individual signals through an array of relatively nonspecific receptors. Each receptor captures certain features, and the overall ensemble response is analyzed by the neural network in our brain, resulting in perception,” the researchers wrote.
“This work demonstrates the potential of perception-based systems for the development of multiplexed sensors of disease biomarkers without the need for specific molecular recognition elements,” the researchers concluded.
In the Nature Biomedical Engineering paper, the researchers described a fined-tuned toolset that could accurately differentiate ovarian cancer biomarkers from biomarkers in individuals who are cancer-free.
“Here we show that a ‘disease fingerprint’—acquired via machine learning from the spectra of near-infrared fluorescence emissions of an array of carbon nanotubes functionalized with quantum defects—detects high-grade serous ovarian carcinoma in serum samples from symptomatic individuals with 87% sensitivity at 98% specificity (compared with 84% sensitivity at 98% specificity for the current best [clinical laboratory] screening test, which uses measurements of cancer antigen 125 and transvaginal ultrasonography,” the researchers wrote.
“We demonstrated that a perception-based nanosensor platform could detect ovarian cancer biomarkers using machine learning,” said Yoona Yang, PhD, a postdoctoral research associate in Lehigh’s Department of Chemical and Biomolecular Engineering and co-first author of the Science Advances article, in the news release.
How Perception-based Machine Learning Platforms Work
According to Yang, perception-based sensing functions like the human brain.
“The system consists of a sensing array that captures a certain feature of the analytes in a specific way, and then the ensemble response from the array is analyzed by the computational perceptive model. It can detect various analytes at once, which makes it much more efficient,” Yang said.
“SWCNTs have unique optical properties and sensitivity that make them valuable as sensor materials. SWCNTS emit near-infrared photoluminescence with distinct narrow emission bands that are exquisitely sensitive to the local environment,” the researchers wrote in Science Advances.
“Carbon nanotubes have interesting electronic properties,” said Daniel Heller, PhD, Head of the Cancer Nanotechnology Laboratory at Memorial Sloan Kettering Cancer Center and Associate Professor in the Department of Pharmacology at Weill Cornell Medicine of Cornell University, in the Lehigh University news release.
“If you shoot light at them, they emit a different color of light, and that light’s color and intensity can change based on what’s sticking to the nanotube. We were able to harness the complexity of so many potential binding interactions by using a range of nanotubes with various wrappings. And that gave us a range of different sensors that could all detect slightly different things, and it turned out they responded differently to different proteins,” he added.
The researchers put their technology to practical test in the second study. The wanted to learn if it could differentiate symptomatic patients with high-grade ovarian cancer from cancer-free individuals.
The research team used 269 serum samples. This time, nanotubes were bound with a specific molecule providing “an extra signal in terms of data and richer data from every nanotube-DNA combination,” said Anand Jagota PhD, Professor, Bioengineering and Chemical and Biomolecular Engineering, Lehigh University, in the news release.
This year, 19,880 women will be diagnosed with ovarian cancer and 12,810 will die from the disease, according to American Cancer Society data. While more research and clinical trials are needed, the above studies are compelling and suggest the possibility that one day clinical laboratories may detect ovarian cancer faster and more accurately than with current methods.
Many other healthcare systems also are partnering with private genetic testing companies to pursue research that drive precision medicine goals
It is certainly unusual when a major health network announces that it will give away free genetic tests to 10,000 of its patients as a way to lay the foundation to expand clinical services involving precision medicine. However, pathologists and clinical laboratory managers should consider this free genetic testing program to be the latest marketplace sign that acceptance of genetic medicine continues to move ahead.
Notably, it is community hospitals that are launching this
new program linked to clinical laboratory research that uses genetic tests for
specific, treatable conditions. The purpose of such genetic research is to
identify patients who would benefit from test results that identify the best
therapies for their specific conditions, a core goal of precision medicine.
Clinical laboratory leaders will be interested in this
initiative, as well other partnerships between healthcare systems and private
genetic testing companies aimed at identifying and enrolling patients in
research studies for disease treatment protocols and therapies.
The Future of Precision Medicine
Modern Healthcare reported that data from the WholeMe DNA study, which was funded through donations to the AdventHealth Foundation, also will be used by the healthcare network for research beyond FH, as AdventHealth develops its genomics services. The project’s cost is estimated to reach $2 million.
“Genomics is the future of medicine, and the field is rapidly evolving. As we began our internal discussions about genomics and how to best incorporate it at AdventHealth, we knew research would play a strong role,” Wes Walker MD, Director, Genomics and Personalized Health, and Associate CMIO at AdventHealth, told Becker’s Hospital Review.
“We decided to focus on familial hypercholesterolemia
screening initially because it’s a condition that is associated with
life-threatening cardiovascular events,” he continued. “FH is treatable once
identified and finding those who have the condition can lead to identifying
other family members who are subsequently identified who never knew they had
the disease.”
The AdventHealth Orlando website states that participants in the WholeMe study receive information stored in a confidential data repository that meets HIPAA security standards. The data covers ancestry and 22 other genetic traits, such as:
Asparagus Odor Detection
Bitter Taste
Caffeine Metabolism
Cilantro Taste Aversion
Circadian Rhythm
Coffee Consumption
Delayed Sleep
Earwax Type
Endurance vs Power
Exercise Impact on Weight
Eye Color
Freckling
Hair Curl and Texture
Hand Grip Strength
Height
Lactose Tolerance
Sleep Duration
Sleep Movement
Sleeplessness
Sweet Tooth
Tan vs. Sunburn
Waist Size
Those who test positive for a disease-causing FH variant will be referred by AdventHealth for medical laboratory blood testing, genetic counseling, and a cardiologist visit, reported the Ormond Beach Observer.
One in 250 people have FH, and 90% of them are undiagnosed,
according to the FH Foundation,
which also noted that children have a 50% chance of inheriting FH from parents
with the condition.
AdventHealth plans to expand the free testing beyond central
Florida to its 46 other hospitals located in nine states, Modern Healthcare
noted.
Other Genetics Data Company/Healthcare Provider Partnerships
Helix (above) is one of the world’s largest CLIA-certified, CAP-accredited next-generation sequencing labs. The partnership with AdventHealth offered study participants Exome+: a panel-grade medical exome enhanced by more than 300,000 informative non-coding regions; a co-branded ancestry + traits DNA product for all participants; secure storage of genomic data for the lifetime of the participant; infrastructure and data to facilitate research; and in-house clinical and scientific expertise, according to Helix’s website. (Photo copyright: Orlando Sentinel.)
Business Insider noted that Helix has focused on clinical partnerships for about a year and seems to be filling a niche in the genetic testing market.
“Helix is able to sidestep the costs of direct-to-consumer
marketing and clinical test development, while still expanding its customer
base through predefined hospital networks. And the company is in a prime
position to capitalize on providers’ interest in population health management,”
Business Insider reported.
Ochsner’s program is the first “fully digital population
health program” aimed at including clinical genomics data in primary care in an
effort to affect patients’ health, FierceHealthcare
reported.
Hereditary breast and ovarian cancer due to
mutations in BRCA1 and BRCA2 genes;
Lynch
syndrome, associated with colorectal and other cancers; and
FH.
Color also offers genetic testing and whole genome sequencing services to NorthShore’s DNA10K program, which plans to test 10,000 patients for risk for hereditary cancers and heart diseases, according to news release.
And, Jefferson Health offered Color’s genetic testing to the healthcare system’s 33,000 employees, 10,000 of which signed up to learn their health risks as well as ancestry, a Color blog post states.
“Understanding the genome warning signals of every patient will be an essential part of wellness planning and health management,” said Geisinger Chief Executive Officer David Feinberg, MD, when he announced the new initiative at the HLTH (Health) Conference in Las Vegas. “Geisinger patients will be able to work with their family physician to modify their lifestyle and minimize risks that may be revealed,” he explained. “This forecasting will allow us to provide truly anticipatory healthcare instead of the responsive sick care that has long been the industry default across the nation.”
It will be interesting to see how and if genetic tests—free
or otherwise—will advance precision medicine goals and population health
treatments. It’s important for medical laboratory leaders to be involved in health
network agreements with genetic testing companies. And clinical laboratories should
be informed whenever private companies share their test results data with
patients and primary care providers.
In the same way that BRCA1 and BRCA2 mutations helped pathologists identify women with increased breast cancer risks in the late 1990s, this new study isolates an additional 72 mutations medical laboratories may soon use to diagnose breast cancer and assess risk factors
For 20 years genetic scientists, anatomic pathologists, and medical laboratories have employed the BRCA1/BRCA2 genes to identify women at higher risk for breast cancer. And, because pathologists receive a high number of breast biopsies to diagnose, physicians and clinical laboratories already have collaborative experience working with genetic mutations supported by ample published evidence outlining their relationship with cancer.
Now, a global research study is adding 72 more mutations to the list of mutations already known to be associated with breast cancer.
In coming years, physicians and anatomic pathologists can expect to use the knowledge of these 72 genetic mutations when diagnosing breast cancer and possibly other types of cancers in which these mutations may be involved.
New Precision Medicine Tools to Improve Breast Cancer Survival
Combining the efforts of more than 550 researchers across 300 institutions and six continents, the OncoArray Consortium analyzed the DNA of nearly 300,000 blood samples. The analysis included samples of both estrogen receptor (ER-positive and ER-negative) cases.
Taken from a study published in the British Journal of Cancer, the graph above illustrates “proportions of familial risk of breast cancer explained by hereditary variants.” It is expected that anatomic pathologists will eventually incorporate these genetic variants into diagnostic test for breast and other cancers. (Graphic copyright: British Journal of Cancer.)
The results of their research were published in two separate studies: one in the scientific journal Nature and the other in Nature Genetics. The studies outlined 72 newly isolated genetic mutations that might help quantify the risk of a woman developing breast cancer in her lifetime.
Among the 72 mutations, seven genes were specifically associated with ER-negative cases. ER-negative breast cancer often fails to respond to hormone therapy. Thus, this discovery could be crucial to developing and administering precision medicine therapies tailored to specific patients’ physiologies and conditions. Treatments that improve patient outcomes and overall survival rates in ER-negative and ER-positive breast cancers.
Genetics Could Help Clinical Laboratories Wage War on All Cancers
According to data published by the Centers for Disease Control and Prevention (CDC), breast cancer is the most common form of cancer among women of all races. It’s the second-leading cause of all cancer deaths among most races and first among Hispanic women.
In the past, it was estimated that 5-10% of breast cancers were inherited through the passing of abnormal genes. However, Lisa Schlager, Vice President of community affairs and public policy for FORCE (Facing Our Risk of Cancer Empowered), told CNN, “This new information may mean that that estimate is low.” FORCE is a national nonprofit organization dedicated to fighting hereditary breast, ovarian, and related cancers.
Schlager calls upon health systems to “embrace the ability to use genetic information to tailor healthcare by providing affordable access to the needed screening and preventive interventions.” As precision therapy and genetic analysis continue to shape the way patients are treated, medical laboratories will play a significant role in providing the information powering these innovative approaches.
Identifying Women at Increased Risk for Breast Cancer
Peter Kraft, PhD, Professor of Epidemiology at Harvard’s T.H. Chan School of Public Health, and a study author, told CNN, “Taken together, these risk variants may identify a small proportion of women who are at three-times increased risk of breast cancer.”
Kraft notes that samples were sourced from women of primarily European ancestry. Further study of other ethnic populations could lead to yet more mutations and indicators for cancers more common outside of the European region.
Research authors also highlight the importance of continued standard screening, such as mammograms. However, they suggest that genetic mutations, such as those found in the OncoArray study, might be used to highlight high-risk individuals and screen sooner, or conduct more in-depth genetic analyses, to catch potential cancer cases earlier and improve outcomes.
“Many women are offered mammogram screening when they are middle-aged,” Georgia Chenevix-Trench, PhD, co-author of the Nature Genetics study and researcher at the QIMR Berghofer Medical Research Institute in Australia, told LabRoots. “But if we know a woman has genetic markers that place her at higher risk of breast cancer, we can recommend more intensive screening at a younger age.”
Anatomic pathologists and clinical laboratories can use these new insights to offer increased options for oncologists and physicians on the front lines of the battle against cancer. While the list of genetic mutations related to cancer is far from complete, each added mutation holds the potential to power a new treatment, improve early detection rates, and improve survival rates of this global killer.
The Technion breathalyzer would give pathology groups and medical laboratories unprecedented ability to support physicians in diagnosing and treating cancers, chronic diseases, and other illnesses
Readers of Dark Daily know that several pathology research teams in America and the UK are developing breath analyzer tests that can detect everything from lung cancer to early-stage infections. Clinical laboratories will soon have a plethora of breath-related tests from which to choose. Now there’s a new kid on the block. A breathalyzer test that can detect up to 17 distinct cancerous, inflammatory, and neurological diseases!
Assuming the cost per test was at a competitive level to existing technologies, what would give this new diagnostic system appeal to physicians and patients alike is that it would be a non-invasive way to diagnose disease. Only a sample of the patient’s breath would be needed to perform the assays.
Researchers at the Israel Institute of Technology, or Technion, published the results of their study in ACS Nano, a monthly journal of the American Chemical Society devoted to “nanoscience and nanotechnology research at the interfaces of chemistry, biology, materials science, physics, and engineering.” (more…)
As tests explore genetic markers related to excessive weight gain, and breast and ovarian cancer, companies as well as employees are seeing returns on investment and participation
In a development that is auspicious for medical laboratories, more genetic tests are making their way into more corporate health benefit plans. Big brands—from Aetna to Visa—are partnering with personalized health companies and clinical lab companies doing genetic testing as they support tests to help employees head-off health risks.
Employers’ sponsorship of genetic testing is a trend that could become more common, noted Fortune. But human resources and benefits experts say the offerings are still uncommon. There are also unresolved issues, such as when genetic test results are inconclusive or questionable.
For medical laboratories, the companies’ genetic testing benefits could prompt more test orders from healthcare consumers. Based on the results of their genetic tests, people might decide to make lifestyle changes, work toward prevention of chronic conditions, and take further tests to assess progress. (more…)
