Should further study validate these findings, clinical laboratories managing hospital blood banks would be among the first to benefit from an abundance of universal donor blood
In a surprising outcome for microbiome research, scientists at the Technical University of Denmark (DTU) and Sweden’s Lund University discovered that the bacteria Akkermansia muciniphila, which resides in the human gut, produces enzymes that can be used to process whole blood in ways that could help produce type-O blood. This “universal” blood type can be given to patients during transfusions when other blood types are in short supply.
Receiving the wrong type of blood via a transfusion could result in a fatal reaction where the immune system launches an attack on foreign antigens. As blood bankers and clinical laboratory scientists know, the A antigens in type A blood are not compatible with the B antigens in type B blood. Type-O blood completely lacks these antigens, which explains why it can be used for individuals of any blood type.
The DTU/Lund discovery—still in its initial stages of development—could eventually give blood bankers in hospital laboratories a way to expand their supply of universal type-O blood. Although individuals with type-O blood are universal donors, often the available supply is inadequate to meet the demand.
“For the first time, the new enzyme cocktails not only remove the well-described A and B antigens, but also extended variants previously not recognized as problematic for transfusion safety,” said Maher Abou Hachem, PhD, Professor of Biotechnology and Biomedicine at DTU, one of the authors of the study, in a news release.
Discovering a way that ensures any blood type can donate blood for all blood types could increase the supply of donor blood while reducing the costs and logistics affiliated with storing four separate blood types. Additionally, the production of a universal blood type using gut microorganisms could reduce the waste associated with blood products nearing their expiration dates.
“We are close to being able to produce universal blood from group B donors, while there is still work to be done to convert the more complex group A blood,” said Maher Abou Hachem, PhD (above), Professor of Biotechnology and Biomedicine at DTU in a news release. “Our focus is now to investigate in detail if there are additional obstacles and how we can improve our enzymes to reach the ultimate goal of universal blood production,” he added. Hospital clinical laboratories that manage blood banks will be among the first to benefit from this new process once it is developed and cleared for use in patient care. (Photo copyright: Technical University of Denmark.)
Creating Universal Donor Blood
The bacterium Akkermansia muciniphila is abundant in the guts of healthy humans. It produces valuable compounds, and it is able to break down mucus in the gut and can have significant, positive effects on body weight and metabolic markers.
“What is special about the mucosa is that bacteria, which are able to live on this material, often have tailor-made enzymes to break down mucosal sugar structures, which include blood group ABO antigens. This hypothesis turned out to be correct,” Hachem noted in the DTU news release.
“Instead of doing the work ourselves and synthesizing artificial enzymes, we’ve asked the question: What looks like a red [blood] cell surface? The mucus in our gut does. So, we simply borrowed the enzymes from the bacteria that normally metabolize mucus and then applied them to the red [blood] cells,” Martin Olsson MD, PhD, professor of hematology and transfusion medicine at Lund University, told Live Science. “If you think about it, it’s quite beautiful.”
The researchers successfully identified long strings of sugar structures known as antigens that render one blood type incompatible with another. These antigens define the four blood types: A, B, AB and O. They then used a solution of gut bacteria enzymes to remove the sugar molecules present on the surface of red blood cells (RBCs).
“We biochemically evaluated 23 Akkermansiaglycosyl hydrolases and identified exoglycosidase combinations which efficiently transformed both A and B antigens and four of their carbohydrate extensions,” the study authors wrote in Nature Microbiology. “Enzymatic removal of canonical and extended ABO antigens on RBCs significantly improved compatibility with group O plasmas, compared to conversion of A or B antigens alone. Finally, structural analysis of two B-converting enzymes identified a previously unknown putative carbohydrate-binding module.”
“Universal blood will create a more efficient utilization of donor blood, and also avoid giving ABO-mismatched transfusions by mistake, which can otherwise lead to potentially fatal consequences in the recipient. When we can create ABO-universal donor blood, we will simplify the logistics of transporting and administering safe blood products, while at the same time minimizing blood waste,” Olsson said in the news release.
Future Progress
The researchers have applied for a patent for the enzymes and their method of enzyme treatment. The two educational institutions hope to make further progress on this joint project over the next three years. They eventually hope to test their theory in controlled patient trials and make it available for commercial production and clinical use.
More research and clinical studies are needed to prove the effectiveness of this discovery. Clinical laboratory professionals—particularly those who manage hospital blood banks—will want to follow DTU’s research. It could someday lead to the availability of a more abundant supply of universal donor blood for transfusions.
Study found highest incidences of occupational carcinogenesis among clinical laboratory and histology technicians, followed by pathologists
It has been known for years that formalin (a form of formaldehyde used as a disinfectant and preservative in the handling of tissues samples in anatomy, pathology, and microbiology labs), as well as xylene and toluene, are dangerous to clinical laboratory workers. Nations around the world have taken steps to minimize exposure to these dangerous chemicals. However, a recent study in Iran found that those measures may not have gone far enough to protect histology and clinical laboratory technicians, pathologists, and medical laboratory scientists.
The study conducted by researchers in the Department of Occupational Health Engineering, School of Public Health, at Tehran University of Medical Sciences, showed that levels of exposure to these chemicals is still significantly higher than recommended, resulting in a higher risk for cancer among lab workers in Iran’s hospitals.
“Employing risk assessment techniques as a complementary tool in monitoring programs for respiratory exposure in the different work setting should be considered to protect the staffs against both non-cancerous and cancer-related hazards,” the study authors wrote.
Lessons learned from the Iranian hospital lab study could benefit clinical laboratory workers in US hospitals and help those who work with formaldehyde, toluene, and xylene worldwide to reduce their chances of developing a vascular condition known as Raynaud’s phenomenon (shown above) which can lead to necrosis and gangrene, as well as other dangerous health conditions affecting the lungs, brain, and other systems and organs in the body. (Photo copyright: Wikipedia.)
Study Details
The Iranian study considered the carcinogenic and non-carcinogenic impact of occupational exposure to formaldehyde in the pathology laboratories of four Tehran hospitals. The researchers “used a quantitative risk assessment method proposed by the United States Environmental Protection Agency (EPA), along with its provided database known as the Integrated Risk Information System (IRIS). Respiratory symptoms were assessed using the American Thoracic Society (ATS) questionnaire,” the study authors wrote in NatureScientific Reports.
The scientists found that “91.23% of exposure levels in occupational groups exceed the NIOSH [National Institute for Occupational Safety and Health] standard of 0.016 ppm.” They determined that “41.03% of all the studied subjects were in the definite carcinogenic risk range (LCR > 10−4), 23.08% were in the possible carcinogenic risk range (10−5 < LCR < 10−4), and 35.90% were in the negligible risk range (LCR < 10−6),” they wrote.
“The highest index of occupational carcinogenesis was observed in the group of lab technicians with a risk number of 3.7 × 10-4, followed by pathologists with a risk number of 1.7 × 10-4,” the scientists wrote. “Furthermore, 23.08% of the studied subjects were within the permitted health risk range (HQ < 1.0), while 76.92% were within the unhealthy risk range (HQ > 1.0),” they added.
“Formaldehyde exhibits high solubility in water and is rapidly absorbed by the nasal cavity, sinuses, throat, and mucous membrane of the upper respiratory tract upon exposure,” the study authors wrote. “Consequently, due to the elevated potential for both carcinogenic and non-carcinogenic formaldehyde exposure among pathology staff—particularly laboratory technicians—the implementation of management measures … becomes imperative to lower the exposure levels of all employees below permissible limits.”
Those management measures include:
“Strict guideline adherence and safe work protocols,
“Increasing staff numbers to decrease exposure duration,
“Adoption of engineering solutions such as localized ventilation systems, and
“Use of respiratory protective equipment during sample handling and tissue processing.”
Previous Reports on Exposure Risk to Clinical Lab Workers
The knowledge of the danger behind these chemicals isn’t new.
In 2017, a pathology lab in Auckland, New Zealand, lost its accreditation because formaldehyde levels were so high the lab had to be evacuated nearly every day, The New Zealand Herald reported.
“In epidemiological studies on industrial workers, pathologists and anatomists, the relationship between exposure to formaldehyde and an increased risk of various types of cancer including nasal cavity, nasopharynx, lung, brain, pancreas, prostate, colon and atopic lymphoma system has been determined,” the Iranian scientists wrote in Nature Scientific Reports.
Call for Stronger Regulations
“The Food and Drug Administration (FDA), the Consumer Product Safety Commission (CPSC), and the Environmental Protection Agency have expressed serious concern about the carcinogenicity of formaldehyde,” the Iranian scientists noted, adding that “the potential carcinogenic risk to humans has been studied in a number of cohort and case-control studies.”
There is room for more studies looking at the health effects of exposure to these chemicals among lab workers, as well as continued evaluation of the risks and preventative measures that could be taken. Perhaps tightened regulations will make its way to US labs, echoing more stringent ones of the European Union.
“It is imperative to implement control measures across various hospital departments to mitigate occupational formaldehyde exposure levels proactively. These findings can be valuable for policymakers in the health sector, aiding in the elimination or reduction of airborne formaldehyde exposure in work environments,” the Iranian scientists wrote.
Managers of histology and clinical laboratories may find useful advice in hospital laboratory studies like that coming out of Iran. Protecting the health of lab workers worldwide starts with reducing their exposure to deadly chemicals.
Declining health of UK’s population also affecting performance of the country’s national health service, report notes
England’s National Health Service (NHS) is “in serious trouble” due to long waiting times, outdated technology, misallocated resources, and numerous other problems, with dire consequences for the country’s populace. That’s according to a new report by NHS surgeon and former Health Minister Lord Ara Darzi, OM KBE FRS FMedSci HonFREng, who was tasked by the United Kingdom’s new Labor government to investigate the ailing healthcare system. His report may contain lessons for US healthcare—including clinical laboratories—as well.
“Although I have worked in the NHS for more than 30 years, I have been shocked by what I have found during this investigation—not just in the health service but in the state of the nation’s health,” Darzi stated in a UK government press release. “We want to deliver high quality care for all but far too many people are waiting for too long and in too many clinical areas, quality of care has gone backwards.”
Many of the problems he identified relate to wait times.
“From access to GPs (general practitioners) and to community and mental health services, on to accident and emergency, and then to waits not just for more routine surgery and treatment but for cancer and cardiac services, waiting time targets are being missed,” he wrote in his report.
For example, “as of June 2024, more than one million people were waiting for community services, including more than 50,000 people who had been waiting for over a year, 80% of whom are children and young people,” he wrote.
Accident and emergency care (A/E) “is in an awful state,” the report noted, “with A/E queues more than doubling from an average of just under 40 people on a typical evening in April 2009 to over 100 in April 2024. One in 10 patients are now waiting for 12 hours or more.”
“In the last 15 years, the NHS was hit by three shocks—austerity and starvation of investment, confusion caused by top-down reorganization, and then the pandemic which came with resilience at an all-time low. Two out of three of those shocks were choices made in Westminster,” said NHS surgeon and former Health Minister Lord Ara Darzi in a government press release. “It took more than a decade for the NHS to fall into disrepair so it’s going to take time to fix it. But we in the NHS have turned things around before, and I’m confident we will do it again.” (Photo copyright: Health Data Research UK.)
Delays in Other Critical Tests
Genetic test results are lagging as well. “In 2024, more than 35,000 genomic tests are being completed each month but only around 60% on time,” Darzi wrote.
He also noted that “only around 5% of eligible patients with brain cancer are able to access whole genome sequencing (WGS), which is important for treatment selection.” Just two-thirds (65.8%) get their first treatment within 62 days, and more than 30% wait more than 31 days for radical radiotherapy, according to the report.
Overall, “the UK has appreciably higher cancer mortality rates than other countries, with no progress whatsoever made in diagnosing cancer at stage one and two between 2013 and 2021,” he wrote.
Patients have also experienced delays in access to cardiovascular treatment. For example, in 2013-2014, high-risk heart attack patients waited an average of 114 minutes for intervention to unblock an artery, Darzi noted in his report. However, in 2022-2023, the average time was 146 minutes, a 28% increase.
“For the most part, once people are in the system, they receive high quality care,” he wrote. “But there are some important areas of concerns, such as maternity care, where there have been a succession of scandals and inquiries.”
Key Factors Leading to Delays
Darzi pointed to four key factors that have led to the problems.
Lack of funding. “The 2010s was the most austere decade since the NHS was founded, with spending growing at around 1% in real terms,” Darzi wrote, compared with a long-term average of 3.4%.
One result was that administrators took funds from the capital budget to cover day-to-day needs, leading to “crumbling buildings that hit productivity,” he noted.
“The backlog maintenance bill now stands at more than £11.6 billion and a lack of capital means that there are too many outdated scanners, too little automation, and parts of the NHS are yet to enter the digital era,” he wrote.
The COVID-19 pandemic. Given the preceding “decade of austerity,” NHS had fewer resources to deal with the crisis than most other high-income health systems, he wrote. As a result, NHS “delayed, cancelled, or postponed far more routine care during the pandemic than any comparable health system.” This led to “a bigger backlog than other health systems.”
Lack of patient and staff engagement. Patient satisfaction “has declined and the number of complaints has increased, while patients are less empowered to make choices about their care,” he wrote. In addition, “too many staff have become disengaged, and there are distressingly high-levels of sickness absence—as much as one working month a year for each nurse and each midwife working in the NHS.”
Management structures and systems. Darzi laid considerable blame on the UK’s Health and Social Care Act of 2012, which led to what he described as “a costly and distracting process of almost constant reorganization of the ‘headquarters’ and ‘regulatory’ functions of the NHS.”
One consequence, he wrote, is that too many clinicians have been deployed in hospitals instead of community-based care, despite years of promises by successive governments to put more emphasis on the latter.
National Health in Decline
Along with issues within the NHS, “the health of the nation has deteriorated and that impacts its performance,” Darzi wrote. “There has been a surge in multiple long-term conditions, and, particularly among children and young people, in mental health needs. Fewer children are getting the immunizations they need to protect their health, and fewer adults are participating in some of the key screening programs, such as for breast cancer.”
Darzi’s investigation included frontline visits to NHS facilities as well as focus groups with NHS staff and patients, the press release states. He also consulted an expert reference group consisting of more than 70 organizations and examined analyses from NHS England, the UK’s Department of Health and Social Care, and external groups.
It is interesting that there is no mention of anatomic pathology and medical laboratory testing services in Lord Darzi’s report. As reported in recent years by new outlets in the United Kingdom, delays in cancer diagnoses—often as long as six months—were severe enough that, in 2018, the NHS announced funding for a program to create a national digital pathology network to improve productivity of pathologists and shorten wait times for the results of cancer tests.
Is it possible that there is a connection between an individual’s gut microbiota and the ability to fight off gastrointestinal (GI) cancer? Findings from a preliminary research study performed by researchers in South Korea suggest that a link between the two may exist and that fecal microbiota transplants (FMTs) may enhance the efficacy of immunotherapies for GI cancer patients.
The proof-of-concept clinical trial, conducted at the Gwangju Institute of Science and Technology (GIST), Gwangju 61005, Republic of Korea, analyzed how an FMT could help 13 patients with metastatic solid tumors that were resistant to the anti-PD-1 antibody drug known as nivolumab (Opdivo). Anti-PD-1 drugs are immunotherapies that help treat cancer by improving an individual’s immune response against cancer cells.
Four of the trial participants had gastric cancer, five had esophageal cancer, and the remaining four had hepatocellular carcinoma. The patients were given a colonoscopy to implant the FMTs. The recipients also received antibiotics to reduce the response of their existing microbiotas.
The FMT donors also had gastric cancer, esophageal cancer, or hepatocellular carcinoma. Prior to donating their fecal matter, the donors experienced complete or partial response to the anti-PD-1 drugs nivolumab or pembrolizumab (Keytruda) for at least six months after receiving initial treatments.
“This research highlights the complex interplay between beneficial and detrimental bacteria within the gut microbiota in determining treatment outcomes,” co-senior study author Hansoo Park, MD, PhD, Assistant Professor, Biomedical Science and Engineering, Gwangju Institute of Science and Technology, told The ASCO Post. “While the connection between gut microbiota and immune response to cancer therapy has been a growing area of interest, our study provides concrete evidence and new avenues for improving treatment outcomes in a broader range of cancers,” he added. Further studies may confirm the need for microbiome testing by clinical laboratories to guide clinicians treating patients with colon cancers. (Photo copyright: Gwangju Institute of Science and Technology.)
Surprising Results
Fecal material for an FMT procedure combines donated fecal matter with a sterile saline solution which is then filtered to produce a liquid solution. That solution is then administered to the recipient via colonoscopy, upper GI endoscopy, enema, or an oral capsule. The solution may also be frozen for later use.
Upon analyzing the recipients, the scientists found that six of the patients (46.2%) who had experienced resistance to immunotherapies for their cancers, benefitted from the FMTs.
“Both donors were long-lasting, good responders to anti-PD-1 inhibitors, but because we did not yet know the causative bacteria responsible for the [FMT] response, we could not predict whether the treatment would be effective,” she added.
The researchers also determined that the presence of a bacterial strain known as Prevotella merdae helped to improve the effectiveness of the FMTs, while two strains of bacteria—Lactobacillus salivarius and Bacteroides plebeius (aka, Phocaeicola plebeius)—had a detrimental impact on the transplants.
Challenges to Widespread Adoption of FMTs
The researchers acknowledge there are challenges in widespread acceptance and use of FMTs in treating cancers but remain optimistic about the possibilities.
“Developing efficient and cost-effective methods for production and distribution is necessary for widespread adoption,” Sook Ryun Park told The ASCO Post. “Addressing these challenges through comprehensive research and careful planning will be essential for integrating FMT into the standard of care for cancer treatment.”
More research and clinical trials are needed before this use of FMTs can be utilized in clinical settings. However, the study does demonstrate that the potential benefits of FMTs may improve outcomes in patients with certain cancers. As this happens, microbiologists may gain a new role in analyzing the microbiomes of patients with gastrointestinal cancers.
“By examining the complex interactions within the microbiome, we hope to identify optimal microbial communities that can be used to enhance cancer treatment outcomes,” Hansoo Park told The ASCO Post. “This comprehensive approach will help us understand how the microbial ecosystem as a whole contributes to therapeutic success.”
Ongoing increases in the global number of prostate cancer cases expected to motivate test developers to deliver better screening tests to pathologists and clinical lab scientists
No less an authority than the peer-reviewed healthcare journal The Lancet is drawing attention to predictions of increasing prostate cancer cases across the globe, triggering calls for the development of cheaper, faster, and more accurate assays that pathologists and medical laboratories can use to screen for—and diagnose—prostate cancer.
Swift population growth and rising life expectancy will cause the prostate cancer death rate to nearly double in the next 20 years, according to a new study that has led scientists to call for immediate, critical improvements in clinical laboratory testing for cancer screening, Financial Times (FT) reported.
“Low- and middle-income countries need to prepare to prevent a sharp rise in fatalities while richer nations should pay more attention to young men at higher risk of the disease,” FT noted. The study, titled, “The Lancet Commission on Prostate Cancer: Planning for the Surge in Cases,” predicts cases will jump from 1.4 million in 2020 to 2.9 million by 2040.
“Prostate cancer is the most common cancer in men in 112 countries, and accounts for 15% of cancers. In this Commission, we report projections of prostate cancer cases in 2040 on the basis of data for demographic changes worldwide and rising life expectancy. … This surge in cases cannot be prevented by lifestyle changes or public health interventions alone, and governments need to prepare strategies to deal with it,” the study authors wrote.
“The findings in this Commission provide a pathway forward for healthcare providers and funders, public health bodies, research funders, governments, and the broader patient and clinical community,” the authors noted. In their Lancet paper, the researchers define clear areas for improvement.
Given the shortage worldwide of pathologists—especially highly-trained pathologists—the gap between the demand/need for expanded prostate cancer testing as screens (along with prostate biopsies) and the available supply of pathologists will encourage companies to develop screening and diagnostic tests that are accurate and automated, thus increasing the productivity of the available pathologists.
“As more and more men around the world live to middle and old age, there will be an inevitable rise in the number of prostate cancer cases. We know this surge in cases is coming, so we need to start planning and take action now,” said Nick James, PhD (above), Professor of Prostate and Bladder Cancer Research at The Institute of Cancer Research, in a press release. Pathologists and medical laboratories worldwide will want to monitor progress of The Lancet Commission’s recommendations. (Photo copyright: Institute of Cancer Research.)
“Evidence-based interventions, such as improved early detection and education programs, will help to save lives and prevent ill health from prostate cancer in the years to come. This is especially true for low- and middle-income countries (LMICs) which will bear the overwhelming brunt of future cases,” he said in a press release.
Communication is key. “Improved outreach programs are needed to better inform people of the key signs to look out for and what to do next,” James N’Dow, MD, Professor and Chair in Surgery and Director of the Academic Urology Unit at the University of Aberdeen in the UK, told the Financial Times. “Implementing these in tandem with investments in cost-effective early diagnostic systems will be key to preventing deaths,” he added.
Capitalizing on artificial intelligence (AI) analysis to help translate results was another area The Lancet Commission researchers focused on, Financial Times noted.
AI could “subdivide disease into potentially valuable additional subgroups to help with treatment selection. In environments with few or no pathologists, these changes could be transformational,” the study authors wrote.
High Income Countries (HICs) would benefit from AI by empowering patients. “Linking cloud-based records to artificial intelligence systems could allow access to context-sensitive, up-to-date advice for both patients and health professionals, and could be used to drive evidence-based change in all settings,” the study authors added. Such a trend could lead to specialist prostate cancer pathologists being referred cases from around the world as digital pathology systems become faster and less expensive.
Effective treatment strategies and bolstering areas of need is also key, the study notes. “Many LMICs have urgent need for expansion of radiotherapy and surgery services,” the study authors wrote. The researchers stress the need to immediately implement expansion programs to keep up with anticipated near-future demand.
Cancer drug therapy should follow suit.
“Research and the development of risk-stratified regulatory models need to be facilitated,” the study authors noted, citing a focus on drug repurposing and dose de-escalation. “Novel clinical trial designs, such as multi-arm platforms, should be supported and expanded,” they added.
Unique Needs of LMICs, HICs
The Lancet Commission researchers’ recommendations shift depending on the financial health of a specific area. HICs are experiencing a 30-year decline in the number of deaths resulting from prostate cancer, presumably from additional testing measures and public health campaigns that may be lacking in LMICs, Financial Times reported. And as population growth soars, low-to-middle income populations “will need to be prepared for the strain the expected surge in cases will put on health resources.”
For HICs, the study dissected the limitations of prostate-specific antigen (PSA) testing. The researchers pointed out that PSA’s inaccuracies in screening symptomless patients can pinpoint “cancers that may never cause symptoms and need no treatment,” Financial Times reported.
Missing high-risk cases was also a cause for concern. “Diagnostic pathways should be modified to facilitate early detection of prostate cancer while avoiding overdiagnosis and overtreatment of trivial disease,” the study notes.
Screenings for high-risk younger men, and continuing public campaigns about prostate cancer, should be a focus for HICs, the study authors noted. “These would include people who have a family history of the disease, are of African ancestry, or carry a genetic mutation known as BRCA2,” Financial Times reported.
While the undertaking may sound intimidating—there is already such a heavy impact worldwide from prostate cancer—the researchers are optimistic of their recommendations.
“Options to improve care are already available at moderate cost. We found that late diagnosis is widespread worldwide, but especially in LMICs, where it is the norm. Early diagnosis improves prognosis and outcomes, and reduces societal and individual costs, and we recommend changes to the diagnostic pathway that can be immediately implemented,” the study authors wrote.
What Comes Next
“More research is needed among various ethnic groups to expand understanding of prostate cancer beyond the findings from studies that were largely based on data from white men,” The Lancet Commission told the Financial Times.
Astute pathologists and medical laboratories will want to monitor efforts to develop assays that are inexpensive, more accurate, and produce faster answers. Demand for these tests will be substantial—both in developed and developing nations.
Study findings could lead to new clinical laboratory diagnostics that give pathologists a more detailed understanding about certain types of cancer
New studies proving artificial intelligence (AI) can be used effectively in clinical laboratory diagnostics and personalized healthcare continue to emerge. Scientists in the UK recently trained an AI model using machine learning and deep learning to enable earlier, more accurate detection of 13 different types of cancer.
DNA stores genetic information in sequences of four nucleotide bases: A (adenine), T (thymine), G (guanine) and C (cytosine). These bases can be modified through DNA methylation. There are millions of DNA methylation markers in every single cell, and they change in the early stages of cancer development.
One common characteristic of many cancers is an epigenetic phenomenon called aberrant DNA methylation. Modifications in DNA can influence gene expression and are observable in cancer cells. A methylation profile can differentiate tumor types and subtypes and changes in the process often come before malignancy appears. This renders methylation very useful in catching cancers while in the early stages.
However, deciphering slight changes in methylation patterns can be extremely difficult. According to the scientists, “identifying the specific DNA methylation signatures indicative of different cancer types is akin to searching for a needle in a haystack.”
Nevertheless, the researchers believe identifying these changes could become a useful biomarker for early detection of cancers, which is why they built their AI models.
“Computational methods such as this model, through better training on more varied data and rigorous testing in the clinic, will eventually provide AI models that can help doctors with early detection and screening of cancers,” said Shamith Samarajiwa, PhD (above), Senior Lecturer and Group Leader, Computational Biology and Genomic Data Science, Imperial College London, in a news release. “This will provide better patient outcomes.” With additional research, clinical laboratories and pathologists may soon have new cancer diagnostics based on these AI models. (Photo copyright: University of Cambridge.)
The researchers then used a combination of machine learning and deep learning techniques to train an AI algorithm to examine DNA methylation patterns of the collected data. The algorithm identified and differentiated specific cancer types, including breast, liver, lung and prostate, from non-cancerous tissue with a 98.2% accuracy rate. The team evaluated their AI model by comparing the results to independent research.
In their Biology Methods and Protocols paper, the authors noted that their model does require further training and testing and stressed that “the important aspect of this study was the use of an explainable and interpretable core AI model.” They also claim their model could help medical professionals understand “the underlying mechanisms that contribute to the development of cancer.”
Using AI to Lower Cancer Rates Worldwide
According to the Centers for Disease Control and Prevention (CDC), cancer ranks as the second leading cause of death in the United States with 608,371 deaths reported in 2022. The leading cause of death in the US is heart disease with 702,880 deaths reported in the same year.
Globally cancer diagnoses and death rates are even more alarming. World Health Organization (WHO) data shows an estimated 20 million new cancer cases worldwide in 2022, with 9.7 million persons perishing from various cancers that year.
The UK researchers are hopeful their new AI model will help lower those numbers. They state in their paper that “most cancers are treatable and curable if detected early enough.”
More research and studies are needed to confirm the results of this study, but it appears to be a very promising line of exploration and development of using AI to detect, identify, and diagnose cancer earlier. This type of probing could provide pathologists with improved tools for determining the presence of cancer and lead to better patient outcomes.
