There’s evidence that a cancer drug can cut deaths from lung cancer by as much as 50% when pathology testing indicates the patient has the EGFR mutation
Results from a decade-long clinical trial indicate that lung cancer patients with the epidermal growth factor receptor (EGFR) mutation have significantly better survival rates when treated with the drug osimertinib. This is a positive step forward for precision medicine and will give clinical laboratories an opportunity to deliver more value to physicians and patients.
The study known as ADAURA was led by scientists at Yale University and funded by British pharmaceutical/biotechnology company AstraZeneca. The researchers recently found that taking the cancer drug osimertinib (brand name Tagrisso) reduces by half the number of deaths among patients who had undergone surgery for EGFR–mutated, stage IB to IIIA non-small-cell lung cancer (NSCLC), according to NBC News.
Lung cancer has been one of the toughest types of cancers to diagnose early. When finally diagnosed, many patients do not have a good prognosis. Thus, the results of this multi-national study—and the connection involving patients with the EGFR gene—is a welcome development that promises better outcomes for cancer patients.
At the same time, this increases the value of EGFR as a biomarker for clinical laboratories and pathology groups that offer EGFR testing. It could become a companion diagnostic test—part of a clinical guideline for diagnosing lung cancer—that helps identify appropriate anti-cancer drugs for specific patients.
“Adjuvant osimertinib is currently the only EGFR tyrosine kinase inhibitor to translate a statistically significant and practice-changing disease-free survival benefit into a significant [overall survival] benefit in a phase 3 trial, supporting osimertinib as the standard of care for patients in this setting,” said Roy Herbst, MD, PhD, Deputy Director and Chief of Medical Oncology at Yale Cancer Center, who led the Yale study, at the 2023 ASCO Annual Meeting, according to an ASCO news release. (Photo copyright: Yale School of Medicine.)
Identifying Best Candidates for Specific Cancer Drugs
The results of the Yale-led study of the cancer drug osimertinib suggest that testing for a mutation in the EGFR gene could become part of the standard-of-care for NSCLC. Researchers found that NSCLC patients with the mutation showed improved survival rates and reduced risk of recurrence when taking the drug following surgery. EGFR tests could thus become companion diagnostics to determine whether patients are good candidates for the drug.
“We have been using one-size-fits-all adjuvant chemotherapy for every patient with lung cancer despite a decade of advances in targeted treatments for select groups of patients that result in dramatically better outcomes,” Nathan Pennell, MD, PhD, Vice Chair of Clinical Research and Director, Lung Cancer Medical Oncology Program Cleveland Clinic Taussig Cancer Institute, told the ASCO Post.
Pennell, who was not involved in the Yale research, described the finding as “a first for the lung cancer field,” and said adjuvant osimertinib “should be the new standard of care” for patients with EGFR-mutated NSCLC.
‘Practice-changing’ Cancer Drug
The study was led by Roy S. Herbst, MD, PhD, Deputy Director and Chief of Medical Oncology at Yale Cancer Center and Assistant Dean for Translational Research at Yale School of Medicine. Herbst is the principal investigator for the ADAURA global multi-site clinical trial which enrolled 682 patients with stage IB-IIIA NSCLC, in an effort to determine the efficacy of the cancer drug osimertinib, a pill taken once a day, which, according to NBC News, has fewer major side effects than chemotherapy.
The FDA approved the drug in 2015 for patients with advanced lung cancer. In 2020, the agency approved its use at earlier stages of the disease.
The ADAURA study included patients from 26 countries across Europe, North America, South America, and the Asia-Pacific region. About half of the patients took the pill each day for three years following surgery. The other half received a placebo.
According to a Yale news release, the researchers reported that 88% of patients treated with the drug were still alive five years later, compared with 78% of patients who received the placebo.
Earlier research demonstrated that the drug prevented recurrence of tumors and kept the disease from spreading to other organs, NBC News reported. “However, what we are seeing now is that patients will also live longer,” said oncologist Charu Aggarwal, MD, MPH, of the University of Pennsylvania’s Perelman School of Medicine, who was not involved in the study.
Herbst described the drug as “practice-changing” in the Yale news story.
An EGFR ‘Off Switch’
Non-small cell lung cancer is the most common form of lung cancer, The Guardian reported, adding that the EGFR mutation “is found in about a quarter of global lung cancer cases, and accounts for as many as 40% of cases in Asia. An EGFR mutation is more common in women than men and in people who have never smoked or have been light smokers.”
The mutation can cause cells to “excessively divide and multiply, which may cause cancer,” NBC News explained. Herbst described osimertinib as an “off” switch for the mutation.
“I think we’re curing some patients,” he said at the ASCO annual meeting, NBC News reported. “We’re really showing progress in lung cancer like never before,” he noted, adding that the results were “about twice as good as we expected.
“Overall survival has historically been considered the gold standard efficacy endpoint for randomized adjuvant clinical trials. The results of the ADAURA trial will broaden treatment access for patients with EGFR-mutated NSCLC,” Herbst told ASCO Post. “Together with the practice-changing disease-free survival data from our primary analysis, the overall survival benefit instills confidence that adjuvant osimertinib is the standard of care for patients with resected EGFR-mutated stage IB to IIIA NSCLC.”
Side effects of the pill include skin rashes and mild diarrhea, but in general the drug is “quite well tolerated,” Herbst said.
Impact on Labs
In Herbst’s view, the results of the Yale study demonstrate that patients diagnosed with lung cancer should be tested for the EGFR mutation, which is not always the case, The Guardian reported. “This further reinforces the need to identify these patients with available biomarkers at the time of diagnosis and before treatment begins,” he said.
Aggarwal agreed, telling NBC News that data from the study could be a “call to action” for more EGFR screening.
In light of the results, clinical laboratories and anatomic pathology groups should expect that EGFR screening may soon become a companion diagnostic test as part of a precision medicine clinical guideline for early diagnosing of lung cancer.
Lapses in security measure testing can give healthcare employees a false sense of protection against data breaches, says cybersecurity expert
Cyberattacks on our nation’s hospitals, clinical laboratories, other healthcare organizations, and health plans, continue to plague the healthcare industry. As of July 7, 2023, 324 data breaches have occurred and are currently under investigation, according to the US Department of Health and Human Services (HHS) Office for Civil Rights (OCR) data breach portal.
This has affected more than 39 million people, HealthITSecurity reported.
Below is a list of the data breaches this year that affected the most people.
“The way that computer network environments work today, users are acknowledged as the weakest link and offer the most potential for access to a hacker,” Ben Denkers (above), former Chief Innovation Officer at CynergisTek, told Dark Daily’s sister publication The Dark Report. He added that data breaches at clinical laboratories can start with “missteps” by lab employees who have a false sense of protection caused by lapses in testing a lab’s security measures. CynergisTek merged with Clearwater in 2022. (Photo copyright: CynergisTek.)
Top Data Breaches in First Six Months of 2023
Here are healthcare’s top 10 data breaches for the first half of 2023, listed by organizations with the most people affected, according to HHS:
Enzo Clinical Labs, clinical reference laboratory, Farmingdale, New York, 2.4 million individuals affected.
ZOLL Services, medical equipment, Pittsburgh, Pennsylvania, 997,097 individuals affected.
Community Health Systems, healthcare provider with 15,000 licensed beds at 89 acute care hospitals in 16 states, Brentwood, Tennessee, 962,884 individuals affected.
CentraState Healthcare System, healthcare provider with a 284-bed acute care medical center, an ambulatory campus, and an urgent care clinic, Freehold, New Jersey, 617,901 individuals affected.
Clinical Laboratory Brings in Cybersecurity Experts
Following a ransomware incident in April on its computer network, Enzo Clinical Labs in Farmingdale, New York, “immediately took steps to secure our systems and began an investigation with the assistance of a cybersecurity firm,” the lab’s Notice of Data Security Incident explains.
“The investigation determined an unauthorized party accessed files on our systems,” the notice continues. “The files contained patient names, dates of service, clinical test information, and, in some instances, Social Security numbers.”
Enzo “has incurred, and may continue to incur, certain expenses related to this attack, including expenses to respond to, remediate and investigate this matter,” according to the lab’s Securities and Exchange Commission (SEC) filing.
Multiple Large Health Systems Suffer Data Breaches
At Community Health Systems (CHS) it was a security incident at Fortra, a cybersecurity firm engaged by CHS, that resulted in “unauthorized disclosure of patient information,” according to CHS’s Notice of Third Party Security Incident.
The extent of data theft from the breach of Fortra’s GoAnywhere MFT secure managed file transfer software was not immediately clear, HIPAA Journal reported.
“The personal information may have included full name, address, medical billing and insurance information, certain medical information such as diagnoses and medication, and demographic information such as date of birth and Social Security number,” the CHS notice explained.
At CentraState Healthcare System, “an unauthorized person obtained a copy of an archived database that stored certain patient information,” the healthcare provider’s Notice of Security Incident states.
“There was no financial account and/or payment card information involved in this incident,” CentraState noted.
Financial Impact of Data Breaches
One of the effects on healthcare providers is costly settlement of lawsuits following data breaches that allege failure to secure patients’ PHI. For example, according to Becker’s Health IT:
UMass Memorial Medical Center in Worcester, Massachusetts, paid $1.2 million “to settle a March 2022 lawsuit regarding a data breach of its payroll management system Kronos.”
Advent Health in Altamonte Springs, Florida, paid $500,000 “to settle a data breach lawsuit alleging that the health system failed to protect patients’ confidential information after a September 2021 data breach.”
CommonSpirit Health in Chicago spent $150 million recovering from a ransomware attack in October 2022 that also sparked lawsuits over stolen PHI.
Tips for Clinical Laboratories on Securing Patient Data
In “Labs Must Audit Their Cybersecurity Measures,” Ben Denkers, former Chief Innovation Officer at CynergisTek, an Austin-based cybersecurity company which has since merged with healthcare cybersecurity and compliance company Clearwater, told Dark Daily’s sister publication The Dark Report, “The way that computer network environments work today, users are acknowledged as the weakest link and offer the most potential for access to a hacker.”
Denkers advises that while training employees is important for cybersecurity because it aims at changing human behavior, laboratories and other healthcare organizations also need to audit the technological measures they have in place to protect data.
“What we find is that organizations have security technology or processes in place that are either not effective or not working as designed,” he said, adding that when data breaches do occur “it’s a complete blindside for a lot of organizations that think they have protections in place because they bought a product, or they developed a policy.
“Testing, validating, and auditing whether measures are working as designed is a change of mentality for a lot of organizations. I would recommend taking those steps,” he added.
Clinical laboratories hold vast amounts of patient data and cannot afford disruptions to testing and results reporting. Vigilance can help labs avoid catastrophic cyberattacks, secure their patients’ protected health information from being stolen, and prevent the subsequent lawsuits that ensue following a data breach.
As scientists gain new insights into the human microbiome and how it influences our health, microbiology labs may gain new diagnostic biomarkers
In a study that took more than five years to complete, researchers from Stanford University have successfully created the first synthetic microbiome model from scratch. The goal of the study was to create a baseline microbiome model so that future studies will have a better understanding of which clinical laboratory tests and medical interventions could be useful for treating specific ailments and improving patient care.
To create their synthetic human microbiome, the Stanford researchers combined 119 species of bacteria, The New York Times reported, adding that “the new synthetic microbiome can even withstand aggressive pathogens and cause mice to develop a healthy immune system, as a full microbiome does.”
According to the National Institute of Health (NIH), the human gut contains trillions of microbes, and no two people share the exact same microbiome composition. This complex community of microbial cells influences human physiology, metabolism, nutrition and immune function, and performs a critical role in overall health.
The Stanford scientists believe researchers now have a common microbiome foundation for future microbial studies.
“We were looking for the Noah’s Ark of bacteria species in the human gut, trying to find the ones that were almost always there in any individual,” said Michael Fischbach, PhD, Associate Professor in the Departments of Bioengineering and Microbiology and Immunology at Stanford University. Future microbial studies that use Stanford’s synthetic human microbiome may develop improved clinical laboratory tests and microbiome therapies. (Photo copyright: Stanford University.)
Creating the ‘Human Community One’ Microbiome
The researchers began their study by examining the gut bacteria makeup of adults involved in the Human Microbiome Project (HMP), an NIH initiative created to sequence the full microbial genomes of more than 300 adults.
The scientists then selected bacterial strains that were present in at least 20% of the HMP individuals. They focused on 104 bacterial species that they grew in individual stocks, and then mixed them into one combined culture to create what they named “Human Community One” (hCom1).
The researchers had to ensure that the final mixture had the stability to maintain a balance where no single species overpowered the rest and could perform all the actions of a natural microbiome.
After being satisfied that the bacterial strains could coexist in a lab situation, the scientists set out to determine if their community would colonize in the gut. To do this, they introduced hCom1 to germ-free mice that are designed to have no natural microbiome.
When transplanted into the mice, the researchers discovered hCom1 was an extremely stable ecosystem, with 98% of the species taking root in the guts of the mice, and the levels of each bacterial species remaining constant over a two-month period.
“We colonized germ-free mice with hCom1 and found that it was stable over time. Its species span six orders of magnitude of relative abundance: from ~10% to less than one in 1,000,000,” Michael Fischbach, PhD, Associate Professor in the Departments of Bioengineering and Microbiology and Immunology at Stanford University and one of the authors of the study, explained on Twitter.
Based on a theory called colonization resistance, the team then introduced a human fecal sample to hCom1 to ensure that all vital microbiome functions would be performed by one or more species. Colonization resistance is the phenomenon where the normal gut microbiome protects itself against invasion by new and often harmful microorganisms. This theory hypothesizes that any bacterium introduced into an existing colony will only survive if it can fill a niche that is not already occupied.
Creating a Second New Microbiome
Some researchers involved in the project were skeptical that introducing human fecal matter to hCom1 would work. They believed it would overtake the synthetic microbiome model.
“The bacterial species in hCom1 had lived together for only a few weeks,” Fischbach explained in a Stanford press release. “Here we were introducing a community that had coexisted for a decade. Some people thought they would decimate our colony.”
However, the scientists found that hCom1 thrived with only about 10% of the cells in the final community originating from the fecal transplant. A few of the original bacterial species died off and approximately 20 new bacterial species were able to successfully colonize hCom1. They ultimately catalogued 119 bacterial strains present in the colony after the transplant and dubbed the new microbiome “Human Community Two” (hCom2).
To further prove the functionality of their synthetic microbiome, the team then introduced an Escherichia coli (E. coli) sample to mice colonized with hCom2 and found that they were able to resist infection.
“Mice colonized by hCom2 look normal immunologically, have similar microbiome-derived metabolites, and exert colonization resistance against E. coli,” said Fischbach on Twitter, “There are improvements to make, but we think hCom2 (in its current form) is a good model system of the microbiome.”
Future Microbial Studies
The Stanford team hopes its synthetic microbiome model will allow researchers around the world to have a common foundation for future studies and provide them with the ability to create engineered microbiome-based therapies.
“We built this consortium for the broader research community,” said Fischbach in the press release. “We want to get this into as many hands as possible to have an impact on the field.”
While direct links to new clinical laboratory tests and microbiome therapies have not yet been established, research like the Stanford study demonstrates the increasing value of the human microbiome as a source of diagnostic information that can guide decisions on better ways to treat patients.
US Department of Justice sends a strong message that it will continue to root out fraud involving clinical laboratory owners and operators
Arkansas clinical laboratory owner/operator Billy Joe Taylor has been sentenced to 15 years in federal prison and ordered to pay nearly $30 million in restitution, according to a June 8 press release from the US Attorney’s Office for the Western District of Arkansas.
Taylor pleaded guilty in October of 2022 to conspiracy to commit fraud and money laundering. He and his accomplices submitted $134 million in false or fraudulent claims to Medicare before and during the COVID-19 pandemic.
The claims came from five laboratory companies owned and operated by Taylor and his co-conspirators. All claims centered around respiratory illness tests or urine drug tests that were either not medically necessary or not ordered by medical providers, the DOJ’s press release states.
Taylor’s 15-year sentence in federal prison and huge restitution reinforces the fact that the federal Department of Justice (DOJ) will indict—and convict—owners and managers of clinical laboratory companies accused of healthcare fraud.
Billy Joe Taylor, owner/operator of five clinical laboratories in four states, was sentenced in June to 15 years in prison and ordered to repay nearly $30 million in fraudulent test claims made to Medicare prior to and during the COVID-19 pandemic. This conviction is part of an ongoing campaign against healthcare fraud being conducted by the US Department of Justice. (Photo copyright: Arkansas Democrat-Gazette.)
Details of Taylor Fraud Case
Taylor allegedly obtained private personal and medical data from Medicare beneficiaries and then used that information to submit and resubmit claims to Medicare for diagnostic tests. More than $38 million was received from Medicare on those fraudulent claims, the DOJ noted.
In 2021, Taylor claimed innocence and told Arkansas Business that the accusations were “sensationalism-type claims from the government that were completely erroneous and false.”
As a young man, Taylor planned to go into the clinical laboratory field when he was still in high school. He got started by volunteering at his hometown hospital in Stigler, Oklahoma, the Free Library reported. Eventually hired by the hospital to draw blood, run tests, and keep quality control and inspection data, Taylor later moved to other hospitals before partnering in 2009 to start Advanced Laboratory Services (ALS) of Oklahoma City, Oklahoma.
A pulmonary embolism and stroke forced Taylor to sell his share in ALS, and not long after returning as a consultant, his business partner sold the lab company. Taylor joined two people from a Tulsa laboratory to start a new company, acquiring Medtest Laboratories LLC of Hurricane, West Virginia, and Vitas laboratory LLC in 2017. He hoped to compete with national laboratories, earning up to $2 million per month, the Free Library reported.
Other Clinical Laboratory Testing Fraud Schemes
The DOJ’s aggressive efforts to crack down on healthcare fraud over the past years have produced multiple court cases against clinical laboratory owners, managers, and the doctors who conspire with them. Dark Daily has covered such fraud cases in numerous ebriefings over the years.
In 2021, the DOJ’s Healthcare Fraud Unit brought “criminal charges against 14 defendants, including 11 newly-charged defendants and three who were charged in superseding indictments, in seven federal districts across the United States for their alleged participation in various healthcare fraud schemes that exploited the COVID-19 pandemic and resulted in over $143 million in false billings,” a DOJ press release announced.
In a statement to the press, Deputy Attorney General Lisa O. Monaco said, “The multiple healthcare fraud schemes charged today describe theft from American taxpayers through the exploitation of the national emergency … These medical professionals, corporate executives, and others allegedly took advantage of the COVID-19 pandemic to line their own pockets instead of providing needed healthcare services during this unprecedented time in our country.
“We are committed to protecting the American people and the critical healthcare benefits programs created to assist them during this national emergency, and we are determined to hold those who exploit such programs accountable to the fullest extent of the law,” she added.
Monaco’s statement emphasizes the DOJ’s expanding focus on healthcare fraud. The DOJ formed the Health Care Fraud Strike Force in 2007 to handle cases like Taylor’s. The program is composed of 15 teams operating out of 25 federal districts. During the 15 plus years the Strike Force has been active, the DOJ has charged more than 5,000 defendants who collectively billed over $24 billion to both private insurers and federal healthcare programs.
Therefore, it behooves clinical laboratory managers to ensure all lab operations are well-within the bounds of legality. The DOJ is taking its hunt for healthcare fraudsters quite seriously.
Cybersecurity experts recommend clinical laboratories have in place a plan for performing tests and distributing results prior to a cyberattack
Hospitals of all sizes continue to be prime targets for sophisticated cyberattacks, where hackers remotely disable a healthcare network’s computer systems—including its laboratory information system—and extort ransomware payments. Similar attacks are happening to clinical laboratories and other providers, although not with the same frequency.
Recently, hospitals in Illinois, Idaho, Vermont, Indiana, and other states had their ability to treat patients severely reduced and, in some cases, completely shut down by cybercriminals, endangering lives and costing millions of dollars in damages.
Today’s hospitals rely on information technology (IT) for patient care workflow, internal/external communication, billing, and medical laboratory testing. It’s this reliance on computer/internet technology combined with the vast quantities of protected health information (PHI), that makes hospitals such ripe targets for attack.
In June, a US cancer center had to take its digital services offline which “significantly reduced patient treatment capability” following a ransomware attack by a group of hackers known as the TimisoaraHackerTeam (THT), MedCity News reported.
“Patients don’t stop getting sick just because a hospital is hit by a ransomware attack,” Christian Dameff, MD, emergency physician at UC San Diego Health and lead author of a study that looked into how cyberattacks affect other hospitals in the area, told ABC News. “They have to go somewhere. So, what this research shows is that those patients go to neighboring hospitals that can be overwhelmed.” Clinical laboratories can also become overwhelmed with test orders when nearby hospitals lose their ability to distribute the results of critical lab tests. (Photo copyright: UC San Diego Health.)
“The attack halted the hospital’s ability to submit claims to insurers, Medicare or Medicaid for months, sending it into a financial spiral,” Linda Burt, RN, Vice President of Quality and Community Services at St. Margaret’s, told NBC News. “We were down a minimum of 14 weeks. And then you’re trying to recover. Nothing went out. No claims. Nothing got entered. So, it took months and months and months.”
Meabwhile, 88-bed Idaho Falls Community Hospital experienced a cyberattack in May that required it to divert ambulances to other hospitals for 24 hours, CNN reported. The provider’s sister healthcare facility, MountainView Hospital in Las Vegas, which shares the same computer system, was also affected.
The Idaho Falls attack “forced nurses and doctors … to use pen and paper rather than computers for patient charts,” a hospital spokesperson told CNN.
At the University of Vermont Medical Center (UVM), Burlington, Vermont, a ransomware attack affected healthcare services for 28 days, costing the provider $50 million to recover, and preventing healthcare workers from accessing critical treatment plans for cancer patients, ABC News reported.
UVM’s President and Chief Operating Officer, Stephen Leffler, MD, an emergency medicine physician, told ABC News that the 2020 cyberattack significantly disrupted clinical laboratory operations at UVM.
“When the laboratory had a critical lab result on someone, they couldn’t put it in the electronic medical record,” he explained. “They couldn’t call the floor. And so, we literally had our administrators start going in the lab, standing there and running a paper result to the floors.
“Everything that we do and rely on was down,” he added. “We actually sent some staff to Best Buy to buy Walkie Talkies!
“It can happen to you—even when you think it’s impossible,” Leffler warned.
And at Johnson Memorial Health, Franklin, Indiana, clinical laboratory tests took two hours to perform instead of 30 minutes, NPR said in its report on cyberattacks affecting Indiana providers. The lab had to use “runners” to share handwritten test results with caregivers and patients, NPR explained.
“You ask many CEOs across the country, ‘What keeps you up at night?’ Of course, they talk about workforce, financial pressures, and they say, ‘the possibility of a cyberattack,” John Riggi, National Advisor for Cybersecurity and Risk at the American Hospital Association (AHA), told NPR.
Cyberattacks Affect Surrounding Hospitals
To make matters worse, cyberattacks have a “blast radius” that impacts the healthcare community around an attacked provider, Christian Dameff, MD, Assistant Professor, Emergency Medical Services, University of California, San Diego, told ABC News. Dameff was lead author in a study that looked at how healthcare providers nearby to an attacked provider are affected.
“Hospitals adjacent to healthcare delivery organizations affected by ransomware attacks may see increases in patient census and may experience resource constraints affecting time-sensitive care for conditions such as acute stroke,” Dameff and co-authors wrote in a JAMA Open Network article titled, “Ransomware Attack Associated with Disruptions at Adjacent Emergency Departments in the US.”
“Healthcare cyberattacks such as ransomware are associated with greater disruptions to regional hospitals and should be treated as disasters,” they wrote.
Vigilance Is Required as Cyberattacks Increase
Ransomware attacks on hospitals climbed from 43 to 91 annually during the years 2016 to 2021, a separate study in JAMA Health Forum reported, adding that large organizations with multiple facilities were increasingly targeted.
The US experienced a 57% increase in cyberattacks in 2022 compared to 2021, according to a Check Point Research (CPR) report. Healthcare ranked second on the list of attacked industries due, according to Check Point, to the quantity and availability of personal and sensitive information, such as social security numbers and medical data.
“We expect the increase in cyber activity to only increase. With AI [artificial intelligence] technologies such as ChatGPT readily available, it is possible for hackers to generate malicious code and emails at a faster, more automated pace,” the CPR report noted.
For its part, the AHA said in a statement it plans to:
Work with federal agencies to mitigate cyber threats.
Advocate for increased government cybersecurity assistance.
Hospital clinical laboratory leaders need to be vigilant and work with colleagues to prevent cyberattacks. Check Point’s report advises, for example, avoiding malicious links and unexpected electronic attachments as well as verifying software is legitimate before downloading it. These are standard warnings, but they only work if staff members actually heed these actions.
Also important for diagnostics professionals is having a plan for performing clinical laboratory and anatomic pathology tests and distributing the results in the event of an attack.
Further development of this novel technology could result in new, more sensitive assays for clinical laboratories to use in the effort to improve antimicrobial stewardship in hospitals
Researchers at McMaster University in Ontario, Canada, have used artificial intelligence (AI) to identify a potential antibiotic that neutralizes the drug-resistant bacteria Acinetobacter baumannii, an antibiotic resistant pathogen commonly found in many hospitals. This will be of interest to clinical laboratory managers and microbiologists involved in identifying strains of bacteria to determine if they are antimicrobial-resistant (AMR) superbugs.
Using machine learning, the scientists screened thousands molecules to look for those that inhibited the growth of this specific pathogen. And they succeeded.
“We trained a neural network with this growth inhibition dataset and performed in silico predictions for structurally new molecules with activity against A. baumannii,” the researchers wrote in their published study.
They discovered that the molecule abaucin inhibited the growth of the antibiotic-resistant pathogen in vitro.
This shows how machine learning and AI technologies are giving biomedical researchers tools to identify new therapeutic drugs that are effective against drug-resistant strains of bacteria. This same research can be expected to lead to new clinical laboratory assays that determine if superbugs can be attacked by specific therapeutic drugs.
“When I think about AI in general, I think of these models as things that are just going to help us do the thing we’re going to do better,” Jonathan Stokes, PhD, Assistant Professor of Biomedicine and Biochemistry at McMaster University in Ontario, Canada, and lead author of the study, told USA Today. Clinical laboratory scientists and microbiologists will be encouraged by the McMaster University scientists’ findings. (Photo copyright: McMaster University.)
McMaster Study Details
Jonathan Stokes, PhD, head of the Stokes Laboratory at McMaster University, is Assistant Professor of Biomedicine/Biochemistry at McMaster and lead author of the study. Stokes’ team worked with researchers from the Broad Institute of MIT and Harvard to explore the effectiveness of AI in combating superbugs, USA Today reported.
“This work highlights the utility of machine learning in antibiotic discovery and describes a promising lead with targeted activity against a challenging Gram-negative pathogen,” the researchers wrote in Nature Chemical Biology.
Stokes Lab utilized the high-throughput drug screening technique, spending weeks growing and exposing Acinetobacter baumannii to more than 7,500 agents of drugs and active ingredients of drugs. When 480 compounds were uncovered that blocked the growth of bacteria, this information was then provided to a computer that was trained to run an AI algorithm, CNN reported.
“Once we had our [machine learning] model trained, what we could do then is start showing that model brand-new pictures of chemicals that it had never seen, right? And based on what it had learned during training, it would predict for us whether those molecules were antibacterial or not,” Stokes told CNN.
The model spent hours screening more than 6,000 molecules. It then narrowed the search to 240 chemicals, which were tested in the lab. The scientists pared down the results to the nine most effective inhibitors of bacteria. They then eliminated those that were either related to existing antibiotics or might be considered dangerous.
The researchers found one compound—RS102895 (abaucin)—which, according to Stokes, was likely created to treat diabetes, CNN reported. The scientists discovered that the compound prevented bacterial components from making their way from inside a cell to the cell’s surface.
“It’s a rather interesting mechanism and one that is not observed amongst clinical antibiotics so far as I know,” Stokes told CNN.
Because of the effectiveness of the antibiotic during testing on mice skin, the researchers believe this method may be useful for creating antibiotics custom made to battle additional drug resistant pathogens, CNN noted.
Defeating a ‘Professional Pathogen’
Acinetobacter baumannii (A. baumannii)—the focus of Stoke’s study—is often found on hospital counters and doorknobs and has a sneaky way of using other organisms’ DNA to resist antibiotic treatment, according to CNN.
“It’s what we call in the laboratory a professional pathogen,” Stokes told CNN.
A. baumannii causes infections in the urinary tract, lungs, and blood and typically wreaks havoc to vulnerable patients on breathing machines, in intensive care units, or undergoing surgery, USA Today reported.
A. baumannii is resistant to carbapenem, a potent antibiotic. The Centers for Disease Control and Prevention (CDC) reported that in 2017 the bacteria infected 8,500 people in hospitals, 700 of those infections being fatal.
Further, in its 2019 “Antibiotic Resistance Threats in the United States” report, the CDC stated that one out of every four patients infected with the bacteria died within one month of their diagnosis. The federal agency deemed the bacteria “of greatest need” for new antibiotics.
Thus, finding a way to defeat this particularly nasty bacteria could save many lives.
Implications of Study Findings on Development of new Antibiotics
The Stokes Laboratory study findings show promise. If more antibiotics worked so precisely, it’s possible bacteria would not have a chance to become resistant in the first place, CNN reported.
Next steps in Stokes’ research include optimizing the chemical structure and testing in larger animals or humans, USA Today reported.
“It’s important to remember [that] when we’re trying to develop a drug, it doesn’t just have to kill the bacterium,” Stokes noted. “It also has to be well tolerated in humans and it has to get to the infection site and stay at the infection site long enough to elicit an effect,” USA Today reported.
Stokes’ study is a prime example of how AI can make a big impact in clinical laboratory diagnostics and treatment.
“We know broad-spectrum antibiotics are suboptimal and that pathogens have the ability to evolve and adjust to every trick we throw at them … AI methods afford us the opportunity to vastly increase the rate at which we discover new antibiotics, and we can do it at a reduced cost. This is an important avenue of exploration for new antibiotic drugs,” Stokes told CNN.
Clinical laboratory managers and microbiologists may want to keep an open-mind about the use of AI in drug development. More research is needed to give substance to the McMaster University study’s findings. But the positive results may lead to methods for fine tuning existing antibiotics to better combat antimicrobial-resistant bacteria, USA Today reported.
