News, Analysis, Trends, Management Innovations for
Clinical Laboratories and Pathology Groups

Hosted by Robert Michel

News, Analysis, Trends, Management Innovations for
Clinical Laboratories and Pathology Groups

Hosted by Robert Michel
Sign In

Scientists in Italy Develop Hierarchical Artificial Intelligence System to Analyze Bacterial Species in Culture Plates

New artificial intelligence model agrees with interpretations of human medical technologists and microbiologists with extraordinary accuracy

Microbiology laboratories will be interested in news from Brescia University in Italy, where researchers reportedly have developed a deep learning model that can visually identify and analyze bacterial species in culture plates with a high level of agreement with interpretations made by medical technologists.

They initially trained and tested the system to digitally identify pathogens associated with urinary tract infections (UTIs). UTIs are the source for a large volume of clinical laboratory microbiological testing.

The system, known as DeepColony, uses hierarchical artificial intelligence technology. The researchers say hierarchical AI is better suited to complex decision-making than other approaches, such as generative AI.

The researchers published their findings in the journal Nature titled, “Hierarchical AI Enables Global Interpretation of Culture Plates in the Era of Digital Microbiology.”

In their Nature paper, the researchers explained that microbiologists use conventional methods to visually examine culture plates that contain bacterial colonies. The scientists hypothesize which species of bacteria are present, after which they test their hypothesis “by regrowing samples from each colony separately and then employing mass spectroscopy techniques,” to confirm their hypotheses.

However, DeepColony—which was designed for use with clinical laboratory automation systems—looks at high-resolution digital scans of cultured plates and attempts to identify the bacterial strains and analyze them in much the same way a microbiologist would. For example, it can identify species based on their appearance and determine which colonies are suitable for analysis, the researchers explained.

“Working on a large stream of clinical data, and a complete set of 32 pathogens, the proposed system is capable of effectively assisting plate interpretation with a surprising degree of accuracy in the widespread and demanding framework of urinary tract infections,” the study authors wrote. “Moreover, thanks to the rich species-related generated information, DeepColony can be used for developing trustworthy clinical decision support services in laboratory automation ecosystems from local to global scale.”

Alberto Signoroni, PhD

“Compared to the most common solutions based on single convolutional neural networks (CNN), multi-network architectures are attractive in our case because of their ability to fit into contexts where decision-making processes are stratified into a complex structure,” wrote the study’s lead author Alberto Signoroni, PhD (above), Associate Professor of Computer Science, University of Brescia, and his researcher team in their Nature paper. “The system must be designed to generate useful and easily interpretable information and to support expert decisions according to safety-by-design and human-in-the-loop policies, aiming at achieving cost-effectiveness and skill-empowerment respectively.” Microbiologists and clinical laboratory managers will want to follow the further development of this technology. (Photo copyright: University of Brescia.)

How Hierarchical AI Works

Writing in LinkedIn, patent attorney and self-described technology expert David Cain, JD, of Hauptman Ham, LLP, explained that hierarchical AI systems “are structured in layers, each with its own distinct role yet interconnected in a way that forms a cohesive whole. These systems are significant because they mirror the complexity of human decision-making processes, incorporating multiple levels of analysis and action. This multi-tiered approach allows for nuanced problem-solving and decision-making, akin to a seasoned explorer deftly navigating through a multifaceted terrain.”

DeepColony, the researchers wrote, consists of multiple convolutional neural networks (CNNs) that exchange information and cooperate with one another. The system is structured into five levels—labeled 0 through 4—each handling a different part of the analysis:

  • At level 0, the system determines the number of bacterial colonies and their locations on the plate.
  • At level 1, the system identifies “good colonies,” meaning those suitable for further identification and analysis.
  • At level 2, the system assigns each good colony to a bacterial species “based on visual appearance and growth characteristics,” the researchers wrote, referring to the determination as being “pathogen aware, similarity agnostic.”

The CNN used at this stage was trained by using images of 26,213 isolated colonies comprising 32 bacterial species, the researchers wrote in their paper. Most came from clinical laboratories, but some were obtained from the American Type Culture Collection (ATCC), a repository of biological materials and information resources available to researchers.

  • At level 3, the system attempts to improve accuracy by looking at the larger context of the plate. The goal here is to “determine if observed colonies are similar (pure culture) or different (mixed cultures),” the researchers wrote, describing this step as “similarity aware, pathogen agnostic.” This enables the system to recognize variants of the same strain, the researchers noted, and has the effect of reducing the number of strains identified by the system.

At this level, the system uses two “Siamese CNNs,” which were trained with a dataset of 200,000 image pairs.

Then, at level 4, the system “assesses the clinical significance of the entire plate,” the researchers added. Each plate is labeled as:

  • “Positive” (significant bacterial growth),
  • “No significant growth” (negative), or
  • “Contaminated,” meaning it has three or more “different colony morphologies without a particular pathogen that is prevalent over the others,” the researchers wrote.

If a plate is labeled as “positive,” it can be “further evaluated for possible downstream steps,” using MALDI-TOF mass spectrometry or tests to determine susceptibility to antimicrobial measures, the researchers stated.

“This decision-making process takes into account not only the identification results but also adheres to the specific laboratory guidelines to ensure a proper supportive interpretation in the context of use,” the researchers wrote.

Nearly 100% Agreement with Medical Technologists

To gauge DeepColony’s accuracy, the researchers tested it on a dataset of more than 5,000 urine cultures from a US laboratory. They then compared its analyses with those of human medical technologists who had analyzed the same samples.

Agreement was 99.2% for no-growth cultures, 95.6% for positive cultures, and 77.1% for contaminated or mixed growth cultures, the researchers wrote.

The lower agreement for contaminated cultures was due to “a deliberately precautionary behavior, which is related to ‘safety by design’ criteria,” the researchers noted.

Lead study author Alberto Signoroni, PhD, Associate Professor of Computer Science, University of Brescia, wrote in Nature that many of the plates identified by medical technologists as “contaminated” were labeled as “positive” by DeepColony. “We maximized true negatives while allowing for some false positives, so that DeepColony [can] focus on the most relevant or critical cases,” he said.

Will DeepColony replace medical technologists in clinical laboratories any time soon? Not likely. But the Brescia University study indicates the direction AI in healthcare is headed, with high accuracy and increasing speed. The day may not be far off when pathologists and microbiologists regularly employ AI algorithms to diagnose disease.

—Stephen Beale

Related Information:

Hierarchical AI Enables Global Interpretation of Culture Plates in the Era of Digital Microbiology

Hierarchical Deep Learning Neural Network (HiDeNN): An Artificial Intelligence (AI) Framework for Computational Science and Engineering

An AI System Helps Microbiologists Identify Bacteria

This AI Research Helps Microbiologists to Identify Bacteria

Deep Learning Meets Clinical Microbiology: Unveiling DeepColony for Automated Culture Plates Interpretation

University of Southern California Researchers Develop Vaccine That Boosts Immunity and Helps Patients Avoid Deadly Infections While in Hospitals

New vaccine could give clinical laboratories and antimicrobial stewardship programs the tool they need to dramatically reduce hospital-acquired infections

Healthcare providers and clinical laboratories continue to struggle against hospital-acquired infections (HAIs) and ever-evolving antimicrobial resistant (AMR) bacteria. But now, the University of Southern California (USC) has developed and patented an experimental vaccine that has been shown to protect against so-called “superbugs,” such as methicillin-resistant Staphylococcus aureus (MRSA), an AMR bacteria that causes potentially deadly staph infections in hospitals and other healthcare settings.

The innovative approach focuses on bolstering the patient’s immune system itself, rather than relying on proteins to fight infections, according to a USC Today article. 

Developed by senior study author Brad Spellberg, MD, Chief Medical Officer at the Los Angeles General Medical Center, and colleagues, “The experimental vaccine takes an entirely different approach: It gooses the body’s preexisting supply of pathogen-gobbling immune cells called macrophages, which engulf and digest bacteria, fungi, and other bad actors. These activated fighters, found in all tissues, quickly neutralize incoming invaders which might otherwise multiply rapidly and overwhelm the body’s defenses,” USC Today reported. 

“This is very different from developing new antibiotics,” Jun Yan, a doctoral student at Keck School of Medicine and the study’s first author, told USC Today. “This is using our own immune system to fight against different superbugs, which is a different approach than everybody else.”

To develop the vaccine [the USC researchers] formed a biotechnology startup called ExBaq LLC in Bethesda, Md.

They published their findings in the journal Science Translational Medicine title, “A Protein-Free Vaccine Stimulates Innate Immunity and Protects against Nosocomial Pathogens.”

Ishwar K. Puri, PhD

“The pandemic stimulated unprecedented innovation in vaccine development, where federal funding and university-industry partnerships were game changers for translating promising discoveries from academic labs for the good of all,” said Ishwar K. Puri, PhD (above), senior vice president of research and innovation at USC. “We are both pleased and proud of the critical support the USC Stevens Center provided to enable the development of ExBaq’s experimental vaccine that protects vulnerable populations from serious infections.” Clinical laboratories that work with hospitals in the fight against hospital-acquired infections understand the importance of this discovery. (Photo copyright: University of Southern California.)

USC Vaccine Details

The USC team developed a “protein-free vaccine, composed of aluminum hydroxide, monophosphoryl lipid A, and fungal mannan, that stimulates the innate immune system and confers protection,” the researchers wrote in Science Translational Medicine.

“Tested in two independent labs, the vaccine works within 24 hours and lasts for up to 28 days. In lab models, the number of pathogen-eating immune cells in the blood increased dramatically, and survival time of invasive blood and lung infections improved. Early data suggest that a second dose could extend the window to prevent infection,” USC Today reported.

Unlike anything currently available, the new vaccine focuses on boosting the body itself instead of creating antibodies against certain pathogens. A mere dose of the vaccine is described to “provide rapid protection against nine different bacteria and fungi species,” USC Today noted.

“It’s an early warning system. It’s like Homeland Security putting out a terror alert. Everybody, keep your eyes open. Keep an eye out for suspicious packages. You’re alerting the soldiers and tanks of your immune system. The vaccine activates them,” Spellberg told USC Today

“The vaccine acted through stimulation of the innate, rather than the adaptive, immune system, as demonstrated by efficacy in the absence of lymphocytes that were abrogated by macrophage depletion. A role for macrophages was further supported by the finding that vaccination induced macrophage epigenetic alterations that modulated phagocytosis and the inflammatory response to infection. Together, these data show that this protein-free vaccine is a promising strategy to prevent deadly antimicrobial-resistant healthcare-associated infections,” the researchers wrote in Science Translational Medicine.

Great Need for This Protection

According to the federal Centers for Disease Control and Prevention (CDC), 1.7 million infections and 99,000 deaths are caused by HAIs annually.

“Patients who acquire infections from surgery spend, on average, an additional 6.5 days in the hospital, are five times more likely to be readmitted after discharge and twice as likely to die. Moreover, surgical patients who develop infections are 60% more likely to require admission to a hospital’s intensive care unit. Surgical infections are believed to account for up to 10 billion dollars annually in healthcare expenditures,” the CDC reports.

“All hospitalized patients are susceptible to contracting a [hospital-acquired] infection. Some patients are at greater risk than others: young children, the elderly, and persons with compromised immune systems are more likely to get an infection. Other risk factors are long hospital stays, the use of indwelling catheters, failure of healthcare workers to wash their hands, and overuse of antibiotics,” the CDC notes.

Therefore, USC’s new vaccine may be just what the doctor ordered to protect patients in hospitals and other healthcare settings from deadly HAIs.

Looking Ahead

There are currently no vaccines that are FDA-approved that treat “the most serious antibiotic resistant infections,” USC Today reported.

“Even if there were such vaccines, multiple vaccines would have to be deployed simultaneously to protect against the full slate of antibiotic-resistant microbes that cause healthcare-acquired infections,” Brian Luna, PhD, assistant professor of molecular microbiology and immunology at USC’s Keck School of Medicine, told USC Today

Thus, USC’s new vaccine could be a boon to hospital antimicrobial stewardship programs. But so far, it has only been tested on mice.

“The next step is getting guidance from the US Food and Drug Administration (FDA) on the design of a clinical trial. The first such trial would be done in healthy volunteers to find the right dose of vaccine that is safe and triggers the same kind of immune response in people as seen in the mice,” USC Today reported.

ExBaq LLC has begun talking with potential larger partners who might be willing to help develop the vaccine into clinical testing.

For years hospitals and other healthcare settings—such as long-term care facilities, urgent care clinics, and clinical laboratories—have fought an uphill battle against superbugs. So, for a vaccine to be on the horizon that can prevent life-threatening hospital-acquired infections would be a game changer.

With antimicrobial stewardships being a requirement in all hospitals, medical laboratory managers and microbiologists may celebrate this new development and its potential to be a useful tool in fighting antimicrobial resistant bacteria in their facilities.

—Kristin Althea O’Connor

Related Information:

Superbugs Including MRSA Thwarted by Unconventional Vaccine

A Protein-Free Vaccine Stimulates Innate Immunity and Protects Against Nosocomial Pathogens

Superbug Vaccine “Hulkifies” Macrophages in Mouse Model

Experimental Low-Cost Blood Test Can Detect Multiple Cancers, Researchers Say

Test uses a new ultrasensitive immunoassay to detect a known clinical laboratory diagnostic protein biomarker for many common cancers

Researchers from Mass General Brigham, the Dana-Farber Cancer Institute, Harvard University’s Wyss Institute and other institutions around the world have reportedly developed a simple clinical laboratory blood test that can detect a common protein biomarker associated with multiple types of cancer, including colorectal, gastroesophageal, and ovarian cancers.

Best of all, the researchers say the test could provide an inexpensive means of early diagnosis. This assay could also be used to monitor how well patients respond to cancer therapy, according to a news release.

The test, which is still in experimental stages, detects the presence of LINE-1 ORF1p, a protein expressed in many common cancers, as well as high-risk precursors, while having “negligible expression in normal tissues,” the researchers wrote in a paper they published in Cancer Discovery titled, “Ultrasensitive Detection of Circulating LINE-1 ORF1p as a Specific Multicancer Biomarker.”

The protein had previously been identified as a promising biomarker and is readily detectable in tumor tissue, they wrote. However, it is found in extremely low concentrations in blood plasma and is “well below detection limits of conventional clinical laboratory methods,” they noted.

To overcome that obstacle, they employed an ultra-sensitive immunoassay known as a Simoa (Single-Molecule Array), an immunoassay platform for measuring fluid biomarkers.

“We were shocked by how well this test worked in detecting the biomarker’s expression across cancer types,” said lead study author gastroenterologist Martin Taylor, MD, PhD, Instructor in Pathology, Massachusetts General Hospital and Harvard Medical School, in the press release. “It’s created more questions for us to explore and sparked interest among collaborators across many institutions.”

Kathleen Burns, MD, PhD

“We’ve known since the 1980s that transposable elements were active in some cancers, and nearly 10 years ago we reported that ORF1p was a pervasive cancer biomarker, but, until now, we haven’t had the ability to detect it in blood tests,” said pathologist and study co-author Kathleen Burns, MD, PhD (above), Chair of the Department of Pathology at Dana-Farber Cancer Institute and a Professor of Pathology at Harvard Medical School, in a press release. “Having a technology capable of detecting ORF1p in blood opens so many possibilities for clinical applications.” Clinical laboratories may soon have a new blood test to detect multiple types of cancer. (Photo copyright: Dana-Farber Cancer Institute.)

Simoa’s Advantages

In their press release, the researchers described ORF1p as “a hallmark of many cancers, particularly p53-deficient epithelial cancers,” a category that includes lung, breast, prostate, uterine, pancreatic, and head and neck cancers in addition to the cancers noted above.

“Pervasive expression of ORF1p in carcinomas, and the lack of expression in normal tissues, makes ORF1p unlike other protein biomarkers which have normal expression levels,” Taylor said in the press release. “This unique biology makes it highly specific.”

Simoa was developed at the laboratory of study co-author David R. Walt, PhD, the Hansjörg Wyss Professor of Bioinspired Engineering at Harvard Medical School, and Professor of Pathology at Harvard Medical School and Brigham and Women’s Hospital.

The Simoa technology “enables 100- to 1,000-fold improvements in sensitivity over conventional enzyme-linked immunosorbent assay (ELISA) techniques, thus opening the window to measuring proteins at concentrations that have never been detected before in various biological fluids such as plasma or saliva,” according to the Walt Lab website.

Simoa assays take less than two hours to run and require less than $3 in consumables. They are “simple to perform, scalable, and have clinical-grade coefficients of variation,” the researchers wrote.

Study Results

Using the first generation of the ORF1p Simoa assay, the researchers tested blood samples of patients with a variety of cancers along with 406 individuals, regarded as healthy, who served as controls. The test proved to be most effective among patients with colorectal and ovarian cancer, finding detectable levels of ORF1p in 58% of former and 71% of the latter. Detectable levels were found in patients with advanced-stage as well as early-stage disease, the researchers wrote in Cancer Discovery.

Among the 406 healthy controls, the test found detectable levels of ORF1p in only five. However, the control with the highest detectable levels, regarded as healthy when donating blood, “was six months later found to have prostate cancer and 19 months later found to have lymphoma,” the researchers wrote.

They later reengineered the Simoa assay to increase its sensitivity, resulting in improved detection of the protein in blood samples from patients with colorectal, gastroesophageal, ovarian, uterine, and breast cancers.

The researchers also employed the test on samples from 19 patients with gastroesophageal cancer to gauge its utility for monitoring therapeutic response. Although this was a small sample, they found that among 13 patients who had responded to therapy, “circulating ORF1p dropped to undetectable levels at follow-up sampling.”

“More Work to Be Done”

The Simoa assay has limitations, the researchers acknowledged. It doesn’t identify the location of cancers, and it “isn’t successful in identifying all cancers and their subtypes,” the press release stated, adding that the test will likely be used in conjunction with other early-detection approaches. The researchers also said they want to gauge the test’s accuracy in larger cohorts.

“The test is very specific, but it doesn’t tell us enough information to be used in a vacuum,” Walt said in the news release. “It’s exciting to see the early success of this ultrasensitive assessment tool, but there is more work to be done.”

More studies will be needed to valid these findings. That this promising new multi-cancer immunoassay is based on a clinical laboratory blood sample means its less invasive and less painful for patients. It’s a good example of an assay that takes a proteomic approach looking for protein cancer biomarkers rather than the genetic approach looking for molecular DNA/RNA biomarkers of cancer.

—Stephen Beale

Related Information:

Ultrasensitive Blood Test Detects ‘Pan-Cancer’ Biomarker

New Blood Test Could Offer Earlier Detection of Common Deadly Cancers

Ultrasensitive Detection of Circulating LINE-1 ORF1p as a Specific Multicancer Biomarker

Noninvasive and Multicancer Biomarkers: The Promise of LINE-1 Retrotransposons

LINE-1-ORF1p Is a Promising Biomarker for Early Cancer Detection, But More Research Is Needed

‘Pan-Cancer’ Found in Highly Sensitive Blood Test

Federal Government Bans Elizabeth Holmes from Participating in Government Health Programs for 90 Years

Theranos founder and former CEO continues down the path she began by defrauding her investors and lying to clinical laboratory leaders about her technology’s capabilities

In the latest from the Elizabeth Holmes/Theranos scandal, the federal government has banned Holmes from participating in government health programs for 90 years, according to a statement from the US Department of Health and Human Services (HHS) Office of the Inspector General (OIG). Many clinical laboratory leaders may find this a fitting next chapter in her story.

As a result of the ban, Holmes is “barred from receiving payments from federal health programs for services or products, which significantly restricts her ability to work in the healthcare sector,” ARS Technica reported.

So, Holmes, who is 39-years old, is basically banned for life. This is in addition to her 11-year prison sentence which was paired with $452,047,200 in restitution.

“The exclusion was announced by Inspector General Christi Grimm of the Department of Health and Human Services’ Office of Inspector General,” ARS Technica noted, adding that HHS-OIG also “excluded former Theranos President Ramesh “Sunny” Balwani from federal health programs for 90 years.” This is on top of the almost 13-year-long prison sentence he is serving for fraud.

“The Health and Human Services Department can exclude anyone convicted of certain felonies from Medicare, Medicaid, and Pentagon health programs,” STAT reported.  

Inspector General Christi Grimm

“Accurate and dependable diagnostic testing technology is imperative to our public health infrastructure,” said Inspector General Christi Grimm (above) in an HHS-OIG statement. “As technology evolves, so do our efforts to safeguard the health and safety of patients, and HHS-OIG will continue to use its exclusion authority to protect the public from bad actors.” Observant clinical laboratory leaders will recognize this as yet another episode in the Elizabeth Holmes/Theranos fraud saga they’ve been following for years. (Photo copyright: HHS-OIG.)

Why the Ban?

“The Office of Inspector General (OIG) for the Department of Health and Human Services (HHS) cited Holmes’ 2022 conviction for fraud and conspiracy to commit wire fraud as the reason for her ban,” The Hill reported.

“False statements related to the reliability of these medical products can endanger the health of patients and sow distrust in our healthcare system,” Grimm stated in the HHS-OIG statement, which noted, “The statutory minimum for an exclusion based on convictions like Holmes’ is five years.

“When certain aggravating factors are present, a longer period of exclusion is justified,” the statement continued. “The length of Holmes’ exclusion is based on the application of several aggravating factors, including the length of time the acts were committed, incarceration, and the amount of restitution ordered to be paid.”

Rise and Fall of Elizabeth Holmes

Readers of Dark Daily’s e-briefs covering the Holmes/Theranos fraud saga will recall details on Holmes’ journey from mega success to her current state of incarceration for defrauding her investors.

In November 2022, she was handed an 11-year prison sentence for not disclosing that Theranos’ innovative blood testing technology, Edison, was producing flawed and false results. Theranos had “raised hundreds of millions of dollars, named prominent former US officials to its board, and explored a partnership with the US military to use its tests on the battlefield,” STAT reported.

To get Holmes physically into prison was a journey unto itself. At one point, evidence showed her as a potential flight risk. “In the same court filings, prosecutors said Holmes and her partner, William Evans, bought one-way tickets to Mexico in December 2021, a fact confirmed by her lawyers,” Dark Daily’s sister publication The Dark Report revealed in “Elizabeth Holmes’ Appeal Questions Competence of CLIA Lab Director.”

Drama around her move into prison continued. “The former CEO’s attorneys are making last-minute legal moves to delay her prison sentence while she appeals her guilty verdict,” Dark Daily reported.

At the same time, Holmes appeared to be on a mission to revamp her public image.

“On May 7, The New York Times profiled Holmes in a massive, 5,000-word story that attempted to portray her as a flawed businessperson who now prefers a simpler life with her partner and two young children,” Dark Daily reported in “Former Theranos CEO Elizabeth Holmes Fights Prison Sentence While Claiming She Was ‘Not Being Authentic’ with Public Image.”

In the Times piece, Holmes talked about her plans to continue to pursue a life in healthcare. “In the story, Holmes contended that she still thinks about contributing to the clinical laboratory field. Holmes told The Times that she still works on healthcare-related inventions and will continue to do so if she reports to prison,” The Dark Report covered in “Elizabeth Holmes Still Wants ‘To Contribute’ in Healthcare.”

In the meantime, her legal fees continued to mount beyond her ability to pay. “Holmes’ prior cadre of lawyers quit after she could not compensate them, The Times reported,” The Dark Report noted. “One pre-sentencing report by the government put her legal fees at more than $30 million,” according to The New York Times.

Apparently, this closes the latest chapter in the never-ending saga of Elizabeth Holmes’ fall from grace and ultimate conviction for defrauding her investors and lying to healthcare executives, pathologists, and clinical laboratory leaders.

—Kristin Althea O’Connor

Related Information:

HHS-OIG Issues Notice of Exclusion to Founder and CEO of Theranos, Inc.

Feds Bar Theranos Founder Elizabeth Holmes from Government Health Programs

Elizabeth Holmes Barred From Federal Health Programs For 90 Years

Elizabeth Holmes Banned from Federal Health Programs for 90 Years

Elizabeth Holmes Still Wants ‘To Contribute’ in Healthcare

Former Theranos CEO Elizabeth Holmes Fights Prison Sentence While Claiming She Was ‘Not Being Authentic’ with Public Image

Elizabeth Holmes’ Appeal Questions Competence of CLIA Lab Director

Dark Report Summary on Elizabeth Holmes

University Hospitals Birmingham Claims Its New AI Model Detects Certain Skin Cancers with Nearly 100% Accuracy

But dermatologists and other cancer doctors still say AI is not ready to operate without oversight by clinical physicians

Dermatopathologists and the anatomic pathology profession in general have a new example of how artificial intelligence’s (AI’s) ability to detect cancer with accuracy comparable to a trained pathologist has greatly improved. At the latest European Academy of Dermatology and Venereology (EADV) Congress, scientists presented a study in which researchers with the University Hospitals Birmingham NHS Foundation Trust used an AI platform to assess 22,356 people over 2.5 years.

According to an EADV press release, the AI software demonstrated a “100% (59/59 cases identified) sensitivity for detecting melanoma—the most serious form of skin cancer.” The AI software also “correctly detected 99.5% (189/190) of all skin cancers and 92.5% (541/585) of pre-cancerous lesions.”  

“Of the basal cell carcinoma cases, a single case was missed out of 190, which was later identified at a second read by a dermatologist ‘safety net.’ This further demonstrates the need to have appropriate clinical oversight of the AI,” the press release noted.

AI is being utilized more frequently within the healthcare industry to diagnose and treat a plethora of illnesses. This recent study performed by scientists in the United Kingdom demonstrates that new AI models can be used to accurately diagnose some skin cancers, but that “AI should not be used as a standalone detection tool without the support of a consultant dermatologist,” the press release noted.

“The role of AI in dermatology and the most appropriate pathway are debated,” said Kashini Andrew, MBBS, MSc (above), Specialist Registrar at University Hospitals Birmingham NHS Foundation Trust. “Further research with appropriate clinical oversight may allow the deployment of AI as a triage tool. However, any pathway must demonstrate cost-effectiveness, and AI is currently not a stand-alone tool in dermatology. Our data shows the great promise of AI in future provision of healthcare.” Clinical laboratories and dermatopathologists in the United States will want to watch the further development of this AI application. (Photo copyright: LinkedIn.)

How the NHS Scientists Conducted Their Study

Researchers tested their algorithm for almost three years to determine its ability to detect cancerous and pre-cancerous growths. A group of dermatologists and medical photographers entered patient information into their algorithm and trained it how to detect abnormalities. The collected data came from 22,356 patients with suspected skin cancers and included photos of known cancers.

The scientists then repeatedly recalibrated the software to ensure it could distinguish between non-cancerous lesions and potential cancers or malignancies. Dermatologists then reviewed the final data from the algorithm and compared it to diagnoses from health professionals.

“This study has demonstrated how AI is rapidly improving and learning, with the high accuracy directly attributable to improvements in AI training techniques and the quality of data used to train the AI,” said Kashini Andrew, MBBS, MSc, Specialist Registrar at University Hospitals Birmingham NHS Foundation Trust, and co-author of the study, in  EADV press release.

Freeing Up Physician Time

The EADV Congress where the NHS researchers presented their findings took place in October in Berlin. The first model of their AI software was tested in 2021 and that version was able to detect:

  • 85.9% (195 out of 227) of melanoma cases,
  • 83.8% (903 out of 1078) of all skin cancers, and
  • 54.1% (496 out of 917) of pre-cancerous lesions.

After fine-tuning, the latest version of the algorithm was even more promising, with results that included the detection of:

  • 100% (59 out of 59) cases of melanoma,
  • 99.5% (189 out of 190) of all skin cancers, and
  • 92.5% (541 out of 585) pre-cancerous lesions.

“The latest version of the software has saved over 1,000 face-to-face consultations in the secondary care setting between April 2022 and January 2023, freeing up more time for patients that need urgent attention,” Andrew said in the press release.

Still, the researchers admit that AI should not be used as the only detection method for skin cancers.

“We would like to stress that AI should not be used as a standalone tool in skin cancer detection and that AI is not a substitute for consultant dermatologists,” stated Irshad Zaki, B Med Sci (Hons), Consultant Dermatologist at University Hospitals Birmingham NHS Foundation Trust and one of the authors of the study, in the press release.

“The role of AI in dermatology and the most appropriate pathway are debated. Further research with appropriate clinical oversight may allow the deployment of AI as a triage tool,” said Andrew in the press release. “However, any pathway must demonstrate cost-effectiveness, and AI is currently not a stand-alone tool in dermatology. Our data shows the great promise of AI in future provision of healthcare.”

Two People in the US Die of Skin Cancer Every Hour

According to the Skin Cancer Foundation, skin cancer is the most common cancer in the United States as well as the rest of the world. More people in the US are diagnosed with skin cancer every year than all other cancers combined.

When detected early, the five-year survival rate for melanoma is 99%, but more than two people in the US die of skin cancer every hour. At least one in five Americans will develop skin cancer by the age of 70 and more than 9,500 people are diagnosed with the disease every day in the US.

The annual cost of treating skin cancers in the United States is estimated at $8.1 billion annually, with approximately $3.3 billion of that amount being for melanoma and the remaining $4.8 billion for non-melanoma skin cancers.

More research is needed before University Hospitals Birmingham’s new AI model can be used clinically in the diagnoses of skin cancers. However, its level of accuracy is unprecedented in AI diagnostics. This is a noteworthy step forward in the field of AI for diagnostic purposes that can be used by clinical laboratories and dermatopathologists.

—JP Schlingman

Related Information:

The App That is 100% Effective at Spotting Some Skin Cancers—as Study Shows Melanoma No Longer the Biggest Killer

AI Software Shows Significant Improvement in Skin Cancer Detection, New Study Shows

Skin Cancer Facts and Statistics

Google DeepMind Says Its New Artificial Intelligence Tool Can Predict Which Genetic Variants Are Likely to Cause Disease

AMA Issues Proposal to Help Circumvent False and Misleading Information When Using Artificial Intelligence in Medicine

UCLA’s Virtual Histology Could Eliminate Need for Invasive Biopsies for Some Skin Conditions and Cancers

IT Experts Demonstrate How AI and Computer Microphones Can Be Used to Figure Out Passwords and Break into Customer Accounts

Clinical laboratories and pathology groups should be on the alert to this new digital threat; telehealth sessions and video conferencing calls particularly vulnerable to acoustic AI attacks

Banks may be the first to get hit by a new form of hacking because of all the money they hold in deposit accounts, but experts say healthcare providers—including medical laboratories—are comparably lucrative targets because of the value of patient data. The point of this hacking spear is artificial intelligence (AI) with increased capabilities to penetrate digital defenses.

AI is developing rapidly. Are healthcare organizations keeping up? The hackers sure are. An article from GoBankingRates titled, “How Hackers Are Using AI to Steal Your Bank Account Password,” reveals startling new AI capabilities that could enable bad actors to compromise information technology (IT) security and steal from customers’ accounts.

Though the article covers how the AI could conduct cyberattacks on bank information, similar techniques can be employed to gain access to patients’ protected health information (PHI) and clinical laboratory databases as well, putting all healthcare consumers at risk.

The new AI cyberattack employs an acoustic Side Channel Attack (SCA). An SCA is an attack enabled by leakage of information from a physical computer system. The “acoustic” SCA listens to keystrokes through a computer’s microphone to guess a password with 95% accuracy.

That’s according to a UK study published in IEEE Xplore, a journal of the IEEE European Symposium on Security and Privacy Workshops, titled, “A Practical Deep Learning-Based Acoustic Side Channel Attack on Keyboards.”

“With recent developments in deep learning, the ubiquity of microphones and the rise in online services via personal devices, acoustic side channel attacks present a greater threat to keyboards than ever,” wrote UK study authors Joshua Harrison, MEng, Durham University; Ehsan Toreini, University of Surrey; and Maryam Mehrnezhad, PhD, University of London.

Hackers could be recording keystrokes during video conferencing calls as well, where an accuracy of 93% is achievable, the authors added.

This nefarious technological advance could spell trouble for healthcare security. Using acoustic SCA attacks, busy healthcare facilities, clinical laboratories, and telehealth appointments could all be potentially compromised.

“The ubiquity of keyboard acoustic emanations makes them not only a readily available attack vector, but also prompts victims to underestimate (and therefore not try to hide) their output,” wrote Joshua Harrison, MEng (above), and his team in their IEEE Xplore paper. “For example, when typing a password, people will regularly hide their screen but will do little to obfuscate their keyboard’s sound.” Since computer keyboards and microphones in healthcare settings like hospitals and clinical laboratories are completely ubiquitous, the risk that this AI technology will be used to invade and steal patients’ protected health information is high. (Photo copyright: CNBC.)

Why Do Hackers Target Healthcare?

Ransomware attacks in healthcare are costly and dangerous. According to InstaMed, a healthcare payments and billing company owned by J.P. Morgan, healthcare data breaches increased to 29.5% in 2021 costing over $9 million. And beyond the financial implications, these attacks put sensitive patient data at risk.

Healthcare can be seen as one of the most desirable markets for hackers seeking sensitive information. As InstaMed points out, credit card hacks are usually quickly figured out and stopped. However, “medical records can contain multiple pieces of personally identifiable information. Additionally, breaches that expose this type of data typically take longer to uncover and are harder for an organization to determine in magnitude.”

With AI advancing at such a high rate, healthcare organizations may be unable to adapt older network systems quickly—leaving them vulnerable.

“Legacy devices have been an issue for a while now,” Alexandra Murdoch, medical data analyst at GlobalData PLC, told Medical Device Network, “Usually big medical devices, such as imaging equipment or MRI machines are really expensive and so hospitals do not replace them often. So as a result, we have in the network these old devices that can’t really be updated, and because they can’t be updated, they can’t be protected.”

Vulnerabilities of Telehealth

In “Penn Medicine Study Shows Telemedicine Can Cut Employer Healthcare Costs by 25%,” Dark Daily reported a study conducted by the Perelman School of Medicine at the University of Pennsylvania (Penn Medicine) which suggested there could be significant financial advantages for hospitals that conduct telehealth visits. This, we projected, would be a boon to clinical laboratories that perform medical testing for telemedicine providers.

But telehealth, according to the UK researchers, may also be one way hackers get past safeguards and into critical hospital systems.

“When trained on keystrokes recorded using the video-conferencing software Zoom, an accuracy of 93% was achieved, a new best for the medium. Our results prove the practicality of these side channel attacks via off-the-shelf equipment and algorithms,” the UK researchers wrote in IEEE Xplore.

“[AI] has worrying implications for the medical industry, as more and more appointments go virtual, the implications of deepfakes is a bit concerning if you only interact with a doctor over a Teams or a Zoom call,” David Higgins, Senior Director at information security company CyberArk, told Medical Device Network.

Higgins elaborated on why healthcare is a highly targeted industry for hackers.

“For a credit card record, you are looking at a cost of one to two dollars, but for a medical record, you are talking much more information because the gain for the purposes of social engineering becomes very lucrative. It’s so much easier to launch a ransomware attack, you don’t even need to be a coder, you can just buy ransomware off of the dark web and use it.”

Steps Healthcare Organizations Should Take to Prevent Cyberattacks

Hackers will do whatever they can to get their hands on medical records because stealing them is so lucrative. And this may only be the beginning, Higgins noted.

“I don’t think we are going to see a slowdown in attacks. What we are starting to see is that techniques to make that initial intrusion are becoming more sophisticated and more targeted,” he told Medical Device Network. “Now with things like AI coming into the mix, it’s going to become much harder for the day-to-day individual to spot a malicious email. Generative AI is going to fuel more of that ransomware and sadly it’s going to make it easier for more people to get past that first intrusion stage.”

To combat these attacks patient data needs to be encrypted, devices updated, and medical staff well-trained to spot cyberattacks before they get out of hand. These SCA attacks on bank accounts could be easily transferable to attacks on healthcare organizations’ patient records.

Clinical laboratories, anatomic pathology groups, and other healthcare facilities would be wise to invest in cybersecurity, training for workers, and updated technology. The hackers are going to stay on top of the technology, healthcare leaders need to be one step ahead of them.

—Ashley Croce

Related Information:

How Hackers Are Using AI to Steal Your Bank Account Password

A Practical Deep Learning-Based Acoustic Side Channel Attack on Keyboards

AI Can Steal Passwords with 95% Accuracy by ‘Listening’ to Keystrokes, Alarming Study Finds

New ‘Deep Learning Attack’ Deciphers Laptop Keystrokes with 95% Accuracy

Can A.I. Steal Your Password? Study Finds 95% Accuracy by Listening to Keyboard Typing

Ransomware in Healthcare: What You Need to Know

Hospital 2040: How Healthcare Cybercrime is Predicted to Escalate

30 Crucial Cybersecurity Statistics (2023): Data, Trends and More

Penn Medicine Study Shows Telemedicine Can Cut Employer Healthcare Costs by 25%

;