Radiological method using AI algorithms to detect, locate, and identify cancer could negate the need for invasive, painful clinical laboratory testing of tissue biopsies
This will be of interest to histopathologists and radiologist technologists who are working to develop AI deep learning algorithms to read computed tomography scans (CT scans) to speed diagnosis and treatment of cancer patients.
“Researchers used the CT scans of 170 patients treated at The Royal Marsden with the two most common forms of retroperitoneal sarcoma (RPS)—leiomyosarcoma and liposarcoma—to create an AI algorithm, which was then tested on nearly 90 patients from centers across Europe and the US,” the news release notes.
The researchers then “used a technique called radiomics to analyze the CT scan data, which can extract information about the patient’s disease from medical images, including data which can’t be distinguished by the human eye,” the new release states.
The research team sought to make improvements with this type of cancer because these tumors have “a poor prognosis, upfront characterization of the tumor is difficult, and under-grading is common,” they wrote. The fact that AI reading of CT scans is a non-invasive procedure is major benefit, they added.
“This is the largest and most robust study to date that has successfully developed and tested an AI model aimed at improving the diagnosis and grading of retroperitoneal sarcoma using data from CT scans,” said the study’s lead oncology radiologist Christina Messiou, MD, (above), Consultant Radiologist at The Royal Marsden NHS Foundation Trust and Professor in Imaging for Personalized Oncology at The Institute of Cancer Research, London, in a news release. Invasive medical laboratory testing of cancer biopsies may eventually become a thing of the past if this research becomes clinically available for oncology diagnosis. (Photo copyright: The Royal Marsden.)
Study Details
RPS is a relatively difficult cancer to spot, let alone diagnose. It is a rare form of soft-tissue cancer “with approximately 8,600 new cases diagnosed annually in the United States—less than 1% of all newly diagnosed malignancies,” according to Brigham and Women’s Hospital.
In their published study, the UK researchers noted that, “Although more than 50 soft tissue sarcoma radiomics studies have been completed, few include retroperitoneal sarcomas, and the majority use single-center datasets without independent validation. The limited interpretation of the quantitative radiological phenotype in retroperitoneal sarcomas and its association with tumor biology is a missed opportunity.”
According to the ICR news release, “The [AI] model accurately graded the risk—or how aggressive a tumor is likely to be—[in] 82% of the tumors analyzed, while only 44% were correctly graded using a biopsy.”
Additionally, “The [AI] model also accurately predicted the disease type [in] 84% of the sarcomas tested—meaning it can effectively differentiate between leiomyosarcoma and liposarcoma—compared with radiologists who were not able to diagnose 35% of the cases,” the news release states.
“There is an urgent need to improve the diagnosis and treatment of patients with retroperitoneal sarcoma, who currently have poor outcomes,” said the study’s first author Amani Arthur, PhD, Clinical Research Fellow at The Institute of Cancer Research, London, and Registrar at The Royal Marsden NHS Foundation Trust, in the ICR news release.
“The disease is very rare—clinicians may only see one or two cases in their career—which means diagnosis can be slow. This type of sarcoma is also difficult to treat as it can grow to large sizes and, due to the tumor’s location in the abdomen, involve complex surgery,” she continued. “Through this early research, we’ve developed an innovative AI tool using imaging data that could help us more accurately and quickly identify the type and grade of retroperitoneal sarcomas than current methods. This could improve patient outcomes by helping to speed up diagnosis of the disease, and better tailor treatment by reliably identifying the risk of each patient’s disease.
“In the next phase of the study, we will test this model in clinic on patients with potential retroperitoneal sarcomas to see if it can accurately characterize their disease and measure the performance of the technology over time,” Arthur added.
Importance of Study Findings
Speed of detection is key to successful cancer diagnoses, noted Richard Davidson, Chief Executive of Sarcoma UK, a bone and soft tissue cancer charity.
“People are more likely to survive sarcoma if their cancer is diagnosed early—when treatments can be effective and before the sarcoma has spread to other parts of the body. One in six people with sarcoma cancer wait more than a year to receive an accurate diagnosis, so any research that helps patients receive better treatment, care, information and support is welcome,” he told The Guardian.
According to the World Health Organization, cancer kills about 10 million people worldwide every year. Acquisition and medical laboratory testing of tissue biopsies is both painful to patients and time consuming. Thus, a non-invasive method of diagnosing deadly cancers quickly, accurately, and early would be a boon to oncology practices worldwide and could save thousands of lives each year.
Pathologists and clinical laboratory managers will want to stay alert to the concerns voiced by tech experts about the need to exercise caution when using generative AI to assist medical diagnoses
GPTs are an integral part of the framework of a generative artificial intelligence that creates text, images, and other media using generative models. These neural network models can learn the patterns and structure of inputted information and then develop new data that contains similar characteristics.
Through their proposal, the AMA has developed principles and recommendations surrounding the benefits and potentially harmful consequences of relying on AI-generated medical advice and content to advance diagnoses.
“We’re trying to look around the corner for our patients to understand the promise and limitations of AI,” said Alexander Ding, MD (above), AMA Trustee and Associate Vice President for Physician Strategy and Medical Affairs at Humana, in a press release. “There is a lot of uncertainty about the direction and regulatory framework for this use of AI that has found its way into the day-to-day practice of medicine.” Clinical laboratory professionals following advances in AI may want to remain informed on the use of generative AI solutions in healthcare. (Photo copyright: American Medical Association.)
Preventing Spread of Mis/Disinformation
GPTs are “a family of neural network models that uses the transformer architecture and is a key advancement in artificial intelligence (AI) powering generative AI applications such as ChatGPT,” according to Amazon Web Services.
In addition to creating human-like text and content, GPTs have the ability to answer questions in a conversational manner. They can analyze language queries and then predict high-quality responses based on their understanding of the language. GPTs can perform this task after being trained with billions of parameters on massive language datasets and then generate long responses, not just the next word in a sequence.
“AI holds the promise of transforming medicine,” said diagnostic and interventional radiologist Alexander Ding, MD, AMA Trustee and Associate Vice President for Physician Strategy and Medical Affairs at Humana, in an AMA press release.
“We don’t want to be chasing technology. Rather, as scientists, we want to use our expertise to structure guidelines, and guardrails to prevent unintended consequences, such as baking in bias and widening disparities, dissemination of incorrect medical advice, or spread of misinformation or disinformation,” he added.
The AMA plans to work with the federal government and other appropriate organizations to advise policymakers on the optimal ways to use AI in healthcare to protect patients from misleading AI-generated data that may or may not be validated, accurate, or relevant.
Advantages and Risks of AI in Medicine
The AMA’s proposal was prompted by AMA-affiliated organizations that stressed concerns about the lack of regulatory oversight for GPTs. They are encouraging healthcare professionals to educate patients about the advantages and risks of AI in medicine.
“AI took a huge leap with large language model tool and generative models, so all of the work that has been done up to this point in terms of regulatory and governance frameworks will have to be treated or at least reviewed with this new lens,” Sha Edathumparampil, Corporate Vice President, Digital and Data, Baptist Health South Florida, told Healthcare Brew.
According to the AMA press release, “the current limitations create potential risks for physicians and patients and should be used with appropriate caution at this time. AI-generated fabrications, errors, or inaccuracies can harm patients, and physicians need to be acutely aware of these risks and added liability before they rely on unregulated machine-learning algorithms and tools.”
According to the AMA press release, the organization will propose state and federal regulations for AI tools at next year’s annual meeting in Chicago.
In a July AMA podcast, AMA’s President, Jesse Ehrenfeld, MD, stressed that more must be done through regulation and development to bolster trust in these new technologies.
“There’s a lot of discomfort around the use of these tools among Americans with the idea of AI being used in their own healthcare,” Ehrenfeld said. “There was a 2023 Pew Research Center poll [that said] 60% of Americans would feel uncomfortable if their own healthcare provider relied on AI to do things like diagnose disease or recommend a treatment.”
WHO Issues Cautions about Use of AI in Healthcare
In May, the World Health Organization (WHO) issued a statement advocating for caution when implementing AI-generated large language GPT models into healthcare.
A current example of such a GPT is ChatGPT, a large language-based model (LLM) that enables users to refine and lead conversations towards a desired length, format, style, level of detail and language. Organizations across industries are now utilizing GPT models for Question and Answer bots for customers, text summarization, and content generation and search features.
“Precipitous adoption of untested systems could lead to errors by healthcare workers, cause harm to patients, erode trust in AI, and thereby undermine (or delay) the potential long-term benefits and uses of such technologies around the world,” commented WHO in the statement.
WHO’s concerns regarding the need for prudence and oversight in the use of AI technologies include:
Data used to train AI may be biased, which could pose risks to health, equity, and inclusiveness.
LLMs generate responses that can appear authoritative and plausible, but which may be completely incorrect or contain serious errors.
LLMs may be trained on data for which consent may not have been given.
LLMs may not be able to protect sensitive data that is provided to an application to generate a response.
LLMs can be misused to generate and disseminate highly convincing disinformation in the form of text, audio, or video that may be difficult for people to differentiate from reliable health content.
Tech Experts Recommended Caution
Generative AI will continue to evolve. Therefore, clinical laboratory professionals may want to keep a keen eye on advances in AI technology and GPTs in healthcare diagnosis.
“While generative AI holds tremendous potential to transform various industries, it also presents significant challenges and risks that should not be ignored,” wrote Edathumparampil in an article he penned for CXOTECH Magazine. “With the right strategy and approach, generative AI can be a powerful tool for innovation and differentiation, helping businesses to stay ahead of the competition and better serve their customers.”
GPT’s may eventually be a boon to healthcare providers, including clinical laboratories, and pathology groups. But for the moment, caution is recommended.
By analyzing strains of the bacterium from a hospital ICU, the scientists learned that most infections were triggered within patients, not from cross-transmission
Tracking the source of Hospital-acquired infections (HAI) has long been centered around the assumption that most HAIs originate from cross-transmission within the hospital or healthcare setting. And prevention measures are costly for hospitals and medical laboratories. However, new research puts a surprising new angle on a different source for some proportion of these infections.
The study suggests that most infections caused by Clostridioides difficile (C. Diff), the bacterium most responsible for HAIs, arise not from cross-transmission in the hospital, but within patients who already carry the bacterium.
A researcher performed whole genome sequencing on 425 strains of the bacterium isolated from the samples and found “very little evidence that the strains of C. diff from one patient to the next were the same, which would imply in-hospital acquisition,” according to a UM news story.
“In fact, there were only six genomically supported transmissions over the study period. Instead, people who were already colonized were at greater risk of transitioning to infection,” UM stated.
Arianna Miles-Jay, PhD, a postdoctoral fellow in The Snitkin Lab at the University of Michigan and Manager of the Genomic Analysis Unit at the Michigan Department of Health and Human Services, performed the genomic sequencing. “By systematically culturing every patient, we thought we could understand how transmission was happening. The surprise was that, based on the genomics, there was very little transmission,” she said in the UM news story.
“Something happened to these patients that we still don’t understand to trigger the transition from C. diff hanging out in the gut to the organism causing diarrhea and the other complications resulting from infection,” said Evan Snitkin, PhD (above), Associate Professor of Microbiology and Immunology, and Associate Professor of Internal Medicine, Division of Infectious Diseases at University of Michigan, in a UM news story. Medical laboratories involved in hospital-acquired infection prevention understand the importance of this research and its effect on patient safety. (Photo copyright: University of Michigan.)
Only a Fraction of HAIs Are Through Cross-Transmission
In the study abstract, the researchers wrote that “despite enhanced infection prevention efforts, Clostridioides difficile remains the leading cause of healthcare-associated infections in the United States.”
Citing data from the US Centers for Disease Control and Prevention (CDC), HealthDay reported that “nearly half a million C. diff infections occur in the United States each year. Between 13,000 and 16,000 people die from the bacterium, which causes watery diarrhea and inflammation of the colon. Many of these infections and deaths have been blamed on transmission between hospitalized patients.”
The new study, however, notes that 9.3% of the patients admitted to the ICU carried toxigenic (produces toxins) C. diff, but only 1% acquired it via cross-transmission. The carriers, the study authors wrote, “posed minimal risk to others,” but were 24 times more likely to develop a C. diff infection than non-carriers.
“Our findings suggest that measures in place in the ICU at the time of the study—high rates of compliance with hand hygiene among healthcare personnel, routine environmental disinfection with an agent active against C. diff, and single patient rooms —were effective in preventing C. diff transmission,” Snitkin told HealthDay. “This indicates that to make further progress in protecting patients from developing C. diff infections will require improving our understanding of the triggers that lead patients asymptomatically carrying C. diff to transition to having infections.”
Recognizing Risk Factors
Despite the finding that infections were largely triggered within the patients, the researchers still emphasized the importance of taking measures to prevent hospital-acquired infections.
“In fact, the measures in place in the Rush ICU at the time of the study—high rates of compliance with hand hygiene among healthcare personnel, routine environmental disinfection with an agent active against C. diff, and single patient rooms—were likely responsible for the low transmission rate,” the UM news story noted.
One expert not involved with the study suggested that hospitals’ use of antibiotics may be a factor in causing C. diff carriers to develop infections.
“These findings suggest that while we should continue our current infection prevention strategies, attention should also be given to identifying the individuals who are asymptomatic carriers and finding ways to reduce their risk of developing an infection, like carefully optimizing antibiotic usage and recognizing other risk factors,” Hannah Newman, Senior Director of Infection Prevention at Lenox Hill Hospital in New York City, told HealthDay.
Snitkin, however, told HealthDay that other factors are likely at play. “There is support for antibiotic disruption of the microbiota being one type of trigger event, but there is certainly more to it than that, as not every patient who carries C. diff and receives antibiotics will develop an infection.”
Another expert not involved with the study told HealthDay that “many patients are already colonized,” especially older ones or those who have been previously hospitalized.
“A lot of their normal flora in their GI tract can be altered either through surgery or antibiotics or some other mechanism, and then symptoms occur, and that’s when they are treated with antibiotics,” said Donna Armellino, RN, Senior VP of Infection Prevention at Northwell Health in Manhasset, New York.
This research also demonstrates the value of faster, cheaper, more accurate gene sequencing for researching life-threatening conditions. Microbiologists, Clinical laboratory scientists, and pathologists will want monitor further developments involving these findings as researchers from University of Michigan and Rush University Medical Center continue to learn more about the source of C. diff infections.
Free at home clinical-laboratory testing for COVID-19 has been provided in the past, but this time the federal government wants to manufacture as many tests as possible in the US
Pathologists and clinical laboratory managers may be interested to learn that the US market is about to be flooded with millions of at-home COVID-19 rapid tests. The federal government has contracted with 12 US-based test manufacturers to produce 200 million at-home self-tests aimed at detecting “currently circulating COVID-19 variants” through the end of this year, according to a US Department of Health and Human Services (HHS) news release.
Federal officials want to head off “supply chain issues” that developed in the past with reliance on tests made overseas, and to address a possible COVID-19 surge during the fall and winter, the Associated Press (AP) reported.
In fact, 500 million tests have already been distributed through US government channels to long-term care facilities, schools, and low-income senior housing.
“Manufacturing COVID-19 tests in the United States strengthens our preparedness for the upcoming fall and winter seasons, reduces our reliance on other countries, and provides good jobs to hardworking Americans,” said Assistant Secretary for Preparedness and Response Dawn O’Connell, JD (above), in an HHS news release. “ASPR’s investments in these domestic manufacturers will increase availability of tests in the future.” With the federal government preparing for what it expects to be a surge in demand for COVID-19 testing, clinical laboratories may want to track the CDC’s weekly reports on the number of positive COVID-19 cases as this year’s influenza season progresses. (Photo copyright: Administration for Strategic Preparedness and Response.)
In Vitro Diagnostics Test Makers Get Government Gigs
This is not the first time federal officials sent out free COVID-19 tests to consumers. According to the AP, more than 755 million tests went out to US households in previous efforts to fight the spread of infections. But unlike those tests, these tests will be manufactured entirely within the US.
The government’s latest wave of free tests is meant to “complement ASPR’s ongoing distribution of free COVID-19 tests to long-term care facilities, low-income senior housing, uninsured individuals, and underserved communities, with 500 million tests provided to date through these channels,” the HHS news release noted.
Both large and lesser-known in vitro diagnostics (IVD) manufacturers were selected by the federal government to receive funding. They include:
HHS advises people to take the test at the first sign of symptoms (fever, sore throat, runny nose, others), after coming into contact someone who has COVID-19, or prior to gathering with a group, as a preventative to spread of the coronavirus.
Reporting laboratories say existing antibodies work against the BA.2.86 variant.
The variant does not appear to be linked in the US with increasing infections or hospitalizations.
It is “unclear how easily BA.2.86 spreads” relative to other variants.
BA.2.86 has been detected in nine states: Colorado, Delaware, Michigan, Ohio, Pennsylvania, Virginia, Washington, and in wastewater in New York and Ohio, as well as in other countries.
For week ending Sept. 23, the CDC reported the following statistics compared to the prior week:
19,079 COVID-19 hospitalizations, down 3.1%.
Total hospitalizations: 6.3 million.
2.7% of total deaths were due to COVID-19, up 8%.
COVID-19 test positivity rate was 11.6%, down 1.1%.
1.8% of emergency department visits were diagnosed with COVID-19, down 11.7%.
According to Verywell Health, BA.2.86 carries more than 30 mutations.
“Even with a lot of mutations, there are a lot of spots in the virus that can be recognized by our immune system, and there are many shared mutations as well. There will be some protection from new vaccine booster as well as prior infections,” Rajendram Rajnarayanan, PhD, Assistant Dean of Research and Associate Professor, Basic Sciences, Arkansas State University, told Verywell Health.
It’s worth noting that the common cold, influenza, SARS, and SARS-CoV-2 are all in the coronavirus family, and thus closely related with similar symptoms. It would not be a surprise that SARS-CoV-2 joins those other viruses as an endemic virus with a similar yearly cycle of infection rates.
If that happens, and no surge in infections appears that would motivate orders for the new COVID-19 at-home tests, the government may find itself with a lot of unused tests at the end of the year. The US Food and Drug Administration (FDA) is aware of this possibility and provides a website where people can check to see if their test has an extended expiration date.
Plus, folks who are tired of the pandemic may not respond at all to the government’s insistence to prepare for possible surges in infection rates.
“Whether or not people are done with it, we know the virus is there, we know that it’s circulating. We know, if past is prologue, it’ll circulate to a higher degree and spread, and cases will go up in the fall and winter seasons,” said Assistant Secretary for Preparedness and Response Dawn O’Connell, JD, in the HHS new release. “Anticipating that that would be true again, or something similar, we want to make sure the American people have these tools.”
Clinical laboratories may want to prepare as well. Many people are not comfortable with at-home self-testing and prefer to have their local medical labs perform the tests.
Clinical laboratory leaders may be aware that many hospitals still do not have capabilities to make a timely diagnosis of sepsis
Despite the fact that “one in three people who dies in a hospital had sepsis during that hospitalization,” recent data from the Centers for Disease Control and Prevention (CDC) show that many hospitals in the US lack the resources to identify sepsis and begin treatment as soon as possible, CNN reported.
According to the CDC, 1.7 million Americans develop sepsis annually. And of that group, at least 350,000 adults die in hospitals or hospice care centers. Clinical laboratories tasked with performing the plethora of tests needed to diagnose sepsis will agree that it is one of the gravest healthcare dangers patients face.
To address this potentially deadly threat, the CDC developed the “Hospital Sepsis Program Core Elements: 2023” to support the implementation of sepsis protocols at all hospitals, to optimize any existing sepsis programs, and to organize staff and identify resources to lower sepsis rates and raise survivability.
“Modeled after CDC’s Core Elements of Antibiotic Stewardship, which has proven to be an impactful resource to protect patients from the harms caused by unnecessary antibiotic use and to combat antimicrobial resistance, the Sepsis Core Elements were created with the expectation that all hospitals, regardless of size and location, would benefit from this resource,” a CDC press release noted.
“CDC’s Hospital Sepsis Program Core Elements are a guide for structuring sepsis programs that put your healthcare providers in the best position to rapidly identify and provide effective care for all types of patients with sepsis,” said Raymund Dantes, MD (above), Medical Advisor, National Healthcare Safety Network, CDC, and Associate Professor, Emory University School of Medicine, in a CDC press release. Hospital medical laboratories will play a key role in the success of the CDC’s sepsis program. (Photo copyright: Emory School of Medicine.)
Seven Elements to Improve Sepsis Diagnosis
Sepsis can occur when chemicals released into the bloodstream to fight off an infection produce massive inflammation throughout the body. This potentially fatal reaction can cause a deluge of changes within the body that damage multiple organs, leading them to fail.
The CDC designed its hospital sepsis program to improve and monitor the management and outcomes of patients with sepsis. The core elements of the program include seven main points:
Hospital Leadership Commitment: Management must dedicate the necessary staff, financial, and information technology resources.
Accountability: Appoint a team responsible for program goals and outcomes.
Multi-professional Expertise: Make sure key personnel throughout the healthcare system are engaged in the program.
Action: Implement structures and processes to improve the identification of the illness and patient outcomes.
Tracking: Develop initiatives to measure sepsis epidemiology, management, overall outcomes, and progress towards established goals.
Reporting: Provide information on sepsis management and outcomes to relevant partners.
Education: Provide healthcare professionals, patients, and family/caregivers with information on sepsis.
“Sepsis is taking too many lives. One in three people who dies in a hospital has sepsis during that hospitalization. Rapid diagnosis and immediate appropriate treatment, including antibiotics, are essential to saving lives, yet the challenges of awareness about and recognition of sepsis are enormous,” said CDC Director Mandy Cohen, MD, in the CDC press release. “That’s why CDC is calling on all US hospitals to have a sepsis program and raise the bar on sepsis care by incorporating these seven core elements.”
Early Diagnosis Presents Challenges
Sepsis care is complex. The condition requires urgent medical intervention to prevent organ damage and death. But the symptoms, which include fever or low temperature, shivering, confusion, breathing difficulties, extreme body pain or discomfort, high heart rate, weak pulse or low blood pressure, and low urine output, can be general and indicative of other illnesses.
The diagnosis of sepsis usually requires the collection of a blood culture specimen that is then incubated until there is enough bacterial growth to identify the specific strains of bacteria in a particular patient. This process can take several days, which can delay the administering of the most effective treatment for the condition. Treatment usually includes antibiotics and intravenous fluids.
A recent CDC survey of 5,221 US hospitals showed that in 2022, only 73% of hospitals reported having a sepsis program, ranging from 53% among hospitals with less than 25 beds to 95% among hospitals with over 500 beds.
That survey, released in the CDC’s August Morbidity and Mortality Weekly Report (MMWR), also discovered that only 55% of all hospitals had personnel with dedicated time to manage and conduct necessary daily activities for a sepsis program.
Raymund Dantes, MD, Medical Advisor, National Healthcare Safety Network, CDC, and Associate Professor, Emory University School of Medicine, told CNN that as many as 1,400 hospitals have no sepsis program in place at all. Therefore, he added, the CDC’s Hospital Sepsis Program Core Elements documents also include a “getting started guide” to help those hospitals create the needed committees.
“For those hospitals that already have sepsis programs underway and have available resources, we have a lot more details and best practices that we’ve collected from hospitals about how to better improve your sepsis programs,” he said. “The seven elements complement clinical guidelines by describing the leadership, expertise, tracking, education, and other elements that can be implemented in a wide variety of hospitals to improve the quality of sepsis care.”
Hospital Laboratories Play a Key Role in Reducing Sepsis
According to the CDC, anyone can get an infection and almost any infection can lead to sepsis. However, some populations are more vulnerable to sepsis than others. They include:
Older persons
Pregnant or recently pregnant women
Neonates
Hospitalized Patients
Patients in Intensive Care Units
People with weakened immune systems
People with chronic medical conditions
According to the World Health Organization (WHO), there were 48.9 million sepsis cases and 11 million sepsis-related deaths worldwide in 2017. This number accounted for almost 20% of all global deaths. Almost half of all the global sepsis cases occurred in children, resulting in 2.9 million deaths in children under the age of five.
“Sepsis is complex, often difficult to identify, and takes a tremendous societal toll in the United States,” said Steven Simpson, MD, Professor of Medicine at the University of Kansas and Chair, Board of Directors, Sepsis Alliance, a non-profit organization dedicated to raising awareness and reducing suffering from sepsis, in a press release. “To tackle the number one killer in American hospitals, we need a comprehensive National Action Plan to find cures, get them in the hands of professionals, and educate the public and professionals alike.”
Hospital medical laboratories can help reduce sepsis by finding ways to support their physicians’ diagnoses of this infection that has taken so many lives.
