Artificial intelligence tools for radiology, clinical laboratory, and pathology diagnostics continue to advance and improve
Researchers in Germany have developed a fully automated, artificial intelligence (AI) tool that improves the diagnosis of prostate cancer. Developed by mediaire, a company that creates AI-based tools for radiologists, the software reduces clinical workloads and could be beneficial in counteracting issues associated with variability in magnetic resonance imaging (MRI) reporting. This is another example of AI’s growth in the clinical diagnostic industry, including clinical laboratory and pathology medicine.
The software, called mdprostate, has received the mandatory certification mark (CE or European Conformity) for products sold within the European Economic Area (EEA). It is now commercially available in those countries and was recently incorporated into the picture archiving and communications system (PACS) of some healthcare organizations and applied to a group of patients who had undergone a multiparametric prostate MRI (mpMRI).
The goal was to compare the overall performance of mdprostate against radiologists who executed the initial interpretations of the mpMRIs, according to Health Imaging.
“Mdprostate is intended to support radiologists by automating time-consuming processes and improving the objectivity of diagnosis through data quantification,” said Tonia Michaely, chief of staff at mediaire, in a news release.
“By providing objective assessments and standardizing lesion detection and classification, AI has the potential to augment radiologists’ performance throughout the PCa [prostate cancer] diagnostic pathway,” Nadine Bayerl, Dr. med., a radiologist with the Institute of Radiology at University Hospital Erlangen and corresponding author of the mediaire study, told Health Imaging. (Photo copyright: University Hospital Erlangen.)
Scoring Cancer Risk
To perform the comparison, a team of researchers applied the AI tool to 123 prostate MRI exams followed by systematic and targeted biopsies. The software was instructed to automatically segment the prostrate, calculate prostate volume, and classify lesions per the Prostate Imaging Reporting and Data System (PI-RADS).
PI-RADS, according to the America College of Radiology, is a reporting method that indicates how likely a lesion is to be clinically significant cancer on a score of one to five:
PI-RADS 1: very low (clinically significant cancer is highly unlikely to be present).
PI-RADS 2: low (clinically significant cancer is unlikely to be present).
PI-RADS 3: intermediate (the presence of clinically significant cancer is equivocal).
PI-RADS 4: high (clinically significant cancer is likely to be present).
PI-RADS 5: very high (clinically significant cancer is highly likely to be present).
For PI-RADS scores greater than two, mdprostate generated 100% sensitivity and dismissed all cancers for lesions that were below that threshold. For PI-RADS scores of four or higher, the AI tool yielded 85.5% sensitivity and specificity of 63.2% for clinically significant cancers.
Deep Learning in Diagnostic Pathway
“In practical terms, these results indicate that when a case falls below the PI-RADS ≥ 2 cutoff, clinicians can rule out malignancy with a high degree of confidence,” the authors explained in the European Journal of Radiology. “This capability is particularly valuable in clinical decision-making, as it allows for the safe avoidance of unnecessary biopsies or further invasive procedures in these patients.”
“Recent advances in deep learning algorithms, facilitated by larger labeled datasets, improved computing hardware, and refined training techniques, have led to several studies highlighting the diagnostic value of deep learning algorithms in prostate imaging,” radiologist Nadine Bayerl, Dr. med., Institute of Radiology at University Hospital Erlangen and corresponding author of the study, told Health Imaging.
The software “demonstrated high diagnostic performance in identifying and grading prostate lesions, with results comparable to those reported in meta-analyses of expert readers using PI-RADS,” the researchers noted in their published study.
“Its ability to standardize evaluations and potentially reduce variability underscores its potential as a valuable adjunct in the prostate cancer diagnostic pathway. The high accuracy of mdprostate, particularly in ruling out prostate cancers, highlights its clinical utility by reducing workload and enhancing patient outcomes,” they concluded.
AI in Clinical Laboratories and Pathology
Dark Daily has frequently covered AI’s expanding role in clinical laboratory testing and pathology diagnostics. At the recent Executive War College, a dozen sessions explored its growth in the industry. During one session, Sam Terese, CEO and president at Alverno Laboratories said, “AI is allowing us to drive our business. It is really resonating that we need to use AI in the future.”
Members who could not attend the 2025 Executive War College can order audio recordings of these valuable sessions by clicking here.
Clinical laboratory data was key in identifying antibiotic-resistant bacteria responsible for surge in BSIs in hospitals and other healthcare facilities in 2020 and 2021
Clinical laboratory data compiled by the European Antimicrobial Resistance Surveillance Network (EARS-Net) shows that a massive increase in bloodstream infections (BSIs) occurred among EU nations during the first two years of the COVID-19 pandemic. The study found that BSIs caused by certain antimicrobial-resistant (AMR) pathogens, known as superbugs, more than doubled in EU hospitals and healthcare facilities in 2020 and 2021.
Microbiologists and clinical laboratory managers in the US may find it valuable to examine this peer-reviewed study into AMR involved in blood stream infections. It could contain useful insights for diagnosing patients suspected of BSIs in US hospitals where sepsis prevention and antibiotic stewardship programs are major priorities.
“Antimicrobial resistance undermines modern medicine and puts millions of lives at risk,” said Tedros Adhanom Ghebreyesus, PhD, Director-General, World Health Organization, in a WHO press release. “To truly understand the extent of the global threat and mount an effective public health response to [antimicrobial resistance], we must scale up microbiology testing and provide quality-assured data across all countries, not just wealthier ones.” Clinical laboratories in the US may be called upon to submit data on bloodstream infections in this country. (Photo copyright: WHO.)
Clinical Laboratories in EU Report Huge Increase in Carbapenem Resistance
To perform their study, researchers measured the increase in Acinetobacter BSIs between 2020 and 2021, the first two years of the COVID-19 pandemic. Their data originated from qualitative regular antimicrobial susceptibility testing (AST) from blood samples collected by local clinical laboratories in the European Union/European economic area (EU/EEA) nations.
The researchers limited their dataset to Acinetobacter BSI information from the European medical laboratories that documented results of carbapenem susceptibility testing for the bacterial species.
Carbapenems are a class of very powerful antibiotics that are typically used to treat severe bacterial infections. A total of 255 EU/EEA clinical laboratories reported their data for the study. The scientists found that the percentages of Acinetobacter resistance varied considerably between EU/EEA nations, so they separated the countries into three different groups:
Nations in Group One—The Netherlands, Belgium, Austria, Estonia, Denmark, Germany, Iceland, Finland, Luxembourg, Ireland, Norway, Sweden, and Malta—experienced less than 10% resistance to carbapenems.
Nations in Group Two—Slovenia, Czech Republic, and Portugal—had carbapenem resistance between 10% and 50%.
Nations in Group Three—Croatia, Bulgaria, Greece, Cyprus, Italy, Hungary, Lithuania, Latvia, Romania, Poland, Spain, and Slovakia—demonstrated carbapenem resistance equal or greater than 50%.
The study also found that Acinetobacter BSIs rose by 57% and case counts increased by 114% in 2020 and 2021 when compared to 2018 and 2019. The percentage of resistance to carbapenems rose to 66% in 2020 and 2021, up from 48% in 2018 and 2019.
Antimicrobial Resistance Especially High in Hospital Settings
The researchers further arranged the data into three hospital ward types: intensive care unit (ICU), non-ICU, and unknown. The increase in BSIs caused by Acinetobacter species resistant to carbapenems was greater in ICU-admitted individuals (144%) than non-ICU-admitted individuals (41%).
There are more than 50 species of Acinetobacter bacteria and various strains are often resistant to many types of commonly-used antibiotics. Symptoms of an Acinetobacter infection usually appear within 12 days after a person comes into contact with the bacteria. These symptoms may include:
Blood infections,
Urinary tract infections,
Pneumonia, and
Wound infections.
Healthy people have a low risk of contracting an Acinetobacter infection with the highest number of these infections occurring in hospitals and other healthcare settings. Acinetobacter bacteria can survive for a long time on surfaces and equipment, and those working in healthcare or receiving treatment are in the highest risk category.
The prevalence of this type of bacteria increases in relation to the use of medical equipment, such as ventilators and catheters, as well as antibiotic treatments.
WHO Report Validates EARS-Net Research
In December of 2022, the World Health Organization (WHO) issued a Global Antimicrobial Resistance and Use Surveillance System (GLASS) report that revealed the presence of an increasing resistance to antibiotics in some bacterial infections. That report showed high levels (above 50%) of resistance in bacteria that frequently caused bloodstream infections in hospitals, such as Klebsiella pneumonia and Acinetobacter.
The WHO report examined data collected during 2020 from 87 different countries and found that common bacterial infections are becoming increasingly resistant to treatments. Both Klebsiella pneumoniae and Acinetobacter can be life threatening and often require treatment with strong antibiotics, such as carbapenems.
More research is needed to determine the reasons behind increases in Acinetobacter infections as reported in European hospitals and other healthcare settings, and to ascertain the extent to which they are related to hospitalizations and the upsurge in antimicrobial resistance during the COVID-19 pandemic.
Microbiologists and clinical laboratory managers in the US may want to learn more about the fIndings of this European study involving AMR and use those insights to plan accordingly for any future increase in bloodstream infections in this country.
Bioeasy stands behind the accuracy of its coronavirus test kits and, in a statement, questioned whether they were being used correctly
How accurate are the SARS-CoV-2 test kits being offered by different in vitro diagnostics companies, as well as the internally-developed COVID-19 tests developed by individual medical laboratories, both here in the United States and in other countries? It’s a question that has not been addressed by the news media nor by healthcare regulators.
That
is why a recent news story reported complaints by authorities in several
European countries that COVID-19 tests they had purchased were “unreliable.”
The source of the COVID-19 test kits was a Chinese company.
On Wednesday, government officials in China announced that manufacturers of test kits for SARS-CoV-2, the novel coronavirus that causes the COVID-19 illness, can no longer export their tests unless China’s National Medical Products Administration (NMPA) has licensed and registered those tests, the South China Morning Post (SCMP) reported.
China issued the new rules after receiving complaints from buyers in Europe about the quality and accuracy of tests kits and other products, including personal protective equipment (PPE), ventilators, and infrared thermometers, SCMP wrote. Previously, Chinese exporters were required only to have CE certification to indicate that their goods conformed to the health and safety standards required for sale in the European Economic Area, SCMP added.
In a joint statement issued March 31, China’s Ministry of Commerce, General Administration of Customs (GAC), and the National Medical Products Administration said the new rule applies to all companies seeking to export test kits, face masks, protective clothing, ventilators, and infrared thermometers.
Spain
Discontinues Use of Rapid Diagnostic Tests from Bioeasy
The new rules came after health authorities in Spain stopped using a rapid diagnostic test (RDT) kit that required a nasopharyngeal (NP) swab to collect specimens to diagnose patients for the SARS-CoV-2 virus, saying the test kits from Shenzhen Bioeasy Biotechnology were unreliable. Turkey also rejected the Shenzen Bioeasy test kits after finding similar problems, according to The Middle East Eye. Ukraine and Georgia also bought kits from Bioeasy, according to published reports.
The low accuracy rate of the Bioeasy coronavirus test kits raises questions about the rapid rate of development for new tests in the United States and worldwide, said Michael Noble, MD, FRCPC, Chair of the University of British Columbia (UBC) Clinical Microbiology Proficiency Testing program and the UBC Program Office for Laboratory Quality Management, in Vancouver.
“There’s
an inherent problem with building a test during a crisis,” Noble said in an
interview with Dark Daily. “Clinical laboratory test developers are
being forced into building tests in a hurry, and the highest likelihood is that
they will fail because these tests take a lot of time if the aim is to get them
right.
“When
a company or a lab feels the need to go too fast, it is likely to take
shortcuts,” he added. “And every time a shortcut is taken, an opportunity for
error is created.
“Also,
the federal Food and Drug Administration (FDA) may be going too fast to issue
emergency use authorizations (EUAs). If laboratory test developers and the FDA
go too fast, then both could make mistakes,” Noble noted.
“The lesson for labs in the United States and everywhere is you can’t go too fast and you don’t want to go too slow either,” Michael Noble, MD (above), Chair of the University of British Columbia Clinical Microbiology Proficiency Testing Program, told Dark Daily. “Instead, you need to proceed as quickly as you can, but also take as long as you need to ensure you follow all the steps accurately.” (Photo copyright: The Dark Report.)
Bioeasy
Questions Whether Tests are Being Used Correctly
On
March 27, SCMP reported that Shenzhen Bioeasy would send new kits to
ensure that “patients get the best diagnostics” and to “ensure the test kits’
sensitivity and specificity.” The company also raised questions about whether
the tests were used properly and promised to send a video explaining how those
administering the tests should collect specimens using NP swabs.
“As
it [is a] rapid test kit, following the protocol is very important,” the
company added, according to SCMP.
Last
week, Zhu Hai, a manager at
Shenzen Bioeasy, said reports that the test kits had a low accuracy rate were
untrue, SCMP reported. A more detailed explanation would be given via
official Chinese government channels, he added.
Shenzen
Bioeasy also issued a statement about the tests, saying, “The production export
of our CE products to Spain has been done according [to] regulations. All
Bioeasy COVID-19 rapid test [kits] are officially CE-IVD approved, so we are free
to [export] and sell in [the EU],” SCMP reported.
The company exported 337,000 tests to South Korea and more than 420,000 test kits to at least 10 countries, including Italy, Qatar, and Ukraine, the company added. It had five million such kits under production, the company said.
Spain
Purchased More than Half a Million Bioeasy Test Kits
One
of the first publications to report the inaccuracy problems was El País, a Spanish
language daily newspaper in Madrid.
The
Shenzen Bioeasy tests functioned much like pregnancy tests, the newspaper
wrote. Once the sample is taken, the NP swab is diluted and placed into a
cartridge with a lined test strip showing whether the result is positive,
negative, or invalid. “The tests detect the presence of antigen and the result is obtained in 10
or 15 minutes,” El País wrote.
Based
in part on a claim that the medical laboratory test kits have an 80% accuracy
rate, the government purchased 640,000 kits to screen health workers and the
elderly. If the Chinese tests were of sufficient quality, negative or doubtful
results would require a confirmatory molecular diagnostics test, the
newspaper added.
The
Chinese embassy in Spain also responded, saying on Twitter on March 26 that
the country’s National Medical Products Administration had not approved the
tests, and that they were not included in the medical supplies the Chinese
government sent to Spain, SCMP reported. “The Chinese Ministry of
Commerce offered Spain a list of approved suppliers, in which Shenzhen Bioeasy
Biotechnology was not included,” the embassy added.
After
the low accuracy rates were reported, the Spanish government said it ordered
€432 million (US$468 million) worth of medical supplies from China, 5.5 million
test kits, 550 million face masks, and 950 ventilators, SCMP added. But
none of the kits in this order were from Shenzen Bioeasy, the government said.
SCMP quoted Professor Leo Poon
Lit-man, BSc, MPhil, DPhil, FFPH, an expert in the SARS-CoV-2 coronavirus
who helped design a testing protocol for the COVID-19 illness, and who is a
Professor and Division Head of the Division of Public Health Laboratory
Sciences at The University of Hong Kong. A claim of 80% accuracy
for a test using nasal swabs was perplexing, because such tests are known to be
inaccurate, Poon said. “It would be dangerous if it’s used on a large scale,
since patients who are supposed to be positive might not be detected,” he
added.
Pathologists
and clinical laboratory scientists know there are many reasons why a clinical
laboratory test can be unreliable or inaccurate. For example, during the
production of a batch of tests, one step in the manufacturing process may have
gone awry and that problem was not detected before those tests were shipped to
a medical laboratory.
Unfortunately,
when lab tests are proved to be “unreliable” or inaccurate, the public or the
medical laboratory profession seldom learn the reasons for these problems and
what steps were taken to resolve them.
