New AI tool doubled efficiency in busy university radiology department
Creative artificial intelligence (AI) solutions are being developed to address critical staffing shortages in radiology that could help with similar shortages in overworked pathology and clinical laboratories as well.
In a recent clinical study at 11-hospital Northwestern Medicine, researchers developed a new generative AI radiology tool to assist radiologists that demonstrates high accuracy and efficiency rates when working with multiple types of imaging scans.
For the study, approximately 24,000 radiology reports were analyzed and then compared for clinical accuracy with and without the AI tool. The tool evaluates an entire scan and generates a report that is 95% complete and personalized to each patient. A template based on that report is then provided to radiologists for review, according to a Northwestern Medicine Feinberg School of Medicine news release.
The study reported an average 15.5% increase in radiograph efficiency without compromising accuracy. Some radiologists even produced gains as high as 40%. The radiology reports were scrutinized during a five-month period last year and enabled radiologists to improve the time it took to return a diagnosis.
“This is, to my knowledge, the first use of AI that demonstrably improves productivity, especially in healthcare. Even in other fields, I haven’t seen anything close to a 40% boost,” said the study’s senior author Mozziyar Etemadi, MD, PhD, assistant professor of anesthesiology and biomedical engineering at Northwestern University McCormick School of Engineering, in the news release. (Photo copyright: Northwestern University.)
Doubled Efficiency for One Radiology Team
“For me and my colleagues, it’s not an exaggeration to say that it doubled our efficiency. It’s such a tremendous advantage and force multiplier,” said study co-author Samir Abboud, MD, emergency radiology in the department of radiology at Northwestern Medicine, in the news release.
“Having a draft report available, even before it is viewed by the radiologist, offers a simple, actionable datapoint that can be quickly and efficiently acted upon” added study senior author Mozziyar Etemadi, MD, PhD, assistant professor of anesthesiology and biomedical engineering at Northwestern University McCormick School of Engineering, in the news release. “This is completely different than traditional triage systems, which need to meticulously be trained one by one on each and every diagnosis.”
The AI tool can also alert radiologists to life-threatening conditions.
“On any given day in the ER, we might have 100 images to review, and we don’t know which one holds a diagnosis that could save a life,” Abboud said. “This technology helps us triage faster—so we catch the most urgent cases sooner and get patients to treatment quicker.”
Relying on In-house Data
Engineers at Northwestern developed the AI model using clinical data within the university’s own network, emphasizing that such tools can be created without assistance from other organizations.
“Our study shows that building custom AI models is well within reach of a typical health system, without reliance on expensive and opaque third-party tools like ChatGPT,” Etemadi noted.
The Journal of the American College of Radiology states the supply of radiologists is expected to increase by approximately 26% over the next 30 years. However, the need for radiologists is expected to grow between 17% and 27% over the same period. Becker’s Hospital Review reports there will be a shortage of up to 42,000 radiologists in the US by 2033.
Some health organizations are using a mixed model of permanent employees and contracted radiologists to meet the increasing demand for services. Others are also looking at options such as internal training programs, better benefits for workers, teleradiology, and remote radiologists to fulfill radiology needs.
“You still need a radiologist as the gold standard,” Abboud said. “Medicine changes constantly—new drugs, new devices, new diagnoses—and we have to make sure the AI keeps up. Our role becomes ensuring every interpretation is right for the patient.”
Can pathology practices and clinical laboratories learn from radiology’s situation? Development of AI solutions for those fields would likely have similar effects on workloads and overworked personnel.
Exploring the benefits of AI may be one way of helping meet clinical laboratory and pathology practice staff shortages.
Pharmaceutical and biotech researchers convened last week to discuss their latest work on targeting neurodegenerative diseases
With all the news this year alone on progress being made with diagnostic testing for Alzheimer’s disease, clinical laboratory professionals will be interested to know that drug discovery efforts to combat neurogenerative diseases are also at a heightened pitch.
Last week at the one-day Neuroimmunology in Drug Discovery forum in Boston, scientists learned about the latest advances in therapeutic research to better treat Alzheimer’s disease, multiple sclerosis, and Parkinson’s disease. As the treatments advance, demand for them will increase, which goes hand-in-hand with medical lab testing to detect signs of these illnesses.
The concern is urgent. The US Food and Drug Administration (FDA) noted that 10% of people age 65 and older have Alzheimer’s disease, and that number could double by 2050. The FDA recently cleared the first in vitro diagnostics device that tests blood to diagnose Alzheimer’s, and other IVD manufacturers and clinical labs are working on other Alzheimer’s tests, Dark Daily reported.
“It’s looking quite promising for NLRP3 inhibitors,” said Cheryl Leyns, PhD, associate principal scientist in discovery neuroscience at Merck Research Laboratories, in discussing how mutations of the NLRP3 protein can lead to neurodegenerative diseases. (Photo copyright: ELRIG.)
Much of the discussion at the Neuroimmunology in Drug Discovery forum centered on the idea that neuroinflammation—in other words, inflammation of the brain or spinal cord—starts well before neurodegenerative diseases arise. Neuroinflammation can accelerate Parkinson’s disease and other neurodegenerative disorders, said Cheryl Leyns, PhD, associate principal scientist, neuroimmunology, at Merck Research Laboratories in Boston, who spoke at the event.
From that perspective, drug discovery researchers are on the prowl for these early signs of future problems.
Leyns discussed NLRP3, a protein that aids the body’s inflammation process. A mutation of NLRP3 can lead to inflammatory problems, making the protein a prime target for researchers. “We have been interested, in the biopharma space, in the potential of NLRP3 inhibitors,” she noted.
Older Immune Systems Are Susceptible
While many in the public correctly associate Alzheimer’s with a person being outwardly older, a lesser-known aspect is that the body’s immune system also ages, becoming more susceptible over time to chronic inflammation.
Wailings’ assertion was not rhetorical. She pointed to numbers which showed scholarly research that involved the terms “inflammation,” “neurodegeneration,” and “aging” was only about 17% of the total amount of journal articles that addressed the first two terms, but which did not include “aging.”
As the pharmaceutical, biotech, and medical fields move aggressively forward to defend people against neurodegenerative diseases like Alzheimer’s, clinical laboratory scientists should take comfort that diagnostic testing trends are solidly in the mix.
Therapeutic advances, along with increased options for testing, show promising signs that patients and their caregivers will have more tools to use in the battle against these illnesses.
At least a dozen sessions at the 2025 Executive War College explored artificial intelligence use in clinical labs
Although not explicitly stated, it was clear at the 2025 Executive War College on Diagnostics, Clinical Laboratory, and Pathology Management conference that artificial intelligence must be a path forward for labs to control costs in an unfavorable economic environment.
Even though the technology is largely unproven in clinical lab settings, the potential of artificial intelligence (AI) in labs is enough reason for laboratory leaders to explore it further.
“AI is allowing us to drive our business,” said Sam Terese, CEO and president at Alverno Laboratories, during a general session at the Executive War College. “It is really resonating that we need to use AI in the future.”
Clinical laboratory leaders should constantly ask themselves whether there is an AI solution to a problem, advised Sam Terese (above), CEO and president at Alverno Laboratories. Terese spoke at the 2025 Executive War College. (Photo copyright: LabX.)
‘Not a Lot of Trust’ in AI from Patients
Terese acknowledged that patients do not yet feel comfortable with the technology. “When you throw AI and healthcare together, from the public’s perspective, there’s not a lot of trust,” he said.
That said, Alverno is committed to increased use of AI in clinical labs in 2025, including for:
Terese urged laboratory owners and executives to not underestimate how quickly AI adoption could spread within the clinical lab industry. Digital pathology took half a century to evolve into its current state, but “AI took five years. The timeline is moving rapidly,” he observed.
Don’t Move Blindly Forward with AI, Experts Warn
At least a dozen sessions at this week’s Executive War College addressed an aspect of AI in labs.
Lab leaders must advise their staff to use AI with systems or processes that can tolerate mistakes because AI will get things wrong, Cecchini added.
“I treat AI like an eager intern where you have to check everything it does,” he said.
Presenter Ankit Ranjan, PhD, founder of AI company Sample Healthcare, agreed with that sentiment. He suggested that clinical laboratories should consider AI as a copilot until its algorithms can prove to lab staff that conclusions or predictions are accurate. The long game for AI in labs is not to cut a few staff from the budget but instead act as a revenue driver.
“Inserting AI into end-to-end processes is what really addresses problems,” Ranjan said.
Watch for much more coverage about the state of AI in clinical laboratories in upcoming issues of The Dark Report. If you’re not a subscriber, it’s a great time to take a free trial of our business intelligence briefings.
Clinical laboratories are particularly tasty targets for cybercriminals seeking the abundance of protect health information contained in patient electronic health records
Recent data from cybersecurity company Netwrix of Frisco, Texas, shows that 84% of healthcare organizations—including clinical laboratories and pathology groups—caught at least one cyberattack in the past year and “69% of them faced financial damage as a result.” That’s according to the company’s latest Hybrid Security Trends Report which notes that 24% of healthcare organizations are “fully cloud-based,” as opposed to just 11% of non-healthcare industries.
“Phishing was the most common type of incident experienced on premises, similar to other industries. Account compromise topped the list for cloud attacks: 74% of healthcare organizations that spotted a cyberattack reported user or admin account compromise,” the Netwrix report notes.
Phishing, where cybercriminals send fake emails and texts to unsuspecting employees that trick them into providing private information, continues to be one of the most prevalent cyberthreats experienced by healthcare organizations and often serves as the catalyst for much larger and more dangerous cyberattacks.
This is particularly dangerous in clinical laboratories where as much as 80% of protected health information (PHI) in patients’ electronic health records (EHRs) is laboratory test results and other personal medical data.
“Protected health information (PHI) is one of the most expensive types of data sold on darknet forums, which makes healthcare organizations a top target for cybercriminals, said Ilia Sotnikov (above), security strategist and VP of user experience at Netwrix, in the report. Clinical laboratory patient electronic health records are particularly weighted toward PHI. (Photo copyright: Netwrix.)
Don’t Open That Email!
Typical phishing scams begin with innocent-looking emails from companies that appear to be legitimate and often contain language that implies urgent action is needed on the part of the user. These emails can be very convincing, appear to originate from reputable companies, and usually instruct users to open an attachment contained in the email or click on a link that goes to a known company website. However, the site is a fake.
Once the harmful file attachment is opened, users will be directed to download fake software or ransomware that attempts to capture the user’s personal information. When visiting a malicious website, consumers will often receive pop-ups with instructions for updating information, but the true purpose is to harvest personal data.
Never provide any personal information to an unsolicited request.
If you believe the contact is legitimate, initiate a contact with the organization using verified data, usually via telephone.
Never provide any passwords over the phone or in response to an unsolicited Internet request.
Review any accounts, such as bank statements, often to search for any suspicious activity.
“Healthcare workers regularly communicate with many people they do not know—patients, laboratory assistants, external auditors and more—so properly vetting every message is a huge burden,” said IT security expert Dirk Schrader, VP of security research at Netwrix, in the report. “Plus, they do not realize how critical it is to be cautious, since security awareness training often takes a back seat to the urgent work of taking care of patients. Combined, these factors can lead to a higher rate of security incidents.”
Top 10 Brands Faked in Phishing Scams
Phishing emails often appear to be from legitimate companies to lull the recipient into a false sense of security. In a January 22 report, Check Point Research (CPR) announced its latest Brand Phishing Ranking for the fourth quarter of 2024. The report reveals the brands that were most frequently impersonated in phishing attacks by cybercriminals for the purpose of stealing personal information from consumers.
According to the CPR report, 80% of disclosed brand phishing incidents occurred within just 10 brands (listed below with each brand’s percentage of phishing attacks). They are:
According to the report, fraudulent domains “replicated official websites to mislead shoppers with fake discounts, ultimately stealing login credentials and personal information. These fraudulent sites replicate the brand’s logo and offer unrealistically low prices to lure victims. Their goal is to trick users into sharing sensitive information, such as login credentials and personal details, enabling hackers to steal their data effectively.”
Steps Clinical Labs Can Take to Protect Patients’ PHI
Clinical laboratories and pathology groups can take precautions that minimize the risk of allowing cybercriminals access to their patients’ PHI.
“A core defense strategy is to minimize standing privileges by using a privileged access management (PAM) solution. Another is to implement identity threat detection and response (IDTR) tools to quickly block malicious actors using compromised credentials,” said Ilia Sotnikov, security strategist and VP of user experience at Netwrix, in the report.
The threat of phishing scams is a lingering issue that everyone in healthcare should be aware of and take necessary precautions to recognize and prevent having one’s PHI stolen. Clinical laboratory management should constantly remind lab personnel and contractors to be vigilant regarding fake emails and texts from well-known brands that ask for private information.
PRESS RELEASE FOR IMMEDIATE RELEASE THE DARK INTELLIGENCE GROUP21806 Briarcliff Dr.Spicewood, TX 78669512-264-7103 o512-264-0969 f Media Contact: Amanda Curtisacurtis@darkreport.com Experts to Identify Essential Steps & Pitfalls to Help Clinical Laboratories Meet the Deadline to Comply with the FDA’s Laboratory Developed Test (LDT) Rule Speaker Panel: Jane Pine Wood with McDonald Hopkins, Valerie Palmieri with MOMENTUM Consulting and Sheila Walcoff with Goldbug Strategies (Photo: Business...
