|
AI Predicts Workload, Mammo Saves Lives, and Fake Radiologist
August 11, 2025
|
|
|
|
|
Together with
|
|
|
|
“What if you could proactively predict your clinical volume for tomorrow and had an opportunity to plan/staff differently? Would your practice be able to respond?”
|
|
James V. Rawson, MD, on a new study using AI to predict radiology workload.
|
|
|
|
AI is touted as a tool that can help radiologists lighten their workload. But what if you could use AI to predict when you’ll need help the most? Researchers in Academic Radiology tried that with an AI algorithm that predicted radiology workload based on three key factors.
Imaging practices are facing pressure from a variety of forces that include rising imaging volume and workforce shortages, with one recent study documenting a sharp workload increase over the past 10 years.
- Many industry observers believe AI can assist radiologists in reaching faster diagnoses, or by removing studies most likely to be normal from the worklist based on AI analysis.
But researchers and vendors are also developing AI algorithms for operational use – arguably where radiology practices need the most help.
- AI can predict equipment utilization, or even create a virtual twin of a radiology facility where administrators can adjust various factors like staffing to visualize their impact on operations.
In the new study, researchers from Mass General Brigham Hospital developed six machine learning algorithms based on a year of imaging exam volumes from two academic medical centers.
The group entered 707 features into the models, but ultimately settled on three main operational factors that best predicted the next weekday’s imaging workload, in particular for outpatient exams…
- The current number of unread exams.
- The number of exams scheduled to be performed after 5 p.m.
- The number of exams scheduled to be performed the next day.
The algorithm’s predictions were put into clinical use with a Tableau dashboard that pulled data from 5 p.m. to 7 a.m. the following day, computed workload predictions, and output its forecast in an online interface they called “BusyBot.”
- But if you’re only analyzing three factors, do you really need AI to predict the next day’s workload?
The authors answered this question by comparing the best-performing AI model to estimates made by radiologists from just looking at EHR data.
- Humans either underestimated or overestimated the next day’s volume compared to actual numbers, leading the authors to conclude that AI did a better job of calculating dynamics and weighting variables to produce accurate estimates.
The Takeaway
Using AI to predict the next day’s radiology workload is an intriguing twist on the argument that AI can help make radiologists more efficient. Better yet, this use case helps imagers without requiring them to change the way they work. What’s not to like?
|
|
Unprecedented Insights Made Possible with AI
With the largest normative dataset of whole-body imaging in the world, Prenuvo’s AI researchers partner with the best academic minds to understand – like never before – what “normal” aging means. Learn about their work today.
|
|
Building an Enterprise Imaging Ecosystem
What’s the best way to bring smaller clinics and rural hospitals into your enterprise imaging ecosystem? Find out how MultiCare Health System did it in this white paper from Merge.
|
|
Synoptic Reporting of Liver Masses
Contrast-enhanced ultrasound exams for focal liver lesions can be challenging to report in at-risk patients. Learn how Kailo Medical’s synoptic reporting solutions can make reporting easier while improving LI-RADS categorization.
|
|
- AI of Malpractice Risk: Another novel non-clinical use case for AI could be in predicting malpractice risk from specific medical procedures. Researchers at South Korea’s Asan Medical Center developed Dr. Lawn, an AI algorithm that analyzes and summarizes medico-legal risk based on data from over 15k previous legal rulings. Users can input a patient’s symptoms, diagnosis, and medical procedures and receive a summary of relevant legal precedents, as well as the guidelines courts used for legal verdicts – and how to avoid such judgments.
- Mammo Screening Saves Lives: A new review of global breast screening programs comes to a conclusion that shouldn’t surprise anyone: mammography screening saves lives. Researchers surveyed countries with organized screening programs (94 of 194), finding that they had 3.74 fewer breast cancer deaths per 100k population than countries without regular screening (17.07 vs. 20.81). The biggest difference was in women aged 50-74 (10.1 fewer deaths), and countries with screening saw breast cancer mortality drop annually (-1.02% vs. +0.45%).
- Black Women and Breast Screening: In a related finding, researchers writing in npj Breast Cancer found that lack of access to mammography screening is one of the most influential factors behind why Black women in the U.S. have worse breast cancer outcomes. Among 5k Black women with breast cancer, mammography underutilization had the biggest correlation with diagnosis at later stages (OR = 3.21), while income below the poverty line was also a factor (OR = 1.91). Other factors like insurance status and lower education were not statistically significant.
- FDA Clears DeepHealth Remote Scanning: The FDA cleared DeepHealth’s TechLive solution for supporting remote scanning of MRI, CT, PET/CT, and ultrasound exams. Faced with shortages of radiologic technologists, providers are turning to remote scanning to enable staff at central command centers to operate equipment and supervise less-experienced technologists at remote sites. TechLive is a vendor-neutral solution that’s already in use with 300 scanners operated by DeepHealth parent RadNet. DeepHealth will now be able to market TechLive outside the RadNet network.
- Inappropriate Thyroid Ultrasound: Inappropriate thyroid ultrasound drives detection of low-level thyroid cancer that isn’t a health risk to patients. A new study in JAMA Otolaryngology – Head & Neck Surgery explores what caused inappropriate thyroid ultrasound among 11.4k patients where 7.6% of scans were unnecessary. Tops was hyperthyroidism (OR = 9.04), followed by referrals from a nonendocrinology specialty, orders not linked to an appointment, and patient age of 18 to 54 (ORs = 3.34, 2.42, and 1.86 respectively).
- Heartflow Shares Jump 50% in IPO: Apparently there’s also appetite on the public markets for investment in AI developers. Shares of cardiac AI specialist Heartflow jumped 50% on August 8, the first day of trading following the company’s IPO. Heartflow raised $317M by issuing 16.7M shares at $19 each, up sharply from proceeds of $215M estimated the week before the IPO. Heartflow’s market capitalization stands at a stunning $2.5B at the current share price.
- Article Details Echo AI’s Advantages: A new review article in Nature Reviews Cardiology provides an overview of the advantages of AI-enhanced echocardiography, which helps overcome many of the traditional challenges of manual echo. Echo AI addresses growing workforce shortages as well as the need for technical expertise to perform echo scans. AI can provide automatic image classification, segmentation, and measurement, while also guiding image acquisition by non-expert healthcare personnel.
- MRI Reveals Super-Ager Secrets: MRI brain scans are providing insights into the secrets of super-agers – people in their 80s and 90s who have memory abilities similar to individuals 20-30 years younger. A group from Northwestern University used MRI to discover that super-agers show less decline in cortical volume and have thicker cingulate gyrus regions. Super-agers tended to be more active, social, and extroverted than their neurotypical peers, a phenomenon that promotes neuroplasticity – and perhaps protection from conditions like Alzheimer’s disease.
- 7T MRI of Brain Aging: In a related study, German researchers used 7T MRI scans to track aging in the cerebral cortex by mapping brain structures in 60 men and women aged 21 to 80. They found that in the primary somatosensory cortex – the area of the brain responsible for the sense of touch – only the deepest layers of tissue showed age-related degeneration. The cortex’s middle and upper layers were more exposed to external stimuli and showed less degeneration, reinforcing the idea that stimulation improves brain health.
- Follow-Up after 0 CAC Score: If someone gets a coronary artery calcium score of 0, how long should it be before their next CAC exam? Researchers in Academic Radiology found that assessing costal cartilage calcification – in cartilage connecting the ribs to the sternum – can help. In 402 patients younger than 50 who got five exams, those with CT-derived CCC scores above the median were more likely to have 25% incidence of CAC (42% vs. 27%), but had a longer period to 2% cardiovascular event incidence (11.2 vs. 9.3 years).
- Europe Report Tracks Healthcare AI Adoption: The European Commission issued a massive report on the state of AI adoption in healthcare. While the report approaches medical AI from a European angle, it also includes data pertaining to the U.S., such as the number of FDA healthcare AI approvals. Medical AI’s challenges are familiar to clinicians on both sides of the Atlantic, such as reimbursement, workflow integration, and usability, which may help explain why so many AI projects never progress past the pilot stage.
- Carebot Preps LLM-Based AI for MSK: Czech AI developer Carebot is developing an AI algorithm for analyzing musculoskeletal X-rays that’s based on large language model technology. The company said LLM functionality will be integrated into its Carebot AI Bones solution to speed up fracture reporting by drafting reports and sending them to the HIS, where radiologists can review and sign. Suspected fractures will be identified with their location noted.
- Fake Radiologist Arrested: A man in India has been arrested for impersonating a radiologist using a fake medical degree he bought for the equivalent of $60k. The man was working at a private ultrasound center in the northern city of Mainpuri for the past two years and had been billing for ultrasound tests fraudulently, but was discovered during an annual review of the center’s registration. Authorities had also received complaints about the fake radiologist.
|
|
Purchasing a Cloud-Hosted Enterprise Imaging Solution
The decision to move your enterprise imaging to the cloud is significant. But how do you choose the right solution? Discover the 10 critical questions to ask in this guide from AGFA HealthCare.
|
|
Cutting-Edge PET/CT to Support Theranostics
Theranostics is an exciting new field that combines diagnostics and therapy. Discover how Florida Theranostics is using United Imaging’s cutting-edge uMI Panorama PET/CT scanner to establish a high-quality level of patient care.
|
|
Optimize Radiology Workflows
Harness cloud and AI technology to help your radiology teams unlock insights, increase efficiencies, and improve patient care. Learn more about an integrated approach to AI in radiology in this e-book from Microsoft.
|
|
- AI-Powered Population Health: DeepHealth closed its acquisition of iCAD, a major step in DeepHealth’s vision to build the future of AI-powered population health. In this Imaging Wire Show, we talked to company executives Kees Wesdorp and Niccolo Stefani about the acquisition and their strategic roadmap.
- The Advantages of Cloud-Based PACS: CloudPACS offers significant advantages to healthcare providers for enterprise imaging, including no on-premise requirements and enhanced reliability. Learn more about the advantages of CloudPACS in this talk from HIMSS 2025 by Visage Imaging’s Steve Deaton.
- AI-Enabled DICOM Data Migration: What are the key elements of DICOM data migration? Visit this page for part 2 of Enlitic’s comprehensive guide, focusing on the critical steps of data extraction, normalization, and cleaning.
- Adding Digital Pathology to Enterprise Imaging: In this on-demand video from SIIM 2025 hosted by Mach7, watch as a panel of industry experts discusses how to add digital pathology images into a healthcare organization’s overall enterprise imaging strategy.
- Discover the Blackford Difference: AI is no longer a futuristic nice-to-have in healthcare, it’s an essential tool. Yet for many providers, the path forward with AI remains unclear. That’s where Blackford comes in – discover the difference today.
- Diagnostic X-Ray Battery for Life: Discover the Radiography 7000 M from Philips, a premium mobile radiography system offering enhanced care and improved operational efficiency. Plus you’ll never have to pay to repair or replace the main system battery. Terms and conditions apply.
- 2 Questions about AI for Radiology Leaders: Are today’s radiology AI solutions solving the right problems? And are there other solutions available for AI of brain MRI? Read this article from SpinTech MRI to learn how their STAGE solution can optimize MRI utilization.
- Integrating AI into Clinical Practice: AI has the potential to revolutionize healthcare, but it requires a collaborative effort between clinicians and AI experts. In this micro-learning course from Calantic by Bayer, learn about the latest developments in healthcare AI.
- AI for Limb Fractures on X-Ray: AI can recognize limb fractures on X-rays and reduce interpretation discrepancies between radiology and emergency departments. Learn how Gleamer’s BoneView AI algorithm performed in this new research study.
- A Pivotal Moment for Clinical AI Policy: In this episode of The Radiology Report podcast, Medality’s Daniel Arnold interviews Peter Shen of Siemens Healthineers about major developments in AI regulation and reimbursement, including the introduction of the Health Tech Investment Act (S.1399).
- Patient-Centered Innovation with Photon-Counting CT: Siemens Healthineers is committed to transforming medical imaging with its NAEOTOM Alpha class, now featuring three photon-counting CT systems. Find out how they can enhance your diagnostic results.
- Presenting Unboxing AI: Check out CARPL’s video series, Unboxing AI, featuring experts discussing AI and its future in radiology. The next episode on August 14 features Stefan Iarca of Rayscape – reserve your seat today.
- New-generation Platform for Managing Multi-Omics Data: QP-Insights from Quibim is a new-generation advanced platform for the management, storage, and analysis of large-scale multi-omics data and medical images for clinical studies and research projects. Learn more on this page.
- How Sports Can Help Save Lives: The Everton F.C. Premier League club integrated AI-enabled point-of-care diagnostics into a one-stop community hub supporting early diagnosis of heart failure and COPD using AI echocardiography from Us2.ai. Discover this project is making early detection more accessible than ever.
- AI Tools for Lung Cancer Screening: CT lung cancer screening is gaining momentum around the world. Learn about AI-based nodule detection tools that can improve the accuracy of low-dose CT scans in this video from Riverain Technologies.
|
|
|
|
|
