|
Teleradiology AI’s Mixed Bag | Technostress and Burnout
July 22, 2024
|
|
|
|
|
Together with
|
|
|
|
“We need to log on all the time, and our password must be a minimum of 15
characters long. You can mistype it so many times a day. Even without mistyping, you repeatedly type the same and the same and the same on your computer.”
|
|
A Danish nuclear medicine provider responding to a survey on technology stress in healthcare.
|
|
|
U.S. military veterans who returned from past overseas deployments have experienced a variety of breathing ailments collectively called deployment-related respiratory disease (DRRD), believed to be caused by exposure to burn pits and other airborne hazards. In this episode of The Imaging Wire Show, we talk to one veteran about her experience, and about technologies from 4DMedical that can help screen for and diagnose DRRD.
|
|
|
|
An AI algorithm that examined teleradiology studies for signs of intracranial hemorrhage had mixed performance in a new study in Radiology: Artificial Intelligence. AI helped detect ICH cases that might have been missed, but false positives slowed radiologists down.
AI is being touted as a tool that can detect unseen pathology and speed up the workflow of radiologists facing an environment of limited resources and growing image volume.
- This dynamic is particularly evident at teleradiology practices, which frequently see high volumes during off-hour shifts; indeed, a recent study found that telerad cases had higher rates of patient death and more malpractice claims than cases read by traditional radiology practices.
So teleradiologists could use a bit more help. In the new study, researchers from the VA’s National Teleradiology Program assessed Avicenna.ai’s CINA v1.0 algorithm for detecting ICH on STAT non-contrast head CT studies.
- AI was used to analyze 58.3k CT exams processed by the teleradiology service from January 2023 to February 2024, with a 2.7% prevalence of ICH.
Results were as follows…
- AI flagged 5.7k studies as positive for acute ICH and 52.7k as negative
- Final radiology reports confirmed that 1.2k exams were true positives for a sensitivity of 76% and a positive predictive value of 21%
- There were 384 false negatives (missed ICH cases), for a specificity of 92% and a negative predictive value of 99.3%
- The algorithm’s performance at the VA was a bit lower than in previously published literature
- Cases that the algorithm falsely flagged as positive took over a minute longer to interpret than prior to AI deployment
- Overall, case interpretation times were slightly lower after AI than before
One issue to note is that the CINA algorithm is not intended for small hemorrhages with volumes < 3 mL; the researchers did not exclude these cases from their analysis, which could have reduced its performance.
- Also, at 2.7% the VA’s teleradiology program ICH prevalence was lower than the 10% prevalence Avicenna has used to rate its performance.
The Takeaway
The new findings aren’t exactly a slam dunk for AI in the teleradiology setting, but in terms of real-world results they are exactly what’s needed to assess the true value of the technology compared to outcomes in more tightly controlled environments.
|
|
|
AI Supports Diagnosis of Cognitive Disorders
How can AI support the early diagnosis of cognitive disorders in elderly people? Read this article from DeepHealth on how AI-powered software with MRI can be used with both neuropsychological tests and clinical information to improve early diagnosis of cognitive impairments.
|
|
Re-Examining Radiology: A Look to the Future
What will the future of radiology look like? In this downloadable white paper from Optum, learn how a constellation of challenges and pressures have come together to change healthcare – and radiology.
|
|
Give Your Patients the Experience They Want
Empower patients to take control of their healthcare journey by giving them mobile access to their records and images with Clearpath, the world’s first digital fulfillment platform for records and films. Book a demo today.
|
|
- Technostress in Healthcare: Is the technology you’re using at work every day causing you stress – AKA technostress? Danish researchers found a connection in a qualitative study in the International Journal of Medical Informatics. In interviews with 15 nuclear medicine healthcare providers, the biggest source of technostress was poor system performance (46%), such as a slow RIS/PACS with poor functionality. In second at 18% was poor organizational procedures like overly complex log-ins. The study highlights the perils of acquiring healthcare technology without getting buy-in from the people using it.
- Doctor Burnout Rate Drops: The physician burnout rate has fallen below 50% for the first time since 2020 – the height of the COVID-19 pandemic. That’s according to a new AMA survey of 12.4k U.S. physicians performed from January-December 2023. The survey found that the physician burnout rate fell in 2023 compared to 2022 (48% vs. 53%), and is down sharply from the peak of 63% in 2021. Job-related stress also fell over the same period (51% vs. 56%). The findings correlate with other recent studies showing declining doctor burnout.
- Burnout Measurement Challenges: In related news, a new meta-analysis in AJR demonstrates the challenge of measuring burnout among healthcare professionals. Researchers analyzed 57 studies of 11.4k radiologists from 1990 to 2023, finding burnout rates ranging from 5% to 85% – not a particularly precise discovery. But when the analysis focused on studies with similar burnout definitions, the rate was more consistent at 34% to 39%. More standardized definitions of burnout would help deliver better and more accurate insights.
- CT, Radiation, and Patient Survival: What percentage of patients are still alive 10 years after getting CT scans? In a new paper in European Journal of Radiology, researchers tracked outcomes of 36.5k scans acquired in 2013, finding that patients who got ≥100 mSv of radiation were nearly 7X more likely to die within two years versus those who got <10 mSv – most likely because they were sicker. Still, 37% were still alive 10 years later, highlighting the need to reduce radiation dose even in very ill patients.
- GE Buys Intelligent Ultrasound: The ultrasound AI segment continues to heat up. GE HealthCare last week acquired the clinical AI business of Intelligent Ultrasound for $51M, giving GE more control over the AI technology for analyzing OB/GYN scans. Intelligent Ultrasound’s ScanNav Assist technology powers applications on GE’s Voluson Expert and Voluson Signature scanners, with the goal of reducing sonographer workload. The acquisition follows GE’s purchase of ultrasound AI firm Caption Health in February 2023.
- AI Alliance for Lung Fibrosis: AI developer Brainomix has cemented an alliance with pharmaceutical company Boehringer Ingelheim to identify patients with progressive pulmonary fibrosis in the U.S. The Brainomix 360 e-Lung algorithm will be used to analyze routine CT scans for signs of pulmonary fibrosis; patients can then be directed to treatment such as with drugs developed by Boehringer Ingelheim. The alliance comes just a few months after Brainomix secured FDA clearance for e-Lung, marking the company’s expansion into lung imaging.
- Lantheus Focuses on New PET Agent: Lantheus Holdings has acquired a company developing a new PET radiopharmaceutical for diagnosing Alzheimer’s disease. Meilleur Technologies’ NAV-4694 (also known as F18-flutafuranol) is in phase III development for detecting beta amyloid on PET scans. The agent complements Lantheus’ own MK-6240 (also known as florquinitau) that targets tau tangles, which like beta amyloid is a biomarker for Alzheimer’s disease. Interest in PET tracers for diagnosing Alzheimer’s disease has grown with the FDA approval of new pharmaceutical treatments.
- AI Reduces Chest X-Ray Workload: An AI algorithm was able to rule out 20% of chest radiographs most likely to have no actionable disease (NAD) in a new study in Academic Radiology. In 14.1k patients with two-view chest X-rays, Siemens Healthineers’ AI NAD Analyzer for Chest X-Ray correctly classified cases with sensitivity of 29% and yield of 21%. Specificity was 99% with a miss rate of 0.3% for all cases and 0.06% for significant findings. No critical findings were missed. AI could identify cases to be read with a streamlined protocol.
- Eden AI Targets Latin America: A Mexican startup company called Eden has raised $10M that it will put to work commercializing radiology AI software for Latin and Central America. The company already offers cloud-based RIS/PACS, and currently processes over 6M studies annually from 1.5k sites in 17 countries. Other products offered by Eden include Eden Portal for patients to view their medical images, Eden PACS DICOM Viewer, and Eden Management workflow orchestrator.
- Q Bio Raises $27M for Full-Body MRI: Another medical imaging startup with a healthy funding round is Q Bio, which raised $27M to commercialize its Mark I full-body MRI scanner. Mark I is being developed to eliminate the need for multiple MRI scans by capturing 3k quantitative anatomical measurements in a 10-minute scanning session using the company’s Tensor Field Mapping protocol. Q Bio will use the funds for accelerating its manufacturing plans and securing regulatory approvals for Mark I.
- HeartFlow Plaque, Interactive and Integrated: HeartFlow’s SCCT 2024 presence was highlighted by a major upgrade to its HeartFlow Plaque Analysis platform, adding new interactive visualization features and direct integration with lesion-specific FFRCT values. First launched in 2022, HeartFlow Plaque Analysis uses AI to analyze CCTAs, creating a 3D model that quantifies and characterizes plaque volume in the coronary arteries. The new FFRCT-integrated generation now provides insights into both quantified plaque and physiology for a “fully integrated view of a patient’s true burden of coronary artery disease.”
|
|
Presenting Unboxing AI
Check out CARPL’s video series, Unboxing AI, featuring experts discussing AI and its future in radiology. The next episode on July 26 features Ryan Lee, MD, of Thomas Jefferson University – reserve your seat today.
|
|
The Importance of Workflow in SPECT/CT
SPECT/CT can impact everything from patient satisfaction to exam efficiency. In this video, learn from two technologists and a physician how Siemens Healthineers’ Symbia Pro.specta SPECT/CT system impacts their daily work, their patients, and their department’s efficiency.
|
|
AI-Driven Novice Heart Failure Screening
We hear a lot about AI’s potential to expand echocardiography to far more users and clinical settings, and a study using Us2.ai’s AI-automated echo analysis and reporting solution showed that echo AI might make novice-led heart failure screening possible.
|
|
- AI-Empowered CT Workflow: CT systems from United Imaging are designed for high image quality and low dose, and their AI-empowered workflow enables fast and reproducible positioning, helping you image patients with confidence. Learn more on this page.
- AI Applications in Neuroradiology: What are the most common AI applications in neuroradiology? This downloadable e-book from Bayer and Calantic Digital Solutions reviews the most common AI applications for brain imaging and the evidence behind them.
- Revolutionizing Chest X-Ray Reporting: A new study in Radiology shows how Gleamer’s ChestView AI solution is revolutionizing chest X-ray reporting by helping radiologists detect lung abnormalities with greater accuracy while also reducing interpretation times.
- Clarity, Speed, and Confidence for MRI Efficiency: Radiologists have used a variety of methods to improve efficiency, but many of these methods come with drawbacks. Find out in this article how SpinTech MRI takes on the challenge of MRI efficiency with its STAGE software.
- Cloud-Based Disaster Recovery: When disaster strikes, have peace of mind knowing your imaging data is safe. Securely store backups with Intelerad’s InteleArchive solution, ensuring your imaging data is there when you need it. Get started by booking a demo today.
- Smart Bytes on Cardiology Workflows: Check out Smart Bytes, a new series of webcasts from AGFA HealthCare giving you bite-sized insights for smarter imaging. At 12:30 ET on August 15 learn about improved cardiology workflows using cutting-edge AI technology.
- An Integrated Approach to Radiology AI: AI automates what radiologists can’t stand, surfaces what radiologists can’t see, and identifies what radiologists can’t miss. But only if it’s implemented in the way radiologists work. See how Nuance helps radiologists achieve these results through a single, streamlined, end-to-end AI experience.
- Imaging in the Cloud: The healthcare imaging market in the U.S. is moving to the cloud. In this new report from KLAS Research, find out why companies like Merge by Merative are instilling confidence in customers thanks to their cloud approach.
- Seamless Integration and Efficient Reading: TeraRecon’s latest Intuition advanced visualization solution now features seamless integration with Mirada Medical’s Mirada XD, providing efficient diagnostic reading with automatic multi-modality and multi-time point registration capabilities. Schedule a demo to learn more.
- Top 5 Benefits of Standardizing Medical Imaging Archives: Efficient data management is crucial for delivering quality patient care and achieving organizational goals. But data migration when transitioning to a new PACS can be daunting. Find out how solutions from Enlitic can streamline the process.
- Keep Patients Engaged with Your Healthcare System: After using PocketHealth, 94% of patients are more confident about their healthcare experience. Learn how to increase follow-up adherence and patient experience with PocketHealth’s MyCare Navigator.
- The Clinical Value of Soft-Tissue Chest X-Ray: Soft-tissue techniques can improve the visibility and accuracy of chest X-ray. Learn about two important soft-tissue methods – bone suppression and dual-energy subtraction – in this white paper from Riverain Technologies.
- AI and Matters of the Heart: As clinicians face increasing pressure from all sides, can AI provide some much-needed breathing space? In this article from Blackford, learn more about how AI is assisting with cardiac imaging with modalities ranging from CT to echocardiography.
|
|
|
|
|
