Radiologist burnout and its lesser-known counterpart, boreout, are critical issues in the field of radiology—especially in light of the global radiologist shortage.1,2 Burnout is characterized by emotional exhaustion, depersonalization or detachment, and a reduced sense of personal accomplishment. It is alarmingly prevalent among radiologists. One study found that 54-72% of diagnostic and interventional radiologists exhibit burnout symptoms.3 Boreout, on the other hand, is defined by chronic boredom and lack of engagement, often resulting from repetitive tasks and insufficient challenges in one’s work. Both are detrimental to radiologists’ well-being, and may impact job satisfaction and performance.
Dr. Wieland Sommer, a radiologist and professor of oncologic imaging, described the current landscape during a recent Radiology Digital Expert Series hosted by GE HealthCare. “There is a staff shortage in most countries. It becomes unsustainable to increase the number of exams if you don’t change something dramatically in how you prepare a radiologist for his or her tasks,” he explained.
Integrating artificial intelligence (AI) into radiology workflow is an effective strategy for curbing radiologist burnout and boreout. AI can alleviate the tedium of some repetitive and routine tasks associated with image interpretation. This frees radiologists to focus on the more engaging and rewarding aspects of their work, such as collaborating on complex cases, interacting with patients, and participating in interdisciplinary patient panels. This shift can enhance a radiologist’s job satisfaction and overall professional experience.
“Rather than having these many manual processes at the moment, which are also very boring, technology can help focus the radiologists on the important decisions, on value creating. For example, interdisciplinary discussions on complex cases, more time with the patient, and so on. The biggest disruption will be more and more automating of the tedious tasks which lead to burnout and boreout of radiologists,” said Dr. Sommer.
Ultrasound is a modality that is increasingly leveraging AI during image acquisition to enhance accuracy and efficiency. Integrating AI during scans helps ensure radiologists work with complete and accurate images, eliminates the need for manual measurements, and enables faster exam throughput.
Ultrasound AI Guidance Serves Up High-Quality Images
The quality of ultrasound images is critical for accurate diagnosis, but it is highly dependent on the skill and experience level of the sonographer capturing images. Variability in an individual sonographer’s approach can make it difficult to distinguish disease progression and regression, impacting a radiologist’s ability to render a diagnosis. Radiologists also cannot work with incomplete or inadequate images, and in some care pathways, they have to perform a quality check and approve exams before the patient can be released and the exam can be added to the reading worklist.
AI-enhanced ultrasound systems provide clinicians with real-time scan guidance, empowering them to capture a complete set of images on the first attempt with minimal training. These systems detect specific organs, blood vessels, or abnormalities, and bring decades of knowledge to the user by adjusting system settings automatically for the organ detected
This guidance can enable organizations to more consistently generate high-quality, standardized ultrasound images across different operators and machines. This can reduce the likelihood repeat exams, and prevent radiologists from having their reading workflow interrupted.
For example, the LOGIQ Auto Abdominal Imaging Suite 1.0, with features like Auto Preset Assistant and Auto Renal Assistant, significantly enhances radiologists' efficiency by standardizing image acquisition and ensuring consistent, high-quality abdominal scans.4
AI-Assisted Measurements and Workflow Productivity
Traditionally, radiologists spend a significant amount of time manually measuring complex, anatomical structures and documenting their findings. Ultrasound AI algorithms can detect or highlight anatomical structures and pathologies, and provide precise measurements of their size, shape, and other relevant characteristics. This reduces the need for radiologists to perform these time-consuming and repetitive tasks. Additionally, AI-generated measurements can be instantly integrated into reports, eliminating the need for manual data entry.
As an example, AI can make sub-specialized reporting more efficient for radiologists. With LOGIQ’sTM Thyroid Assistant, powered by Koios DS TM *, radiologists can interpret exams 24% faster5, and inter-reader variability drops by 41%6 , compared to non-Koios-aided exams.
Executive Summary:
The Power of Ultrasound + Artificial Intelligence
AI Supports Efficient Breast Ultrasound Throughput
Traditional ultrasound interpretation is often time-consuming, requiring meticulous analysis of many images. AI-enhanced ultrasound can enable radiologists to reduce interpretation time via algorithms that pre-analyze images, highlighting areas of concern and providing preliminary assessments. This allows radiologists to focus on verifying AI findings rather than starting from scratch.
For instance, one study found that use of a concurrent-read aided-detection system for interpretation of screening automated breast ultrasound (ABUS) studies helps reduce interpretation by 33% using AI-based QVCAD™, from 3 minutes 33 seconds to 2 minutes 24 seconds, with no loss of diagnostic accuracy in cancer detection.7
Breast assistant, powered by Koios DS, on the LOGIQ platform and the Invenia ABUS 2.0 ultrasound, are available AI tools that can identify potential lesions and classify them based on their likelihood of being benign or malignant.
AI is Part of a Holistic Go-Forward Solution
The current and immediate future of the radiology workforce is increasingly being characterized as unsustainable, making the mental health and job satisfaction of radiologists a significant concern. While AI is not the sole solution, its thoughtful integration into workflows can equip radiologists to face the growing demand for imaging services. By assisting with routine and repetitive tasks, AI can improve efficiency and allow radiologists to focus on more complex and valuable activities. This balanced approach holds promise for creating a more sustainable and fulfilling work environment in radiology.
REFERENCES
1. “Radiology Facing a Global Shortage,” RSNA News, last modified May 10 2022, https://www.rsna.org/news/2022/may/global-radiologist-shortage.
2. “ACR, RBMA Urge Congress to Address Workforce Shortages,” American College of Radiology, last modified March 23 2023, https://www.acr.org/Advocacy-and-Economics/Advocacy-News/Advocacy-News-Issues/In-the-March-25-2023-Issue/ACR-RBMA-Urge-Congress-to-Address-Workforce-Shortages.
3. Cheri Canon et al., “Physician Burnout in Radiology: Perspectives from the Field,” American Journal of Roentgenology 218, no. 2 (2022): 370-374.
4. LOGIQ Auto Abdominal Imaging Suite AI study. November 2023. JB29531XX
5. Koios Medical internal data. Presented at Society for Imaging Informatics in Medicine annual meeting, 2021.
6. Koios Medical internal data. Available upon request.
7. Yulei Jiang et al., “Interpretation Time Using a Concurrent-Read Computer-Aided Detection System for Automated Breast Ultrasound in Breast Cancer Screening of Women with Dense Breast Tissue,” American Journal of Roentgenology 211, no. 2 (2018): 452-461.
Footnotes:
Koios DS is a trademark of Koios Medical
QVCAD is a trademark of QView Medical, Inc.
JB30131XX
![](https://pixel.welcomesoftware.com/px.gif?key=YXJ0aWNsZT05ZWFmYWNlYTRlOWUxMWVmOGQ2YmVlNDlkNmFiMDNjZg==)