In early March, all of healthcare, including radiology, was introduced to the concept of social distancing. For the industry, that meant a quick shift to remote reading for most providers. The close proximity usually needed for most aspects of diagnostic imaging made it tough to accomplish this goal, but the experience of one large academic medical center shows that not only is the pivot to at-home reading possible, but it can also be done quickly.
Still, said Srini Tridandapani, M.D., Ph.D., vice chair of imaging informatics at the University of Alabama at Birmingham (UAB) Health System, there are financial, engineering, equipment, and workflow challenges to consider and conquer. Together, he said, he and his team addressed these concerns to successfully implement at-home PACS workstations for UAB’s radiologists.
“Remote interpretation of imaging studies can contribute to social distancing, protect vulnerable radiologists and others in the hospital, and ensure seamless interpretation capabilities in emergency scenarios,” he and his team wrote in a May 21 article published in the American Journal of Roentgenology.
Initially, UAB had resisted incorporating a work-at-home option for radiologists, citing the importance of having providers on-site and the difficulties of managing and supporting multiple several PACS. However, to protect faculty and residents, administration leaders embraced the idea, increasing the number of home-based PACS from two to more than two dozen.
Many individuals at the university volunteered their computers to be converted to PACS, but most lacked the processing and memory capacity required. Fortunately, the department had recently purchased the hardware necessary to cycle out end-of-life PACS and monitors. Ultimately, the department opted to build additional PACS workstations with standard monitors because they can be used to interpret CT, ultrasound, and MRI studies. High-end monitors are only needed for radiographs.
In addition, the department submitted a financial support request – that was quickly approved – for a hardware virtual private network system (VPN) and 44 standard display monitors. The VPN was used to mirror the functionality of the on-site workstations for UAB’s iSite PACS. The remote workstations were installed and ready for use within three weeks of when department leaders started the process.
Even though the department would have liked to accommodate at-home reading for all providers, enough funding to do so was not available. After an assessment, Tridandapani said, department leaders decided to provide at-home PACS to four emergency radiologists who live out-of-state because they frequently interpret a wide variety of studies from multiple modalities and organ systems.
Alongside the emergency radiologists, section chiefs made individual determinations about how to allocate the remaining at-home systems, taking into consideration the work volume and the need to keep radiologists who are at greater risk safe. These at-home work stations are temporary, though, he said, and will be returned to the department once providers are allowed to return to work after the COVID-19 outbreak.
While most providers in the department are currently working from home, the decision was made to keep at least one provider from each section on-site to work with technologists, providing additional guidance and support when needed.
Social Distancing with At-Home PACS
How one large academic medical center quickly pivoted to keep radiologists safe.
In early March, all of healthcare, including radiology, was introduced to the concept of social distancing. For the industry, that meant a quick shift to remote reading for most providers. The close proximity usually needed for most aspects of diagnostic imaging made it tough to accomplish this goal, but the experience of one large academic medical center shows that not only is the pivot to at-home reading possible, but it can also be done quickly.
Still, said Srini Tridandapani, M.D., Ph.D., vice chair of imaging informatics at the University of Alabama at Birmingham (UAB) Health System, there are financial, engineering, equipment, and workflow challenges to consider and conquer. Together, he said, he and his team addressed these concerns to successfully implement at-home PACS workstations for UAB’s radiologists.
“Remote interpretation of imaging studies can contribute to social distancing, protect vulnerable radiologists and others in the hospital, and ensure seamless interpretation capabilities in emergency scenarios,” he and his team wrote in a May 21 article published in the American Journal of Roentgenology.
Initially, UAB had resisted incorporating a work-at-home option for radiologists, citing the importance of having providers on-site and the difficulties of managing and supporting multiple several PACS. However, to protect faculty and residents, administration leaders embraced the idea, increasing the number of home-based PACS from two to more than two dozen.
Many individuals at the university volunteered their computers to be converted to PACS, but most lacked the processing and memory capacity required. Fortunately, the department had recently purchased the hardware necessary to cycle out end-of-life PACS and monitors. Ultimately, the department opted to build additional PACS workstations with standard monitors because they can be used to interpret CT, ultrasound, and MRI studies. High-end monitors are only needed for radiographs.
In addition, the department submitted a financial support request – that was quickly approved – for a hardware virtual private network system (VPN) and 44 standard display monitors. The VPN was used to mirror the functionality of the on-site workstations for UAB’s iSite PACS. The remote workstations were installed and ready for use within three weeks of when department leaders started the process.
Even though the department would have liked to accommodate at-home reading for all providers, enough funding to do so was not available. After an assessment, Tridandapani said, department leaders decided to provide at-home PACS to four emergency radiologists who live out-of-state because they frequently interpret a wide variety of studies from multiple modalities and organ systems.
Alongside the emergency radiologists, section chiefs made individual determinations about how to allocate the remaining at-home systems, taking into consideration the work volume and the need to keep radiologists who are at greater risk safe. These at-home work stations are temporary, though, he said, and will be returned to the department once providers are allowed to return to work after the COVID-19 outbreak.
While most providers in the department are currently working from home, the decision was made to keep at least one provider from each section on-site to work with technologists, providing additional guidance and support when needed.
New Study Examines Short-Term Consistency of Large Language Models in Radiology
While GPT-4 demonstrated higher overall accuracy than other large language models in answering ACR Diagnostic in Training Exam multiple-choice questions, researchers noted an eight percent decrease in GPT-4’s accuracy rate from the first month to the third month of the study.
The Reading Room Podcast: Emerging Trends in the Radiology Workforce
Richard Duszak, MD, and Mina Makary, MD, discuss a number of issues, ranging from demographic trends and NPRPs to physician burnout and medical student recruitment, that figure to impact the radiology workforce now and in the near future.
Is Elon Musk’s Foray into Radiology AI an Opportunity to Reexamine the Embarrassment of Learning?
Self-imposed fears of embarrassment may lead to an inadvertent defensive stance that prevents us from learning.
Current Trends in X-ray Imaging
KA Imaging President and Chief Executive Officer Amol Karnick and Chief Technology Officer Karim S. Karim, Ph.D., offer insights into current X-ray imaging trends, as well as opportunities for innovation.
Can Innovations with AI Help Address the Impact of Staffing Shortages on Radiology Workflow?
While staffing shortages in radiology continue to persist after the COVID-19 pandemic, current and emerging innovations powered by artificial intelligence (AI) may help facilities navigate these challenges and mitigate rising costs of health care.
Radiology Reimbursement Advice: Ignore the RVUs If You Can
Eschewing the pursuit of sweet spots with RVUs, this radiologist emphasizes consistent variety in your case mix to help ensure optimal marketability.
New Study Examines Short-Term Consistency of Large Language Models in Radiology
While GPT-4 demonstrated higher overall accuracy than other large language models in answering ACR Diagnostic in Training Exam multiple-choice questions, researchers noted an eight percent decrease in GPT-4’s accuracy rate from the first month to the third month of the study.
The Reading Room Podcast: Emerging Trends in the Radiology Workforce
Richard Duszak, MD, and Mina Makary, MD, discuss a number of issues, ranging from demographic trends and NPRPs to physician burnout and medical student recruitment, that figure to impact the radiology workforce now and in the near future.
Is Elon Musk’s Foray into Radiology AI an Opportunity to Reexamine the Embarrassment of Learning?
Self-imposed fears of embarrassment may lead to an inadvertent defensive stance that prevents us from learning.
Current Trends in X-ray Imaging
KA Imaging President and Chief Executive Officer Amol Karnick and Chief Technology Officer Karim S. Karim, Ph.D., offer insights into current X-ray imaging trends, as well as opportunities for innovation.
Can Innovations with AI Help Address the Impact of Staffing Shortages on Radiology Workflow?
While staffing shortages in radiology continue to persist after the COVID-19 pandemic, current and emerging innovations powered by artificial intelligence (AI) may help facilities navigate these challenges and mitigate rising costs of health care.
Radiology Reimbursement Advice: Ignore the RVUs If You Can
Eschewing the pursuit of sweet spots with RVUs, this radiologist emphasizes consistent variety in your case mix to help ensure optimal marketability.