In locations with fewer resources, social media messaging is playing a key role in COVID-19 identification.
Patients with potential COVID-19 infections are descending upon hospitals almost everywhere, putting a strain on radiologists who are asked to review suspicious CT scans. And, for locations without enough resources – scanning equipment or thoracic radiologists – handling the mounting caseload can be overwhelming.
In these situations, some radiology groups are turning to social media apps in an effort to pool expert knowledge. Recently, the Iranian Society of Radiology (ISR) partnered with radiologists in North America to create a teleradiology consultation service, called Iranian Society of Radiology COVID-19 Consultants (ISRCC), using WhatsApp, a securing messaging platform.
Lead authors Amir Davarpanah, M.D., from Emory Univeristy School of Medicine, and Morteza Sanei Taheri, M.D., with Shahid Beheshti University of Medical Sciences in Iran, detailed the results of this endeavor in a recently published article in the Journal of the American College of Radiology.
“Our humanitarian teleconsultation strategy allows reliable triage of COVID-19 infection using radiology experts from centers from around the world to provide consultation in regions with limited access to thoracic radiology expertise during a rapidly growing epidemic,” Davarpanah wrote.
Although ISR, a non-government, non-profit organization, has 3,000 radiologist members, Iran doesn’t have enough radiologists with sub-specialty thoracic training to handle the growing caseload. As one of the hardest-hit countries, Iran has identified more than 38,000 COVID-19 cases, and it also doesn’t have enough equipment to meet the challenge – the country only has 6.5 CT scanners per 1 million individuals.
Consequently, the group partnered with 11 volunteer radiologists (nine from Iran, one from Canada, and one in the United States), to gather second opinions for CT scans from patients with early clinical or lab findings suspicious for COVID-19 infection. Having volunteers in multiple time zones ensured round-the-clock coverage.
This type of system could help alleviate overcrowding in hospitals already struggling to meet patient needs, they said.
“Teleradiology services alleviate the need to send patients to overpopulated hospitals and provide near real-time consultation from experts located around the country and the world to meet the local need,” they said. “An increasing number of health care professionals have adopted social media for education and information exchange in various clinical settings.”
To get the outside, expert read, the Iranian radiologists submitted anonymized CT images in JPEG or MP4 format to the private WhatsApp group that was restricted to the participating radiologists. DICOM was used in instances with low image quality – roughly 19 percent of cases - and other patient information, such as age, main complaint, lab results, vital signs, and course of care were also submitted. Images received a case number and were posted to the ISRCC for interpretation. Volunteer experts accessed the images using their password-protected smartphones, and all final reports were sent to the referring radiologist via WhatsApp or email within two hours.
According to the study results, 1,138 CT exams were submitted from 65 cities between Feb. 18, 2020, and March 8, 2020. Of those exams, 43 percent had imaging patterns that suggested viral pneumonia and were sent for further real time reverse transcription-polymerase chain reaction (rRT-PCR) testing. Imaging patterns from an additional 41 percent weren’t consistent with viral pneumonia, and they were referred for management of other diagnoses. Sixteen percent were categorized as indeterminate and referred for either observation or CT follow-up.
Overall, the authors said, they were able to fulfill the current CT scan needs with 11 volunteers, but they acknowledged the demand for thoracic radiology expertise will expand in coming weeks. It is possible, they said, that the need will exceed the capabilities of both traditional and social media teleradiology. They also acknowledged potential data security and privacy protection concerns, as well as the likelihood that the broader definition of infection could lead to a higher number of false-positive cases.
Still, they asserted, the WhatsApp group had a positive benefit.
“Our priority was to identify the majority of suspicious cases on chest CT and use rRT-PCR testing in a more selective fashion to minimize resource drain,” they wrote.
CT Perfusion Study Shows Enhanced Detection of Medium Vessel Occlusions with Emerging AI Software
May 21st 2025The Rapid CTP AI software offered 23 percent greater detection of medium vessel occlusions in comparison to the Viz CTP AI software, according to research presented at the European Stroke (Organization) Conference (ESOC).
Can AI Predict Future Lung Cancer Risk from a Single CT Scan?
May 19th 2025In never-smokers, deep learning assessment of single baseline low-dose computed tomography (CT) scans demonstrated a 79 percent AUC for predicting lung cancer up to six years later, according to new research presented today at the American Thoracic Society (ATS) 2025 International Conference.
Can Emerging AI Software Offer Detection of CAD on CCTA on Par with Radiologists?
May 14th 2025In a study involving over 1,000 patients who had coronary computed tomography angiography (CCTA) exams, AI software demonstrated a 90 percent AUC for assessments of cases > CAD-RADS 3 and 4A and had a 98 percent NPV for obstructive coronary artery disease.
CT Perfusion Study Shows Enhanced Detection of Medium Vessel Occlusions with Emerging AI Software
May 21st 2025The Rapid CTP AI software offered 23 percent greater detection of medium vessel occlusions in comparison to the Viz CTP AI software, according to research presented at the European Stroke (Organization) Conference (ESOC).
Can AI Predict Future Lung Cancer Risk from a Single CT Scan?
May 19th 2025In never-smokers, deep learning assessment of single baseline low-dose computed tomography (CT) scans demonstrated a 79 percent AUC for predicting lung cancer up to six years later, according to new research presented today at the American Thoracic Society (ATS) 2025 International Conference.
Can Emerging AI Software Offer Detection of CAD on CCTA on Par with Radiologists?
May 14th 2025In a study involving over 1,000 patients who had coronary computed tomography angiography (CCTA) exams, AI software demonstrated a 90 percent AUC for assessments of cases > CAD-RADS 3 and 4A and had a 98 percent NPV for obstructive coronary artery disease.
2 Commerce Drive
Cranbury, NJ 08512