Wouldn’t it be great if, when you were reading an imaging study, you had all the relevant patient history and medical data available to you - without having to switch systems or even take your eyes off the study?
Wouldn’t it be great if, when you were reading an imaging study, you had all the relevant patient history and medical data available to you - without having to switch systems or even take your eyes off the study?
You’d have more than the basic patient info (55 year-old male with history of back pain, for example), and have easy access to previous studies, medication lists, full medical history - right at your fingertips.
That’s what Eliot Siegel, MD, of the University of Maryland, described as his ideal next-generation PACS. He spoke at webinar today called “Radiology Efficiency, The Leading Edge,” hosted by imagingBiz.
Siegel described such a system as an automated resident or fellow. Just like a trained fellow, the system could retrieve information from multiple sources and have it summarized and available at the time of the image interpretation. Having all that information from various systems readily available and integrated into the workflow would improve the radiologist’s efficiency and quality of the interpretation.
For example, that patient with a history of lower back pain? Depending on the patient’s history and conditions (such as the fact that he has a history of urinary tract infections and he’s diabetic), the interpretation of his study could either be expected or a surgical emergency, Siegel explained.
“I would have a much more focused and specific interpretation” with all the necessary patient information, Siegel said.
With the pressures on radiologists to be efficient, it’s unreasonable to think the radiologist is always going to track down all that information by combing the electronic medical record or talking with the technologist or the patient, he said. Instead, Siegel envisioned a system right at his PACS workstation that provided links to other relevant information.
Khan Siddiqui, MD, of Microsoft Corporation, who was also speaking for the webinar, explained a solution that aims to do exactly what Siegel described. The Amalga for PACS provides additional relevant patient data to allow for a more precise diagnosis, he said.
Providing more information can make the radiologist more efficient, as well as allow for more high-level analytics to help improve quality of care and organizational efficiencies.
What do you think of such a system? Does your system already incorporate all the information you need? How you would envision your ideal next-generation PACS?
Can AI Enhance CT Detection of Incidental Extrapulmonary Abnormalities and Prediction of Mortality?
September 18th 2024Emphasizing multi-structure segmentation and feature extraction from chest CT scans, an emerging AI model demonstrated an approximately 70 percent AUC for predicting significant incidental extrapulmonary findings as well as two-year and 10-year all-cause mortality.
Comparing Digital Breast Tomosynthesis to Digital Mammography: What a Long-Term Study Reveals
September 17th 2024In a study involving over 272,000 breast cancer screening exams, digital breast tomosynthesis (DBT) had a higher breast cancer detection rate and a lower rate of advanced cancer presentation at the time of diagnosis in comparison to digital mammography.
Can Radiomics Enhance Differentiation of Intracranial Aneurysms on Computed Tomography Angiography?
September 17th 2024Radiomics models offered a pooled AUC of 86 percent for differentiating between ruptured and unruptured intracranial aneurysms, according to a recently published meta-analysis.