Radiologists require access to patient data stored in the electronic medical record, but finding the information they need can be time consuming. If a clinician needs to click through all the tabs in the EMR to find relevant pieces of patient information, they may skip it because of the time involved.
Radiology IT expert Rik Primo, principal with the consulting firm Primo Medical Imaging Informatics, spoke with Radiology Business about this issue following the Healthcare Information Management Systems Society (HIMSS) 2023 meeting. He was formerly a radiology software developer and PACS product manager with Siemens, Philips and Agfa,
"I am talking to a lot of healthcare professionals, CEOs and CMOs, and they all tell me that the accessibility of EMR data is an issue," Primo explained. "I would say that was probably one of the most important things that I saw at HIMSS as a demand in the market that is currently not addressed by the majority of PACS vendors. But it also is not the role of a typical PACS company to do that. The company that comes out with a solution to address that will be a winner. And in my opinion, it's probably not going to be a PACS company."
Since most IT systems will not plug-and-play with EMRs that offer the functionality some radiology departments desire, Primo said several IT-interfacing vendors have developed software to create the necessary links. These can provide custom dashboard views with the data relevant to radiologists.
"EMRs are good as repositories for all the information needed to review the clinical condition of a patient, but you do not have a single overview," Primo said. "PACS vendors have been proclaiming that interfacing and integrating the healthcare enterprise will be the solution to that problem; however, it's not."
Companies that specialize in creating application programming interfaces can help solve the issue, which Primo said was a giant step toward interoperability. But interfaces are not enough, and today companies are looking at using artificial intelligence to tell these APIs where to look for data and how to present it in a usable format.
Some solutions also can present both structured and unstructured information. Unstructured data includes free text fields from which IT systems can have difficulties extracting information. The systems can pull the data into readable text formats for radiologists. This sometimes involves natural language processing to sort through the information and be able to understand and digest it.
"About 40 years ago we discovered DICOM is great. But then years later we found DICOM needed to be integrated or interfaced into different systems. Then 20 years ago, we realized interfacing is one thing, but interoperability is very different and much more complex," Primo said.
Find more of Primo's observations on medical imaging IT trends in the article and video: 3 key radiology IT systems trends.
Dave Fornell has covered healthcare for more than 17 years, with a focus in cardiology and radiology. Fornell is a 5-time winner of a Jesse H. Neal Award, the most prestigious editorial honors in the field of specialized journalism. The wins included best technical content, best use of social media and best COVID-19 coverage. Fornell was also a three-time Neal finalist for best range of work by a single author. He produces more than 100 editorial videos each year, most of them interviews with key opinion leaders in medicine. He also writes technical articles, covers key trends, conducts video hospital site visits, and is very involved with social media. E-mail: dfornell@innovatehealthcare.com