A fact that will surprise absolutely no one is that as the spread of EHRs has increased the amount of data available to physicians, the amount of time physicians spend reviewing that data has increased.
But perhaps some new AI can help.
That’s the proposition researchers at Stanford University recently tested by tapping AI for a system that organized patient records, improved data retrieval and – the ultimate goal – reduced the amount of time providers had to spend reviewing clinical data.
According to the study, published recently at JAMA, “To evaluate the system on time and accuracy, a nonblinded, prospective study was conducted at a single academic medical center. Recruitment emails were sent to all physicians in the gastroenterology division, and 12 clinicians agreed to participate. Each of the clinicians participating in the study received 2 referral records: 1 AI-optimized patient record and 1 standard (non–AI-optimized) patient record. For each record, clinicians were asked 22 questions requiring them to search the assigned record for clinically relevant information. Clinicians reviewed records from June 1 to August 30, 2020.”
Researchers compared the time and accuracy of the searches of both the AI-optimized patient records and the standard patient records. Moreover, participating physicians were asked to assess their overall satisfaction with the AI system, their preferred method of review, and other topics to evaluate clinical utility.
According to the researchers, when compared to the standard patient record review, the AI system saved physicians 18 percent of the time used to answer clinical questions. There was also no significant change in accuracy when physicians retrieved the data either with the AI system or without.
Finally, the researchers reported, “(e)leven of 12 clinicians (92%) found the software useful and agreed, to various extents, that it would improve clinician efficiency in reviewing patient records. Clinicians reported that the software could provide an estimated time savings ranging from 5 to 30 minutes; the mean (SD) savings estimated was 14.5 (11.1) minutes when reviewing a new patient record. Most physicians reported that they preferred the AI-optimized record and would be interested in using it in their clinic.”
In short, the AI system was able to help physicians extract relevant patient data in a shorter amount of time while remaining accurate.
“In general,” the researchers concluded, “the supportive responses of our survey highlight the importance of this issue as an area of need that can likely be generalized and expanded to multiple other medical subspecialties that share similar challenges, because many referral records contain similar types of information (eg, progress notes, radiology reports, pathology findings, procedure notes, etc).”
Moreover, they noted, “This is particularly relevant in an era in which practitioners are confronting increasing volumes of EHR data and the loss of face-to-face interaction with patients.”
Photo by estherrr/Getty Images