Site icon TopoDate

External AI doesn’t improve performance across the board, research finds

​Researchers said that the public accessibility of Nuance’s Dragon Ambient Experience navigator in Atrium Health’s electronic health records did not show considerable improvements in essential metrics for the organization, despite further studies could be conducted to further examine the utility of Nuance’s conceptual artificial intelligence voice-enabled documentation tool for clinician subgroups and other medical implementations. WHY IT MATTERSLast year, Charlotte, North Carolina-based Atrium Health, which merged with and became Advocate Health in 2022, touted itself as the second U. S. health system to install AI-driven external medical documentation to manage the creation of medical documentation during physician visits. Researchers from Atrium and Wake Forest University School of Medicine evaluated the benefits of the participating professionals after the health program implemented Nuance’s DAX Copilot in the post-DAX application review, which was published in the New England Journal of Medicine AI. Between June and August 2023, they first enrolled 238 inpatient centres in North Carolina and Georgia, with the aim of five tides. Those who participated in the class testing on DAX received a one-hour education and were given accounts via their Epic Records. The researchers evaluated outcomes related to the EHRs over 180 days, including time in EHR, labor time outside of work, time-in-note, completed visit level, same-day closing price and note length, and economic metrics, such as work equivalent value units per visit. According to them, the last empirical sample that was analyzed included 103 clinicians from the control, non-DAX user group and 112 from the software user group. They found that three-fourths of “active DAX users” ( 84/112 ) transferred more than 25 % of their DAX notes to Epic and approximately 60 % of “high DAX users” ( 67/112 ) transferred more than 60 % of their DAX notes to their EHRs. After controlling for age, sex, company form, years of practice and foundation outcome, the researchers said they found couple” statistically significant differences” between DAX users and the control group – save note time. According to their report,” High DAX users had an overall decrease of about 7 % in documentation hours compared to the control group.” According to research, using DAX at a high utilization level or deploying DAX to specific clinician subgroups may result in minor shortening the duration of the note. Wake Forest University Health Sciences, a part of the university’s medical school that serves as the academic core of Advocate Health, funded the study. THE LARGER TRENDMany organizations expanded their use of DAX Copilot this past year, including Intermountain Health, Pennsylvania-based WellSpan Health and others. In an effort to reduce clinician burnout, EHR vendors also established partnerships to integrate the documentation pool. In January, Epic fully embedded the Nuance AI copilot and in March, Meditech Expanse EHR announced its integration. Meanwhile, in October, Microsoft reported that, after a year of availability, DAX was seeing momentum, and highlighted that the AI tool was used in at least 50 % of patient encounters at Northwestern Medicine in Chicago. According to the tech giant, the health system’s clinicians spent an average of 24 % less time drafting notes and increased the number of patients they could see by an average of 11 %. These findings, taken together, point to the possibility that lower markers of burnout may be achieved for a subset of clinicians and perhaps more broadly when DAX adoption is higher, according to the researchers in their NEJM AI report. However, it’s unlikely that widespread application of DAX in its current form will result in significant productivity gains for healthcare systems. Email: afox@himss .org Healthcare IT News is a HIMSS Media publication. 

Exit mobile version