Finding an electronic health record (EHR) system that works perfectly with a healthcare network’s preferred care delivery process is like finding a needle in a haystack. However, AI offers a solution to improve EHRs and make them more user-friendly for clinicians, according to an analysis in the Harvard Business Review.
There are several ways to address EHR issues such as inefficiency, cost-effectiveness and inflexibility. For one, the systems could be designed to be more integrated and streamlined or open sourced. However, the most promising solution to making EHR systems more flexible and intelligent is AI.
“This is a critical goal, as EHRs are complicated and hard to use and are often cited as contributing to clinician burnout,” Thomas H. Davenport, lead author of the report, president’s distinguished professor in management and information technology at Babson College, research fellow at the MIT Initiative on the Digital Economy, and a senior adviser at Deloitte Analytics, et. al wrote. “Today, customizing EHRs to make them easier for clinicians is largely a manual process, and the systems’ rigidity is a real obstacle to improvement. AI, and machine learning specifically, could help EHRs continuously adapt to users’ preferences, improving both clinical outcomes and clinicians’ quality of life.”
Using AI would also help make existing EHR systems more flexible and intelligent. EHRs that currently use already AI have several capabilities:
- Data extraction from free text
- Diagnostic and/or predictive algorithms
- Clinical documentation and data entry
- Clinical decision support
For this method to be effective in EHRs, AI capabilities must be tightly integrated. While most current AI options are offered as standalone features and require physicians to learn how to use new interfaces, some mainstream EHR vendors are beginning to add AI capabilities to make their systems easier to use, the report stated.
“Firms like Epic, Cerner, Allscripts and Athena are adding capabilities like natural language processing, machine learning for clinical decision support, integration with telehealth technologies and automated imaging analysis. This will provide integrated interfaces, access to data held within the systems, and multiple other benefits—though it will probably happen slowly,” the researchers wrote.
To read the full report, click the link below.