Since electronic health records were introduced en masse across the healthcare system with the HITECH Act of 2009, there’s been no shortage of discussion focused on the possible ways of making them more effective and more easily integrated into healthcare delivery networks.
While those discussions are bound to continue for the foreseeable future, a recent article at Harvard Business Review points to the rapidly emerging option of using AI to make existing EHR systems more flexible and intelligent.
The authors that AI capabilities for EHRs are currently relatively narrow but they expect them to rapidly improve and to include, among other attributes:
Data extraction from free text: Providers can already extract data from faxes using current AI tools, they note, and one vendor recently announced a cloud-based service that uses AI to extract and index data from clinical notes.
Clinical documentation and data entry: Capturing clinical notes with natural language processing allows clinicians to focus on their patients rather than keyboards and screens, and the writers point to new AI-supported tools that integrate with commercial EHRs to support data collection and clinical note composition.
Clinical decision support: Finally, they point out that while “decision support, which recommends treatment strategies, was generic and rule-based in the past,” machine-learning solutions are emerging today “that learn based on new data and enable more personalized care.”
Looking more broadly across the EHR landscape, the authors suggest that “while AI is being applied in EHR systems principally to improve data discovery and extraction and personalize treatment recommendations, it has great potential to make EHRs more user friendly. This is a critical goal, as EHRs are complicated and hard to use and are often cited as contributing to clinician burnout.”
Currently, they point out, 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.”
The key to being able to take advantage of these and other capabilities is that they need to be tightly integrated with EHRs to be effective. “Most current AI options are ‘encapsulated’ as stand-alone offerings and don’t provide as much value as integrated ones, and require time-pressed physicians to learn how to use new interfaces.”
That said, mainstream EHR vendors are beginning to add AI capabilities to make their systems easier to use and are “adding capabilities like natural language processing, machine learning for clinical decision support, integration with telehealth technologies and automated imaging analysis.”