Where AI innovation has taken one EHR vendor in 2023
Healthcare IT news sat down with Paul Brient, chief product officer of athenahealth, to understand how artificial intelligence can improve patient and healthcare experiences, simplify healthcare interactions and make healthcare more accessible, and to hear how the electronic health record provider is using AI today.
He said new AI-driven features in athenaOne are already helping to improve healthcare efficiency and address physician burnout by reducing administrative tasks, such as the proactive identification of missing prior authorization information, reducing the number of tasks completed is reduced by 18% among EHR users.
Looking ahead to 2024 and beyond, Brient said AI-generated reports will be available to help providers prepare for healthcare meetings with providers, while generative AI has the potential to soon reach patients far beyond the clinical setting.
Predictive analytics is an area that could guide patient care by suggesting additional services and treatment modalities that similar patients have used.
It has been shown to identify patient non-adherence and help reduce mortality in hospitalized patients, but it is often difficult to get doctors on board with data-driven medicine. Some say predictive analytics in EHRs is not yet effective enough to support clinical decisions at the point of care, and that physicians should be the sole decision makers.
Because rapidly advancing AI technologies have enormous potential to improve healthcare and its outcomes, how to ensure their safe use in clinical care could be the issue of the year for 2023, if not the decade.
“It is important to note that while AI has the potential to improve healthcare delivery, it should always be used in conjunction with clinical expertise and human judgment,” Brient said.
“AI algorithms must be transparent, explainable and continuously validated to ensure their accuracy, reliability and ethical use in healthcare.”
Q. How can AI be used to improve predictive analytics in clinical use?
A. There are several ways AI can help improve predictive analytics in a clinical environment.
Risk stratification and early detection: AI models can be trained to identify high-risk patients. By analyzing historical patient data, AI algorithms can identify patterns that indicate a patient is at high risk and could benefit from an immediate intervention such as care management, rather than waiting for the next scheduled visit.
Clinical decision support: AI-powered CDS can provide healthcare providers with real-time guidance by analyzing patient data and providing evidence-based recommendations. These systems can help code diagnoses, identify gaps in care, expedite orders, and alert physicians to potential drug interactions.
Resource optimization: AI can help healthcare organizations improve resource allocation by predicting patient demand and adjusting schedules and resource availability to better match demand and reduce unused appointment times. This can lead to improved operational efficiency, shorter wait times and improved access to care.
Q. How will AI improve patient experiences and outcomes as time goes on? Can it help make healthcare more accessible in the future?
A. AI can fundamentally change physicians' experience with an EHR by making it an intelligent partner for the physician. With AI, the EHR can “understand” the patient record, process/parse unstructured data, and present this information to physicians in the context of the visit, the patient's situation, and provider preference.
For example, if a healthcare provider visits a Medicare patient for an annual wellness visit, AI can review all of the patient's information and understand what preventive measures have been taken and what is missing so the doctor can order these services quickly and easily. and then spend the majority of the visit with the patient, making sure there are no other underlying issues that need to be addressed.
From a patient perspective, we will almost certainly see AI-enabled triage and chatbots that help patients better understand where best to go to seek care – similar to the “ask a nurse” triage lines.
Additionally, our long-term outlook envisions genAI, such as ChatGPT, bridging communication gaps to improve healthcare accessibility, simplify medical information, and further improve the patient-provider experience.
For example, there is enormous potential to use ChatGPT to communicate with patients outside the clinical setting and overcome communication barriers or even close gaps in care.
A major survey of Spanish speakers in the U.S. found that about 25 million people receive one-third less health care than other Americans. Additionally, the study found that Hispanics had 36% fewer outpatient visits compared to non-Hispanic adults. This clearly shows that technology is needed to break down language barriers.
ChatGPT or other AI-based language translation systems can serve as a tool for multilingual interaction and simultaneous translation, and can help deliver a message in a patient's first language, reducing language-based gaps in healthcare and increasing patient access until health care is improved. healthcare.
Q. Athenahealth has long used machine learning to improve its electronic health record offerings. How has EHR automation increased efficiency and reduced administrative burden for service providers over time?
A. Athenahealth has been using various forms of ML and AI to simplify the user experience for EHR and practice management systems for nearly a decade. Our use of ML is aimed at solving critical pain points for our customers, streamlining work and removing administrative burdens that hinder the focus on patient care.
For example, we have enabled automatic selection of insurance packages based on a photo or scan of a patient's insurance card. Using optical character recognition and advanced ML to instantly select an insurance plan and confirm patient eligibility, this feature eliminates the need to manually enter data, improving both accuracy and efficiency for front desk staff, while patient experience is improved.
This feature is already delivering a 31% reduction in insurance-related claims in practices using this capability, saving practice staff more than 6,500 hours of administrative time over the last 12 months.
To simplify patient record keeping, we use voice commands to allow healthcare providers to quickly and easily navigate and retrieve the athenaOne mobile app. For example, instead of typing in an order or prescription, the provider can simply say, “Order 20 mg of Lipitor once a day.” The app also predicts the most likely next action a provider will take in response to an item in the inbox and presents it as a one-click action at the top of the provider list.
To simplify document management, we use ML and natural language processing to classify and archive incoming patient documents across our network. This ensures that the patient's file is as complete and easily accessible as possible.
Q. How has automation evolved over the past year since ChatGPT came on the scene? What do athenahealth customers want and how has their feedback shaped the new offering?
A. We continuously process input from customers – and especially suppliers – to improve their experience and satisfaction. While athenahealth has been using traditional AI models to streamline administrative work for years, this year's Codefest (a homegrown coding event focused on designing, developing and testing new HIT features) aimed to ensure that our engineering teams are fully up-to-date on genAI and implementing four genAI-compatible features that are top priorities for our customers.
Two of these new features are available today for select athenahealth customers and are showing significant, quantifiable results. They are:
Proactive identification of missing prior authorization information: As many as 10% of prior authorization tasks are returned to providers due to missing clinical information, creating additional work and delays in obtaining authorization approvals. New capabilities embedded in athenaOne identify missing or incorrect information before the prior authorization is submitted and suggest the appropriate additions to maximize the likelihood of the authorization being approved, saving time and reducing costs for practices while improving the patient experience .
Concepts of Patient Case Responses: Providers on the network respond to approximately four million patient cases each month and spend more than 35% of clinical inbox time managing patient case documents. This capability allows providers to have pre-prepared responses available for consideration, review, and editing to increase productivity without replacing the provider's expert judgment.
In addition, we identified another forty potential features that could enable generative AI. We are actively evaluating these for deployment in future product releases to reduce the administrative burden providers and their staff face, while also providing new tools to help providers deliver high-quality care to their patients.
Q. How does athenahealth use genAI to help healthcare providers surface relevant clinical information at the point of care?
A. Providers today have access to an unprecedented amount of information about their patients from a variety of sources. Unfortunately, there are times when documents within these records are not labeled in an intuitive or useful way, requiring providers to open each document and hope it contains the information they are looking for.
One of athenahealth's newly implemented genAI features solves this problem by intelligently summarizing the contents of these documents so that healthcare providers can quickly and easily find the right one and, in many cases, gather the information they need without having to read the entire document. have to open and read.
Additionally, athenahealth care managers will soon receive AI-generated “Huddle Reports” to prepare for weekly care meetings with providers.
These reports help facilitate conversations between care managers and providers and are a crucial tool for maintaining an open flow of information to improve patient care. Automatically generating these reports streamlines conversations between care managers and physicians, helping physicians deliver more personalized care across the care continuum. The time savings allow care managers to provide individualized care to a larger number of patients.
Andrea Fox is editor-in-chief of Healthcare IT News.
Email: afox@himss.org
Healthcare IT News is a HIMSS Media publication.