Dr. James Barr, vice president of physician value programs at Atlantic Health System and chief medical officer of Optimus Healthcare Partners, an accountable care organization within that health system, is emphatic when it comes to artificial intelligence and how it’s being deployed: “Your reason for using AI tools can’t just be because we want to show that we’re ahead of the curve.”
THE PROBLEM
Barr says the challenge for accountable care organizations is to design and manage successful AI implementations that solve specific pain points and deliver exponential value to clinicians and the health status of the population.
“Our two top priorities were to decongest clinicians’ workflows and understand what’s unique to each patient,” he explained. “Our clinicians and care teams were challenged by ‘data noise’ and poorly organized insights that couldn’t be integrated into existing workflows. We also needed a way to integrate a critical source of insights: the patient.
“In addition to standard data aggregations from EHRs, payer claims, prescription files, laboratory sources, and other inputs, “We needed an AI system that would continuously ask for patient input and could feed AI algorithms with numerous date functions,” he continued.
“This must be done in a way that strengthens the doctor-patient relationship through tailored stories rather than standard, uninteresting communication.”
Optimus Healthcare Partners wanted AI systems that would amaze patients, understand them better, improve their adherence to care plans, and inspire healthy lifestyle choices. These challenges highlighted the need for AI within Atlantic Health System’s accountable care organizations.
Since its founding in 2012, Optimus Healthcare Partners ACO, part of Atlantic Alliance, the clinically integrated network, has invested in practice transformations, evidence-based protocols, care management structures, and measurement/incentive processes that deliver “better care” to patients.
“While the effort has yielded consistent gains, it has come at the expense of ACO activity and physician burden, and we still have untapped potential for patient outcomes,” Barr noted. “It is cumbersome and inefficient to ask clinicians to dig through EHR tabs or cross-reference card reminders to identify gaps.
“Without a complete picture of healthcare service utilization, EHR-level clinical data, and patient-generated data features, it is difficult to generate the right screening cues, care insights, or patient-specific interventions,” he added.
At the same time, payers were asking for connections to practice EHRs for the same purpose. Optimus realized it could improve the care its physicians were delivering by using a data platform to connect its diverse set of EHRs and surface insights directly within the clinical workflow. It had to bridge this gap.
PROPOSAL
The AI technologies evaluated by Atlantic Health System ACOs focused on improving efficiency within clinical quality and coding workflows, supporting robust clinical decision-making, and improving patient access and experience.
By integrating generative AI tools, Optimus Healthcare Partners ACO wanted to automate routine tasks, reduce administrative burden and enable care providers to focus more on patient care.
“The technology platforms can aggregate patient data from disparate sources longitudinally,” Barr explains. “Then apply AI algorithms to prioritize and deliver critical insights within care visits or interactions. Additionally, generative AI can enable back-and-forth conversations with physicians and patients via AI chatbots, providing real-time access for physician decision-making and patient self-management.”
“To ensure responsible and ethical use, we planned to implement strict guidelines and continuous validation processes, with a focus on maintaining accuracy, privacy, and data security,” he continued. “The proposal emphasized training and mentoring team members to effectively navigate AI tools.”
Because AI implementation was challenging, the strategy included identifying existing pain points for clinicians and patients, assessing their adaptability, and establishing transparent quality assurance processes to build trust.
TOOK UP THE CHALLENGE
The Optimus ACO uses four AI system suppliers to to address the challenges of public health. Optimus invested in vendor Innovaccer to connect the disparate EHRs of independent affiliated physicians, enabling critical data aggregation that improves the quality of care and delivers AI healthcare insights, Barr explained.
“The platform takes this EHR data and organizes and curates it with claims, pharmacy, lab and other data sources to identify gaps in care,” he said. “When the EHR patient record is opened by a clinician, the InNote system prompts the clinician to review and close any open quality gaps and evaluate assigned HCC coding capabilities.
“If there are any questions, with one click, the clinician can open Patient360 to see a summary of recent or upcoming visits, labs, tests and/or procedures ordered by the specialist, and social determinants of health indicators. This reduces the burden of follow-up tests and saves them time,” he continues.
“Initial impact analysis shows a 10% improvement in closing the quality gap, a key measure of ACO network performance, and a 16% improvement in coding and documentation accuracy.”
At Optimus Healthcare Partners ACO, saving time is the greatest satisfaction for physicians.
“Previously, clinicians had to search the EHR to cross-reference specialist notes and confirm that patients were up to date on preventive and chronic disease screening goals,” Barr explains. “Now, with Innovaccer’s AI, notes are automatically scanned for updates at the point of care, allowing clinicians to focus on their patients, and this can save up to 30 minutes per day.”
“To drive adoption, Optimus trains clinicians one-on-one and uses performance incentives to reward practices for building new workflow habits,” he added. “Peer-to-peer training, supplemented with webinars and on-site coaching as needed, also supports this effort. Finally, the vendor’s population health analytics system helps generate provider scorecards and payer reports, allowing clinicians to monitor their performance.”
In addition to Innovaccer, Atlantic Health System member ACOs are using AI algorithms to support adherence to evidence-based care, and generative AI to produce tailored patient stories, improve patient access, and enhance the patient experience through 24/7 access to a secure AI chatbot.
“Behavioral health, pharmacoanalytics for medication management, and prescriptive analytics tools are other AI systems out there,” Barr noted. “We’ve had tremendous feedback from clinicians, practices, and patients. When AI is used correctly, it provides one of the strongest vehicles we’ve seen for positive change.”
RESULTS
All interventions and innovations within the ACOs include an impact analysis. Optimus Healthcare Partners ACO has standard KPI metrics such as quality improvements, patient experience surveys, clinical and care team experience surveys, ED utilization/hospitalizations/readmissions and cost of care.
Additional metrics such as adoption, engagement, and unique clinical outcomes are added, specific to the use cases where the AI tool is deployed.
Using Innovaccer’s platform and population health management systems, Optimus achieved a 10 percent improvement in closing the quality gap, a key performance metric for ACO networks that will generate $1 million in potential incentive payments, and a 16 percent improvement in documentation accuracy, Barr reported.
“Using a secure AI chatbot platform has buffered over 90% of patient messages to physician offices,” he said. “This significantly reduces their daily burden. Initial quality outcomes and adherence to recommended screenings have also been improved through AI chatbot outreach, education and reminders to patients.
“We look forward to additional KPIs as the results are evaluated,” he continued. “The excitement from physicians, care teams, and patients is already evident. A perfect example is a patient’s conversation with his doctor where he says he recommends everyone switch doctors unless their doctor has similar AI tools.”
ADVICE FOR OTHERS
For healthcare organizations considering implementing AI technology, it’s critical to start with a clear understanding of the specific problems they need to solve and ensure AI systems are aligned with those challenges, Barr advises.
“Engage all stakeholders, including clinicians, care teams and patients, early in the process to identify pain points and assess their readiness for new technologies,” he said. “Transparent communication and education are essential to building trust and ensuring broad adoption across the organization.
“In addition to these steps, healthcare institutions must be proactive in setting up and implementing “Enforcement of AI governance and guidelines,” he continued. “While there will be government oversight, we in healthcare must demonstrate that we fully understand the complexities of AI and responsibly regulate its use within our frameworks.”
Continuous validation and monitoring must be an integral part of the implementation process to maintain high standards and respond to emerging challenges, he added.
“Finally, establish clear success criteria, such as improvements in workflow efficiency, patient satisfaction, and cost-effectiveness. Evaluate these criteria regularly to ensure the AI technology is delivering the desired results,” he concluded.
Follow Bill’s HIT reporting on LinkedIn: Bill Siwicki
Send him an email: bsiwicki@himss.org
Healthcare IT News is a publication of HIMSS Media.