How does one get a win in this current era of skilled nursing? Trust machine learning technology to improve clinical interventions and outcomes.

Paris Girginis, VP of Innovation and Reimbursement for Mission Health Communities (MHC), pressed with responsibility to ensure proper and reimbursable clinical interventions to improve care, decided to explore how AI machine learning could assist him with his objectives. 

In order to improve data capture and ensure proper Patient Driven Payment Model (PDPM) reimbursement, Girginis knew that a human would not have the time nor the focus to locate subtleties within the documentation. Finding a solution would be hard; however, what Girginis didn’t know at the time was that there was a solution available to skilled nursing facility providers.

Machine learning is a field of study in artificial intelligence concerned with the development and study of statistical algorithms that can learn from data and generalize unseen data, and thus perform tasks without explicit instructions. 

In machine learning, scientists don’t give the machine instructions. Instead, the scientist gives the machine objectives and a lot of data. The machine, in turn, produces the outcomes. 

Solving the issue

In early 2023, Girginis and his clinical team embarked on a machine learning journey to assist clinicians with insight into better decision-making. Incorporating machine learning into the daily clinical cadence allowed MHC to strategically review all patient records for opportunities to provide clinical interventions, thus improving overall patient outcomes. 

“It comes down to trusting the data and noticing the subtle changes in condition in order to adequately intervene and provide clinical support,” Girginis advised. 

Through utilizing machine learning, providers such as MHC will be better equipped to provide clinical interventions. 

“The outcomes are real,” he said.

MHC has significantly improved its overall clinical intervention process and clinical decision-making. As a result, the patients are experiencing fewer unplanned transfers or less decline in condition. Moreover, by utilizing machine learning, MHC has experienced significant reimbursement outcomes. 

“We make sure that we are getting reimbursed for the services we provide,” Girginis said.

The future in PAC

Over the course of 30 years, two major shifts have occurred within post-acute care (PAC). First, PAC providers have shifted to employing primarily licensed practical nurses (LPN), followed by an overall increase in patient acuity. 

According to Mordy Eisenberg, Co-Founder & Chief Growth Officer of TapestryHealth, these two major shifts have presented a “perfect storm” for PAC providers. 

“In the near future, we will see more PAC providers embrace machine learning technology to confront nursing skill deficits, appropriate clinical interventions and care pathway management,” Eisenberg said.

Moving forward, PAC providers will find it increasingly difficult to successfully prioritize care for their patients without the help of machine learning and remote patient monitoring using passive monitoring devices. 

“As long as we have a technological overlay to prioritize patients, nurses will be better equipped to handle high acuity patients,” Eisenberg said.

The future of machine learning

The future of machine learning is bright for PAC providers. Data scientists and computer engineers are both looking into the PAC industry to solve highly complex problems such as clinical decline, fall management, wound care and rehospitalizations. 

“Machine learning and intelligent augmentation have an important role in post-acute care,” says Gill Bejerano, Professor of Computer Science at Stanford University. “One of the most important values of utilizing machine learning is for clinicians to adequately predict, prioritize, prevent and profit on their services rendered.” 

As PAC providers continue to be challenged with staffing, financial resources and time, machine learning will continue to play a larger role in post-acute care.

Mike Logan is a 23-year healthcare executive and is currently responsible for the Customer Success division at SAIVA AI, a machine learning healthcare start-up.

The opinions expressed in McKnight’s Long-Term Care News guest submissions are the author’s and are not necessarily those of McKnight’s Long-Term Care News or its editors.

Have a column idea? See our submission guidelines here.