New York City-based Urban Health Plan has used artificial intelligence to improve operational efficiency and patient care, while addressing the high annual patient absentee rate with interventions cost-effective for patients.
The rate of missed appointments is higher than average
Absences are due to a variety of factors, including social determinants of health such as transportation.
But they are also a long-term challenge for healthcare organizations that can impact quality of care for patients, increase healthcare organization costs, and unnecessarily reduce accessibility. patient’s overall view of health care appointments.
In March, Urban Health Plan had 42,000 wellness visits — the highest in its history, according to a presentation at eClinicalWorks’ wellness summit in Boston last week.
“We took a multifaceted approach to just addressing overall patient access and interaction,” said Alison Connelly-Flores, director of medical information for Urban Health Plan. Healthcare IT News.
That achievement is significant because every year, UHP experiences a large number of missed appointments, and waiting patient appointments are sometimes “overbooked”. Connelly-Flores said providers are often overbooked to accommodate no-shows.
Federally qualified community health center organization, one of the largest in the state of New York, providing primary care, 18 specialties, diagnostics, and other services to approximately 86,000 patients. core. Absence rates are very high across 12 UHP locations in the South Bronx, Corona Queens and Central Harlem neighborhoods, 12 school health centers and behavioral health services.
Although UHP planned for 794,322 visits by 2022, only 57.6% were completed compared to the national average in eClinicalWorks EHR data – 71%.
With 336,600 no-shows and overbooking, outcomes can include long wait times, patient dissatisfaction and strain on providers, all of which can be exacerbated more burnout.
The organization needs to change things around to keep the medical centers open.
Management wants to know if their absenteeism rates are higher or lower than the national average and who are the patients who consistently miss their appointments.
Through the pilot, UHP learned that their absenteeism rate was 16.52% higher than its peers in the EHR industry.
It also learned that despite attrition across low, medium, and high probability groups, UHP impressions remained consistent for each group from 2019-2022 – even during a pandemic .
“It’s interesting that those groups behave the same. I didn’t expect it… it’s definitely a pattern.” Connelly-Flores said after the session.
Machine learning analysis of network-level data
The Absence Algorithm is a refinement analysis that allows for consistent and systematic sorting of data, allowing data analysts and users to view data at the network level.
Sameer Bhat, co-founder and vice president of sales at eClinicalWorks, said: “I can basically chat with this data prior to the discussion of UHP’s algorithm pilot testing, part of the research. save larger eClinicalWorks with more customers.
Bhat demonstrated how to consider demographics such as ethnicity and poverty levels on the healing panel, and noted that the platform cannot trust the EHR.
According to the company’s website, the platform can also aggregate discrete EHR data to identify gaps in care.
When introducing Connelly-Flores and the pilot team, he said, “we were surprised by some of the findings.”
They say the algorithm can find a needle in a haystack and can help identify patients with a high probability of absence with 85-90% accuracy.
Interventions for missed appointments are effective
In addition to working with the absence prediction model, the UHP team adapted their outreach using eClinicalMessenger.
UHP already manages more than one million annual voice messages, secure text messages and email reminders, according to eClinicalWorks’ announcement of the pilot.
After the model identified patients with the highest and moderate risk of missing appointments, UHP tested new focused interventions to help ensure that patients make the appointments they want. scheduled.
Would a phone call help? Connelly-Flores said with 3,000 appointments a day, UHP can’t call all of its patients that are scheduled.
eClinicalWorks holds 38,431 with a high probability of absence in the control group. The company shared 18,061 high-absence cases, as well as 908 average-absence cases with UHP for testing focused interventions.
UHP distributed high-risk absence reports to designated associates and provided a scenario for making calls and texting as consistent as possible. Designated associates recorded the call results.
Patients who missed appointments that day have the opportunity to switch to same-day virtual visits by initiating telemedicine or rescheduling appointments. UHP doctors will call patients who have missed appointments themselves.
Connelly-Flores says that if a patient is approached by a doctor, nearly 100% will accept the same-day virtual reschedule option. They use a video app to call those patients and only switch to telemedicine after the patient accepts.
An eClinicalWorks blog in March 2023 said: “If you receive a ‘last-minute’ cancellation or reschedule notice, you can still restore your appointment.”
“If the last-minute change is due to transportation or travel issues, perhaps a telemedicine visit would suffice. This can save appointments and even encourage more frequent visits. for its convenience.”
For scheduled telehealth visits with patients with a high or moderate probability of being late and not seen for 15 months or more, UHP sent additional text messages.
UHP also increased access to extended hours virtual care to 89 hours per week.
To better support providers, the healthcare organization modified their workload analysis templates to account for each provider’s absenteeism rate and added the same time slots. days to match the transition to virtual care.
While these adjustments may require monitoring, overall, UHP found that the strategies could reduce absenteeism even further.
The algorithm was implemented in January 2023 and this intervention resulted in an additional 4,432 hits during the 3-month testing period.
The low probability of absenteeism for 2023 is so far 5% higher than it was four years ago.
Results between the two groups of trial patients also showed a 24.14% increase in their ability to book an appointment for patients at high risk of absences and an 8.08% improvement for those at intermediate risk. jar.
While attendance rates for patients most likely to miss an appointment increased by 154%, UHP interventions also increased attendance by 19.17% for intermediate-risk absentees. jar.
UHP added a specific full-time role and tweaked an existing role to provide part-time support in order to call only those roles that the algorithm identifies as having the highest risk of absenteeism.
During the pilot period, the targeted phone calls were about 400 per day, Connelly-Flores said.
“It’s not a big elevator.”
She said UHP’s next steps include integrating the algorithm into its EHR, related to case management, addressing barriers to care, sending more customized appointment reminders to those who need care. patients are at high risk of missing appointments and dig deeper into the data to learn more.
Girish Navani, CEO and co-founder of eClinicalWorks, said: “By leveraging the power of data and machine learning, we can help service providers like Urban Health Plan deliver services. more effective care for their patients and reduce the burden of missed appointments.”
“This ultimately helps reduce healthcare costs and supports better patient outcomes.”
“When patients receive timely care, they see better health outcomes.” Connelly-Flores said.
Andrea Fox is the senior editor of Healthcare IT News.
Email: [email protected]
Healthcare IT News is a publication of HIMSS Media.
