Phoebe Physician Group Achieves Big ROI Using AI to Deal with No-Shows
Phoebe Physician Group of Albany, Georgia, a subsidiary of Phoebe Putney Health System, serves a largely rural, 41-county service area. Health care providers say missing doctor’s appointments is increasingly acceptable in the eyes of patients.
THE PROBLEM
As such, the physician group’s overall no-show rate was 12 percent — more than double the Medical Group Management Association’s reported national average of about 5 percent. In urban markets, for example, providers can pay for taxi receipts; in southern Georgia, that’s not an option. Automated reminders and calls didn’t help.
Phoebe Physician’s size, its extensive clinic markets, and the challenges of staffing in rural areas only exacerbated the problem. Frequent turnover and minimal staff experience led to inconsistent scheduling, double bookings, and variable appointment confirmation practices.
“You think your staff is sending these reminders, but often they’re not, or not effectively,” said Matthew Robertson, Chief Administrative Officer at Phoebe Physician Group. “So we decided to explore how artificial intelligence technology could facilitate higher patient volumes while minimizing disruptions to providers and improving the patient experience.”
PROPOSAL
It started with a conversation with Berkeley Research Group. Phoebe Physician staff told BRG about the problem and that reminders and calls weren’t working. And that the organization needed to remove the human element to free up staff time and ensure their work actually got done.
“BRG proposed an AI tool, Tool Development and Piloting MelodyMD, that they had developed in collaboration with Trajum ML,” Robertson explained. “The tool uses machine learning to analyze years of patient visit data and predict the likelihood that a given patient will miss their appointment.
“When new patients are scheduled, MelodyMD communicates with Phoebe Physician’s scheduling system to analyze patient no-shows and automatically create a back-to-back appointment time if the likelihood of no-shows exceeds set thresholds,” he added.
TOOK UP THE CHALLENGE
The tool’s developers examined data points to identify those with the strongest correlation to a patient’s likelihood of no-showing. These included patient demographics, provider specialty, appointment scheduling turnaround time, prior appointment history, and insurance. As new patient visit data was added, the developers continued to refine the model.
“A key element that we worked out over time was ensuring that double bookings were limited every day,” Robertson noted. “That is, ensuring that only patients with a high probability of no-show were eligible for double bookings. Exclusions were then applied to specific clinics and appointment types.
“As the model was rolled out and tested, we made adjustments to the reminder process to improve communication with patients and ensure our team had sufficient time to fill available appointments,” he continued.
The AI tool, he added, also enabled the organization to measure performance and make improvements at the following levels:
Patient access. Provides regular monitoring of utilization, missed appointments, completed visits, cancellations, cancellations within 24 hours, and rescheduled visits.
Referral management. Enables regular monitoring of referral volume, patient churn and retention rates, and the number of splitters and competitors.
Scorecard for providers. Provides regular monitoring of work relative value units, visit types, evaluation and management coding, average number of visits per session, median days to book appointments for new and existing patients, no-show rates, and payer mix by provider.
Advanced practice physician/provider productivity. Provides regular review of work-related value units, visit type, evaluation and management coding, and details of current procedural terminology per provider.
Personnel not provided by the supplier. Ensures regular monitoring of full-time equivalent, productivity and overtime to ensure there are sufficient staff to meet demand.
RESULTS
From January 2023 to February 2024, Phoebe Physician saw an average increase of 168 encounters per week. This equates to approximately 7,800 additional encounter numbers and $1.4 million in new net patient revenue.
While people are still not showing up and the perception in rural areas that doctor appointments are necessary is still a barrier, the element of double booking has helped to significantly reduce the impact of such events, Robertson said.
ADVICE FOR OTHERS
“It’s absolutely important to talk to your providers early in the process and be transparent about what’s happening,” Robertson advised. “You want to clearly articulate the problem, the goals, and the potential impact that you expect the AI technology to have. When we talked to our 20 primary care providers and told them they were seeing 84 people a day not showing up, they were shocked. It helped them try a new solution.
“You also want to make sure that you’re taking health equity into account,” he continued. “For example, how do you make sure that the AI tool doesn’t introduce implicit scheduling biases? How do we refine the algorithm to make sure that underinsured and uninsured patients or patients with certain types of insurance aren’t being disproportionately impacted by having their appointment time always double-booked and potentially resulting in longer wait times in the office?”
And of course, AI is only as good as the underlying data, he added.
“We worked with BRG to clean and organize three years of patient data, which we were then able to use to build an effective model,” 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.