Urban Health Plan, a community health center in New York State, has been using AI to identify patients at risk of missing appointments and implementing targeted interventions to reduce its no-show rates. The organization has been working with eClinicalWorks to develop an AI algorithm that can identify patients with a high probability of missing appointments. Since the algorithm was implemented in January 2023, the intervention has resulted in 4,432 more visits during the three-month pilot. The low no-show probability rate for 2023 so far is more than 5% higher than the previous four years.
Urban Health Plan, a federally qualified community health center organization in New York State, has been working to improve operational efficiency and patient care using artificial intelligence (AI). One of the organization’s biggest challenges has been reducing high no-show rates among its patients. While social determinants of health like transportation can be a factor in missed appointments, no-shows can lead to a reduction in patient access to healthcare appointments, lower care quality, and increased healthcare organization costs.
In March, Urban Health Plan recorded its highest number of health visits in history, with 42,000 visits, which was achieved through a multifaceted approach to addressing patient access and engagement. The organization typically experiences high numbers of missed appointments, leading to overbooking to accommodate no-shows. This can result in long wait times, patient dissatisfaction, and stress on providers, exacerbating burnout.
Urban Health Plan has been working with eClinicalWorks, a healthcare IT solutions provider, to develop an AI algorithm that can help identify patients with a high probability of missing their appointments. Through the pilot program, Urban Health Plan discovered that its no-show rate was 16.52% higher than its peers’ in electronic health record (EHR) data. The algorithm can identify patients with a high no-show probability with 85%–90% accuracy, allowing for targeted interventions to be made.
The organization has been using eClinicalMessenger to adjust its outreach process and target patients with a high probability of missing their appointments. Telemedicine visits are offered as an alternative for patients who have missed their appointments that day, and the organization has increased access to virtual care to 89 hours per week. To better support providers, workload analysis templates have been revised to factor in each provider’s no-show rate, and same-day slots have been added to accommodate a switch to virtual care.
The AI algorithm has been implemented since January 2023, and the intervention has resulted in 4,432 more visits during the three-month pilot. The low no-show probability rate for 2023 so far is more than 5% higher than the previous four years, with a 24.14% increase in the likelihood to make appointments for patients at high risk for no-shows and an 8.08% improvement for those with moderate risk.
Overall, the pilot program has shown that by leveraging data and machine learning, healthcare providers can improve patient care and reduce the burden of missed appointments. As AI technology continues to evolve, more healthcare organizations will likely turn to it as a tool for improving efficiency and reducing costs while delivering high-quality patient care.
