How dental clinics are solving their cancellation epidemic
Students of dental medicine learn just about every facet of oral hygiene and dentistry at school but one thing they don’t prepare you for, is how many idle hours you’ll spend due to a plague of cancelled appointments.
As it turns out around 20% of dental appointments are cancelled last minute. In some clinics this number can be as high as 50% especially when no-shows are taken into consideration. Of these at least 75% remain unfilled which amounts to about $11.4bn annually in lost revenue for the industry.
When we examine the causes behind this patient behavior we can see that many patients cancel when they book appointments more than two to four weeks in advance -anything above four weeks has a much higher risk of getting cancelled.
This is logical, as most people’s schedules are primarily governed by their unpredictable boss, their children who forgot tell them about an upcoming PTA meeting or a deadline that crept up too soon at school and so on.
Another predictor for cancellations would be insurance type, which is strongly correlated with socio-economic status. Patients from lower income households with public insurance, are notorious no-shows. Penalties, and the introduction of a few tactical services such as Lighthouse 360 and Solution Reach aimed at reminding patients of their appointments, have managed to change this behavior to a degree. However, they have managed to reduce no-shows but not cancellations, as former would-be, no-shows now simply cancel a day or two in advance.
These changes in behavior, while providing a claim to success for these companies, remain mostly unhelpful to the industry, as these cancelled appointments still remain largely vacant.
A Boston based, health-tech startup is offering a rare, fresh take on this industry enigma. EarlierCare aims to reduce cancellations, to close to zero by applying a machine-learning algorithm to study the booking patterns and behavior of cancelled appointments. This data will allow dental clinics to see a heatmap of their most frequently cancelled slots and be given suggestions on how to modify the availability for these red areas in their schedule to reduce them as much as possible.
In addition to employing AI, EarlierCare aims to reduce cancellations by creating a platform, which would essentially ”re-sell” these newly opened slots through an app to a pool of existing patients as well as new ones.
Patients can then mark the times of day and week they would ideally like to visit their dentist, thus creating a personalized alert calendar, notifying them if a cancellation suddenly makes a slot available. This creates a win-win for both patients and clinics as patients now have access to more convenient appointments they are more certain they can keep. And clinics have their vacancies automatically filled up both from their existing database and from an outside pool of EarlierCare patients.
No matter how much machine-learning develops, uncertainty is here to stay. But by studying our behavior we can harness the power of habits which eventually shine through terabytes of seeming random data, helping solve decades-old issues.
Written by Daniel Brownwood
