Between the lack of trained doctors, nursing staff shortages, and general attrition of health care workers, securing an appointment with a doctor is no easy task in today’s clinical landscape. Indeed, the time value for dating has never been greater.
This piece is exactly what Microsoft’s latest artificial intelligence (AI) tool is trying to tackle: reducing missed appointments in healthcare. Merav Davidson, VP of Microsoft Industry AI, wrote on the Microsoft Industry blogs: “The annual cost of missed appointments in the healthcare industry is over $150 billion in the US alone. Missed appointments not only lead to poor patient health, but the patient’s financial impact does not significantly impact clinic operations and fixed cost calculations, resulting in overstaffing and unplanned downtime, leaving healthcare providers struggling with the daily functions”.
Davidson highlights an important phenomenon. Missed appointments are not only detrimental to the patient, but also to the entire clinical ecosystem. For example, if a patient does not show up for their assigned slot, that room will now remain unused for that time period. In most cases, it can’t just fill up with the next person in line, since it’s an appointment-based service, and the next person probably won’t arrive until the scheduled time. While a missed appointment or two may be negligible, when viewed in a holistic perspective, this unused time costs the system billions of dollars annually. Most importantly, perhaps, is the fact that a missed appointment is a missed opportunity for someone else who really needed to see a doctor but couldn’t make it. With current waiting lists for primary care physicians resulting in months of waiting nationwide, this is a very real problem.
Microsoft’s tool is integrated into the powerful Cloud for Healthcare platform and has an easy learning curve: “The model is easily deployable and can be trained in as little as two hours, leaving the healthcare provider ready to use the solution in just one day. This offering benefits both clinicians and patients. With a user-friendly and familiar interface, missed appointment prediction enables office staff and clinicians to predict patient no-shows without data science training or staffing.”
Davidson further explains that “Several types of input data have been found to be important in predicting missed appointments in healthcare. Demographics, historical patterns, social determinants, and appointment data such as type and time of day are examples of input that care teams can use to train the model.” The intricacies behind the software have been explained in detail by Microsoft, which also insists that “The model is not pre-trained and should be trained by the user of a healthcare provider.”
Notably, clinics and outpatient clinics aren’t the only places that could benefit from this tool. There may eventually be an important role for this software in almost all clinical settings, ranging from the emergency department to inpatient care settings.
Indeed, while this AI engine likely needs more work and testing before its full potential is realized, the concept holds great promise for using data and objective metrics to improve clinical outcomes.