Abstract: A System, Method, and Apparatus for Predicting Medical No-Shows and for Scheduling is provided. The system is based on a patient appointment schedule and indicators including office type, practice area, appointment type, engagement with the office leading up to appointment, and a variety of other characteristics of each patient and appointment. The indicators can be selected, weighted proportionately, and input into an algorithm for analysis and processing. The algorithm can then predict the likelihood of a no-show for the respective patient and appointment. The likelihood can then be used for scheduling to minimize the negative impact on the medical professional of the no-show. The algorithm can be used in conjunction with machine learning to improve its accuracy as it informs itself with experience and additional data points. The likelihood of a no-show can be incorporated into scheduling programs and made accessible on mobile devices, computers, and other monitoring devices.

Abstract: A System, Method, and Apparatus for Predicting Medical No-Shows and for Scheduling is provided. The system is based on a patient appointment schedule and indicators including office type, practice area, appointment type, engagement with the office leading up to appointment, and a variety of other characteristics of each patient and appointment. The indicators can be selected, weighted proportionately, and input into an algorithm for analysis and processing. The algorithm can then predict the likelihood of a no-show for the respective patient and appointment. The likelihood can then be used for scheduling to minimize the negative impact on the medical professional of the no-show. The algorithm can be used in conjunction with machine learning to improve its accuracy as it informs itself with experience and additional data points. The likelihood of a no-show can be incorporated into scheduling programs and made accessible on mobile devices, computers, and other monitoring devices.