A hybrid analytic approach for understanding patient demand for mental health services

The increase in digital/data resources available in the healthcare sector has heightened the emphasis of applying analytics to extract information to provide solutions to problems. However, the process of providing analytic-based healthcare solutions may introduce factors that require multiple analytic techniques or a hybrid approach. Data resources can involve complexities including formatting and volume issues or multiplicity of sub-tasks in achieving a full problem solution. This work extends the previous research on AI in forecasting patient demand and adds clustering methods to identify the types of ailments that need to be treated according to diagnostic codes. The hybrid approach is applied to data from a US-based psychiatry/behavioral health center and the results indicate clustering can add value to demand forecasts established by AI by identifying the type of ailments that patients require treatment for. With this information, care providers can better optimize staffing resources to meet demand in a cost-effective and efficient way by better understanding not only the amount of patient demand, but also the type of treatment that is required for select ailments.