Predictive modeling for user condition prediction

A pressure-injury prediction system, comprising:

• a memory configured to store computer-executable instructions;
• and
• a processor configured to access the memory and execute the computer-executable instructions to at least:
• receive user data associated with a user record of a user of a service unit, the user record being one of a plurality of user records maintained by a service management system of a service organization, the service unit being one of a plurality of service units affiliated with the service organization;
• train a first prediction model using first training data representing first user samples drawn from the service organization;
• train a second prediction model using second training data representing second user samples drawn from the service unit;
• define a trained prediction model using the first prediction model and the second prediction model;
• input the user data into the trained prediction model, the user data comprising a plurality of data points that respectively correspond to one of a plurality of categories, the plurality of data points weighted relative to each other by the trained prediction model;
• determine a risk assessment corresponding to a level of risk that the user has or will develop a pressure injury;
• and
• provide the risk assessment to a user device of a user service agent for use in determining whether the user should receive a wound consult for the pressure injury.

One or more non-transitory computer-readable storage devices comprising computer-executable instructions that, when executed by one or more computer systems, cause the one or more computer systems to perform operations, comprising:

• receiving user data associated with a user record of a user of a service unit, the user record being one of a plurality of user records maintained by a service management system of a service organization, the service unit being one of a plurality of service units affiliated with the service organization;
• training a first prediction model using first training data representing first user samples drawn from the service organization;
• training a second prediction model using second training data representing second user samples drawn from the service unit;
• defining a trained prediction model using the first prediction model and the second prediction model;
• inputting the user data into the trained prediction model, the user data comprising a plurality of data points that respectively correspond to one of a plurality of categories, the plurality of data points weighted relative to each other by the trained prediction model;
• determining a risk assessment corresponding to a level of risk that the user has or will develop a pressure injury;
• and
• providing the risk assessment to a user device of a user service agent for use in determining whether the user should receive a consultwound consult for the pressure injury.