Systems and methods for healthcare provider dashboards
Inventors
Nida, Dean • Brown-Hayes, Michael • Chung, James • Espinoza, Carolyn • Emerson, Michael • Larson, John • Tschirpke, Jennifer • Driver, Stephani • Yoo, Daniel Jaesup • Curry, Jenifer
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-12080398-B2
Publication Date
2024-09-03
Expiration Date
Abstract
Systems and methods for generating dashboards for healthcare providers are provided. In one embodiment, a method comprises receiving, from a user of a client device, a selection of a patient, determining an order of a plurality of display modules, each display module displaying information relating to the patient, generating a dashboard including the plurality of display modules displayed in the order, and transmitting the dashboard to the client device for display to the user. In this way, members may be identified for intervention in a timely manner, and the most relevant information for a healthcare provider may be prioritized for display to a healthcare provider.
Core Innovation
The disclosed systems and methods collect medical claims associated with a patient from one or more healthcare databases and generate a clinical prediction or patient care predictions using machine learning models. A user of a client device selects the patient, and the system determines an order of a plurality of display modules automatically based on the clinical prediction or on predicted actionability for each display module, including determining a positioning of the display modules relative to one another.
The plurality of display modules is included in a dashboard that is generated and transmitted to the client device for display to the user. In an actionability-driven variant, actionability for each display module is predicted using a second machine learning model based on patient data and a user profile of the user, and the plurality of display modules can include a display module comprising a visual timeline of one or more clinical predictions for the patient.
The approach further receives feedback from the client device regarding the order of the plurality of display modules and trains the machine learning model based on the feedback. In another variant, the order of the plurality of display modules is adjusted based on the first patient care prediction and the second patient care prediction, and feedback regarding the adjusted order is used to train the third machine learning model.
Claims Coverage
The partial content includes three independent claims. Across these claims, there are inventive features centered on generating machine-learning-based clinical or patient care predictions, predicting actionability per dashboard display module using a user profile, automatically determining and positioning an ordered set of display modules on a dashboard, transmitting the dashboard to a client device, receiving user feedback about module order, and training a machine learning model based on that feedback; one claim also includes adjusting the module order based on first and second patient care predictions.
Automatically ordering patient-related display modules based on a clinical prediction
Automatically determining an order of a plurality of display modules based on the clinical prediction, wherein each display module displays information relating to the patient and wherein determining the order includes determining a positioning of the plurality of display modules relative to one another.
Machine learning prediction and dashboard display with client feedback training loop
Generating a dashboard including the plurality of display modules displayed in the order determined, transmitting the dashboard to the client device for display, receiving feedback regarding the order of the plurality of display modules, and training the machine learning model based on the feedback.
Predicting display-module actionability using patient data and a user profile
Predicting with a second machine learning model an actionability for each display module of a plurality of display modules based on the patient data and a user profile of the user, wherein the plurality of display modules includes a display module comprising a visual timeline of the one or more clinical predictions for the patient.
Actionability-based automatic module ordering and training based on feedback
Determining an order of the plurality of display modules automatically based on the actionability for each display module of the plurality of display modules, generating a dashboard including the plurality of display modules displayed in the order determined, transmitting the dashboard to the client device, receiving feedback regarding the order, and training the first machine learning model based on the feedback.
Adjusting dashboard module order based on first and second patient care predictions
Adjusting the order of the plurality of display modules based on the first patient care prediction and the second patient care prediction.
Training a machine learning model based on feedback regarding an adjusted order
Receiving, from the client device, feedback regarding the adjusted order of the plurality of display modules and training the third machine learning model based on the feedback.
Across the independent claims, the core inventive coverage is the combination of machine-learning-based clinical or patient care predictions, actionability prediction for multiple dashboard display modules using patient data and a user profile, automatic ordering and positioning of the modules on a dashboard, and training of the machine learning model based on client feedback; one claim further adjusts module order based on first and second patient care predictions.
Stated Advantages
Documented Applications
No documented applications found
Interested in licensing this patent?