EHR Agent Highlighting Relevant Patient Data to Cut Network Load
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional EHR agents struggle with efficiently displaying relevant patient health records due to large data volumes and irrelevance of certain records in treatment contexts, leading to inefficient network resource use.
Innovation Solution
A distributed EHR agent system with server-side and client-side functionalities uses a computer-implemented machine learning model to identify and highlight contextually relevant clinical data domains, optimizing the virtual patient object (VPO) for presentation to healthcare workers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If all health records are transmitted to client device for display, then complete patient information is provided, but network resources are inefficiently used
Solution Approach 1:
The server EHR agent extracts only the relevant portions of patient health records by executing the machine learning model to identify contextually relevant information, then transmits only these extracted portions to the client EHR agent, avoiding transmission of unnecessary complete records
Solution Approach 2:
The server EHR agent performs preliminary processing by executing the machine learning model before data transmission to determine which health record portions are relevant, allowing the client device to receive pre-filtered information rather than raw complete records
2Loss of information
If all health records are displayed to healthcare worker, then complete information is available, but relevant information is difficult to identify
Solution Approach 1:
The system applies different quality levels to different portions of health records by highlighting contextually relevant information with visual indicators (such as bold text or background colors) while presenting other information in standard format, enabling healthcare workers to quickly identify important details
Solution Approach 2:
The machine learning model analyzes the healthcare worker's interactions with the system and provides feedback to refine future recommendations, improving the accuracy of relevant information identification over time based on actual usage patterns
3Adaptability or versatility
If health records are gathered from many sources, then comprehensive patient data is obtained, but data volume becomes very large
Solution Approach 1:
The system segments patient health records into distinct domains (e.g., demographics, medical history, medications, lab results) and processes each domain separately through the machine learning model, enabling selective transmission of relevant segments rather than transmitting the entire large dataset
Data Source
AI summary
An improved electronic health records agent application (EHR agent) is disclosed herein. A server EHR agent receives an identifier for a healthcare worker and an identifier for a patient from a client computing device. The server EHR agent retrieves an audit table for the healthcare worker using the identifier for the healthcare worker and a virtual patient object (VPO) for the patient using the identifier for the patient. The audit table comprises a history of interactions of the healthcare worker with the EHR agent. The VPO comprises domains of clinical data for the patient aggregated from a plurality of sources. The server EHR agent provides the audit table and the VPO to a computer-implemented machine learning model, wherein the machine learning model identifies a subset of domains in the domains of clinical data that is likely to be used by the healthcare worker in treating the patient.