Graph Convolutional Neural Network for Personalized Care Paths
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for generating personalized patient care paths are inefficient, costly, and fail to account for real-time patient data, resulting in generic care paths that deviate from actual patient experiences, leading to mistrust and suboptimal health outcomes.
Innovation Solution
A system utilizing a graph convolutional neural network-based model and patient-bucket-procedure graph to integrate demographic and medical data from various sources, generating personalized care paths by contextualizing Current Procedural Terminology (CPT) codes and predicting optimal care paths in real-time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual compilation by clinicians is used, then care path accuracy is improved, but time consumption and cost increase
Solution Approach 1:
The patent replaces the manual mechanical process of clinician compilation with an automated machine learning system. The graph convolutional neural network automatically processes patient data, retrieves relevant information from healthcare databases, and generates care paths without human intervention, thereby eliminating time consumption while maintaining accuracy through data-driven algorithms.
Solution Approach 2:
The system enables self-service by allowing the machine learning model to autonomously generate care paths based on patient data. The automated system independently performs data processing, pattern recognition, and care path formulation without requiring clinician involvement, making the process self-sufficient and time-efficient.
2Measurement precision
If manual compilation by clinicians is used, then care path accuracy is improved, but cost increases
Solution Approach 1:
The patent replaces the expensive manual process of clinician compilation with a cost-effective machine learning system. The automated graph convolutional neural network processes patient data and generates care paths using computational resources rather than human expertise, significantly reducing operational costs while maintaining or improving accuracy through algorithmic pattern recognition.
Solution Approach 2:
The system achieves cost reduction through self-service automation where the machine learning model independently generates care paths without requiring paid clinician involvement. The autonomous system eliminates labor costs associated with manual compilation while maintaining accuracy through data-driven automated processing.
3Stability of the object's composition
If generic care paths are provided, then standardization is improved, but patient engagement decreases
Solution Approach 1:
The patent applies local quality by customizing care paths to individual patient characteristics, needs, and preferences rather than providing uniform generic paths. The graph convolutional neural network analyzes specific patient data and generates personalized care paths that resonate with individual patients, thereby improving engagement while maintaining standardization through structured care path frameworks.
Solution Approach 2:
The system introduces dynamics by making care paths adaptive and personalized rather than static and generic. The machine learning model continuously processes patient data and generates dynamic care paths that evolve based on individual patient responses and changing conditions, thereby improving engagement while maintaining structural standardization through the care path framework.
4Device complexity
If conventional methods are used, then simplicity is maintained, but adaptability to real-time data changes is reduced
Solution Approach 1:
The patent replaces simple conventional methods with an automated machine learning system that naturally handles real-time data adaptability. The graph convolutional neural network continuously processes updated patient data and generates current care paths, automatically adapting to real-time changes without requiring complex manual updates or interventions, thus achieving adaptability while maintaining operational simplicity.
Solution Approach 2:
The system achieves self-service adaptability where the machine learning model autonomously processes real-time patient data and automatically generates updated care paths. The autonomous system continuously adapts to changing patient conditions and data without requiring manual intervention, achieving real-time adaptability while maintaining simplicity through automated self-processing.
Data Source
AI summary
Systems and methods are disclosed for generating a personalized care path for a patient. The method includes receiving, by one or more processors, relevant data associated with the patient from a plurality of data sources. The relevant data includes demographic data and medical data associated with the patient. The one or more processors using a graph convolutional neural network-based model determine the personalized care path for the patient based on the relevant data associated with the patient. The graph convolutional neural network-based model is trained based on a plurality of care paths of a plurality of patients represented by a patient-bucket-procedure (PBP) graph. The one or more processors provide data associated with the determined personalized care path for the patient to a device associated with a user.