Heart Disease Triage Microservices on a Scalable Care Platform
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing healthcare systems lack a comprehensive end-to-end platform capable of seamlessly integrating with diverse medical devices for patient monitoring, leading to clinical blind spots and gaps in care, particularly in managing chronic diseases like congenital heart disease, resulting in missed interventions, unnecessary readmissions, and preventable morbidity and mortality.
Innovation Solution
A Cardiovascular Care Platform (CVCP) that utilizes a scalable data container orchestration platform with machine learning algorithms to analyze patient-specific data, including echocardiogram records, to generate a triage score for patients, identifying those needing urgent care, and integrating with backend systems through APIs for real-time monitoring and alerting.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If a centralized healthcare management system is implemented, then data analysis and decision support capabilities are improved, but seamless integration with diverse medical devices is hindered
Solution Approach 1:
The system is divided into independent microservices that can be deployed separately and scaled independently. Each microservice handles specific healthcare functions (patient management, appointment scheduling, billing) allowing the system to integrate with diverse medical devices through standardized interfaces while maintaining specialized data analysis capabilities in dedicated services.
Solution Approach 2:
The container orchestration platform provides universal functionality by managing multiple diverse medical device integrations through a common infrastructure. The load balancer and service mesh enable a single platform to serve multiple functions including data collection from various devices, real-time monitoring, and centralized analysis without requiring separate systems for each device type.
2Productivity
If the number of computing devices is increased to handle more patient data, then data processing capacity is improved, but computational efficiency deteriorates due to resource underutilization
Solution Approach 1:
The system implements dynamic scaling where the number of computing devices and their resource allocation automatically adjusts based on real-time data traffic and processing demands. The load balancer continuously monitors system state and redistributes workloads to ensure optimal resource utilization, preventing both over-provisioning and under-provisioning of computational resources.
Solution Approach 2:
The container orchestration platform incorporates feedback mechanisms that monitor computational efficiency metrics and resource utilization in real-time. This feedback loop enables automatic adjustment of computing resources, scaling up when processing capacity is needed and scaling down when resources are underutilized, thereby maintaining high computational efficiency while handling variable patient data loads.
3Reliability
If real-time patient monitoring is implemented, then patient care quality is improved, but system complexity increases
Solution Approach 1:
The service mesh acts as an intermediary layer between the diverse medical devices and the centralized management system. It provides standardized communication protocols, automatic service discovery, and simplified data routing, thereby enabling real-time patient monitoring from multiple devices without increasing the complexity of individual system components.
Solution Approach 2:
The system uses containerization to create standardized, replicated instances of healthcare services that can be deployed across multiple computing devices. These container copies maintain consistent interfaces and behaviors, allowing real-time monitoring data from various sources to be processed uniformly without requiring complex custom integration logic for each device type.
4Adaptability or versatility
If microservices are deployed across multiple computing devices, then system scalability is improved, but deployment and management complexity worsens
Solution Approach 1:
The container orchestration platform implements self-service capabilities that automatically handle service deployment, configuration, and management across multiple computing devices. The system performs automated service registration, health checking, and load distribution without requiring manual intervention, thereby enabling scalable microservices deployment while simplifying management through automation of routine operational tasks.
Data Source
AI summary
A method and a system include at least one processor of a plurality of computing devices that execute a plurality of heart disease triage (HDT) microservices operating on a scalable data container orchestration platform. The platform is configured to continuously receive a plurality of patient-specific data files that include medical data and provider visit data for each patient. Patient-specific diagnostic text of the medical history, the provider visit, and echocardiogram data in the patient-specific data files of patients identified as having echocardiogram data are tokenized using a feature-space transformation to generate a patient-specific tokenized diagnostic feature set. The patient-specific tokenized diagnostic feature set for each identified patient is inputted to an HD severity determination machine learning model to generate a heart disease (HD) severity score. A triage scoring algorithm based on the HD severity score and provider visit data are used to generate a triage score for each identified patient.