Closed-Loop Medication Control With Automation Risk Thresholds
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing closed loop systems for insulin delivery lack the ability to assess and mitigate risks associated with automated therapy decisions, leading to potential adverse patient conditions and the need for constant clinician intervention.
Innovation Solution
A system that incorporates an automation risk monitor and a rule-based application to evaluate the risk of therapy automation, allowing clinicians to customize rules for determining whether automated therapy adjustments are safe or require user intervention based on predefined thresholds.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automated therapy decisions are implemented, then productivity is improved and clinician burden is reduced, but reliability deteriorates due to potential adverse patient conditions
Solution Approach 1:
The system continuously monitors patient conditions and feedback from therapy delivery, comparing actual outcomes against predicted results. This feedback loop enables the system to detect when automated decisions may lead to adverse conditions and adjust or alert clinicians accordingly, maintaining reliability while preserving automation benefits.
Solution Approach 2:
The system performs preliminary risk assessment before executing automated therapy decisions. By evaluating potential adverse conditions in advance and predicting possible outcomes, the system can prevent harmful actions from being executed, thus maintaining patient safety while enabling automation.
2Reliability
If clinician intervention is required for all therapy decisions, then reliability is maintained through human oversight, but productivity decreases and clinician burden increases
Solution Approach 1:
The system applies different levels of automation based on local risk characteristics. High-risk situations require clinician intervention, while low-risk situations can be automated. This localized approach to human oversight maintains reliability where needed while maximizing productivity where safe.
Solution Approach 2:
The system performs self-monitoring and self-adjustment for routine therapy decisions, automatically evaluating patient conditions and delivering appropriate therapy without clinician involvement. This self-service capability handles routine cases independently, freeing clinicians to focus on complex situations requiring human judgment.
3Speed
If automated therapy adjustments are made frequently, then responsiveness to patient conditions is improved, but the risk of adverse conditions increases without proper monitoring
Solution Approach 1:
The system performs preliminary risk assessment before each automated adjustment, predicting whether the proposed change could lead to adverse conditions. This advance evaluation prevents harmful frequent adjustments while maintaining rapid response to genuine patient needs through continuous monitoring and selective automation.
Data Source
AI summary
A system and method for monitoring and delivering medication to a patient includes a controller that has a control algorithm and a closed loop control that monitors the control algorithm. A sensor is in communication with the controller and monitors a medical condition. A rule base application in the controller receives data from the sensor and the closed loop control and compares the data to predetermined medical information to determine the risk of automation of therapy to the patient. The controller then provides a predetermined risk threshold where below the predetermined risk threshold automated closed loop medication therapy is provided. If the predetermined risk threshold is met or exceeded, automated therapy adjustments may not occur and user/clinician intervention is requested.