Personalized Pharmacologic Dosing Using Fuzzy Response Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current dosing regimens for pharmacologic agents, such as erythropoietin, fail to account for individual subject variability, leading to suboptimal therapeutic responses and increased risk of adverse events.
Innovation Solution
A computer-based system and method for personalized dosing using a Multiple Model Predictive Control (MMPC) approach, which includes input devices, data storage, and processing units to determine personalized dose sets based on fuzzy set theory and response profiles, optimizing dosing through iterative optimization algorithms.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If standardized dosing regimens are used for pharmacologic agents, then ease of operation and standardized care are improved, but therapeutic response precision and adaptability to individual subjects deteriorate
Solution Approach 1:
The system transitions from static standardized dosing regimens to dynamic personalized dosing by continuously adjusting doses based on real-time patient response data. The dosing algorithm adapts to individual variability in pharmacologic response, allowing the system to maintain both ease of operation through automation and high precision through individualization.
Solution Approach 2:
The system changes the dosing parameter from fixed standardized values to variable personalized values. By modifying the dosing parameter based on individual patient characteristics and response patterns, the system achieves both standardized care protocols and precise therapeutic responses for each patient.
2Device complexity
If standardized dosing regimens are used, then device complexity is reduced, but reliability of therapeutic outcomes deteriorates
Solution Approach 1:
The system incorporates feedback mechanisms that monitor patient response to dosing and use this information to adjust future dosing decisions. This feedback loop increases reliability by continuously learning from individual patient responses while the automated nature of the system keeps complexity manageable through algorithmic decision-making.
Solution Approach 2:
The dosing system performs self-adjustment based on built-in algorithms that automatically modify dosing parameters according to patient response patterns. This self-service capability improves reliability without requiring complex manual intervention, as the system manages its own optimization.
3Ease of manufacture
If dosing regimens do not account for individual variability, then ease of manufacture and implementation are improved, but loss of information about patient-specific responses increases
Solution Approach 1:
The system creates a virtual model or copy of the patient's pharmacologic response characteristics through algorithmic profiling. This digital representation captures individual variability information that would otherwise be lost, allowing the system to maintain implementation simplicity while preserving crucial patient-specific data through computational modeling.
Data Source
AI summary
A system and method for personalized dosing of a pharmacologic agent include: executing, using a processing device, a plurality of dosing regimen program modules to determine a respective plurality of dose sets in response to receiving, from an input device, a target response value for a patient; and executing, using the processing device, a dosing selection algorithm module, following executing the plurality of dosing regimen program modules and in response to receiving from the input device a response profile and a monitoring frequency of the patient, to determine a recommended dose set computed as a combination of the plurality of dose sets weighted by degrees of matching computed using fuzzy sets and the response profile.