Personalized Dosing Algorithm for Pediatric Thyroid Treatment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods struggle to determine optimal individual dosing regimens for pediatric thyroid diseases, leading to suboptimal treatment outcomes and increased risk of adverse events.
Innovation Solution
A method combining pharmacokinetic/pharmacodynamic modeling, empirical Bayesian estimation, and optimal control algorithms to calculate personalized dosing regimens based on clinical and laboratory data, while accounting for clinical constraints.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If fixed dosing regimens are used for pediatric thyroid diseases, then treatment simplicity is maintained, but treatment efficacy and safety deteriorate due to individual variability in disease progression and drug response
Solution Approach 1:
The patent implements dynamic dosing regimens where dosage parameters (amount, frequency, timing) are continuously adjusted based on individual patient responses and disease progression. The system modifies dosing parameters in real-time using Bayesian estimation and optimal control algorithms, transforming fixed dosing into adaptive dosing to resolve the contradiction between treatment reliability and regimen complexity.
Solution Approach 2:
The patent establishes a closed-loop feedback system where patient responses (laboratory values, clinical status) are continuously monitored and fed back to the dosing optimization algorithm. This feedback mechanism enables the system to learn from individual patient data and adjust future dosing recommendations, improving treatment efficacy while managing complexity through automated decision support.
2Measurement precision
If frequent laboratory controls and dose adjustments are implemented, then detection of over- and underdosing is improved, but treatment burden and loss of time increase
Solution Approach 1:
The patent performs preliminary dosing optimization calculations before actual administration, using predictive modeling to anticipate the optimal dosing regimen. By pre-calculating dosing recommendations based on available data and disease progression models, the system reduces the need for frequent reactive adjustments and minimizes treatment burden while maintaining precise detection of dosing adequacy.
Solution Approach 2:
The system enables self-adjustment of dosing regimens through automated algorithmic recommendations that clinicians can implement without extensive manual intervention. The Bayesian estimation and optimal control frameworks allow the system to self-optimize dosing parameters based on incoming data, reducing the time and effort required for manual dose adjustments while maintaining high measurement precision.
3Adaptability or versatility
If standardized dosing guidelines are followed, then ease of operation is maintained, but adaptability to individual patient needs deteriorates
Solution Approach 1:
The patent introduces an automated dosing optimization system as an intermediary between standardized guidelines and individual patient needs. This intermediary layer processes patient-specific data through Bayesian and optimal control algorithms, translating general dosing principles into personalized recommendations while preserving clinical workflow simplicity. The system acts as a bridge that maintains ease of operation through automated calculations while achieving high adaptability to individual patients.
4Speed
If higher starting doses of levothyroxine are administered, then speed of achieving target T4 levels is improved, but risk of over dosing and adverse events increases
Solution Approach 1:
The patent implements dynamic dosing regimens where the starting dose and subsequent adjustments are continuously optimized based on individual patient pharmacokinetics and disease severity. Rather than using fixed high starting doses, the system adapts dosing intensity in real-time, enabling rapid achievement of target T4 levels while dynamically controlling the risk of over dosing through continuous monitoring and algorithmic adjustment.
Solution Approach 2:
The patent applies partial action by using moderate initial doses combined with rapid iterative optimization rather than excessive initial dosing. The Bayesian estimation framework allows the system to start with conservative dosing and progressively increase to optimal levels based on patient response, achieving the benefit of rapid T4 normalization while avoiding the harms of excessive initial dosing and adverse events.
Data Source
Figure 1A(A)~1A(G)
Figure 1B
Figure 2~3(d)
AI summary
The present invention relates to a method for automatically determining an optimal individual dosing regimen of at least one drug for a patient suffering from a known disease, the optimal individual dosing regimen being optionally subject to at least one clinical constraint, wherein the method comprises the steps of: providing a mathematical model adapted to model a progression of said disease and an effect of the at least one drug on the progression of the disease, the model comprising individual model parameters associated with the patient; utilizing an empirical Bayesian estimation to automatically and numerically estimate the individual model parameters of the mathematical model utilizing patient data associated with the patient; automatically calculating an optimal individual dosing regimen for the mathematical model by solving an optimal control problem based on a desired progression of the disease, the estimated individual model parameters, and an initial guess for the dosing regimen; and adjusting the optimal individual dosing regimen to optionally account for at least one clinical constraint to yield the optimal individual dosing regimen subject to said at least one clinical constraint.