ML-Guided Clinical Trial Parameter Search from Simulation Outcomes

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Clinical trials face inefficiencies due to the lack of straightforward analytical methods for calculating operating characteristics, leading to high computational demands, extensive simulations, and slow optimization processes, especially in complex trials with multiple variables, which are costly and less responsive to real-time data adjustments.

Innovation Solution

A method and system using machine learning trained on simulation outcomes to efficiently map the multidimensional parameter space of clinical trial design, reducing the need for extensive simulations by up to 25 times while maintaining accuracy, by integrating advanced computational techniques to predict operating characteristics.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If extensive simulations are conducted to calculate operating characteristics of complex clinical trials, then accuracy of results is improved, but computational time and cost increase significantly

Engineering Contradiction:

Improveaccuracy of operating characteristicsVSAvoidcomputational time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent applies preliminary action by pre-calculating and storing operating characteristics for various trial configurations in a lookup table before actual trial design optimization is needed. This allows the system to quickly retrieve pre-computed results rather than performing extensive simulations in real-time, thereby reducing computational time while maintaining accuracy.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent uses copying by creating a simplified surrogate model (lookup table) that replicates the complex simulation results. Instead of running full simulations repeatedly, the system copies the essential relationships between trial parameters and operating characteristics into a pre-computed database, enabling fast queries without re-running expensive simulations.

Inventive Principle:

Principle #26Copying

2Reliability

If the number of simulations is increased to meet statistical requirements for complex trials, then reliability of results is improved, but computational resources and cost increase

Engineering Contradiction:

Improvestatistical reliabilityVSAvoidcomputational resources

Core Design Contradiction:

ReliabilityVSUse of energy by moving object

Solution Approach 1:

The system performs preliminary simulations to build a comprehensive lookup table that captures the statistical relationships across the parameter space. Once this table is constructed, subsequent trial designs can be optimized by querying pre-computed results rather than running new simulations, significantly reducing computational resource requirements while maintaining statistical reliability.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent creates a surrogate representation (lookup table) that copies the essential statistical information from extensive simulations. This copied structure allows the system to reliably estimate operating characteristics for new trial configurations without reproducing the full computational burden of the original simulations.

Inventive Principle:

Principle #26Copying

3Adaptability or versatility

If manual optimization methods are used for complex trials with multiple degrees of freedom, then flexibility in adjustment is maintained, but optimization efficiency deteriorates

Engineering Contradiction:

Improveflexibility in trial design adjustmentVSAvoidoptimization efficiency

Core Design Contradiction:

Adaptability or versatilityVSProductivity

Solution Approach 1:

The patent introduces an intermediary optimization engine that acts as a mediator between the trial designer's requirements and the complex parameter space. This engine uses the pre-computed lookup table to automatically identify optimal configurations based on specified criteria, maintaining flexibility in adjusting trial design parameters while dramatically improving optimization efficiency through automated search and selection algorithms.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS20250384972A1Method and system for identifying optimal clinical trial design parameters using machine learning trained on simulation outcomes

Publication Date: 2025.12.18 PHASEV TRIALS LTD

AI summary

Disclosed are method and system for identifying optimal clinical trial design parameters, the method including a first plurality of simulations for selected working points; training a machine learning model on the plurality of simulations and their respective simulated outcomes to obtain an ML model configured to output predicted simulation outcomes for non-simulated working points within the space of working points; and reiterating the process until an optimal set of working points and their associated parameters are obtained.