CAR T-Cell Manufacturing With Machine-Learning Response Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The manufacturing process for cell therapies, particularly genetically engineered T-cells like CAR T-cells, is highly variable and resource-intensive, often resulting in poor cell quality and variable patient responses.
Innovation Solution
Applying machine learning techniques to manufacturing process data and clinical measurements to predict patient response and optimize process parameters, using visualization tools to simulate the impact of parameter changes on cell quality and quantity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If machine learning models are applied to predict clinical responses, then manufacturing precision and reliability are improved, but device complexity increases
Solution Approach 1:
The patent introduces machine learning models as intermediary components that mediate between manufacturing process parameters and clinical outcomes. These models process complex relationships between numerous process parameters (temperature, pressure, flow rates, cell concentrations) and predict clinical responses, enabling precise predictions without requiring direct complex measurements of all process variables.
Solution Approach 2:
The patent replaces traditional mechanical/experimental approaches with computational models. Instead of relying solely on physical experimentation and statistical analysis of manufacturing processes, the system uses AI/ML algorithms to simulate and predict clinical outcomes based on process parameters, reducing the need for extensive physical testing and complex manual analysis.
2Productivity
If extensive manufacturing resources are deployed, then productivity increases, but loss of substance increases due to failed manufacturing runs
Solution Approach 1:
The patent applies machine learning models to predict clinical responses before actual manufacturing runs occur. By analyzing process parameters and predicting outcomes in advance, the system identifies potential failures before they happen, allowing corrective actions to be taken or problematic runs to be avoided, thereby preventing cell loss and reducing the need for repeat manufacturing.
Solution Approach 2:
The system implements feedback loops where actual manufacturing outcomes and clinical responses are fed back into the machine learning models. This continuous feedback enables the models to learn from real-world data, improve their predictions, and optimize manufacturing parameters to reduce failures and cell loss over time, balancing productivity with resource efficiency.
Data Source
AI summary
Disclosed are systems and methods for improving processes for developing cell therapies by applying machine learning to data including manufacturing process data and clinical measurements (e.g., patient response and treatment data) to determine parameters and settings for a manufacturing process for engineering cells for use in cell therapy. Parameters and settings for a manufacturing process for genetically engineered T-cells including, but not limited to, Chimeric Antigen Receptor (CAR) T cells can be determined. A method can include receiving a set of process parameters of a cell engineering process, predicting a clinical response associated with an output of the cell engineering process by applying a machine learning model on the received set of process parameters, where the machine learning model is trained on process parameter data and clinical response data, and generating a visualization for use in a graphical user interface of the predicted clinical response.