Synthetic Controls for Survival Data Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In medical trials, especially for terminally ill patients, all eligible patients may prefer to receive the new treatment, making it challenging to form a control group for data collection, and existing methods require a large number of patients and computational resources.
Innovation Solution
A computerized method is developed to create synthetic controls in survival analysis by forming a target group and a control group from patient data, applying weights to common features of control group patients to match a particular patient in the target group, and creating synthetic patients that mimic the target patients, thereby reducing the need for actual control groups and minimizing computational processing time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If a control group of patients who have not been given the treatment is formed, then data on the effects of the treatment can be collected, but the number of patients required increases and computational resources are consumed
Solution Approach 1:
The patent creates synthetic control patients by copying and combining features from actual control group patients. Instead of requiring real patients to serve as controls, the system generates artificial patient records that replicate the statistical characteristics of actual control patients, thereby reducing the number of real patients needed while preserving the ability to collect treatment effect data
Solution Approach 2:
The patent merges features from multiple actual control group patients into synthetic control patients. By combining and aggregating data from multiple real patients, the system creates fewer synthetic patients that still represent the control population, reducing the total number of patients required while maintaining statistical validity
2Loss of information
If a control group of patients who have not been given the treatment is formed, then data on the effects of the treatment can be collected, but computational processing time increases
Solution Approach 1:
The patent creates synthetic control patients by copying and combining features from actual control group patients. Instead of requiring real patients to serve as controls, the system generates artificial patient records that replicate the statistical characteristics of actual control patients, thereby reducing the number of real patients needed while preserving the ability to collect treatment effect data
Solution Approach 2:
The patent performs preliminary processing of control group patient data to create synthetic controls before the main analysis. By pre-computing and storing synthetic control patients with their features and weights, the system avoids repeated computational processing during subsequent treatment effect analysis, thereby reducing overall computational time
Data Source
AI summary
A computerized system and method for creating synthetic controls in survival analysis is provided. A target group of patients who are administered a drug and a control group of patients who are not administered the drug are created from real data of patients. A weight is applied to a common feature of each patient in the control group of patients so that a linear combination of the common feature of the patients in the control group of patients becomes similar to a particular patient in the target group of patients. A synthetic patient is created for each patient in the control group of patients. Because the common feature of the synthetic patient is similar to the particular patient in the target group, an efficacy of the drug may be determined by comparing the target group of patients with the synthetic patient.