Trial Patient Records Simulation 

Table of Contents

Trial Patient Records Simulation

Synthetic patient records generation is a way around privacy issues when sharing clinical trial records or healthcare data. Specifically, we want to train a generative model based on the real records, as $p(h^{syn}|h_1,h_2,\dots,h_n; \theta)$ , where $h^{syn}$ is the synthetic records, $h_1,h_2,\dots,h_n$ are the real records, and $\theta$ are the parameters of the model. When the patient data is a sequence, we can apply the generative model to the conditional generation. Given the previous visits $v_{1:t-1}$ , we can generate the next visit record $v_t$ as $v_t \sim p(v_t|v_{1:t-1}; \theta)$ .

Depending ono the input patient data format: tabular or sequence, we have the following two subtasks: trial_simulation.tabular and trial_simulation.sequence.

Trial Patient Records Simulation 

Tabular Patient: Index 

Sequential Patient: Index 

Tabular Patient: Example 

Sequential Patient: Example 

Trial Patient Records Simulation

Tabular Patient: Index

Sequential Patient: Index

Tabular Patient: Example

Sequential Patient: Example

Trial Patient Records Simulation 

Tabular Patient: Index 

Sequential Patient: Index 

Tabular Patient: Example 

Sequential Patient: Example 