Patient-Trial Matching
Table of Contents
The patient-trial matching is a process that identifies patients who are eligible to participate in a clinical trial. The matching process is based on the patient’s electronic healthcare records (EHRs) and the trial’s inclusion/exclusion criteria. To formulate it as a machine learning problem, we first need to define the input and output of the matching process.
A patient’s EHR can be represented by a sequence of visits , where each visit is a sequence of events . We can encode to a compact embedding as the patient’s representation. The trial’s inclusion/exclusion criteria can be represented by a sequence of inclusion/exclusion criteria . We can encode to a compact embedding the trial’s representation (each criterion is a vector). Such that, the neural matching process is just compute the similarity between and to get the criterion-level affinity.
Patient-Trial Matching: Index
Here is the list of colab examples on each model for this task.
Patient-Trial Matching: Example
Here, we highlight the usage of trial_patient_match.deepenroll
model for this task. Other models have the similar pipeline.