Synthetic Data for Testing

We used the open-source Synthea software to generate synthetic data for testing. We modified three core disease modules from Synthea's library (Lung Cancer, Breast Cancer, and Colorectal Cancer) to meet our testing use case. We also connected them with an updated version of the disease module for COVID-19 to incorporate the experience of the pandemic into these oncology modules.

In the table below we show how the Laboratory Test Types included in this IG were incorporated into the Synthea disease modules. The table also provides a link to an example FHIR Observation resource for each test type that we included in the pilot.

Laboratory Test Types Included in Synthetic Disease Modules

Laboratory Test Type ValueSets Synthetic Disease Module Synthetic Disease Submodule Comments Example FHIR Observation
5-hydroxyindoleacetate (5HIAA) Lung Cancer (+ COVID-19) 5-HIAA testing is indicated in Carcinoid Tumors (e.g. GI tract, lung). The base Lung Cancer module from Synthea was modified to include a pathway for neuroendocrine neoplasms and 5-HIAA testing. Example
Alpha-1-Fetoprotein AFP testing is indicated in certain liver, testicular, and ovarian cancers, for which Synthea does not have modules.
Beta-2-Microglobulin Colorectal Cancer (+ COVID-19) Example
Cancer Ag 125 CA-125 testing is indicated in ovarian cancers, for which Synthea does not have a module.
Cancer Ag 15-3 Breast Cancer (+ COVID-19) Example
Cancer Ag 19-9 Colorectal Cancer (+ COVID-19) Example
Cancer Ag 27-29 Breast Cancer (+ COVID-19) Example
Carcinoembryonic Ag Colorectal Cancer (+ COVID-19) Example
Estrogen receptor Breast Cancer (+ COVID-19) Hormone Diagnosis (BC) Example
HER2 Breast Cancer (+ COVID-19); Colorectal Cancer (+ COVID-19) Hormone Diagnosis (BC) Example
Programmed cell death-ligand 1 (PD-L1) Breast Cancer (+ COVID-19) Hormone Diagnosis (BC) For triple negative patients only Example
Progesterone receptor Breast Cancer (+ COVID-19) Hormone Diagnosis (BC) Example
Prostate specific Ag COVID-19 Frequent Measurements (COVID-19) For males only Example
Complete Blood Count Colorectal Cancer (+ COVID-19), Lung Cancer (+ COVID-19) Example: RBC
Comprehensive Metabolic Panel Colorectal Cancer (+ COVID-19), Lung Cancer (+ COVID-19) Example: Glucose
Glomerular Filtration Rate COVID-19 Daily Measurements (COVID-19) Example
Gleason Score Component of a prostate biopsy report. Not implemented in the synthetic data set because Synthea does not have a module for it.
Mean Platelet Volume Colorectal Cancer (+ COVID-19) Part of the CBC Panel Example
Creatinine Clearance COVID-19 Daily Measurements (COVID-19) Part of Creatinine Clearance Panel Example
Prothrombin Time COVID-19 Frequent Measurements (COVID-19) Example
Lactate Dehydrogenase COVID-19 Frequent Measurements (COVID-19) Example
Magnesium COVID-19 Frequent Measurements (COVID-19) Example
Vitamin B12 COVID-19 Frequent Measurements (COVID-19) Example
O2 Saturation COVID-19 Daily Measurements (COVID-19) This is recorded as a "vital-sign", not a laboratory result Example
SARS-CoV-2 (COVID-19) COVID-19 Example