TriNetX
TriNetX is a Research Cohort Exploration and Data Analytics Tool. The TriNetX platform helps investigators at healthcare organizations and life sciences companies with:
Protocol Design and Feasibility
- Determine if a sufficient population matches a protocol
- Investigate attributes and comorbidities of a cohort
- Analyze inclusion/exclusion criteria and the impact of changes
Ability to match site investigators to industry sponsored trials
- Sponsors are able to locate study sites based upon the availability of eligible patients matching a protocol
- Predict the arrival rate of newly eligible patients
- Engage the right contact within the clinical trials office at study sites
Generation of Real-World Evidence
- Explore and compare cohorts
- Compare outcomes of interest
- Characterize drug efficacy and burden of illness
Collaboration with Peers
- Participate in multi-site research across organizations
- Pursue grant-based research funding
- Strengthen relationships between healthcare organizations and sponsors
The main source of TriNetX data comes from healthcare organizations (HCOs) around the globe. Ranging from specialty clinics to large academic medical centers, HCOs start with providing data typically found in a structured format (e.g. Diagnoses, Procedures, Medications, Labs, and Vitals) from their electronic health records system (EHR). From there, HCOs can opt into sharing additional data not typically found in their EHR, such as cancer registry, genomics data, and data found in notes (extracted via natural language processing).
Availability of data can vary by institution or region. For example, nearly all of USA HCOs provide four or five of the main data types (Diagnoses, Procedures, Medications, Labs, and Vitals), but Procedures and Medications might not be as readily available to ingest from ex-USA HCOs.
See this link for more details (requires a TriNetX login).
How does TriNetX map the data?
As part of onboarding an HCO, their data is mapped to a set of standard terminologies. Demographics data (e.g., race and ethnicity) are mapped to HL7 administrative standards. Diagnoses are represented by ICD-9-CM and ICD-10-CM. Procedures are represented by ICD-9-CM, ICD-10-PCS and CPT. Medications are mapped to RxNorm ingredients. Laboratory test results and vital signs are mapped to LOINC. Molecular genomics data conforms to HGNC for gene naming and HGVS for variant descriptions.
The TriNetX Master Terminology also includes lab roll-ups and derived facts. For example, to ease finding and using common labs, LOINC codes are rolled up to clinically significant level for most frequent labs. One case you’ll see this is the lab TNX:LAB:9029 Sodium [Moles/volume] in Serum, Plasma or Blood corresponds to 2947-0 Sodium [Moles/volume] in Blood and 2951-2 Sodium [Moles/volume] in Serum or Plasma.
Examples of derived and calculated facts include:
- The Oncology Treatments hierarchy identifies patients who have received radiation, chemotherapy, targeted therapy, hormone therapy, and stem cell transplants.
- Chemotherapy Lines of Treatment identifies patients who received anywhere from 1 to 5 lines of chemotherapy.
- Glomerular Filtration Rate (GFR) is based on serum creatinine and other information according to MDRD, CKD-EPI, and Schwartz formulas.
https://support.trinetx.com/hc/en-us/articles/360004240994-How-does-TriNetX-process-the-data-from-HCOs-https://support.trinetx.com/hc/en-us/articles/360004241034-Which-coding-systems-does-TriNetX-use-to-present-data-
At Penn, the TriNetX data is mapped to the OMOP common data model. The data in TriNetX are medication, diagnosis, labs, demographics and vitals. The Penn Medicine TriNetX network is Penn data only and can only be accessed by Penn researchers. It is a limited data set as the dates are not shifted. All other networks include Penn + other health care centers data and are considered deidentified via expert determination.
TriNetX / Penn Med Available Networks
|
Network |
Description |
|
COVID-19 Research Network 114.3M+ lives |
The COVID-19 Research Network empowers healthcare researchers to analyze cohorts of patients infected or likely infected with the Novel Coronavirus (SARS-CoV-2).
This Network is a spin-off of the Research network, also including ex-us HCOs to create a more global representation of the COVID-19 landscape.
The privacy policies of this Network are identical to those of the TriNetX Research Network. That is, neither patient counts nor any other data on the network are attributed to any Healthcare Organization. Neither Trial Connect nor data downloads are available on this network.
|
|
Diamond Network 213M+ lives
|
A network of third-party claims data.
Note, data available to August 2020 only.
|
|
Global Collaborative Network 133M+ lives
|
The Global Collaborative Network gathers the data from all participating Healthcare Organizations (HCOs).
HCOs who are already members of the Research Network, which supports data downloads, are added to the regional collaborative network as well as to the Global Collaborative Network.
Note, data download is not permissible on the Global Collaborative Network.
|
|
HCO Collaborative Network (contingent on HCOs count)
|
Two or more HCOs may, upon mutual agreement, contribute their de-identified data to a shared network in a way that attributes HCO source to the patients that make up a cohort.
In this case, the HCOs agree to mutual transparency. These HCOs may even agree to allow for downloaded datasets. TriNetX will not associate patient_ids in a dataset to their HCO source.
A group of HCOs may wish to form a specialty collaborative network based on shared research interests (e.g. oncology) and/or similar patient populations (e.g. pediatrics).
If you are interested in setting up a collaborative Network, please contact Laura Fluharty lauraee@upenn.edu
|
|
Linked Network 13M+ lives |
The Linked Network includes data sets with claims data. Claims and mortality data are “tokenized” and then linked.
Both HCO data and claims data are longitudinal in nature and include relative time between events associated with patient- level encounters.
|
|
Penn Medicine 4.6M+ lives |
A Network of Penn Medicine data (only) |
|
Research Network 116M+ lives |
A subset of the Global Network (83 healthcare organizations) optimized for clinical research and the downloading of datasets.
|
|
Regional Collaborative Network APAC – 3.8M+ lives EMEA – 15.8M+ lives LATAM – 28.6M+ lives US – 104M+ lives |
TriNetX supports five collaborative networks specifically for HCOs to anonymously contribute their de- identified data. In doing so, each HCO gains research access to a broader patient population, making research into rarer diseases and treatment regimens much more feasible. This network is only available to our Healthcare Partners ONLY.
HCOs participating in our regional collaborative networks contribute their de-identified patient data to two networks:
TriNetX users from participating HCOs may:
HCOs on regional collaborative networks are anonymous. The platform will not display the number of patients contributed by a particular HCO (either by name or pseudonym) to any cohort. Note: Dataset downloads are not permitted on regional collaborative networks. However, our Research Network does support data downloads while maintaining HCO anonymity. |
TriNetX access is provided on an as-needed basis and is currently only available to Penn Medicine (UPHS or PSOM) employees (faculty or staff) with a PMACS AD account. Individuals who would like to access TriNetX must complete the requisite training, which includes the following:
- Complete human research/biomedical researcher training through CITI and HIPAA training through Workday
- Complete TriNetX “Read and Acknowledge” training through Workday
TriNetX accounts may be requested through an IS Self Service Ticket. Please complete the TriNetX Access Form and submit that with the ticket to PenDnA.
Documentation of completed TriNetX “Read and Acknowledge” training must be attached to this request. After the ticket is submitted, it is assigned to the Research Analytics team for compliance review. Once review is completed and approved, a new TriNetX account is created, linked to the user’s PMACS AD account, and login information is sent to the requestor.
In order to access TriNetX the only required trainings are:
- Complete human research/biomedical researcher training through CITI and HIPAA training through Workday
- Complete TriNetX “Read and Acknowledge” training through Workday
Additionally Training though TriNetX are highly recommended.
- TriNetX 101: Network(s) Overview, Query Building and Patient Counts
- TriNetX 102: Basic Analytics for Clinical Trial Optimization Insights
- TriNetX 242: Best Practices in Querying COVID-19
- TriNetX 401 – Part 1: Advanced Analytics – Analyze Outcomes, Compare Outcomes, and Compare Cohorts
- TriNetX 401 – Part 2: Advanced Analytics – Treatment Pathways and Incidence and Prevalence
You can also watch on-demand training in the TriNetX Platform Help Center.
Visit the TriNetX Help Center for the most up to date tools, trainings and resources. You can also ask experts about your cohort or query builder design and get real time feedback.
The TriNetX user platform has many helpful resources including:
- On demand training and webinars
- Recorded training content
- FAQs
- Additional Resources
- Community Connection to other TriNetX user
If you are having trouble accessing the Help Center remember to use your PMACS username and password and you must have an active TriNetX account.
For Penn specific guidance you may access the Penn Med TriNetX Guidance Tip Sheet
CONTACT
For more information about TriNetX contact the Office of Clinical Research.