# How do we extract and link relationships from scientific research?

<figure><img src="https://1319432449-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F-M1zWgwfNb8Lu2WVCnfw%2Fuploads%2FSe4FpmDoYQ6FHbL1OfUz%2FScreen%20Shot%202023-05-03%20at%201.50.47%20PM.png?alt=media&#x26;token=bc498f9b-3271-4f17-9c7d-79086f227fc5" alt=""><figcaption></figcaption></figure>

We extract relationships from scientific research by using large language models (LLMs) to scan studies and pull out each of the components reported (i.e., variables, and the following as available: mechanism type, statistic type, statistic value, confidence interval, and p-value). For every extraction, traceability to the original source is preserved by storing all data at the highest resolution, true-to-source, along with links to the underlying sources, which are provided to users.

Once extracted, we link findings together by mapping each of the variables in a relationship to a higher-level concept or topic grounded in external ontologies such as MESH, ICD-10, SNOMED CT, and DSM-5, LNC, and Wikidata. For example, a variable named “daily aspirin usage” would be assigned to the topic of “Aspirin” \[MESH ID: [D001241](https://meshb.nlm.nih.gov/record/ui?ui=D001241), Wikidata ID: [Q18216](https://www.wikidata.org/wiki/Q18216)], and thus discoverable by searching for that associated topic. The result is an up-to-date and interoperable graph of evidence-based findings.  &#x20;