Skip to main content

A Quick Look at I2E 5.4 and 5.4.1

It's been more than a few months since the last blog post about I2E - enough time for two versions to be released!

In this post, I will highlight one feature from each release, as well as one part of the product that improves with every release.

I2E 5.4.1 - Blank Smart Query Slots

Previously, Smart Queries required a search term in each field: you had to include a Phase (or multiple Phases). In I2E 5.4.1, it is now possible to design the smart query with a field that is allowed to be blank. For example, you may want to make it possible to leave the Phase field blank (that is, allow clinical trials with any Phase) but still search for an Indication (or multiple Indications).

This applies to Dates, Authors, Locations, etc. any Smart query item can have its field blank. A great example of this is the collection of Table queries in the Resources query tree: they now allow table headers to contain Any item.

The software screenshot shows that an out-of-the-box Table Extraction queries supports the new ability to allow a Smart query field to match Anything

Fig. 1 Out-of-the-box Table Extraction queries support the new ability to allow a Smart query field to match Anything

I2E 5.4.1 - Query Gold Standard Evaluation

I2E 5.4 introduced the new Query Gold Standard Evaluation feature. In use for several years at Query Development Hackathons at Linguamatics events, this is now available to all users of I2E to allow you to objectively measure the quality of your queries against a pre-determined gold standard dataset. Running the evaluation will score your run your query on your index, compare it against the gold standard and generate a measure of precision, recall and an F-score. Evaluation can be run in either training or test mode: training mode will also show you the query results classified as true positives, false positives and false negatives.

The screenshot software shows a results page generated by evaluating a Smoking Categorization I2E query against a gold standard dataset in training mode

Fig. 2 Results page generated by evaluating a Smoking Categorization I2E query against a gold standard dataset in training mode

I2E 5.4 and I2E 5.4.1 - Ontology Updates

Ontologies get improved with every release of I2E and these improvements automatically appear for I2E OnDemand customers and are made available on Linguamatics Community Site for Enterprise deployments. The ontologies will include the latest source data from their various sources.

For the various ontologies that Linguamatics create or enhance, we also make improvements to help the user to benefit from better ways of using these terminologies. An example of this can be nicely illustrated with a I2E 5.4.1 change and a I2E 5.4 change.

 "Signs and Symptoms" and "Diseases and Disorders", this is Diseases and Symptoms

Fig. 3 In I2E 5.4, the Linguamatics Diseases ontology was split into two major branches: "Signs and Symptoms" and "Diseases and Disorders"

 Pharmacy and Pharmacy Providers

Fig. 4 In I2E 5.4.1, the Linguamatics Organizations by Sector ontology included a new top-level branch: Pharmacy and Pharmacy Providers

If you would like to find out more about I2E 5.4.1, visit our web page or get in touch with the team.

Ready to get started?

Request a Demo

Questions? Ask our experts