
Much of the work of researchers builds on previous discoveries, possibly best expressed by Isaac Newton: "If I have seen further, it is by standing on the shoulders of giants". In fact, one definition of research is: "a systematic investigation of sources in order to establish facts and reach new conclusions". To some extent, then, text analytics is a key tool for research, to enable users to see further and to reach new conclusions, by gaining a comprehensive and systematic view of what has already been found.
Clinical research is surely an area where re-use of data is of great scientific value. Using existing data to see further can bring benefits in speeding up drug development, and thereby enhancing patient care. Linguamatics have many customers using I2E to extract existing information from past and on-going clinical trials.
One example of data re-use is shown by Eric Su, Principal Research Scientist at Eli Lilly and Company. Eric uses I2E to extract summary statistics on clinical endpoints for therapeutic areas such as oncology and diabetes, to feed into clinical trial design and competitive environment analysis.
Published clinical trial records can provide insights to help design new clinical trials, and enable metanalysis by combining data from many trials. Done manually, this is a resource-intensive, repetitive and error-prone task. Using I2E, Eric can extract data from unstructured text, both from Citeline’s TrialTrove database and also from structured tables contained within ClinicalTrial.gov records. Extracted data includes key oncology outcomes such as median overall survival, median progression-free survival, or metabolic indicators such as BMI, body weight change, etc.
The agile nature of I2E allows queries to be rapidly built, tested and modified to increase precision and recall. At Lilly, once the queries are performing well, they are deployed to non-expert end-users using I2E’s Smart Query feature. In this way, I2E removes the need for days of tedious manual work, and the results are then, of course, less prone to error.
These summary results data are also used within Lilly by health outcome researchers to answer questions from payers (and potentially from FDA).
Eric Su said, “I2E provides data that would take 10s or 100s times longer with tedious manual work. It enables downstream calculations to provide insight. Some work would not have been done or done comprehensively without I2E.”
So, this really is a case where text analytics can enable researchers to stand on others' shoulders, to build on earlier data and earlier discoveries. Linguamatics I2E can’t affect the results of a clinical trial, but it can make several aspects of the process, such as clinical trial analysis, and assisting with trial design, easier and, as a result, less expensive.
If you could like to learn more about fast-tracking clinical trials at Eli Lilly and Company, you can download the full case study here.
