2020 Bio-IT World Innovative Practices Award

Cambridge Healthtech Institute and Bio-IT World have awarded Roche a 2020 Innovative Practices Award in Focused Research for their use of the IQVIA Linguamatics Natural Language Processing (NLP) platform to glean patient insights from social media to improve clinical trial design.

Each year, Bio-IT World highlights outstanding examples of technology innovation in the life sciences. The Innovative Practices Awards are designed to recognize partnerships and projects pushing the industry forward, by sharing strategies that can be implemented across the industry to improve the quality, pace, and reach of the life sciences.

NLP over social media identifies clinical endpoints relevant to Parkinson’s disease patients

Bio-IT World judges selected Roche in the patient-focused research category for its work to discover if social media, particularly patient blogs and forums, can provide a good substrate to develop clinical endpoints relevant to Parkinson’s disease patients. Roche researchers established a series of NLP-based text mining queries to analyze patient discussions around Parkinson’s. The study identified symptoms confirmatory of the clinical trial endpoints, and also revealed new symptoms; a number of which have been added to the conceptual disease model used in the clinical trial.

NLP that speeds time to patient-focused insights at reduced costs

By performing an NLP-enabled social media text-mining analysis Roche enhanced its understanding of symptoms that impact Parkinson’s patients. These insights can be used to improve the design of future clinical trials, ensuring that new models encompass patient needs. By using NLP to analyze social media data, Roche researchers were able to rapidly collect and analyze patient-reported outcomes. Capturing this sort of information using primary market research and patient interviews is time-consuming, resource intensive and expensive.

For example, a primary market research exercise with patient reviews may cost in the region of $150,000 and take six months. In comparison, the Roche team estimated the NLP-enable approach required 11 days of effort at a total employee cost of approximately $10,000.  In addition, compared to standard approaches such as patient interviews, the number of data points collected and the insights gained demonstrated that social media mining is a highly effective approach to collect patient-reported outcomes. Indeed, the new capabilities defined in this project can be re-used effectively for future studies in other disease areas, which Roche is already doing.

Encompassing patient needs through patient-centered drug development

Roche’s approach is an example of patient-centered drug development (an FDA initiative) and ensures that clinical disease models encompass patient needs. The Linguamatics team congratulates Roche for winning this well-deserved award and for their innovative use of technology to advance research. This is the third consecutive year that Linguamatics or one of our partners has earned a Bio IT World award: In 2019, Novo Nordisk won an Innovative Practices Award for its workflow to integrate NLP to generate actionable insights from real world data; and, in 2018, the Linguamatics team were recognized with the prestigious Bio-IT World’s Best of Show Judges’ Prize.