Jennifer A. Flynn’s scientific contributions

Patients' increasing digital participation provides an opportunity to pursue patient-centric research and drug development by understanding their needs. Social media has proven to be one of the most useful data sources when it comes to understanding a company's potential audience to drive more targeted impact. Navigating through an ocean of information is a tedious task where techniques such as artificial intelligence and text analytics have proven effective in identifying relevant posts for healthcare business questions. Here, we present an enterprise-ready, scalable solution demonstrating the feasibility and utility of social media-based patient experience data for use in research and development through capturing and assessing patient experiences and expectations on disease, treatment options, and unmet needs while creating a playbook for roll-out to other indications and therapeutic areas.

UNSTRUCTURED Patient-focused drug development (PFDD) aims to incorporate the patient perspective to improve the quality, relevance, safety, and efficiency of drug development and to inform drug evaluation. Gathering patient perspectives to support PFDD has become more feasible with the increased digital presence and participation of patient groups that communicate their treatment experiences, needs, preferences, and priorities through online forums. Social media listening (SML) is a method of gathering a substantial amount of feedback directly from patients themselves; however, the quantity of data produced can be challenging to distill into actionable insights. Artificial intelligence (AI)–enabled methods have been leveraged to process data from SML studies, such as natural language processing (NLP) approaches to produce qualitative data. Here, we describe a novel, trainable, AI-enabled, SML workflow to classify posts made by patients or caregivers that uses NLP methods to provide qualitative data regarding patient or caregiver experiences. We report an overview of the workflow and methodologic learnings from 2 studies in oncology. Our approach is an iterative process balanced between human expert–led milestones and AI-enabled processes to support data preprocessing (ie, relevancy screening), patient and caregiver classification, and NLP methods (tagging of relevant patient experience concepts) to produce qualitative data. We explored the applicability of this workflow in 2 case studies in oncology, one in patients with head and neck cancers and another in patients with esophageal cancer. We found that iterative refinement of AI-enabled algorithms was essential in enhancing the utility of the results, which was possible due to the seamlessly native end-to-end nature of the workflow. This approach and workflow contribute to the establishment of well-defined standards of SML studies and advance the methodologic quality and rigor from the perspective of researchers contributing to, conducting, and evaluating SML studies in a PFDD context.