OBJECTIVES: Drug development can benefit from including patient and caregiver social media listening (SML) as part of patient-focused drug development (PFDD) strategy. This work introduces an Artificial Intelligence (AI)-enabled SML concept to identify and understand patient and caregiver experience to inform characterization of unmet medical need, target product profiles, value demonstration strategies, evidence generation strategies, definition of patient centered outcome (PCO) endpoints, and selection of PROs in trial design.

METHODS: This work proposes leveraging capabilities from outcomes research and text analytics experts to create inhouse scalable SML solutions for application across therapeutic areas. Natural language processing (NLP) techniques coupled with machine learning (ML) algorithms can be leveraged for data cleansing and categorization of records, while quantitative and qualitative analyses performed by research analysts are suggested for insight generation. These solutions have the potential to facilitate better understanding the experiences of patients and their caregivers and characterize their priorities, preferences, treatment experiences, and unmet needs. This methodology can reach a greater number of patients at relatively lower cost when compared to traditional research methods.

RESULTS: Important factors to consider when developing, implementing and using SML tools include data access and data privacy considerations, subject matter expertise of team, geographic and language inclusions, research questions in scope, and application of quantitative and qualitative research methods for insight generation. Additionally, the lack of well-established AI-enabled SML methodology standards is an important factor to consider when conducting such type of research, which highlights the importance of establishing clear operational definitions of patients and caregivers, as well as concepts of interest, and incorporating a combination of quantitative (accuracy metrics) and qualitative analyses (expert review).

CONCLUSIONS: Establishing well-defined SML study standards will advance the methodological quality and contribute to the credibility of such work from the perspective of those contributing to, conducting and evaluating SML studies in a PFDD context.