Monitoring conversations on Facebook, Twitter, and patient forums to identify and assess adverse drug reactions (ADRs) is becoming very popular with pharma companies and healthcare organisations providing useful data for strategy development, competitive research and patient segmentation.
But what remains unclear is how social data analytics compares in terms of reliability to more established pharmacovigilance processes. Obviously, it would be a great advantage if data from the two could be regarded as equivalent as the combined dataset would offer greater potential for reducing and preventing adverse drug events.
To this end a recent report looking at the differences and similarities between ADRs stored in electronic health records (EHRs) and patient reports on social media does support a growing role for social data in pharmacovigilance. The study focused on two drugs, aspirin and Lipitor, that had a relatively high prevalence among the ADR reports in both the clinical and the social media databases analysed. The analysis revealed significant overlap between the clinical and social media databases and supported the clinical validity of data extracted from healthcare consumers’ online conversations.
The data from this study also provided key insights into how drugs perform outside a carefully crafted clinical environment: off-label usage, drug adherence and patient’s perception of a drug’s effects.
Whilst certain issues still persist e.g. establishing causality and determining the true frequency of ADRs the researchers felt that developments in natural language processing would soon help neutralise these variables.
So pharmaceutical companies and regulators need to prepare themselves for the day when social data analytics will be an established part of pharmacovigilance, hopefully resulting in better drugs and healthier lives.