Indian pharma industry is now increasingly looking to bring Big Data Analytics into the pharmacovigilance space. This is to simplify the large volume of structured and unstructured information which is difficult to process by putting in place simple data base management.
 
Big Data also references artificial intelligence, infrastructure and services, as well as automated processing operations that facilitate collection, storage and analysis of data gathered and being produced in ever increasing quantities.
 
According to Dr. Krishna Bahadursingh, head, corporate and product strategy, RxLogix, Big Data in Pharmacovigilance is contextualised by 4Vs: volume, variety, velocity and veracity. Significant resources of time, money and personnel are required for the development, implementation, validation and maintenance for each information.
 
Spontaneous Reporting Systems (SRSs) are inalienable components of pharmacovigilance, but on its own can never offer a complete picture of patient safety information. This is because the number of reports received cannot be used as a basis for determining the incidence of a reaction as neither the total number of reactions occurring in the population nor the number of patients exposed to a health product is known, said Dr. Bahadursingh at the DIA multicity event while deliberating on Big Data in PV approaches, utilisation and challenges.
 
The data collected often has limited patient information including medical histories, concomitant treatments and pre-existing illness conditions. There is under-reporting of adverse reactions with both voluntary and mandatory surveillance systems. The reporting rates may vary widely for drugs. Numerical comparisons cannot be made between reactions associated with different health products on the basis of the data, he added.

The reported data does not represent all known safety information concerning the suspected health products and cannot be used in isolation to make decisions regarding an individual's treatment regimen. This is because the sources of information, including the prescribing information for the product, should be consulted.
 
Utilisation of Big Data in Pharmacovigilance will brings in the potential to complement traditional spontaneous reporting systems, by allowing an epidemiological approach to determine the incidence of adverse events in the population.
 
Enhanced ability to identify and investigate adverse drug reactions which occur over a longer time period, may not be identified. However, there is greater potential for the investigation of signals across different sub-populations.
 
But, there are challenges of big data for pharmacovigilance. These are stringent restrictions in data-sharing due to privacy, data protection and security laws. The absence of a technical infrastructure: like global platform capable of capturing large amounts of data from multiple sources and storing in a common data model does not currently exist. Further various coding and standardisation in currently existing datasets would not allow immediate and systematic use of available ‘raw’ Big Data. Being extremely resource intensive, it requires human, finance allocation for Big Data projects, said Dr. Bahadursingh.