With regulators, Health Technology Assessment (HTA) agencies and payers demanding greater evidence of value it is becoming increasingly difficult and costly for Pharma companies to not only get new products approved, but also to negotiate premium reimbursement or ensure continuing reimbursement for licensed brands. Today, within a fiercely-competitive market, success or failure of an existing brand can suddenly become critically-dependent upon demonstrating value-differentiation. Accordingly, a brand must exhibit previously-unidentified comparative superiority within an approved indication whereby it uniquely fulfils an unmet clinical need or provides a therapeutic benefit that cannot be matched by competing brands.

Whereas big data is perceived as the way forward in identifying new value that historically was not apparent within the constraints of randomized controlled trials (RCTs), in practice real world evidence is buried within what is rapidly-becoming an unmanageable and unfathomable sea of disparate observations. Although the enthusiasm and need for generating real-world evidence cannot be denied, unfortunately, the practical methods and skills for designing observational studies or interrogating large patient data registries are lagging behind. Moreover, with big data, from the outset investigators and analysts need some insights into which data subsets offer a high probability of yielding value-differentiation through either prospective or retrospective approaches. Failing this, then efforts become vague and costly, and have been aptly described as a futile attempt to find a white softball in snow.

When faced with uncertainty about where to search, achieving value-differentiation using big data can be facilitated by McCormack Pharma’s CEME which has as its starting point, experimental data. Historically, the CEME methodology evolved from the fundamental tenet of a quasi-chaotic relationship that exists between experimental data and real world clinical outcomes. That is, small differences between physical properties of drugs result in significant differences in clinical outcomes.

As a modified form of an association rule learning algorithm (association rule mining), CEME identifies previously-unknown relationships between the candidate drug’s experimental data and data that characterizes an approved indication for the drug. In turn, CEME matches (decodes) these previously-unknown relationships with the most probable clinical outcomes (correlates). In practical terms it is these clinical correlates of previously-unknown relationships that show with a high probability of success where value-differentiation (as real world evidence) resides within big data.

Restated, CEME directs access to real world evidence that is buried within big data. The presentation… CEME - fidelity and precision in gathering and sorting real world data… shows why McCormack Pharma’s CEME has evolved as an essential prelude for enabling fidelity and precision when seeking value-differentiation through the use of real world data.