Enabling your commercialization team via rep triggers is of paramount importance – studies show the largest chunk of spend for brand teams goes to field sales, so it stands to reason that any data-driven endeavors should create immediate, consistently-updating value there.
Swoop’s data science solutions do just that, identifying HCPs with patients likely to be in your Ideal Patient Population and providing rep triggers on a biweekly basis. When Swoop builds a model of your Ideal Patient Population, it comes with a robust NPI list of HPCs with the highest potential value, and the near-real-time nature of our data ensures you receive these updates regularly. This also ensures the shortest possible time between a newly-diagnosed patient and the appropriate treatment – improving health outcomes and reducing healthcare expense by finding, engaging and converting your Ideal Patient Population’s associated healthcare providers.
Don’t miss out on finding the right HCP because your NPI list is out of date. Rely on Swoop’s trigger lists to keep your commercialization team informed of the newest HCPs with patients likely to be in your Ideal Patient Population as they are identified. Precision medicine demands precision timing, and Swoop’s trigger lists enable that.
Swoop Finds Ideal Patient Candidates For Life-Changing Gene Therapy
A large biotech company, having developed a first-in-class gene therapy for restoring vision, turned to Swoop to find patients with a specific gene genotype within a more common phenotype and their associated HCPs. The primary challenge revolved around there being no direct code-based way to identify the patients with the genetic mutation of interest.
In order to find the Ideal Patient Population and their associated HCPs, Swoop:
- Imported the client’s deidentified patient-level lab data and matched it to our data universe to build a claims profile of the Ideal Patient
- Used AI/ML tools to distinguish Ideal Patients from negative controls based on the patients’ healthcare claims footprint
- Generated a focused list of target providers based on a total patient volume that was consistent with epidemiology estimates of the rare condition
The resulting predictive model is able to concentrate the likelihood of finding the right patients within a predicted population to over ten percent (up from infinitesimally small). The client’s confidence in the results is driving their KOL mapping effort and they now receive biweekly triggers to direct rep activity based on real-world evidence.