An American Biopharmaceutical Company Improved Their Patient Engagement Strategy Through Patient Risk Scoring

Industry

Pharma

Region

AMER

Solution

Patient Risk Scoring

The tools provided the Marketing and Patient Outreach team with variables and triggers to improve the patient engagement strategy

A research-based biopharmaceutical company in the US wanted to identify patients who are at-risk of falling off their Patient Services Program (PSP) that is offered for their blockbuster drug. The PSP offers financial assistance, a dedicated nurse representative and therapy assistance through email, apps, phone, and the website. The company wanted to design a risk-scoring algorithm that could enable them to evaluate the standard of care for patients enrolled in the program.  

Data Processing

  • Obtained interaction level data of patients considering ten unique interactions from two databases
  • Filtered data from the year since nurse representations were introduced
  • Applied business rules and curated an interaction universe of all the interactions done by patients from between a specific period.

 

Feature Engineering  

  • Created aggregated metrics including average days between interactions, tenure etc. and brought the data to patient level
  • Quantified patient behavior on the platform and formulated a churn definition
  • The analytical dataset consisted of demographic, therapy, and aggregated interaction level variables at patient level.
  • Shortlisted variables using Correlation and Variance Inflation Factor (VIF) along with business sense

 

Model Development

  • Designed and developed a risk scoring algorithm using various techniques to identify characteristics of patients at-risk of disengagement
  • A classification model was built using patients’ demographic, therapy and interaction data, to predict a risk score with 67% precision.
  • Established drivers of churn and drivers of engagement using the built model

 

Profiling and recommendations

  • Patients were segmented into risk profiles (Low Risk, Medium Risk, High Risk and Very High Risk) based on their probability to drop off the PSP
  • Curated Insights and recommendations for mitigation of churn
  • Built a diagnosis tool to provide both an overview and a detailed view of the risk profiles and the enrolled patients 

 

Want to know more about us and how we can help you take your business to new heights? Reach out to info@themathcompany.com  

Related resources

Subscribe to Authentic Intelligence – our monthly newsletter

Stay up to date with the latest marketing, sales, and service tips and news.

X
Subscribe

Subscribe to our newsletter to receive latest updates