Learn how integrated structured and unstructured real-world data helped identify rare disease patients, quantify the addressable population, and strengthen commercial and payer strategies ahead of launch.
A global pharmaceutical company preparing for its first drug launch needed to quantify a rare disease patient population that was difficult to identify due to a lack of ICD-10 diagnosis codes for the condition; build its commercial, payer, and physician education and targeting strategies; identify key decision makers and HCPs to target for commercial affairs purposes; and create a robust health economics and outcomes research (HEOR) story to share with payers.
The primary challenge was the lack of a formal diagnosis code for the rare disease, making it nearly impossible to identify patients using conventional claims and structured EHR data. Without structured RWD that could reliably indicate disease presence, the company was unable to discern the patient population with high confidence.
Using NorstellaLinQ, Norstella developed a robust, unified dataset integrating U.S. open claims, closed claims, labs, and unstructured EHR clinical notes to provide comprehensive insights into the potential addressable rare disease population.
To address the lack of formal diagnostic coding, Norstella used:
With NorstellaLinQ, the client was able to pinpoint healthcare providers who frequently treated suspected and confirmed rare disease patients and allowing for a more strategic and differentiated approach to provider engagement and targeting. At the JP Morgan Healthcare Conference, the client publicly shared the quantified estimate of the rare disease population derived from Norstella’s analysis. No previous studies had been able to identify these patients with high confidence, and the client integrated these insights into their press release and investor discussions, demonstrating a strong data-driven market entry strategy.
With a well-defined patient population and resource utilization insights, the client is now leveraging Norstella’s data to develop robust payer strategies. The ability to track patients across closed claims played a pivotal role in negotiating reimbursement rates and demonstrating the economic value of its upcoming drug launch.
Get Started
Frequently asked questions
By combining claims, laboratory data, structured EHR records and unstructured clinical notes, integrated real-world data enables pharmaceutical companies to identify rare disease patients who cannot be found using structured data alone.
Clinical notes often contain diagnostic details that are not captured by ICD-10 codes or structured EHR fields. Applying machine learning and clinical review to unstructured EHR data helps identify true rare disease cases with greater accuracy.
Machine learning analyzes unstructured clinical notes to detect potential disease cases, while advanced modeling and manual clinical review improve accuracy by reducing false positives and validating patient identification.
Quantifying the addressable patient population and tracking longitudinal patient journeys gives manufacturers the evidence needed to improve provider targeting, support HEOR initiatives, strengthen payer value discussions and prepare for successful product launches.
Norstella identified hidden rare disease patients, quantified the addressable patient population with high confidence, enabled more strategic provider engagement, strengthened payer negotiations and provided data that supported investor communications and launch planning.
