The client has an effective treatment for asthma patients which would address patients with unmet needs and improve patient outcomes. It was critical to appropriately target the correct patients, specifically patients with uncontrolled asthma, using real-world data, in order to optimize patient outcomes. Despite the availability of granular data sources, they are fragmented and often limited by strict privacy rules.

To meet their needs, the client needed a precise predictive model that could bring together disparate data sources and target the right patients.

Challenge The client sought IQVIA’s expertise to accurately identify asthma patients with specific unmet needs.

The client wanted to use their improved understanding of the patient journey, and the factors that influence patients to switch treatment modalities, to improve healthcare outcomes.

In many global markets, there are prominent challenges around data privacy. There are often fragmented data sources and restrictive privacy rules and governance where, without advanced machine learning approaches, the right target patients are diluted in a broader cohort.

In this scenario, those challenges must be accounted for to allow IQVIA to adequately support the client and ensure that only asthma patients are targeted, rather than the entire respiratory market.

Solution IQVIA deployed its AIML platform, maximizing on multiple real-world data assets and sophisticated machine learning approaches, to accurately identify the right patients for this need. Patient profiling was based on sub-national concentration, patient demographics, and other clinical drivers.

IQVIA also identified key physicians treating patients from this population and factors around the therapy which led patients to switch. IQVIA monitored, via real-world data, the impact of the treatment’s adoption and found a notable reduction in uncontrolled disease status among asthma patients.

Results IQVIA’s solution allowed the client to improve precision around targeting uncontrolled asthma patients by 30%.

This improved targeting led to a significant improvement in outcomes for patients. An analysis of real-world data over six months showed a 17% reduction in uncontrolled disease status for asthma patients in the region compared to pre-launch figures.

The client was able to approach dissemination of their treatment with unprecedented granularity using specific therapeutic insights and improved patient profiling that could not have been achieved without machine learning.