Mapping patient journeys in oncology and rare disease

With over 600 indication approvals by the FDA since 2000 in oncology and over 150 indication launches in rare diseases since 2011, specialty therapies are becoming increasingly crowded and competitive, forcing organizations to maximize opportunities within a very short window. To navigate this complex landscape, pharma companies must develop a deep understanding of patient journeys, which are key to a therapy’s commercial success from prelaunch to launch.

Patient journeys have a wide variety of applications, ranging from identifying points of intervention and forecasting to performance tracking, evidence studies and market mapping, among others. But individual data sources are incomplete, making creating and understanding the patient’s end-to-end journey difficult. And the evolution of our understanding for some disease areas means that the treatment journey changes even as therapies are developed.

The challenges faced by big pharma are different from emerging pharma in building patient journeys. With big pharma companies, often setting up the groundwork to scale is a major challenge. For emerging pharma, it’s navigating the more foundational elements, such as identifying the right data to use or having the team with the right skillsets.

Regardless of size though, organizations must focus on quickly harmonizing datasets, interconnecting them and building patient journeys and visualizations. In order to understand the patient journey, it is necessary for stakeholders to see the patient journeys to remove the barriers to their therapeutic areas. 

Gathering the right data is necessary to bring the patient journey into focus. In oncology and rare diseases, that means combining multiple data sources, like third-party claims, electronic health records (EHRs), specialty pharmacy, genomics and social drivers of health, to have a cohesive whole view of the patient. With this wealth of information though, it can be difficult for stakeholders to select the most effective data for their needs.

Organizations must have a clear vision, the technology infrastructure in place to integrate new data sources and an effective communication mechanism to disseminate the new and relevant data sources that have been purchased. To make it scalable, use cases should be harmonized so they can be replicated across different datasets. Collaboration and intelligent cataloging are both ways to achieve this.

Claims, EHRs and lab data are incomplete and can make it difficult to gain a comprehensive view of a patient’s longitudinal journey. Most of the oncology and rare disease treatments come under medical benefits, and capture is often an issue with the way medical benefit products are sourced.

There are multiple claims data enrichment solutions, some that leverage AI and others that involve linking multiple datasets together through tokenization, capturing as much information on the patient as possible.

The sheer volume of data makes patient journey analysis an exploratory process that can be time-consuming and challenging. To facilitate easy sharing, accelerate insight generation and standardize outputs, organizations need effective knowledge management.

That means business rules, cohort definitions and patient journey studies are well-documented, standardized and stored in a centralized repository. It means that patient journey outputs must be standardized while also allowing for customization to support a range of applications, from forecasting and reporting patient journey KPIs to patient prediction.

Gathering the data is just part of building a comprehensive patient journey. You then need the ability to analyze that data to create strategy. Finding individuals with strong technical expertise in real-world data analytics and specific experience in oncology and rare disease therapy areas is often challenging.

Additionally, due to the complex nature of treating oncology patients, the right balance between having complex business rules that can capture the treatment nuances for patient cohorts and then being able to communicate those across the organization is key to having a usable patient journey mapped.

At the same time, having a centralized repository that acts as a single source of truth for all the business rules helps with standardization, saving time and adding credibility.

Visualizing the outputs of the patient journey is crucial for creating an actionable strategy. An easy-to-use graphical interface that supports self-service analytics, integrates multiple data sources and builds patient journeys empowers business users to explore data and derive insights without requiring deep technical expertise.

Power users may prefer using analytics programming languages (SQL, R or Python) but must ensure best practices by standardizing processes and workflows. This will ensure consistency, reproducibility and the ability to troubleshoot across teams within the organization.

Visualization tools are important for disseminating patient journey outputs to business stakeholders. Visualization tools should be user-friendly, scalable, capable of integrating data, flexible and customizable to create charts and share key insights in an easily digestible manner.

Generative AI can make insight consumption more conversational, allowing users to engage with the data instead of scanning through charts and datasets.

Pharma organizations typically require continuous updates to KPIs. It is essential to have a robust process in place that can ingest data, perform quality checks and transformations, and effectively disseminate data. Having the capability to automate the patient journey and subsequent KPI creation processes can be done in an independent manner using different tools or in a modularized platform to reap productivity gains and democratize the insights across the organization.

These datasets are large, and a powerful cloud computing capability with the ability to scale is often an overlooked factor that should be part of any tool that companies implement.

To build the patient journey and ensure scalability, it’s crucial to hire the right team with the relevant skills in analytics. Organizations will want to establish a process that enables conversion to the standardized data models like the OMOP model, which simplify the harmonization and integration of real-world data sources. Ensure that the analytics teams have access to the right technology, be it in the form of cloud computing or data processing tools or a platform that makes it easy for both the business and power user.

Leveraging tools like ZAIDYN® Cohort Builder and Patient Journey and Patient Radar, which offer easy-to-use workflows, pre-built stencils and intuitive visualization, will help standardize data sources effectively, as well as make them leverageable tools for professionals with business expertise.