Leveraging Real-World Data and machine learning to identify pre-diagnosis lung cancer patients

A leading life sciences organization needed to identify likely lung cancer patients before formal diagnosis to target deployment of a diagnostic tool, since lung cancer is often caught only at advanced stages. Symphony Health used its Integrated Dataverse (IDV®) claims data covering over 300 million US patient lives, mapped pre-diagnostic patient journeys (symptoms like persistent cough and unexplained weight loss, imaging orders, pulmonologist referrals, treatment patterns) around lung cancer diagnosis as the "end event," and applied machine learning (random forest, gradient boosting, logistic regression) to flag undiagnosed patients. The work produced a validated list of predictive indicators, ranked attribution of providers managing likely patients, and an interactive geographic/specialty dashboard, and the methodology was replicated across nine more cancer types (pancreatic, ovarian, colorectal, prostate, and others), identifying thousands of high-risk undiagnosed candidates for testing.

The customer is anonymised in Symphony Health’s own case study — not withheld by us.

Symphony Health is a commercial claims and prescriber-data provider, recently divested from ICON plc to HealthVerity, supplying open/closed claims data for pharma commercial insight.

This sits in the Data Providers stage of the AI use-case lifecycle: Named examples from the real-world-data, claims and competitive-intelligence providers pharma AI systems are trained on, benchmarked against, or run inside of.