Case Study: Discovery Health achieves 48% reduction in COVID-19 mortality and identifies 20,000 high-risk members with Cloudera

Leveraging data science and machine learning to gain invaluable insights and save lives during a pandemic

Discovery Health is a South African health insurer and medical scheme administrator serving over 3.5 million beneficiaries with a data-driven, shared-value model that rewards healthier behavior. As its data sources grew, the company needed better analytics—an urgent problem when COVID‑19 hit and it saw a sharp drop in care-seeking (30% fewer GP consultations among chronically ill members)—so Discovery sought a partner to help identify members at highest risk of hospitalization and intervene early.

Using Cloudera’s platform and the Patient‑X© machine learning pipeline on Cloudera Data Science Workbench, Discovery combined ~900 demographic, lifestyle and clinical data points to proactively target high‑risk members with outreach and pulse oximeters. The initiative produced measurable impact: a 48% reduction in mortality for patients who received an oximeter, 20,000 additional high‑risk members identified versus standard rules, and the launch of a COVID Resilience Index—while maintaining regulatory-grade privacy—enabling ongoing, predictive interventions to save lives.

Discovery Health

Shirley Collie

Chief Health Analytics Actuary