A Data and Knowledge Driven Randomization Technique for Privacy-Preserving Data Enrichment in Hospital Readmission Prediction

In health care predictive analytics, limited data is often a major obstacle for developing highly accurate predictive models. The lack of data is related to various factors: minimal data available as in rare diseases, the cost of data collection, and privacy regulation related to patient data. In order to enable data enrichment within and between hospitals, while preserving privacy, we propose a system for data enrichment that adds a randomization component on top of existing anonymization techniques. In order to prevent information loss (inclusive loss of predictive accuracy of the algorithm) related to randomization, we propose a technique for data generation that exploits fused domain knowledge and available data-driven techniques as complementary information sources. Such fusion allows the generation of additional examples by controlled randomization and increased protection of privacy of personally sensitive information when data is shared between different sites. The initial evaluation was conducted on Electronic Health Records (EHRs), for a 30-day hospital readmission prediction based on pediatric hospital discharge data from 5 hospitals in California. It was demonstrated that besides ensuring privacy, this approach preserves (and in some cases even improves) predictive accuracy.