Patient health data are often found spread across various sources. However, precision medicine and personalized care requires access to the complete medical records. The first step towards this is to enable the linkage of health records spread across different sites. Existing record linkage solutions assume that data is centralized with no privacy/security concerns restricting sharing. However, that is often untrue. Therefore, we design and implement a portable method for privacy-preserving record linkage based on garbled circuits to accurately and securely match records. We also develop a novel approximate matching mechanism that significantly improves efficiency.
Keyphrases
- electronic health record
- health information
- healthcare
- big data
- hiv testing
- genome wide
- public health
- clinical decision support
- social media
- mental health
- men who have sex with men
- adverse drug
- palliative care
- case report
- quality improvement
- dna methylation
- machine learning
- global health
- antiretroviral therapy
- data analysis