Privacy-Preserving Similar Patient Queries for Combined Biomedical Data

Abstract

The decreasing costs of molecular profiling have fueled the biomedical research community with a plethora of new types of biomedical data, enabling a breakthrough towards more precise and personalized medicine. Naturally, the increasing availability of data also enables physicians to compare patients’ data and treatments easily and to find similar patients in order to propose the optimal therapy. Such similar patient queries (SPQs) are of utmost importance to medical practice and will be relied upon in future health information exchange systems. While privacy-preserving solutions have been previously studied, those are limited to genomic data, ignoring the different newly available types of biomedical data. In this paper, we propose new cryptographic techniques for finding similar patients in a privacy-preserving manner with various types of biomedical data, including genomic, epigenomic and transcriptomic data as well as their combination. We design protocols for two of the most common similarity metrics in biomedicine: the Euclidean distance and Pearson correlation coefficient. Moreover, unlike previous approaches, we account for the fact that certain locations contribute differently to a given disease or phenotype by allowing to limit the query to the relevant locations and to assign them different weights. Our protocols are specifically designed to be highly efficient in terms of communication and bandwidth, requiring only one or two rounds of communication and thus enabling scalable parallel queries. We rigorously prove our protocols to be secure based on cryptographic games and instantiate our technique with three of the most important types of biomedical data – namely DNA, microRNA expression, and DNA methylation. Our experimental results show that our protocols can compute a similarity query over a typical number of positions against a database of 1,000 patients in a few seconds. Finally, we propose and formalize strategies to mitigate the threat of malicious users or hospitals.

CPU and GPU Accelerated Fully Homomorphic Encryption

“…Contemporary desktop computers come with 4 to 8 cores containing a maximum of 16 threads. There have been multiple attempts [29] to use a large number of CPUs collectively for parallel operations, whereas we show that single GPU is equivalent (and better performing) for most FHE operations.…”

Ultra-secure storage and analysis of genetic data for the advancement of precision medicine

“…Since each key-switching key is a single ciphertext, the storage required remains minimal at approximately 31 gigabytes (GB) for 1000 researchers. Supplementary Figure 7: The runtime of the L2 similarity score computation for SQUiD and [59] (Other) for 100 SNPs and 1,000 SNPs. For score computation with fewer than 4,000 patients, [59] exhibits faster performance for both 100 and 1,000 SNPs.…”

“…Supplementary Figure 7: The runtime of the L2 similarity score computation for SQUiD and [59] (Other) for 100 SNPs and 1,000 SNPs. For score computation with fewer than 4,000 patients, [59] exhibits faster performance for both 100 and 1,000 SNPs. However, as the patient dataset scales up, SQUiD consistently outperforms [59], demonstrating its superior efficiency in handling larger datasets.…”

Efficient privacy-preserving whole-genome variant queries

“…In Salem et al (2019) , the authors developed a privacy-preserving protocol for similar patient queries for combined medical databases. The proposed methods work on various types of biomedical data, including genomic, epigenomic and transcriptomic data as well as their combination.…”