Research Article
Medical Diagnostics Based on Encrypted Medical Data
@INPROCEEDINGS{10.1007/978-3-030-24202-2_8, author={Alexey Gribov and Kelsey Horan and Jonathan Gryak and Kayvan Najarian and Vladimir Shpilrain and Reza Soroushmehr and Delaram Kahrobaei}, title={Medical Diagnostics Based on Encrypted Medical Data}, proceedings={Bio-inspired Information and Communication Technologies. 11th EAI International Conference, BICT 2019, Pittsburgh, PA, USA, March 13--14, 2019, Proceedings}, proceedings_a={BICT}, year={2019}, month={7}, keywords={Clinical decision support Data mining Machine learning Privacy preserving classifier Encryption}, doi={10.1007/978-3-030-24202-2_8} }- Alexey Gribov
Kelsey Horan
Jonathan Gryak
Kayvan Najarian
Vladimir Shpilrain
Reza Soroushmehr
Delaram Kahrobaei
Year: 2019
Medical Diagnostics Based on Encrypted Medical Data
BICT
Springer
DOI: 10.1007/978-3-030-24202-2_8
Abstract
We utilize a type of encryption scheme known as a Fully Homomorphic Encryption (FHE) scheme which allows for computation over encrypted data. Our encryption scheme is more efficient than other publicly available FHE schemes, making it more feasible. We conduct simulations based on common scenarios in which this ability is useful. In the first simulation we conduct time series analysis via Recursive Least Squares on both encrypted and unencrypted data and compare the results. In simulation one, it is shown that the error from computing over plaintext data is the same as the error for computing over encrypted data. In the second simulation, we compute two known diagnostic functions over publicly available data in order to calculate computational benchmarks. In simulation two, we see that computation over encrypted data using our method incurs relatively lower costs as compared to a majority of other publicly available methods. By successfully computing over encrypted data we have shown that our FHE scheme permits the use of machine learning algorithms that utilize polynomial kernel functions.
