A fast privacy-preserving patient record linkage of time series data

Abstract

Recent advances in technology have led to an explosion of data in virtually all domains of our lives. Modern biomedical devices can acquire a large number of physical readings from patients. Often, these readings are stored in the form of time series data. Such time series data can form the basis for important research to advance healthcare and well being. Due to several considerations including data size, patient privacy, etc., the original, full data may not be available to secondary parties or researchers. Instead, suppose that a subset of the data is made available. A fast and reliable record linkage algorithm enables us to accurately match patient records in the original and subset databases while maintaining privacy. The problem of record linkage when the attributes include time series has not been studied much in the literature. We introduce two main contributions in this paper. First, we propose a novel, very efficient, and scalable record linkage algorithm that is employed on time series data. This algorithm is 400× faster than the previous work. Second, we introduce a privacy preserving framework that enables health institutions to safely release their raw time series records to researchers with bare minimum amount of identifying information.

Chemical Composition, Repellent, and Phytotoxic Potentials of the Fractionated Resin Essential Oil from Araucaria heterophylla Growing in Tunisia

“…The most abundant compound was α-pinene (44.9-62.6 %) in most cases, except in the study by Soliman et al (2023), where caryophyllene oxide (14.9 %) was identified as the main compound. [41] The results of the present work differ significantly from those reported in the literature, supposedly due to a chemical variability in resin oils of A. heterophylla induced by ecological, genetical, and/or environmental factors. [43]…”

“…[40] Still for the Egyptian species, caryophyllene oxide (14.9 %), (+)-sabinene (12.1 %), D-limonene (11.2 %), caryophyllene (10.4 %), α-copaene (8.0 %), β-pinene (6.4 %) were the dominant compounds in the chemical profile of the REO isolated by Soliman et al (2023). [41] While the REO extracted by the microwave technique was reported by Abd-ElGawad et al (2023) to be rich in monoterpene hydrocarbons (77.9 %), with a remarkable dominance of α-pinene (62.6 %). [42] In the present study, the essential oil hydrodistilled from the resin exuded by the trunk bark of A. heterophylla tree growing in Tunisia was subjected to chemical and biological analyses.…”

Comparative assessment of synthetic time series generation approaches in healthcare: leveraging patient metadata for accurate data synthesis

“…Up to now, clinical SDG has mostly been focused on generating private and useful tabular static data, while the longitudinal component, and the joint generation of both, have fallen behind. Considering this scenario, it is worth noting the need to ensure the privacy of both mentioned components [ 7 ]. The combination of metadata with time series could potentially help re-identification and compromised data breaches, but synthesizing time series brings inherent challenges with it, as temporal correlations must be learnt by data generators apart from the usual intervariable correlations.…”