Differential privacy in health research: A scoping review

Abstract

Objective Differential privacy is a relatively new method for data privacy that has seen growing use due its strong protections that rely on added noise. This study assesses the extent of its awareness, development, and usage in health research. Materials and Methods A scoping review was conducted by searching for [“differential privacy” AND “health”] in major health science databases, with additional articles obtained via expert consultation. Relevant articles were classified according to subject area and focus. Results A total of 54 articles met the inclusion criteria. Nine articles provided descriptive overviews, 31 focused on algorithm development, 9 presented novel data sharing systems, and 8 discussed appraisals of the privacy-utility tradeoff. The most common areas of health research where differential privacy has been discussed are genomics, neuroimaging studies, and health surveillance with personal devices. Algorithms were most commonly developed for the purposes of data release and predictive modeling. Studies on privacy-utility appraisals have considered economic cost-benefit analysis, low-utility situations, personal attitudes toward sharing health data, and mathematical interpretations of privacy risk. Discussion Differential privacy remains at an early stage of development for applications in health research, and accounts of real-world implementations are scant. There are few algorithms for explanatory modeling and statistical inference, particularly with correlated data. Furthermore, diminished accuracy in small datasets is problematic. Some encouraging work has been done on decision making with regard to epsilon. The dissemination of future case studies can inform successful appraisals of privacy and utility. Conclusions More development, case studies, and evaluations are needed before differential privacy can see widespread use in health research.

Exploring the Privacy-Utility Tradeoff in Differentially Private Federated Learning for Mobile Health: A Novel Approach using Simulated Privacy Attacks

“…Similarly, there have been many uses of DP in healthcare applications [17], including drug sensitivity prediction [18] and coronary heart disease diagnosis [19]. Other work has combined DP with FL to achieve enhanced privacy protection [20].…”

COMMUTE: communication-efficient transfer learning for multi-site risk prediction

“…This level of privacy protection is common in a collaborative research environment, where the risk for membership inference or tracing attack is low. In practice, when it is necessary, our method can be combined with other privacy protection techniques, for example, differential privacy 17,18 , and data encryption 2,57 to further improve privacy protection. However, some of these approaches may compromise the prediction accuracy.…”

“…Moreover, compared to federated algorithms that require iterative sharing of information, such as the gradients of objective functions, COMMUTE has less risk of being attacked by programs that can learn the distribution of individual-level data from the shared gradients 23 . In practice, when necessary, our method can be combined with other privacy protection techniques, such as differential privacy 14,15 and data encryption 2,62 , to further improve privacy protection. It is worth noticing that some of these approaches may compromise prediction accuracy.…”

Towards effective data sharing in ophthalmology: data standardization and data privacy

“…Although differential privacy is being applied to the healthcare space, real-world implementations are scant [47 ▪ ]. We are not aware of any implementations in the ophthalmology space, although feasibility has been demonstrated for other imaging [48].…”