Using game theory to thwart multistage privacy intrusions when sharing data

Applications and Concerns of ChatGPT and Other Conversational Large Language Models in Health Care: Systematic Review

BACKGROUND

The launch of ChatGPT (OpenAI) in November 2022 attracted public attention and academic interest to large language models (LLMs), facilitating the emergence of many other innovative LLMs. These LLMs have been applied in various fields, including health care. Numerous studies have since been conducted regarding how to use state-of-the-art LLMs in health-related scenarios.

OBJECTIVE

This review aims to summarize applications of and concerns regarding conversational LLMs in health care and provide an agenda for future research in this field.

METHODS

We used PubMed, ACM, and the IEEE digital libraries as primary sources for this review. We followed the guidance of PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) to screen and select peer-reviewed research articles that (1) were related to health care applications and conversational LLMs and (2) were published before September 1, 2023, the date when we started paper collection. We investigated these papers and classified them according to their applications and concerns.

RESULTS

Our search initially identified 820 papers according to targeted keywords, out of which 65 (7.9%) papers met our criteria and were included in the review. The most popular conversational LLM was ChatGPT (60/65, 92% of papers), followed by Bard (Google LLC; 1/65, 2% of papers), LLaMA (Meta; 1/65, 2% of papers), and other LLMs (6/65, 9% papers). These papers were classified into four categories of applications: (1) summarization, (2) medical knowledge inquiry, (3) prediction (eg, diagnosis, treatment recommendation, and drug synergy), and (4) administration (eg, documentation and information collection), and four categories of concerns: (1) reliability (eg, training data quality, accuracy, interpretability, and consistency in responses), (2) bias, (3) privacy, and (4) public acceptability. There were 49 (75%) papers using LLMs for either summarization or medical knowledge inquiry, or both, and there are 58 (89%) papers expressing concerns about either reliability or bias, or both. We found that conversational LLMs exhibited promising results in summarization and providing general medical knowledge to patients with a relatively high accuracy. However, conversational LLMs such as ChatGPT are not always able to provide reliable answers to complex health-related tasks (eg, diagnosis) that require specialized domain expertise. While bias or privacy issues are often noted as concerns, no experiments in our reviewed papers thoughtfully examined how conversational LLMs lead to these issues in health care research.

CONCLUSIONS

Future studies should focus on improving the reliability of LLM applications in complex health-related tasks, as well as investigating the mechanisms of how LLM applications bring bias and privacy issues. Considering the vast accessibility of LLMs, legal, social, and technical efforts are all needed to address concerns about LLMs to promote, improve, and regularize the application of LLMs in health care.

HydraGAN: A Cooperative Agent Model for Multi-Objective Data Generation

Generative adversarial networks have become a de facto approach to generate synthetic data points that resemble their real counterparts. We tackle the situation where the realism of individual samples is not the sole criterion for synthetic data generation. Additional constraints such as privacy preservation, distribution realism, and diversity promotion may also be essential to optimize. To address this challenge, we introduce HydraGAN, a multi-agent network that performs multi-objective synthetic data generation. We theoretically verify that training the HydraGAN system, containing a single generator and an arbitrary number of discriminators, leads to a Nash equilibrium. Experimental results for six datasets indicate that HydraGAN consistently outperforms prior methods in maximizing the Area under the Radar Curve (AuRC), balancing a combination of cooperative or competitive data generation goals.

PanDa Game: Optimized Privacy-Preserving Publishing of Individual-Level Pandemic Data Based on a Game Theoretic Model

Sharing individual-level pandemic data is essential for accelerating the understanding of a disease. For example, COVID-19 data have been widely collected to support public health surveillance and research. In the United States, these data are typically de-identified before publication to protect the privacy of the corresponding individuals. However, current data publishing approaches for this type of data, such as those adopted by the U.S. Centers for Disease Control and Prevention (CDC), have not flexed over time to account for the dynamic nature of infection rates. Thus, the policies generated by these strategies have the potential to both raise privacy risks or overprotect the data and impair the data utility (or usability). To optimize the tradeoff between privacy risk and data utility, we introduce a game theoretic model that adaptively generates policies for the publication of individual-level COVID-19 data according to infection dynamics. We model the data publishing process as a two-player Stackelberg game between a data publisher and a data recipient and then search for the best strategy for the publisher. In this game, we consider 1) average performance of predicting future case counts; and 2) mutual information between the original data and the released data. We use COVID-19 case data from Vanderbilt University Medical Center from March 2020 to December 2021 to demonstrate the effectiveness of the new model. The results indicate that the game theoretic model outperforms all state-of-the-art baseline approaches, including those adopted by CDC, while maintaining low privacy risk. We further perform an extensive sensitivity analyses to show that our findings are robust to order-of-magnitude parameter fluctuations.

Current status and challenges in establishing reference intervals based on real-world data

Reference intervals (RIs) are the cornerstone for evaluation of test results in clinical practice and are invaluable in judging patient health and making clinical decisions. Establishing RIs based on clinical laboratory data is a branch of real-world data mining research. Compared to the traditional direct method, this indirect approach is highly practical, widely applicable, and low-cost. Improving the accuracy of RIs requires not only the collection of sufficient data and the use of correct statistical methods, but also proper stratification of heterogeneous subpopulations. This includes the establishment of age-specific RIs and taking into account other characteristics of reference individuals. Although there are many studies on establishing RIs by indirect methods, it is still very difficult for laboratories to select appropriate statistical methods due to the lack of formal guidelines. This review describes the application of real-world data and an approach for establishing indirect reference intervals (iRIs). We summarize the processes for establishing iRIs using real-world data and analyze the principle and applicable scope of the indirect method model in detail. Moreover, we compare different methods for constructing growth curves to establish age-specific RIs, in hopes of providing laboratories with a reference for establishing specific iRIs and giving new insight into clinical laboratory RI research. (201 words).

Differentially private knowledge transfer for federated learning

Extracting useful knowledge from big data is important for machine learning. When data is privacy-sensitive and cannot be directly collected, federated learning is a promising option that extracts knowledge from decentralized data by learning and exchanging model parameters, rather than raw data. However, model parameters may encode not only non-private knowledge but also private information of local data, thereby transferring knowledge via model parameters is not privacy-secure. Here, we present a knowledge transfer method named PrivateKT, which uses actively selected small public data to transfer high-quality knowledge in federated learning with privacy guarantees. We verify PrivateKT on three different datasets, and results show that PrivateKT can maximally reduce 84% of the performance gap between centralized learning and existing federated learning methods under strict differential privacy restrictions. PrivateKT provides a potential direction to effective and privacy-preserving knowledge transfer in machine intelligent systems.

Supporting COVID-19 Disparity Investigations with Dynamically Adjusting Case Reporting Policies

Data access limitations have stifled COVID-19 disparity investigations in the United States. Though federal and state legislation permits publicly disseminating de-identified data, methods for de-identification, including a recently proposed dynamic policy approach to pandemic data sharing, remain unproved in their ability to support pandemic disparity studies. Thus, in this paper, we evaluate how such an approach enables timely, accurate, and fair disparity detection, with respect to potential adversaries with varying prior knowledge about the population. We show that, when considering reasonably enabled adversaries, dynamic policies support up to three times earlier disparity detection in partially synthetic data than data sharing policies derived from two current, public datasets. Using real-world COVID-19 data, we also show how granular date information, which dynamic policies were designed to share, improves disparity characterization. Our results highlight the potential of the dynamic policy approach to publish data that supports disparity investigations in current and future pandemics.

Managing re-identification risks while providing access to the All of Us research program

OBJECTIVE

The All of Us Research Program makes individual-level data available to researchers while protecting the participants' privacy. This article describes the protections embedded in the multistep access process, with a particular focus on how the data was transformed to meet generally accepted re-identification risk levels.

METHODS

At the time of the study, the resource consisted of 329 084 participants. Systematic amendments were applied to the data to mitigate re-identification risk (eg, generalization of geographic regions, suppression of public events, and randomization of dates). We computed the re-identification risk for each participant using a state-of-the-art adversarial model specifically assuming that it is known that someone is a participant in the program. We confirmed the expected risk is no greater than 0.09, a threshold that is consistent with guidelines from various US state and federal agencies. We further investigated how risk varied as a function of participant demographics.

RESULTS

The results indicated that 95th percentile of the re-identification risk of all the participants is below current thresholds. At the same time, we observed that risk levels were higher for certain race, ethnic, and genders.

CONCLUSIONS

While the re-identification risk was sufficiently low, this does not imply that the system is devoid of risk. Rather, All of Us uses a multipronged data protection strategy that includes strong authentication practices, active monitoring of data misuse, and penalization mechanisms for users who violate terms of service.

A Multifaceted benchmarking of synthetic electronic health record generation models

Synthetic health data have the potential to mitigate privacy concerns in supporting biomedical research and healthcare applications. Modern approaches for data generation continue to evolve and demonstrate remarkable potential. Yet there is a lack of a systematic assessment framework to benchmark methods as they emerge and determine which methods are most appropriate for which use cases. In this work, we introduce a systematic benchmarking framework to appraise key characteristics with respect to utility and privacy metrics. We apply the framework to evaluate synthetic data generation methods for electronic health records data from two large academic medical centers with respect to several use cases. The results illustrate that there is a utility-privacy tradeoff for sharing synthetic health data and further indicate that no method is unequivocally the best on all criteria in each use case, which makes it evident why synthetic data generation methods need to be assessed in context.

Sociotechnical safeguards for genomic data privacy

Recent developments in a variety of sectors, including health care, research and the direct-to-consumer industry, have led to a dramatic increase in the amount of genomic data that are collected, used and shared. This state of affairs raises new and challenging concerns for personal privacy, both legally and technically. This Review appraises existing and emerging threats to genomic data privacy and discusses how well current legal frameworks and technical safeguards mitigate these concerns. It concludes with a discussion of remaining and emerging challenges and illustrates possible solutions that can balance protecting privacy and realizing the benefits that result from the sharing of genetic information.