Dataset Information

Privacy protections to encourage use of health-relevant digital data in a learning health system.

ABSTRACT: The National Academy of Medicine has long advocated for a "learning healthcare system" that produces constantly updated reference data during the care process. Moving toward a rapid learning system to solve intractable problems in health demands a balance between protecting patients and making data available to improve health and health care. Public concerns in the U.S. about privacy and the potential for unethical or harmful uses of this data, if not proactively addressed, could upset this balance. New federal laws prioritize sharing health data, including with patient digital tools. U.S. health privacy laws do not cover data collected by many consumer digital technologies and have not been updated to address concerns about the entry of large technology companies into health care. Further, there is increasing recognition that many classes of data not traditionally considered to be healthcare-related, for example consumer credit histories, are indeed predictive of health status and outcomes. We propose a multi-pronged approach to protecting health-relevant data while promoting and supporting beneficial uses and disclosures to improve health and health care for individuals and populations. Such protections should apply to entities collecting health-relevant data regardless of whether they are covered by federal health privacy laws. We focus largely on privacy but also address protections against harms as a critical component of a comprehensive approach to governing health-relevant data. U.S. policymakers and regulators should consider these recommendations in crafting privacy bills and rules. However, our recommendations also can inform best practices even in the absence of new federal requirements.

SUBMITTER: McGraw D

PROVIDER: S-EPMC7782585 | biostudies-literature | 2021 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Privacy protections to encourage use of health-relevant digital data in a learning health system.

McGraw Deven D Mandl Kenneth D KD

NPJ digital medicine 20210104 1

The National Academy of Medicine has long advocated for a "learning healthcare system" that produces constantly updated reference data during the care process. Moving toward a rapid learning system to solve intractable problems in health demands a balance between protecting patients and making data available to improve health and health care. Public concerns in the U.S. about privacy and the potential for unethical or harmful uses of this data, if not proactively addressed, could upset this bala ...[more]

PMID: 33398052

Similar Datasets

Project description:ImportanceDigital health information has many potential health applications, but privacy is a growing concern among consumers and policy makers. Consent alone is increasingly seen as inadequate to safeguard privacy.ObjectiveTo determine whether different privacy protections are associated with consumers' willingness to share their digital health information for research, marketing, or clinical uses.Design, setting, and participantsThis 2020 national survey with an embedded conjoint experiment recruited US adults from a nationally representative sample with oversampling of Black and Hispanic individuals. Willingness to share digital information across 192 different scenarios reflecting the product of 4 possible privacy protections, 3 uses of information, 2 users of information, and 2 sources of digital information was evaluated. Each participant was randomly assigned 9 scenarios. The survey was administrated between July 10 and July 31, 2020, in Spanish and English. Analysis for this study was conducted between May 2021 and July 2022.Main outcomes and measuresParticipants rated each conjoint profile on a 5-point Likert scale measuring their willingness to share their personal digital information (with 5 indicating the most willingness to share). Results are reported as adjusted mean differences.ResultsOf the 6284 potential participants, 3539 (56%) responded to the conjoint scenarios. A total of 1858 participants (53%) were female, 758 (21%) identified as Black, 833 (24%) identified as Hispanic, 1149 (33%) had an annual income less than $50 000, and 1274 (36%) were 60 years or older. Participants were more willing to share health information with the presence of each individual privacy protection, including consent (difference, 0.32; 95% CI, 0.29-0.35; P < .001), followed by data deletion (difference, 0.16; 95% CI, 0.13-0.18; P < .001), oversight (difference, 0.13; 95% CI, 0.10-0.15; P < .001), and transparency of data collected (difference, 0.08; 95% CI, 0.05-0.10; P < .001). The relative importance (importance weight on a 0%-100% scale) was greatest for the purpose of use (29.9%) but when considered collectively, the 4 privacy protections together were the most important (51.5%) factor in the conjoint experiment. When the 4 privacy protections were considered separately, consent was the most important (23.9%).Conclusions and relevanceIn this survey study of a nationally representative sample of US adults, consumers' willingness to share personal digital health information for health purposes was associated with the presence of specific privacy protections beyond consent alone. Additional protections, including data transparency, oversight, and data deletion may strengthen consumer confidence in sharing their personal digital health information.

Project description:BackgroundIn 2020, the number of internet users surpassed 4.6 billion. Individuals who create and share digital data can leave a trail of information about their habits and preferences that collectively generate a digital footprint. Studies have shown that digital footprints can reveal important information regarding an individual's health status, ranging from diet and exercise to depression. Uses of digital applications have accelerated during the COVID-19 pandemic where public health organizations have utilized technology to reduce the burden of transmission, ultimately leading to policy discussions about digital health privacy. Though US consumers report feeling concerned about the way their personal data is used, they continue to use digital technologies.ObjectiveThis study aimed to understand the extent to which consumers recognize possible health applications of their digital data and identify their most salient concerns around digital health privacy.MethodsWe conducted semistructured interviews with a diverse national sample of US adults from November 2018 to January 2019. Participants were recruited from the Ipsos KnowledgePanel, a nationally representative panel. Participants were asked to reflect on their own use of digital technology, rate various sources of digital information, and consider several hypothetical scenarios with varying sources and health-related applications of personal digital information.ResultsThe final cohort included a diverse national sample of 45 US consumers. Participants were generally unaware what consumer digital data might reveal about their health. They also revealed limited knowledge of current data collection and aggregation practices. When responding to specific scenarios with health-related applications of data, they had difficulty weighing the benefits and harms but expressed a desire for privacy protection. They saw benefits in using digital data to improve health, but wanted limits to health programs' use of consumer digital data.ConclusionsCurrent privacy restrictions on health-related data are premised on the notion that these data are derived only from medical encounters. Given that an increasing amount of health-related data is derived from digital footprints in consumer settings, our findings suggest the need for greater transparency of data collection and uses, and broader health privacy protections.

Project description:BackgroundThe use of wearables facilitates data collection at a previously unobtainable scale, enabling the construction of complex predictive models with the potential to improve health. However, the highly personal nature of these data requires strong privacy protection against data breaches and the use of data in a way that users do not intend. One method to protect user privacy while taking advantage of sharing data across users is federated learning, a technique that allows a machine learning model to be trained using data from all users while only storing a user's data on that user's device. By keeping data on users' devices, federated learning protects users' private data from data leaks and breaches on the researcher's central server and provides users with more control over how and when their data are used. However, there are few rigorous studies on the effectiveness of federated learning in the mobile health (mHealth) domain.ObjectiveWe review federated learning and assess whether it can be useful in the mHealth field, especially for addressing common mHealth challenges such as privacy concerns and user heterogeneity. The aims of this study are to describe federated learning in an mHealth context, apply a simulation of federated learning to an mHealth data set, and compare the performance of federated learning with the performance of other predictive models.MethodsWe applied a simulation of federated learning to predict the affective state of 15 subjects using physiological and motion data collected from a chest-worn device for approximately 36 minutes. We compared the results from this federated model with those from a centralized or server model and with the results from training individual models for each subject.ResultsIn a 3-class classification problem using physiological and motion data to predict whether the subject was undertaking a neutral, amusing, or stressful task, the federated model achieved 92.8% accuracy on average, the server model achieved 93.2% accuracy on average, and the individual model achieved 90.2% accuracy on average.ConclusionsOur findings support the potential for using federated learning in mHealth. The results showed that the federated model performed better than a model trained separately on each individual and nearly as well as the server model. As federated learning offers more privacy than a server model, it may be a valuable option for designing sensitive data collection methods.

Project description:BACKGROUND:The exploitation of synthetic data in health care is at an early stage. Synthetic data could unlock the potential within health care datasets that are too sensitive for release. Several synthetic data generators have been developed to date; however, studies evaluating their efficacy and generalizability are scarce. OBJECTIVE:This work sets out to understand the difference in performance of supervised machine learning models trained on synthetic data compared with those trained on real data. METHODS:A total of 19 open health datasets were selected for experimental work. Synthetic data were generated using three synthetic data generators that apply classification and regression trees, parametric, and Bayesian network approaches. Real and synthetic data were used (separately) to train five supervised machine learning models: stochastic gradient descent, decision tree, k-nearest neighbors, random forest, and support vector machine. Models were tested only on real data to determine whether a model developed by training on synthetic data can used to accurately classify new, real examples. The impact of statistical disclosure control on model performance was also assessed. RESULTS:A total of 92% of models trained on synthetic data have lower accuracy than those trained on real data. Tree-based models trained on synthetic data have deviations in accuracy from models trained on real data of 0.177 (18%) to 0.193 (19%), while other models have lower deviations of 0.058 (6%) to 0.072 (7%). The winning classifier when trained and tested on real data versus models trained on synthetic data and tested on real data is the same in 26% (5/19) of cases for classification and regression tree and parametric synthetic data and in 21% (4/19) of cases for Bayesian network-generated synthetic data. Tree-based models perform best with real data and are the winning classifier in 95% (18/19) of cases. This is not the case for models trained on synthetic data. When tree-based models are not considered, the winning classifier for real and synthetic data is matched in 74% (14/19), 53% (10/19), and 68% (13/19) of cases for classification and regression tree, parametric, and Bayesian network synthetic data, respectively. Statistical disclosure control methods did not have a notable impact on data utility. CONCLUSIONS:The results of this study are promising with small decreases in accuracy observed in models trained with synthetic data compared with models trained with real data, where both are tested on real data. Such deviations are expected and manageable. Tree-based classifiers have some sensitivity to synthetic data, and the underlying cause requires further investigation. This study highlights the potential of synthetic data and the need for further evaluation of their robustness. Synthetic data must ensure individual privacy and data utility are preserved in order to instill confidence in health care departments when using such data to inform policy decision-making.

Project description:BACKGROUND:Sharing research data uses resources effectively; enables large, diverse data sets; and supports rigor and reproducibility. However, sharing such data increases privacy risks for participants who may be re-identified by linking study data to outside data sets. These risks have been investigated for genetic and medical records but rarely for environmental data. OBJECTIVES:We evaluated how data in environmental health (EH) studies may be vulnerable to linkage and we investigated, in a case study, whether environmental measurements could contribute to inferring latent categories (e.g., geographic location), which increases privacy risks. METHODS:We identified 12 prominent EH studies, reviewed the data types collected, and evaluated the availability of outside data sets that overlap with study data. With data from the Household Exposure Study in California and Massachusetts and the Green Housing Study in Boston, Massachusetts, and Cincinnati, Ohio, we used k-means clustering and principal component analysis to investigate whether participants' region of residence could be inferred from measurements of chemicals in household air and dust. RESULTS:All 12 studies included at least two of five data types that overlap with outside data sets: geographic location (9 studies), medical data (9 studies), occupation (10 studies), housing characteristics (10 studies), and genetic data (7 studies). In our cluster analysis, participants' region of residence could be inferred with 80%-98% accuracy using environmental measurements with original laboratory reporting limits. DISCUSSION:EH studies frequently include data that are vulnerable to linkage with voter lists, tax and real estate data, professional licensing lists, and ancestry websites, and exposure measurements may be used to identify subgroup membership, increasing likelihood of linkage. Thus, unsupervised sharing of EH research data potentially raises substantial privacy risks. Empirical research can help characterize risks and evaluate technical solutions. Our findings reinforce the need for legal and policy protections to shield participants from potential harms of re-identification from data sharing. https://doi.org/10.1289/EHP4817.

Dataset Information

Privacy protections to encourage use of health-relevant digital data in a learning health system.

Publications

Privacy protections to encourage use of health-relevant digital data in a learning health system.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets