Dataset Information

A digital mask to safeguard patient privacy.

ABSTRACT: The storage of facial images in medical records poses privacy risks due to the sensitive nature of the personal biometric information that can be extracted from such images. To minimize these risks, we developed a new technology, called the digital mask (DM), which is based on three-dimensional reconstruction and deep-learning algorithms to irreversibly erase identifiable features, while retaining disease-relevant features needed for diagnosis. In a prospective clinical study to evaluate the technology for diagnosis of ocular conditions, we found very high diagnostic consistency between the use of original and reconstructed facial videos (κ ≥ 0.845 for strabismus, ptosis and nystagmus, and κ = 0.801 for thyroid-associated orbitopathy) and comparable diagnostic accuracy (P ≥ 0.131 for all ocular conditions tested) was observed. Identity removal validation using multiple-choice questions showed that compared to image cropping, the DM could much more effectively remove identity attributes from facial images. We further confirmed the ability of the DM to evade recognition systems using artificial intelligence-powered re-identification algorithms. Moreover, use of the DM increased the willingness of patients with ocular conditions to provide their facial images as health information during medical treatment. These results indicate the potential of the DM algorithm to protect the privacy of patients' facial images in an era of rapid adoption of digital health technologies.

SUBMITTER: Yang Y

PROVIDER: S-EPMC9499857 | biostudies-literature | 2022 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A digital mask to safeguard patient privacy.

Yang Yahan Y Lyu Junfeng J Wang Ruixin R Wen Quan Q Zhao Lanqin L Chen Wenben W Bi Shaowei S Meng Jie J Mao Keli K Xiao Yu Y Liang Yingying Y Zeng Danqi D Du Zijing Z Wu Yuxuan Y Cui Tingxin T Liu Lixue L Iao Wai Cheng WC Li Xiaoyan X Cheung Carol Y CY Zhou Jianhua J Hu Youjin Y Wei Lai L Lai Iat Fan IF Yu Xinping X Chen Jingchang J Wang Zhonghao Z Mao Zhen Z Ye Huijing H Xiao Wei W Yang Huasheng H Huang Danping D Lin Xiaoming X Zheng Wei-Shi WS Wang Ruixuan R Yu-Wai-Man Patrick P Xu Feng F Dai Qionghai Q Lin Haotian H

Nature medicine 20220915 9

The storage of facial images in medical records poses privacy risks due to the sensitive nature of the personal biometric information that can be extracted from such images. To minimize these risks, we developed a new technology, called the digital mask (DM), which is based on three-dimensional reconstruction and deep-learning algorithms to irreversibly erase identifiable features, while retaining disease-relevant features needed for diagnosis. In a prospective clinical study to evaluate the tec ...[more]

PMID: 36109638

Similar Datasets

Project description:ImportanceDigital technology is part of everyday life. Digital interactions generate large amounts of data that can reveal information about the health of individual consumers (the digital health footprint).ObjectiveΤo describe health privacy challenges associated with digital technology.Design, setting, and participantsFor this qualitative study, In-depth, semistructured, qualitative interviews were conducted with 26 key experts from diverse fields in the US between January 1 and July 31, 2018. Open-ended questions and hypothetical scenarios were used to identify sources of digital information that contribute to consumers' health-relevant digital footprints and challenges for health privacy. Participants also completed a survey instrument on which they rated the health relatedness of digital data sources.Main outcomes and measuresHealth policy challenges associated with digital technology based on qualitative responses to expert interviews.ResultsAlthough experts' ratings of digital data sources suggested a possible distinction between health and nonhealth data, qualitative interviews uniformly indicated that all data can be health data, particularly when aggregated across sources and time. Five key characteristics of the digital health footprint were associated with health privacy policy challenges: invisibility (people are unaware of how their data are tracked), inaccuracy (data in the digital health footprint can be inaccurate), immortality (data have no expiration date and are aggregated over time), marketability (data have immense commercial value and are frequently bought and sold), and identifiability (individuals can be readily reidentified and anonymity is nearly impossible to achieve). There are virtually no regulatory structures in the US to protect health privacy in the context of the digital health footprint.Conclusions and relevanceThe findings suggest that a sector-specific approach to digital technology privacy in the US may be associated with inadequate health privacy protections.

Project description:BackgroundIn hospitals, digital versions of dry-erase whiteboards are increasingly becoming more common. One of the purposes with such whiteboards is to support coordination of care by augmenting visibility and availability of clinical information. However, clinical information usually concerns patients and is regarded as sensitive personal health information, meaning that it should be access controlled. The purpose of this study is to explore how digital whiteboards can be designed for supporting coordination of care, by providing clinicians with useful information in a usable way, and at the same time protect patient privacy.MethodsA demo application was designed, demonstrated and evaluated iteratively. In total, 15 professional ward nurses role-played a scenario in which the application played a central part. Afterwards, the participants were interviewed. All interviews were recorded, transcribed verbatim, and analysed qualitatively.ResultsThe participants valued having updated clinical information presented on a digital whiteboard, even if the information was de-identified and abstracted. According to the participants, such information could possibly improve inter-departmental communication, reduce the number of electronic health record-logins, and make nurses more rapidly aware of new information. The participants expected that they would be able to re-identify much of the de-identified information in real situations based on their insight into their patients' recent and expected care activities. Moreover, they also valued being able to easily access more detailed information and verify patient identities. While abstraction and de-identification was regarded to sufficiently protect the patients' privacy, the nurses also pointed out the importance of having control over what can be seen by other patients and passers-by if detailed medical information was accessed on a digital whiteboard.ConclusionsPresenting updated information from patient care activities on a digital whiteboard in a de-identified and abstracted format may support coordination of care at a hospital ward without compromising patient privacy.

Dataset Information

A digital mask to safeguard patient privacy.

Publications

A digital mask to safeguard patient privacy.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets