New 'digital masks' touted as ways to protect patient privacy

New ‘digital masks’ touted as ways to protect patient privacy

Photo: Al David Sacks/Getty Images

Technologists writing in the journal Nature have created a digital “mask”, dubbed the DM, which they say offers a pragmatic approach to protecting patient privacy in electronic health records and during virtual healthcare visits.

There also appear to be clinical benefits for DM.

The technology is based on real-time 3D reconstruction and deep learning, and aims to retain clinical attributes contained in patient videos, while minimizing access to non-essential biometric information. This is designed for greater personal privacy in clinical practice.

The first experimental results show that with DM, examination videos of patients with eye disease can be accurately reconstructed from 2D videos containing original faces. A comparison of clinical diagnoses showed that ophthalmologists achieved high consistency in obtaining the same diagnosis when using the original videos and the corresponding reconstructed DM videos.

This technology could effectively remove identity attributes and met with a positive response in patients with eye diseases. They have expressed a growing desire to share their personal information and store it digitally with that added layer of biometric protection.


Patient privacy and data use are frequently cited as concerns by patients worried about data breaches. Compared to crude but still widely used options, such as covering identifiable areas with very large bars or completely cropping those areas, DM represents a potentially more sophisticated tool for anonymizing facial images.

The DM selects the relevant features for reconstruction, but it is impossible to reconstruct the original data relevant to patient identification. And compared to other face swap technologies, the DM can obtain quantitative parameters – such as degree of eyeball rotation, eyelid shape parameters, blink rate and rotation frequency – which , according to the authors, could prove essential in the future for intelligently diagnosing a disease or studying the relationships between diseases and certain facial characteristics.

DM can also be applied to telehealth, including automatic online diagnosis and patient triage. The mask can encrypt data before it is submitted to the cloud, allowing clinicians or AI algorithms to review the reconstructed data and allay the concerns of patients whose medical records contain sensitive biometric data.

But the protection of privacy does not equate to the absolute suppression of identity characteristics. According to the Privacy Rule of the Health Insurance Portability and Accountability Act, protecting patient privacy refers to reducing the risk of health information being identified. One of the most important principles is to balance the risk of disclosure against the usefulness of the data.

To this end, the goal of DM is to protect health information as much as possible without compromising the clinician’s need to make a diagnosis.


Trust in the security and privacy of personal health information is beginning to erode, according to the results of a recent survey. Published by the American Medical Association, the study showed that more than 92% of patients believe that privacy is a right and that their health data should not be available for purchase.

Nearly 75% of 1,000 patients surveyed by Savvy Cooperative expressed concern about protecting the privacy of personal health data, and only 20% of patients said they knew the scope of companies and individuals with access to their data .

The survey revealed that an overwhelming percentage of patients demand accountability, transparency and control when it comes to the privacy of health data. Around 94% of patients want companies to be held legally accountable for the use of their health data, while 93% want health app developers to be transparent about how their products use and share patient data. personal health.

Industries are increasingly being sued by consumers over data breaches, but the sector with the biggest rise in litigation is healthcare, according to findings released in April by law firm BakerHostetler.

In fact, healthcare accounts for 23% of lawsuits due to data breaches, according to BakerHostetler. Next come business and professional services with 17%, followed by finance and insurance (15%), education (12%) and manufacturing (10%).

Twitter: @JELagasse
Email the author:

#digital #masks #touted #ways #protect #patient #privacy

Leave a Comment

Your email address will not be published.