AI-based image redaction guards trial patient privacy

By Jenni Spinner

- Last updated on GMT

(Khosrork/iStock via Getty Images Plus)
(Khosrork/iStock via Getty Images Plus)

Related tags Artificial intelligence Patient safety Data integrity Clinical trials Data management compliance

Bioclinica’s Image Redact AI tool enables trials to edit sensitive information from videos, photos and PDFs to ensure compliance and safeguard patient data

Clinical technology provider Bioclinica has launched Image Redact AI, an artificial intelligence (AI) based technology that enables clinical trials to redact sensitive patient identifiers from photos, videos and PDFs. While in the past researchers have found it challenging to ensure videos fully comply with patient privacy requirements (risking the incurrence of costly penalties and downstream issues), Image Redact AI’s technology reportedly makes it possible to do, quickly and effectively.

Bioclinica’s chief innovation officer Dan Gebow, PhD, told Outsourcing-Pharma that in addition to potential risk of having to pay for non-compliance of privacy requirements, failure to protect patient information could lead to damage to a sponsor’s reputation.

Bioclinica Image Redact AI safeguards sensitive clinical trial data by automatically redacting patient identifiers from videos, photos, and PDFs​,” he explained. “This solution leads the industry with its ability to pair a high level of AI-driven de-identification with the human oversight of an experienced quality control team; this combination helps ensure videos and photos comply with 21 CFR Part 11, EU GDPR, and other privacy regulations​."

Gebow said before a video, photo or PDF is uploaded into the system, Image Redact AI prescreens images to verify file type and size, then quickly conducts the de-identification process to remove all sensitive patient information. Next, the company’s image quality control technicians perform a visual QC review.

This two-step process confirms complete de-identification before the image can be made available​,” he told us.

While other products currently available purport to screen clinical patient images, these products unfortunately tend to fall short in fully protecting patient information.

For some research it is necessary to see parts of the face, such as the upper lip, forehead, or the color of the skin; in these instances, a sponsor’s only previous option was to perform the redaction themselves​,” Gebow said. “This manual process is error-prone and time-intensive, and it can consume valuable research dollars​.”

The introduction of Image Redact AI comes after Bioclinica’s acquisition of the Saliency platform, which delivers custom AI models faster and more accurately.

After evaluating a variety of medical imaging AI platforms, we knew the Saliency platform was and is head and shoulders above others in the market as far as its ability to deliver value for our clients​,” Gebow related. “Our acquisition of Saliency empowers industry stakeholders with the absolute latest in medical imaging technology by delivering custom AI models faster and with more accuracy​.”

The Image Redact AI platform uses proprietary algorithms to quickly build and train AI models from a small number of de-identified images; these newly created models can then be used to accurately and efficiently screen, redact, or interpret medical images to support a wide range of therapeutic areas. This capability will be embedded into Bioclinica’s imaging solutions in accordance with EU GDPR and other privacy regulations.

This advancement is one of many that our innovation team has in our pipeline to accelerate the pace of clinical trials, increase data integrity, and protect patient privacy​,” Gebow added. “We are looking forward to releasing these related enhancements to our fellow researchers over the coming months​.”

Related news

Show more

Related products

show more

More Data, More Insights, More Progress

More Data, More Insights, More Progress

Content provided by Saama | 04-Mar-2024 | Case Study

The sponsor’s clinical development team needed a flexible solution to quickly visualize patient and site data in a single location

Using Define-XML to build more efficient studies

Using Define-XML to build more efficient studies

Content provided by Formedix | 14-Nov-2023 | White Paper

It is commonly thought that Define-XML is simply a dataset descriptor: a way to document what datasets look like, including the names and labels of datasets...

Related suppliers

Follow us

Products

View more

Webinars