NYU Langone adopts Amazon’s palm print scanner for patients

Patient check-in is getting futuristic at NYU Langone Health as patients will soon have the option to use a new palm print scanning technology called Amazon One. 

According to Amazon, the palm scanning technology analyzes palm and vein imagery, recognizing users in less than one second with a 99.9999% accuracy rate. The strategy is purportedly 100 times more accurate than double iris scanning – and, therefore, presumably exponentially more accurate than using traditional demographic identifiers and human verification to ensure the right patients are checking in to the right places at the right time.  

The tool works with AWS cloud architecture, as well as NYU Langone’s Epic Systems EMR platform, to authenticate patient identities. As patients hold their hand over the device, images are immediately encrypted and sent to the AWS cloud, where a unique palm signature is created.   

In a press release on the partnership, which represents Amazon One’s largest third-party rollout to date, Amazon stresses the presence of multiple security controls to protect sensitive data, including encryption, data isolation, and dedicated secure zones with restricted access controls.   

“One of NYU Langone’s goals is to leverage cutting-edge technology to enhance the patient experience,” says Nader Mherabi, executive vice president and vice dean, chief digital, and information officer at NYU Langone. “We make all decisions with our patients in mind first and foremost, and we’re always looking for ways to improve their experience through technology. As with all new initiatives and technology of this scale, we will optimize over time and meet the needs of our patients.” 

The system is built with generative AI (GenAI) with accuracy and privacy in mind, explained Gerard Medioni, Vice President and Distinguished Scientist, AWS. 

“Training Amazon One on millions of synthetically generated images of the palm and the vessels underneath allowed us to boost the system’s accuracy,” he wrote in a 2023 blog introducing the Amazon One product. “To begin with, it quickly generated hands reflecting a myriad of subtle changes, like varying illumination conditions, hand poses, and even the presence of a Band-Aid.”  

“But that’s not all. The images were also automatically ‘annotated,’ which is normally a long and laborious process. This saved time and allowed us to move faster, as we didn’t have to label the pictures and tell the computer that it was looking at the pattern lines of your palm, a scar, or a wedding band. We also trained our system to detect fake hands, such as a highly detailed silicon hand replica, and reject them.” 

The strategy helps solve for some of the hardest problems in identification.  For example, it’s relatively easy for a phone to use facial recognition to match an image of a face to an existing user profile in a one-to-one manner, he said.  

“That’s because if your face is on your phone, it already knows who you are and just verifies that it is you. We call this a one to one mapping,” he wrote. “With Amazon One, we don’t know who you are when you put your hand over the scanner. We need to identify you from other people, and do it fast. And if you are not enrolled, we also need to be able to say, you’re not in the system.” 

With GenAI, the platform can make these determinations quickly and accurately, making it suitable for large-scale applications without having to store data on the local palm scanning device. 

Patients will not be required to use the palm scanning technology, and can still verify their identities using other methods if desired. NYU Langone users will also be able to unenroll if they wish to stop using their palm print, and can request the data to be deleted at any time. 

The health system plans to roll out this new capability to all its facilities soon. Meanwhile, Amazon hopes to bring the technology to more health systems in the near future to simplify patient identification and streamline the check-in process for both consumers and administrative staff.  

Jennifer Bresnick is a journalist and freelance content creator with a decade of experience in the health IT industry.  Her work has focused on leveraging innovative technology tools to create value, improve health equity, and achieve the promises of the learning health system.  She can be reached at [email protected].