AI helps Mount Sinai organize and unlock massive unused surgical data

Today there can be significant variability in surgical outcomes – not only in different parts of the world but also within the same hospital – depending on complications, readmissions and operative time, with a direct impact on patient care and hospital economics.

Problem

While hospitals understand that there is inherent variability in outcomes, ranging from postoperative complications, re-operations, re-hospitalizations, length of stay and more, the solution is not clear. Why is it like this? Some experts say this points directly to the data. Data are missing from the hospital analysis to assess outcomes.

Proposal

Dr. Ketan Badani is the Vice Chairman of Urology and Robotics Operations at Mount Sinai in New York City. He understood this problem very well. And they turned to the vendor cheater for help in solving the problem.

Theatre is a health IT company that leverages proprietary AI to tackle disparities and variability in surgery and improve outcomes.

“Today, there is no way to routinely and automatically capture all minimally invasive and robotic surgical procedures,” Badani said. “Existing technologies require staff to remember to press record, and then usually require a thumb drive to download the video from the operating room camera system and upload it to the hard drive.

He further added, “The video needs to be structured for any meaningful analysis to take place.” “This process is time-intensive and adds friction to something that technology can solve.”

The new AI platform automates the entire process without adding cameras or sensors to the OR. SaaS technology automatically and routinely captures all minimally invasive and robotic surgical video, identifies it, and structures the video with procedural steps. It lists interaction events (for example, bleeding), safety milestones, procedure complication, and more.

Badani explained, “It goes beyond simply structuring procedural steps – it also analyzes the complexity of each case, when an intraoperative event such as bleeding occurs, when safety milestones are achieved, when the camera is out of the body Happens and a lot more happens.”

He continued, “To truly understand the impact of intraoperative techniques, instruments, procedure complexity and more, and how they impact patient recovery, you need to link surgical video to patient outcomes, which are placed in the EHR system.

The EHR contains a postoperative note, which is a written document of what happened during the procedure. However, because these notes are made retrospectively, they are often not entirely accurate.

“This is a widely reported issue in the industry and it is important that we ground ourselves in truth and find a new way to structure our surgical data in a fair and accurate manner and in real time, so that we can make the most of the data. ensure timeliness, Badani said.

“The AI ​​platform addresses this issue by linking surgical video to patient outcomes through one-way integration with the EHR, helping us to ultimately understand, for example, which surgical practices deliver optimal outcomes. where there may be an opportunity to standardize a certain practice across a hospital system to reduce variability in postoperative complications, and in what ways we can improve surgical quality,” he said.

meet the challenge

Mount Sinai installs theater technology ahead of the Society of Urologic Robotic Surgeons (SURS) Annual Meeting, held December 9-10, 2022 at Mount Sinai Hospital. Two live procedures were broadcast from the operating room to an auditorium filled with more than 300 surgical attendees. , who were able to view the surgery in real time and interact live with the surgeon.

“For the first time, using AI technology, these operations were streamed with real-time, AI-driven annotations generated by the Surgical Intelligence Platform,” Badani recalled. “Featuring annotations such as surgical steps, intraoperative events and safety milestones, this information was transmitted during surgery, in a completely accurate manner, along with the surgical video.

“This was the first time this capability was demonstrated at a surgical conference and demonstrated the vendor’s ability to use AI to power the structuring of surgical video in real time with high accuracy,” he added. Said.

He said the technology has gone a step further — adding patient outcomes after the operation — to help Mount Sinai correlate and better understand how what happens intraoperatively can affect recovery. So that staff can improve patient outcomes across the board.

Result

Mount Sinai has already presented an abstract on the use of the theater’s surgical intelligence platform technology at the American Urology Association annual meeting in May 2023.

“We believe the use of AI has enormous potential to transform surgical care today,” Badani said. “In the field of urology, surgical robots are already used every day to augment our efforts, helping us perform minimally invasive operations with greater precision using more agile equipment.

“Although hardware innovation in OR has improved significantly throughout my career, it has largely stopped there,” he continued. “But now, with this AI, a positive digitization of the OR has arrived.”

There is an enormous amount of data left on the OR floor every day, literally hours and hours of surgical video, that are not captured nor analyzed to identify trends, patterns and ways to improve patient care, he said. Analyzed, the industry is hurting itself.

“This cannot be done manually – we need the help of technology,” he said.

“And this technology needs to be designed thoughtfully,” he added. “It needs to be clinically relevant, have the highest security and privacy standards in the industry, and not be tied to any specific camera system or device, but rather be agnostic to what we already have, so that surgeons and hospitals can May help to prepare better for any particular. patient recovery and help surgeons make the best decisions for their patients.”

advice for others

“First and foremost, any AI technology you are considering using in the OR must receive the highest privacy and security certifications in the industry – HITRUST and SOC2TypeII,” Badani advised. “We are dealing with highly confidential information, and it needs to be treated as such.

“Second, the AI ​​needs to be at least as accurate as a human, ideally more, and it needs to draw conclusions without significant delay,” he continued. “The insights provided must be clinically relevant, actionable and digestible to enable health systems to improve the care of their patients.”

He added that not all AI systems provide these important assurances and that it is up to hospital and health system workers to be diligent in finding the right ones.

They concluded, “The manual effort to record, catalog, and annotate surgical videos is highly labor intensive.” “So much so that it doesn’t necessarily happen in most institutions. Allowing a digital platform to organize and analyze surgical video is critical for hospitals and surgeons to access this powerful and untapped data.

Follow Bill’s HIT coverage on LinkedIn: Bill Siwicki
Email him at: bsiwicki@himss.org
Healthcare IT News is a HIMSS Media publication.