AI May Increase Surgical Safety, But Not Everyone Is Into It

A 2016 Johns Hopkins study found that some 250,000 Americans die each year from medical mistakes, making them the third leading cause of death in the US. One reason: during surgeries, errors can be so subtle that there’s little opportunity to spot them, let alone learn from them. However, AI startups are bringing an innovative approach to the healthcare industry that could potentially transform surgical safety.

Bringing the Black Box to Surgery

Adding recording devices to planes in the ’70s drastically reduced aviation accidents. Now, the operating room is applying similar technology. Surgical Safety Technologies (SST), founded by Stanford professor Teodor Grantcharov, uses a combination of cameras, microphones, and a tablet to collect around 500,000 data points per day. This vast amount of data is then fed through a specially-trained AI model that can highlight potential dangers.

Even elements such as the proportion of off-topic conversations happening in the surgery room can reveal valuable clues about what went wrong. This method aims to provide a comprehensive view of the surgical environment, allowing for more effective analysis and prevention of errors.

The Growing Industry of AI in Surgery

The potential of AI to improve surgical outcomes has attracted significant interest and investment. In March, Nvidia and Johnson & Johnson MedTech announced a partnership to collaborate on new AI-powered surgical devices, such as a real-time tumor identification tool. Meanwhile, AI startup Theator helps surgeons rethink their biases, suture choices, and decision-making processes by providing insights into which approaches are statistically safest. This is crucial because sometimes the least-used methods turn out to be the most effective.

Resistance from the Medical Community

Despite the promising potential of AI in enhancing surgical safety, not all surgeons are convinced. Some errors are unavoidable, especially during emergencies. Additionally, many surgeons are concerned that constant tracking of their every movement could lead to lawsuits or other professional penalties. 

SST addresses these concerns by anonymizing all the data it collects to ensure that no healthcare worker can be singled out. “The focus is on how we can build a system that makes it difficult for this to happen,” Grantcharov told the MIT Technology Review. “This is a system issue.”

How AI Tools are Used in Surgery

Implementing AI tools in surgery involves several key steps:

1. Integration of Recording Devices: Install cameras and microphones in the operating room to capture detailed data during surgeries. Ensure that the setup does not interfere with the surgical procedures.
2. Data Collection: Utilize tablets or other devices to gather around 500,000 data points per day. This data includes visual and auditory information, which provides a comprehensive view of the surgical environment.
3. AI Model Training: Feed the collected data through specially trained AI models. These models are designed to analyze the data and highlight potential dangers, such as subtle errors or deviations from best practices.
4. Data Anonymization: To address privacy and legal concerns, anonymize all the collected data. This step ensures that no individual healthcare worker can be identified, focusing on system-level improvements instead.
5. Real-time Analysis and Feedback: Use the AI models to provide real-time analysis and feedback during surgeries. This can help surgeons make more informed decisions and potentially prevent errors before they occur.
6. Post-Surgery Review: After surgeries, review the AI-generated insights to understand what went right and what could be improved. This continuous learning process helps refine surgical techniques and protocols over time.

By following these steps, healthcare providers can leverage AI tools to enhance surgical safety and improve patient outcomes.

Conclusion

AI has the potential to revolutionize surgical safety by providing detailed, real-time insights into the operating room environment. While there are concerns and resistance from some in the medical community, the anonymization of data and focus on system-level improvements offer a promising path forward. As AI technology continues to advance, its integration into surgical practices could lead to significant reductions in medical errors and improvements in patient care.

See also: Google To Launch AI Chatbots Based On Celebrities And Influencers