How AI is reshaping cancer care and diagnosis

by MMC
0 comment

Artificial intelligence could have profound implications in the field of oncology, concluded panelists speaking to journalist and moderator Katie Couric at the Constellation Forum 2023 in Northwell Health last week.

Dr. Richard Barakat, chief medical officer and executive director of the Cancer Services and Research Division at Northwell Health, noted that the use of AI in imaging will assist radiologists and serve as a clinical “co-pilot.” designed to help avoid errors, such as false negative mammograms.

“The key thing we need to focus on with artificial intelligence is providing those backup systems,” he said. “But I think the role of AI is much more than that.”

Barakat said another area his team plans to use AI is to help match cancer clinical trials. He added that AI could also help predict the side effects of some of these treatments, allowing oncologists to try to proactively mitigate them.

Andy Moye, CEO of Paige.AIan AI-based diagnostic platform for oncologists and pathologists, agreed that AI is really beneficial in making better diagnoses and reducing human errors.

“(Oncologists) need to start with making the right diagnosis and get it right the first time,” he said. “What we’re striving to do is take these glass slides, these analog instruments, and digitize them, and once they’re digital, you can unlock this vast world of machine learning and AI and everything that comes with it.”

The challenge lies in how this vast volume of data can be stored and analyzed.

“Each slide can hold up to two gigabytes of data, and 30 to 40 million slides are produced each year, perhaps more than that,” Moye said.

“We think about genomic information, clinical laboratory data, your clinical notes – you take all that data and you can build models that then have predictive values ​​and really start to analyze the population health side of things up front.” , did he declare. explain.

This helps determine who in a population might be at greater risk for breast or prostate cancer.

“But downstream, if you get that mammogram, you can get better predictive results,” he said. “These are the kinds of things where we see a really bright future.”

Daisy Wolf, investment partner at venture capital firm Andreessen Horowitzsays AI can help manage spiraling healthcare costs by reducing the number of tasks currently performed by clinicians.

“The very high cost of healthcare is due to many labor shortages, and AI will help us very soon by removing work from the human plate,” she explains. “And then every patient will have an amazing AI doctor and nurse in their pocket, who will complement their real doctor.”

She added that while ChatGPT wasn’t explicitly trained in medicine, from her perspective he’s still “better than the average person with Google,” and she was impressed by the progress they’ve made.

“I am very optimistic about the impact of technology and AI on human health,” Wolf said.

Moye nevertheless addressed the issue of implicit bias in AI, emphasizing that every clinician and patient should have access to what he called the “nutrition label” for an AI model.the datasets on which the model was trained.

“If you have this model that comes out, especially these large language models that are built on billions and billions and almost billions of parameters“There are implicit biases in human nature, and these big language patterns are built on that,” Moye said. “It’s unfortunately going to reflect a lot of those things.”

From another perspective, Barakat highlighted that AI could help address the biases generated in many clinical trials.

“The reality is that the patients who benefit from the most advanced new therapies are those who know how to get to the right places, and underserved and minority patients do not benefit from the most advanced clinical trials,” he said. he declares.

He said what would be helpful would be if clinical trials were open to everyone and health professionals could learn from everyone because there are “clearly” genetic reasons that differentiate some patients.

“One of the deadliest forms of brain cancer, glioblastoma, is almost unknown among African Americans.there’s a reason for that,” he said. “There’s a genetic reason for that. Let’s learn this and apply this to other populations. It’s bidirectional. We must learn from everyone. »

Barakat added that despite the promise of AI, it is critical to understand that only some have the ability to access generative AI tools, highlighting the importance of healthcare professionals understanding the technology.

“We can’t assume that all this great technology is available to everyone,” he said. “My advice is to do our best so that we can guide you and allow us to understand AI to get patients where they belong.”

You may also like

Leave a Comment

The news website dedicated to showcasing Africa news is a valuable platform that offers a diverse and comprehensive look into the continent’s latest developments. Covering everything from politics and economics to culture and wildlife conservation

u00a92022 All Right Reserved. Designed and Developed by PenciDesign