As debates surrounding AI continue across industries, researchers at Cedars-Sinai Medical Center are using the technology to help improve cancer treatment outcomes.
According to Cedars-Sinai, investigators at the California-based health system co-developed an AI-powered platform to predict, on an individual basis, which of two chemotherapy options may be more effective for pancreatic cancer patients.
Andrew Hendifar, MD, medical director of Pancreatic Cancer at Cedars-Sinai Cancer and first author of the study, noted that a major challenge in treating advanced pancreatic cancer is that there is currently no conclusive data showing which of the two approved chemotherapy regimens works best for each patient.
As a result, physicians often begin treatment with one regimen, monitor the patient’s response, and switch therapies if necessary. Hendifar noted that the approach can be harmful because ineffective chemotherapy may further weaken a patient’s health instead of improving it.
“If the chance that a particular treatment will benefit a patient is 50-50, which is quite common in cancer therapy, then this may serve as a powerful tool to aid physician and patient decision-making,” Hendifar said. “And we can train the digital tool not just to choose between two available treatments, but to choose between multiple available treatments.”
Developing The AI-Powered Cancer Tool
Researchers developed the tool using the Computational Histology Artificial Intelligence (CHAI) platform, which analyzes microscope images of tumor tissue collected during biopsies.
The researchers examined tissue samples from 25,000 pancreatic cancer patients who received one of two chemotherapy treatments. Using AI, the researchers analyzed more than 30,000 tissue features and matched them to patient treatment responses to build the predictive tool.
In testing with data from a large clinical trial, the tool successfully predicted how patients would respond to their treatment.
“Unlike most biomarker tests, where you need an extra sample of tissue or blood, this test requires only a scanned image of the patient’s existing biopsy slide,” Hendifar said. “You just send the image electronically and quickly receive a result with the treatment preference. And you don’t just learn which treatment is preferred. You learn how much more effective it is likely to be.”
If validated through additional studies, researchers say the tool could help improve treatment selection across nearly any type of cancer and may eventually compare the effectiveness of treatments such as radiation therapy and surgery.
“This endeavor is an example of applying AI technology to an unmet clinical need, and offers tremendous translational potential,” said Robert Figlin, MD, interim director of Cedars-Sinai Cancer. “It aligns perfectly with our goal of personalizing cancer treatment for our patients and improving outcomes for all.”
How AI Is Transforming Cancer Care
Cedars-Sinai is not the first organization to apply AI to cancer care, but its latest tool adds to a growing wave of innovation in healthcare.
As AFROTECH™ previously reported, biopharmaceutical company Bristol Myers Squibb and Microsoft have partnered to use Microsoft’s AI-enabled radiology platform to detect lung cancer at earlier stages. Lung cancer causes nearly 125,000 deaths annually in the United States, with disproportionately higher rates among medically underserved populations who are less likely to receive appropriate screening, according to a Bristol Myers Squibb press release.
The agreement enables the deployment of FDA-cleared AI radiology algorithms through Microsoft’s Precision Imaging Network, AFROTECH™ noted. The tools analyze X-ray and CT scans to help detect lung nodules that can be difficult to identify.
The technology is also expected to improve workflows for radiologists and expand access across the majority of U.S. hospitals.
“This new Microsoft collaboration reflects our commitment to breaking down barriers and addressing healthcare challenges,” Andrew Whitehead, VP and head of population health at Bristol Myers Squibb, said in the release.
“At BMS, health equity is not a standalone initiative—it is embedded in everything we do. By deploying this solution and bringing advanced AI tools to the front lines, together we will help to address health disparities in lung cancer,” he added.
