Cedars-Sinai Researchers Develop AI Tool to Predict Chemotherapy Treatment for Cancer Patients

The newly developed AI tool is designed to analyze digital images of tumor biopsy slides and evaluate microscopic tissue patterns associated with how tumors respond to different treatments.

Researchers at Cedars-Sinai Health Sciences University have developed an artificial intelligence–based tool aimed at predicting which chemotherapy regimen may be more effective for patients with advanced pancreatic cancer.

The newly developed AI tool is designed to analyze digital images of tumor biopsy slides and evaluate microscopic tissue patterns associated with how tumors respond to different treatments.

As per reports, pancreatic cancer treatment typically involves choosing between two commonly used chemotherapy combinations, FOLFIRINOX and Gemcitabine-based therapies. Currently, oncologists often select treatment based on clinical judgement because there are limited biomarkers available to predict which regimen will work best for individual patients.

The AI system seeks to assist clinicians in selecting first-line chemotherapy options for patients diagnosed with pancreatic ductal adenocarcinoma.

According to the researchers, the model was trained by analyzing tissue characteristics in samples from 25,000 pancreatic cancer patients who had received one of the two chemotherapy regimens.

By leveraging computational histology, the system’s AI capabilities evaluated more than 30,000 microscopic features in digitized pathology slides.

By correlating these features with treatment outcomes, the model identified patterns that may indicate whether a patient is more likely to respond to one chemotherapy regimen over another.

Furthermore, when the researchers tested the tool by using data from a large clinical trial involving the two pancreatic cancer treatment regimens, the system was able to predict each patient’s response to the treatment received.

The researchers further noted that the platform could potentially be applied to other solid tumor types and to compare different treatment modalities, including chemotherapy, radiation therapy, and surgery.

Commenting on the new New AI tool, Andrew Hendifar, MD, medical director of Pancreatic Cancer at Cedars-Sinai Cancer said, “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, 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 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. And we can train the digital tool not just to choose between two available treatments, but to choose between multiple available treatments,” he added.

Stay tuned for more such updates on Digital Health News