Artificial Intelligence Provides Precise Treatment Recommendations
Artificial intelligence indicates that patients with head and neck cancer could be receiving more radiation than necessary.
Source: Getty Images
By - Case Western Reserve University researchers are using artificial intelligence to identify which patients with certain head and neck cancers would benefit from reducing the intensity of treatments, including radiation therapy and chemotherapy.
Head and neck cancers total more than a half-million cases and 300,000 death a year, making it them the sixth leading cancer worldwide, according to the World Health Organization.
Although most patients with human papillomavirus (HPV)-driven head and neck cancer benefit from aggressive treatment, the team said their research revealed a significant group of patients is receiving more aggressive therapy than necessary to achieve positive outcomes.
However, clinicians cannot easily make that distinction by looking at the tissue scans, creating the need for artificial intelligence methods. Without the technology, all patients with these cancers are treated with a full course of chemo and radiation.
“We have been overtreating many patients with chemotherapy and radiation that they do not need because we didn’t have a way to find out which patients would benefit from de-escalation,” Center for Computational Imaging and Personal Diagnostics (CCIPD) director and the Donnell Institute Professor of Biomedical Engineering at the Case School of Engineering, Anant Madabhushi, said in a press release.
“We’re saying that now we do — and that someday physicians could modulate the way we care for people and not just give the standard high dose of radiation to everyone who comes through the door.”
Additionally, reducing radiation for patients could lead to fewer side effects such as dry mouth, swallowing dysfunction, and taste changes.
“There are already national clinical trials ongoing investigating the reduction of radiation therapy and chemotherapy intensity in favorable HPV positive oropharynx cancer patients,” said Shlomo Koyfman, director of head and neck and skin cancer radiation at Cleveland Clinic and a study collaborator.
“However, properly selecting the ideal patients for this treatment reduction has been a challenge. This imaging classifier can help us better select patients for these novel treatment paradigms.”
Using AI tools like those they developed over the last decade, researchers asked the computer to analyze digital images of tissue samples taken from 438 patients with a type of head and neck cancer, known as HPV-associated oropharyngeal squamous cell carcinoma (OPCSCC) from six hospital systems.
The computer program successfully detected a subset of patients who could benefit from a significantly reduced dose of radiation therapy. According to the research team, their next step is to test the AI method’s accuracy in clinical trials.
This latest research builds on previous research by the CCIPD in developing novel imaging biomarkers for risk stratification and outcome prediction of head and neck cancer.
