A groundbreaking artificial intelligence (AI) tool has been developed by a team of researchers from Mass General Brigham and Dana-Farber Cancer Institute, offering a noninvasive method to predict the progression of oropharyngeal cancer, a type of head and neck cancer. This innovation promises to guide treatment decisions by identifying patients who may require more aggressive interventions. The findings have been published in the Journal of Clinical Oncology.
The AI tool, created under the leadership of Dr. Benjamin Kann, a radiation oncologist and member of the Artificial Intelligence in Medicine (AIM) Program, is designed to predict whether a patient’s cancer will spread, thus determining the necessity for intensive treatment strategies. “Our tool may help identify which patients should receive multiple interventions or would be ideal candidates for clinical trials of intensive strategies such as immunotherapy or additional chemotherapy,” said Dr. Kann. He further noted, “Our tool can also help identify which patients should undergo de-intensification of treatment, such as surgery alone.”
Understanding the Need for Precision in Cancer Treatment
Treatments for oropharyngeal cancer often involve a combination of surgery, radiation therapy, and chemotherapy, which can be challenging for patients to endure and may result in long-term adverse effects. Therefore, accurately identifying which patients require more or less intensive treatment is crucial. A key factor in this decision-making process is the presence of pathologic extranodal extension (ENE), which occurs when cancer cells spread beyond the lymph node into surrounding tissue. Currently, ENE can only be confirmed through surgical removal and examination of lymph nodes.
To offer a pre-treatment assessment method, Dr. Kann and his colleagues developed an AI-based tool that analyzes imaging data from computed tomography (CT) scans. This tool predicts the number of lymph nodes with ENE, providing important prognostic information about the patient’s condition and potential benefits from intensified therapy.
Integration and Validation of the AI Tool
The AI tool was tested on imaging scans from 1,733 patients with oropharyngeal carcinoma. It successfully predicted uncontrolled cancer spread and poor patient survival outcomes. By integrating the AI’s insights with existing clinical risk predictors, the researchers achieved improved risk stratification, leading to more accurate predictions of survival and cancer spread for individual patients.
“The AI tool enables the prediction of the number of lymph nodes with ENE, which could not be done before, and shows that it is a powerful, novel prognostic biomarker for oropharyngeal cancer that could be used to improve the current staging scheme and treatment planning,” said Dr. Kann.
Implications for Future Cancer Treatment
This development represents a significant advancement in the precision of cancer treatment. By enabling more tailored treatment plans, the AI tool could reduce unnecessary interventions for some patients while ensuring that others receive the aggressive treatment they need. The potential to incorporate such AI tools into clinical practice could revolutionize how oncologists approach cancer treatment, emphasizing personalized medicine.
Beyond its immediate clinical applications, the research underscores the growing role of AI in healthcare. As AI technologies continue to evolve, they hold the promise of transforming various aspects of medical diagnostics and treatment planning, potentially leading to better patient outcomes and more efficient healthcare systems.
Research Team and Funding
The study was conducted by a multidisciplinary team including Zezhong Ye, Reza Mojahed-Yazdi, Anna Zapaishchykova, Divyanshu Tak, and several others, with contributions from institutions across North America and Europe. The research received financial support from the National Institutes of Health, the European Union—European Research Council, the Radiological Society of North America, and the Canadian Institutes of Health Research.
Funding acknowledgments include grants from NIH (U24CA194354, U01CA190234, U01CA209414, R35CA22052; K08: DE030216), the European Union—European Research Council (866504), RSNA (RSCH2017), and CIHR (426366).
This study, titled “Automated Lymph Node and Extranodal Extension Assessment Improves Risk Stratification in Oropharyngeal Carcinoma,” marks a pivotal step in integrating AI into oncological practice, setting the stage for future innovations in cancer care.
