AI predicts heart injury following lung cancer treatment

Researchers from Brigham and Women’s Hospital have successfully mapped multiple classes of arrhythmia risk following exposure to radiation during lung cancer treatment, according to a study published today in JACC: CardioOncology.

The research team emphasized that arrhythmias are common in patients undergoing radiotherapy for non-small cell lung cancer (NSCLC). Because of the heart and lungs’ proximity, alongside the propensity of NSCLC tumors to form near or around the heart, the heart can be at risk of radiation dose spillage during cancer treatment.

Previous research has demonstrated that the heart’s exposure to radiotherapy is significantly associated with cardiac issues, but the researchers sought to explore the risk for different types of arrhythmias in more depth.

“Radiation exposure to the heart during lung cancer treatment can have very serious and immediate effects on a patient’s cardiovascular health,” said corresponding author Raymond Mak, MD, of the department of radiation oncology at Brigham and Women’s Hospital, in a press release. “We are hoping to inform not only oncologists and cardiologists, but also patients receiving radiation treatment, about the risks to the heart when treating lung cancer tumors with radiation.”

To explore the relationship between lung cancer therapy and arrhythmia risk, the research team conducted a retrospective analysis of data from 748 patients treated with radiation for locally advanced NSCLC. From there, various arrhythmia subtypes — including atrial fibrillation, atrial flutter, other supraventricular tachycardia, bradyarrhythmia, and ventricular tachyarrhythmia or asystole — were classified using AI.

The analysis revealed that arrhythmia risk varied significantly depending on the pathophysiology and cardiac structures exposed to radiation.

Within the patient cohort, approximately one out of every six experienced at least one grade 3 arrhythmia — a serious subtype that often requires intervention and hospitalization — within two years of radiotherapy.

Of those who experienced arrhythmias, nearly one-third also went on to suffer a major adverse cardiac event.

While the study did not take into account all possible heart complications that could result from lung cancer treatment, the research team emphasized that the findings could help provide insight into potential pathophysiological pathways to minimize cardiac toxicity following radiotherapy.

The researchers further noted that such information could be useful to radiation oncologists and cardiologists working together to reduce radiation exposure to the most at-risk parts of the heart, potentially mitigating adverse events and advancing precision medicine.

“An interesting part of what we did was leverage artificial intelligence algorithms to segment structures like the pulmonary vein and parts of the conduction system to measure the radiation dose exposure in over 700 patients. This saved us many months of manual work,” said Mak. “So, not only does this work have potential clinical impact, but it also opens the door for using AI in radiation oncology research to streamline discovery and create larger datasets.”

Shania Kennedy has been covering news related to health IT and analytics since 2022.