Tool predicts nerve damage from breast cancer treatment

Many women treated for breast cancer using taxanes, a type of cytostatic drug, often experience side effects in the nervous system. Researchers at Linköping University have developed a tool that can predict the risk level for each individual. The tool could help doctors adapt treatment to avoid persistent side effects in those at the greatest risk.

The work is published in the journal npj Precision Oncology in a paper titled "Prediction models of persistent taxane-induced peripheral neuropathy among breast cancer survivors using whole-exome sequencing."

More and more people are becoming cancer survivors. But even if they have survived the disease, an increasing number still suffer from the side effects of cancer treatment. In a study from Linköping University, researchers studied the side effects of taxanes, a chemotherapy drug used to prevent breast cancer recurrence. The drawback of the treatment is that some patients suffer nerve damage as a side effect.

"Side effects in the form of nerve damage are very common after treatment with taxanes for breast cancer, and they often persist for several years. For those affected it is extremely stressful, and it has a major impact on quality of life. So it is a major clinical problem, which has received more attention in recent years, but there has been no way to know which individuals are at greatest risk of side effects," says Kristina Engvall, who recently completed her Ph.D. at Linköping University and is a doctor at the oncology clinic at Ryhov County Hospital in Jönköping.

The researchers began by carefully surveying side effects in patients treated for breast cancer with either docetaxel or paclitaxel, the two most common taxane drugs.

Between two and six years had passed since treatment. A total of 337 patients were asked to describe the severity of the nerve damage they experienced, or peripheral neuropathy as it is also called. Most common was cramps in the feet, which more than one in four patients had. Other side effects included difficulty opening a jar, numbness in feet, tingling in feet and difficulty climbing stairs.

The researchers sequenced the patients' genes and then built models that link genetic characteristics to various side effects of the taxane treatment. This allows the models to predict the risk of nerve damage. This type of model, known as a prediction model, has not previously existed for taxane-induced peripheral neuropathy. The researchers succeeded in modeling the risk of persistent numbness and tingling in feet.

The two models were able to separate the patients into two clinically relevant groups: one with a high risk of persistent side effects, and one that corresponded to the frequency of peripheral neuropathy in the normal population.

The researchers used two-thirds of the data to train the models through machine learning. They were then able to use the remaining third of the patients to validate the models, which was found to work very well. Validating that the models also work in a different group is an important step.

"This is the first time a prediction model has been developed that can predict the risk of nerve damage from taxane treatment. Women who have been treated with taxanes after breast cancer surgery make up a very large group in health care worldwide, so this is a major and clinically relevant problem," says Henrik Gréen, professor at Linköping University, who led the study.

"This can be a tool to individualize treatment, and not only to look at the benefits, but also to look at the risks for the individual patient. Today we are so good at treating breast cancer that we need to focus more on the risk of complications and side effects that affect the patient long after treatment," says Engvall.

In the long term, the prediction model could be adopted as routine in health care. But first, research is needed in order to find out whether the prediction model also works well in other population groups than the Swedish population.

"It also emerged that three of the five symptoms we focused on are so biologically complex that we could not model them. These include, for example, difficulty opening cans. Opening a can involves both motor and sensory nerves, which makes it very difficult to predict which individuals are at greatest risk of developing that symptom," says Gréen.