Breast cancer is the most common tumour disease in women, and it is estimated that one in every eight women in the Western world will suffer from the disease during their lifetime.
“It is well known that knowledge of the spread of breast cancer to the axillary lymph nodes provides important information on the course of the disease, and lymph nodes are routinely removed for investigation. Around 70 per cent of patients are found to have healthy lymph nodes, and surgery could be avoided if they could instead be assessed in a different way”, says Lisa Rydén, professor of surgery with a focus on breast cancer at Lund University and consultant at Skåne University Hospital.
Gene expressions from approximately 3 000 breast tumours have been studied together with other tumour- and patient-related factors concerning the link between the spread of disease to the lymph nodes. The results were published in Clinical Cancer Research, and showed that the size of the tumour and the invasion of cancer cells into vessels were significant factors in predicting the spread of disease.
In patients with hormone-sensitive breast tumours (approximately 80 per cent of all breast cancer), a developed prediction model, based on the tumour’s genetic profile and routinely collected data on tumour characteristics, was able to identify 6-7 per cent more women with healthy lymph nodes than other models.
“It would therefore be possible to reduce the number of lymph node operations by up to 30 per cent in this group if the model were used to predict the spread of disease to the lymph nodes”, noted the authors of the article.
Through artificial neural networks, three prediction models have been produced in a separate study published in BMC Cancer; one to identify healthy lymph nodes (where diagnostic surgery could potentially be avoided), one to identify limited disease in the lymph nodes (where the removal of a small number of diagnostic lymph nodes is sufficient) and one for widespread lymph node disease indicating more extensive surgery or primary oncological treatment with chemotherapy. This study also showed that the prediction model for healthy lymph nodes could have reduced the number of surgical interventions by 30 per cent.
“The results indicate that we may be a step closer to more personalised surgical treatment by using the prediction models as a decision support tool. In order to ascertain the results for clinical use, further studies are required on other patient material to be able to confirm the reliability and precision of the models and independently evaluate our results”, concludes Lisa Rydén.
Publications:
Artificial Neural Network Models to Predict Nodal Status in Clinically Node-Negative Breast Cancer
Prediction of Lymph Node Metastasis in Breast Cancer by Gene Expression and Clinicopathological Models: Development and Validation within a Population Based Cohort
Contact:
Lisa Rydén, professor of surgery with a focus on breast cancer at Lund University and consultant at Skåne University Hospital
+46 46 706-720923
lisa [dot] ryden [at] med [dot] lu [dot] se