Among patients with colorectal cancer that has spread to lymph nodes, a deep learning marker can identify one-third with an excellent prognosis and therefore no need for adjuvant chemotherapy. Dual-agent chemotherapy is the current standard of care for these patients and can lead to serious side effects and even death.
New research shows how deep learning can be used to guide the choice of chemotherapy after surgery for patients with colorectal cancer. In particular, many patients currently being treated with adjuvant chemotherapy can safely avoid such treatment.
Applying the method in clinical practice may thus reduce the morbidity and costs associated with colorectal cancer treatment and perhaps also prevent deaths by making it possible to offer chemotherapy earlier to patients who really need it.”
Professor Håvard E. Greger Danielsen
Danielsen is the leader of the research study, the director of the Institute of Cancer Genetics and Informatics (ICGI) at Oslo University Hospital, a professor in the Department of Informatics (IFI) at the University of Oslo and a visiting professor at the University. of Oxford.
No treatment benefit
Colorectal cancer is one of the most common types of cancer, especially in western countries. The tumor is usually resected, and patients at increased risk of cancer recurrence and death are usually offered adjuvant chemotherapy.
– Because current methods cannot accurately predict which patients need chemotherapy, the current standard of care is to offer adjuvant chemotherapy to large patient groups that include many patients who will not benefit from the treatment, explains Danielsen.
For patients in whom the cancer has spread to the lymph nodes, the current standard of care is dual-agent chemotherapy, as it has been shown to benefit more patients than less aggressive treatments, but it is recognized that about half of the patients would not have needed adjuvant chemotherapy at all. Neuropathy is a common side effect of dual-agent chemotherapy and can sometimes be both severe and prevalent years after treatment has ended. In some cases, chemotherapy can even lead to death.
Use deep learning
Two years ago, a study published in The Lancet demonstrated that deep learning can be used to predict which patients are most likely to die from colorectal cancer after surgery. Building on this discovery, research recently published in The Lancet Oncology shows how to integrate the deep learning marker with markers currently used in clinical practice and that the combination can be used to better deliver adjuvant chemotherapy by tailoring treatment to patients. patients who actually need this.
Among patients with colorectal cancer that has spread to lymph nodes, new adjuvant chemotherapy screening method may identify one-third of patients who should not receive adjuvant chemotherapy, even if the current standard of care is dual chemotherapy agent. Indeed, these patients have excellent prognoses, similar to those without lymph node spread who are not treated with adjuvant chemotherapy by current standards of care. In fact, treating this third with dual-agent chemotherapy should result in a similar number of treatment-related deaths to the number of cancer deaths averted by the treatment.
Dr. Andreas Kleppe notes that not treating these patients with adjuvant chemotherapy will allow them to recover more quickly from cancer treatment and they won’t have to experience such significant side effects. Kleppe is the first author of the new research paper, a researcher at ICGI and an associate professor at IFI.
More individualized treatment
The new method is also designed to indicate how aggressive adjuvant chemotherapy should be and to guide treatment decisions for patients with colorectal cancer without spread to lymph nodes. Some patients without spread are recommended for adjuvant chemotherapy under the current standard of care, but only a fraction of them will benefit from the treatment as most do not need adjuvant therapy, while a few may possibly benefit more aggressive adjuvant chemotherapy such as dual agent chemotherapy.
– More accurate determination of patients who need adjuvant chemotherapy and the aggressiveness of treatment can improve the quality of life for many patients and possibly prevent some cancer deaths, Kleppe says.
Chemotherapy entails significant financial costs related to drugs, medical personnel and sick leave. Application of the new method to enable more individualized selection of adjuvant chemotherapy will therefore improve the cost-benefit ratio of colorectal cancer treatment.
The new method was developed and validated as part of an IKTPLUSS Lighthouse program funded by the Research Council of Norway, DoMore!, which aimed to apply artificial intelligence to improve current cancer treatment. The method is ready for application in clinical practice and has recently been CE marked for use in European countries.
Kleppe, A. et al. (2022) A clinical decision support system optimizing adjuvant chemotherapy for colorectal cancers by integrating deep learning and disease staging markers: a development and validation study. Lancet Oncology. doi.org/10.1016/S1470-2045(22)00391-6.