Artificial intelligence (AI) and related technologies are increasingly prevalent in business and society and are becoming a mainstay in healthcare. These technologies have the potential to transform many aspects of patient care. In this groundbreaking study, artificial intelligence (AI) engineers, together with pathologists, have trained an algorithm to determine which patients with lung cancer have a higher risk of relapse after treatment.
TRACERx: a nine-year longitudinal AI study conducted by Cancer UK
This new study, led by Dr Yinyin Yuan from The Institute of Cancer Research (ICR) is part of the TRACERx (Tracking Cancer Evolution through therapy [Rx]) lung study – a £14 million, nine-year study funded by Cancer Research UK. TRACERx is Cancer Research UK’s single biggest investment in lung cancer research, revealing incredible insights into how tumors evolve and evade treatment, a leading cause of cancer death. The AI tool was able to differentiate between immune cells and cancer cells, enabling researchers to build a detailed picture of how lung cancers evolve in response to the immune system in individual patients.
The new AI tool–developed by researchers at The Institute of Cancer Research, London, in collaboration with scientists at University College London Cancer Institute and the Francis Crick Institute–was trained by pathologists to differentiate immune cells from cancer cells. This allowed the tool to map out areas in tumors where the number of immune cells were high compared to the number of cancer cells. In patients with lung cancer, this enabled researchers to build a detailed picture of how lung cancers evolve in response to the immune system in individual patients.
Why specifically lung cancer?
Lung cancer is often the most difficult cancer to treat and often has the highest mortality rate. Furthermore, according to Dr Yinyin Yuan, new insights from the study have shown that lung cancers can cloak themselves to escape the attention of the immune system–and in doing so can continue to evolve and develop. Cancer’s ability to evolve and return after treatment is one of the biggest challenges facing cancer researchers and doctors today. The current research, because of its scale and scope, has revealed fresh insights into why some lung cancers are so difficult to treat. Researchers look forward to a brighter future for patients with lung cancer as a result of this study.
Immune “hot” and “cold” regions
The researchers suggest that areas of the tumor with fewer immune cells may have developed a “cloaking” mechanism under evolutionary pressure from the immune system. This system allows the tumor to hide from the body’s natural defenses. This AI tool can assess how many regions with this cloaking mechanism exist within a tumor, which is critical given that these immune “cold” areas are associated with cancer relapses.
Different regions of a lung tumor evolve separately, creating a myriad of different tumor characteristics, which are reflected in different levels of immune activity. Mapping out immune “hot” and “cold” areas using artificial intelligence gives a new way to look at tumors and could allow doctors to predict how well a patient will respond to certain treatments and even help personalize care.
Using the AI tool, the team found that while some parts of the tumor were packed with immune cells, described as “hot” regions, other parts of the tumor appeared to be completely devoid of them. They described these regions of the tumor as “cold” regions. When the researchers followed the progress of patients who had a higher number of “cold” regions, they found these patients were at a higher risk of relapse. Tumors with more than one immune “cold” region had a higher risk of relapse, independently of tumor size, stage, and number of samples per patient.
Researchers can now predict which patients may have a recurrence of lung cancer after surgery by detecting tumor DNA in the blood. They can thus pinpoint the people who may need additional chemotherapy to help prevent relapse. This test will now be validated in clinical trials.
Furthermore, some lung cancer cells double their genome, particularly in those patients with lung cancer who have a history of smoking. This doubling is not seen in healthy cells. This finding could lead to new targeted treatments that would leave healthy cells relatively untouched.
In addition, researchers are developing better tests that use machine learning to predict clinical outcomes at the point of diagnosis using biopsies, which traditionally have been underused due to the genetic diversity of lung cancer.
Although this research is in its early stages, this groundbreaking approach could speed up how doctors can predict which patients are more likely to see their lung cancer return, so they can then be closely monitored with tailored treatment plans.
This groundbreaking TRACERx study is proving to be a breath of fresh air in terms of cancer research and will potentially transform the future of cancer research and create a better prognosis for lung cancer patients.
Written by Joanne Myers
- New AI tool could predict risk of lung cancer recurrence
- Geospatial immune variability illuminates differential evolution of lung adenocarcinoma | Nature Medicine
- The potential for artificial intelligence in healthcare
- New report highlights AI’s potential to revolutionize health care
- Cancer Stat Facts: Lung and Bronchus Cancer