Doctors and researchers have managed to develop an artificial intelligence (AI) tool capable of accurately predicting the likelihood of tumors growing back in cancer patients.
So says an unprecedented study by the Royal Marsden NHS Foundation Trust, the Cancer Research Institute, London, and Imperial College London, published in The Lancet’s eBioMedicine.
AI also allows recurrence to be detected earlier in patients considered to be at high risk. In this way, you can ensure that they receive treatment more urgently. And, in low-risk cases, it is possible to reduce the occurrence and frequency of visits to the hospital for unnecessary follow-up exams.
More efficient than traditional methods
In the study, a machine learning model was developed to determine whether it would be possible to identify which non-small cell lung cancer (NSCLC) patients treated with radiotherapy were at risk of recurrence.
The researchers used clinical data from 657 NSCLC patients treated at five UK hospitals and added several other prognostic factors such as age, sex, body mass index (BMI), smoking, intensity of radiation therapy and tumor characteristics.
Then the researchers used AI to categorize patients into low and high risk of recurrence; how long it may take until recurrence; and overall survival two years after treatment.
The tool was considered more efficient in predicting results than traditional methods.
Less fear, less anxiety
“This is an important step for us to use AI to understand which patients are most at risk of recurrence. And also to detect this relapse earlier so that the new treatment can be more effective,” said Richard Lee, a physician specializing in respiratory medicine. and early diagnosis at the Royal Marsden NHS Foundation Trust.
In addition, Lee, who is also the lead investigator of the study, explains that the solution is quite useful because the patients’ fear of having a relapse generates a lot of anxiety.
“We hope to push boundaries to improve the care of cancer patients, help them live longer and reduce the impact the disease has on their lives,” he says.
The research is “an exciting first step” towards the launch of a national and international tool to guide post-treatment surveillance of cancer patients, added Sumeet Hindocha, an oncologist at Royal Marsden and Imperial College London.