A cancer test that can pinpoint the best medicine for each patient could be a breakthrough in speeding up treatment, scientists say
- A test that analyzes tumors has given cancer patients new hope
- It can predict the most effective drugs for individual cancer patients
- The breakthrough will make a major contribution to the global fight against cancer
Cancer patients have found new hope with a test that analyzes tumors to predict the most effective drugs for each patient.
The breakthrough provides a result in just 24 hours and is more accurate than current genetic approaches to personalize treatment.
Scientists at the Institute for Cancer Research in London Let’s say the technique, which uses artificial intelligence to analyze large amounts of data from tumor samples, allows doctors to quickly determine which drug combinations are most likely to work.
The researchers tested tumor cells from lung cancer patients and looked at how seven drugs affected 52 proteins linked to the growth and spread of the disease.
Cancer patients have been given new hope with a test that analyzes tumors to predict the most effective drugs for individual patients (file image)
Of 252 drug combinations tested, 128 showed some degree of synergy, meaning that their combined effect exceeded that of the individual drugs taken together.
Researchers are now planning a larger follow-up study.
Institute director Kristian Helin said: “One of the biggest challenges we face is the ability of cancer to progress and become drug-resistant.
“We believe that the future of cancer treatment will be combinations of therapies to overcome resistance, but we need to be better able to predict which drug combinations will work best for individual patients.”
Study leader Professor Udai Banerji added: “Our test provides a proof of concept for using AI to analyze changes in the way information flows within cancer cells and to make predictions about how tumors are likely to respond to drug combinations will.
“With a rapid turnaround time of less than two days, the test has the potential to help physicians assess which treatments are most likely to benefit individual cancer patients.
‘It is an important step in moving away from our current focus on using genetic mutations to predict responses.
Study leader Professor Udai Banerji added: “Our test provides a proof of concept for using AI to analyze changes in the way information flows within cancer cells and to make predictions about how tumors are likely to respond to drug combinations (file image).
“Our results show that our innovative approach is feasible and makes more accurate predictions than genetic analysis for patients with non-small cell lung cancer.
“Before this test can go into the clinic and guide personalized treatment, we need to further validate our results — for example, by conducting a study where we run the test in patients who are already receiving treatment to check if the predictions are correct.”
Genetic analysis of tumors can reveal mutations that promote cancer growth, allowing doctors to prescribe drugs that target those changes.
However, genomics alone do not provide sufficiently accurate predictions about which drug combination is most appropriate.