Making use of complex algorithms and machine-learning techniques, AI could be about to help doctors make more accurate predictions about the effectiveness of immunotherapy.
Doctors do not as yet have access to markers that enable them to identify with any great certainty which patients would be likely to respond favourably to immunotherapy, a treatment that boosts the body’s natural defences to fight illnesses, such as cancer. While only15-30% of patients respond well to the treatment, the use of artificial intelligence could enable doctors to more accurately assess the chances of anti-cancer immunotherapy succeeding.
An ability to analyse tumours
In a study published in The Lancet, French doctors/researchers explain how they have designed software capable of predicting the effectiveness of a course of immunotherapy. Making use of machine learning, they developed and trained an algorithm to analyse data extracted from patient scanners.
Immunotherapy has been found to work better on tumours in a rich immune environment in which lymphocytes are present. Working on medical images alone, the algorithm learns to recognise which tumours are most likely to respond to immunotherapeutic treatment.
Easier and more cost-effective monitoring
Doctors hope the technique will help them identify the biological behaviour of tumours without having to carry out biopsies. Such a solution, which presents less of a risk to the patient, would also result in a significant reduction in costs, as reported by Inserm, the French National Institute of Health and Medical Research.
“This technique will also prevent us from giving false hope and allow us to offer better guidance,” said Professor Eric Deutsch, the head of the Radiotherapy Department in Villejuif (France). “The faster we go, the quicker we will be able to guide patients towards the right treatment, the more time we will save, and the better the chances of us playing the right card at the right time.”
A promising technique
Immunotherapy is adopting an increasingly prominent role in the fight against cancer. Currently provided in addition to more intensive treatments, it could one day replace chemotherapy. It has already yielded some encouraging results in the treatment of melanoma skin cancers and breast, lung, bladder, uterus and prostate cancer.
Contact Allianz Partners
Dec 6, 2017
While the Apple Watch is not equipped to measure blood pressure or quality of sleep, with the help of an algorithm to analyse data from the pedometer and the cardiofrequencemeter which [...]
USA, Apr 26, 2018
The US Food & Drug Administration (FDA) has just delivered its first authorisation for AI-based equipment to make an autonomous medical diagnosis without the intervention of a doctor.
Oct 4, 2018
The MIT has developed an artificial intelligence tool designed to predict depressive tendencies through text or audio recordings. With an accuracy rate of 77%, this neuronal-network mod [...]