French researchers have developed software to better diagnose cases of kidney transplant rejection. Doctors will be able to better adapt the treatment for their patients.
It took four and a half years to create this new tool that simplifies the work of doctors. This software works like an artificial intelligence to determine, from the analyzes of a patient, his biopsy, all his medical data, if there is rejection or not of the kidney transplant. “The machine does the work we did before in our head, it does it itself but it is not mistaken”explains Valentin Goutaudier.
>> Health: artificial intelligence “can lighten the technical work of the doctor”, explains Professor Jean-Emmanuel Bibault
This researcher and kidney transplant specialist is part of Alexandre Loupy’s team, the brain behind this medical innovation. It was he who came up with the idea for this online platform, noting that diagnostic errors were far too frequent, around 40%. These errors were mainly due to an overly complex classification, the Banff classification, a reference for the diagnosis of transplant rejection, with millions of possible scenarios to confirm or invalidate a rejection.
“Doctors had long complained that this classification was far too complicated, and he speculated that automating the classification would stop making mistakes.”
Alexandre Loupy, doctorat franceinfo
From the interface, one can enter patient data one by one, “and in less than a second, you have your diagnosis”, explains Alexandre Loupy. A small revolution both technological and medical French, which allows depending on the answer to adapt the treatment.
An experiment carried out on 3,000 patients
This tool has already been put into practice at the Saint-Louis hospital in Paris, where the doctor Gillian Divard works. “This kind of tool will never replace a doctor”he says, “but it actually allows us to accompany us on the fact that it is the right diagnosis and that we can go on a treatment, it is really very useful in practice.”
“What the patient gains is safety, because typically a rejection that is not diagnosed is a rejection that is not treated. And an untreated rejection increases the risk of loss of grafts.”
Gillian Divard, doctor at Saint-Louis Hospitalat franceinfo
“It is therefore a patient who returns to dialysis or a transplant, which has catastrophic consequences, whether in terms of quality of life or life expectancy for the patient”, adds Gillian Divard. An experiment conducted with 3,000 patients has proven the effectiveness of this computer tool. It will soon be used by teams around the world to improve patient care.