A new algorithm developed thanks to the University of Copenhagen uses 23 years of medical records to predict the chances of survival of patients undergoing intensive care.
Determining which treatment is best for each critically ill patient is a major challenge, and existing methods can be greatly improved with the use of AI and machine learning.
The new algorithm, presented in Lancet magazine, leverages Danish patient health data from the Danish National Patient Registry, an endless database that collects millions of patients, "And is able to define for each patient the benefit associated with the treatment received," explains the professor Søren Brunak of the Novo Nordisk Foundation Center for Protein Research at the University of Copenhagen.
230,000 times thanks
The researchers used data from over 230.000 patients to develop the algorithm admitted to the intensive care unit in Denmark in the period 2004-2016. The study includes the medical history of patients who had illnesses up to 23 years earlier.
The calculations also included measurements and tests of the first 24 hours of hospitalization, to improve the accuracy of the mortality risks associated with the first care applied.
"Excess treatment presents collateral risks that need analysis in order to be able to properly calibrate treatments in such delicate moments in a patient's life," adds the professor Anders Perner from the intensive care and clinical medicine department at Rigshospitalet.
30- and 90-day forecasts
The algorithm, like a modern oracle, offers three predictions: the risk of the patient dying in hospital (and within how many days), the risk of dying within 30 days of admission to the unit, the risk of dying within 90 days.
"We 'instructed' the algorithm to remember which diagnoses had the greatest effect on the patient's chances of survival net of his age (young patients risk on average less than elderly ones): analyzing not only the statistics but also the methods adopted we able to establish not only how many life chances there are, but also what are the best treatments to administer, " says Brunak.
The researchers hope to be able to use the algorithm in clinical trials within a couple of years. Then the refinement of the algorithm (with the collection of more data) will allow him to detail the forecasts to understand how many hours of life a patient who has arrived in hospital remains, and what treatments can save his life immediately.
Photos: University of Copenhagen
