AI helps evaluate pain levels in people with sickle cell disease

AI algorithms can determine the pain that someone with sickle cell disease is experiencing through the use of just their essential signs. Doing this could ensure people receive the the most suitable pain management therapy because of their condition.

“There’s always a trade-off between giving persons sufficient medicine to lessen the pain and giving people too much medication in order that they have bad unwanted effects or a higher threat of addiction,” says Daniel Abrams at Northwestern University in Illinois.

But since pain is subjective, it really is difficult to measure in a standardised way. Abrams and his colleagues set out to determine whether physiological data that is already routinely taken – including body’s temperature, heart rate and blood circulation pressure – could possibly be used to devise something that assesses pain levels in a more objective manner.

Advertisement

The team used data from 46 adults and children with sickle cell disease over a combined total of 105 hospital stays, looking at the physiological data along with patient-reported pain scores to build up models that could deduce pain levels and detect changes in pain level through machine learning.

Read more: Computer knows just how much pain you are in by studying that person

The researchers then compared their new models against existing kinds that try to evaluate degrees of pain but that don’t utilise physiological measurements. The brand new models outperformed the prevailing ones.

“The picture as a whole is that people want to better know how persons experience pain,” says Abrams. “We’re hoping that the long-term outcome of the type of research is a more quantitative method of pain management.”

“I believe the most crucial part of this research may be the wider impact that these results could have on pain treatment,” says James Henshaw at the University of Manchester, UK.

This could be especially useful for children, says Abrams, because children often struggle to explain the amount of pain they are experiencing.

The team believes that method can be extended to other styles of pain. This study is merely the first rung on the ladder in a wider investigation of pain inference and prediction.

“My research group is in the center of trying to collect an enormous set of data on an incredible number of hospitalisations and not merely for sickle cell disease but also post-operative pain and other sources of chronic pain,” says Abrams.

Journal reference: PLoS Computational Biology , DOI: 10.1371/journal.pcbi.1008542

Leave a Comment