Artificial Intelligence Performed Better Than Humans When Suggesting Treatment Strategies For Sepsis Cases, New Research Finds
Throughout countless industries, artificial intelligence (AI) has shown that it can revolutionize business practices– saving time and resources while mitigating mistakes. Healthcare is no different.
AI has already performed successful medical diagnostic tests. For instance, categorizing images based on pathological changes with high accuracy.
Still, it had been more challenging to teach AI to examine patient conditions– which are time-varying– and make treatment suggestions.
But in a recent study conducted by researchers at TU Wien and the Medical University of Vienna, this very feat was accomplished.
Using extensive data collected from the intensive care units (ICUs) of various hospitals, the team developed artificial intelligence that was able to provide treatment suggestions for sepsis patients who required intensive care. Remarkably, analyses also revealed that artificial intelligence performed better than humans in terms of decision quality.
“In an intensive care unit, a lot of different data is collected around the clock. The patients are constantly monitored medically. We wanted to investigate whether these data could be used even better than before,” said Professor Clemes Heitziner of the Institute for Analysis and Scientific Computing at TU Wien.
Healthcare professionals already make their treatment decisions based on various parameters– which must be taken into account before any plans are suggested and followed. Although, artificial intelligence is able to process more parameters than a human could, which might even result in better decision-making.
So, in the team’s study, they used “reinforcement learning,” which is a type of machine learning.
“This is not just about simple categorization– for example, separating a large number of images into those that show a tumor and those that do not– but about a temporally changing progression, about the development that a certain patient is likely to go through,” Heitzinger explained.
Svitlana – stock.adobe.com – illustrative purposes only, not the actual person
“Mathematically, this is something quite different. There has been little research in this regard in the medical field.”
Essentially, the AI makes its own decisions. And if the patient is doing well, the computer will be “rewarded.” On the other hand, if the patient’s condition declines or the patient dies, the computer will be “punished.”
So, the AI is tasked with reaching the highest possible “virtual reward” by completing successful actions.
And through this strategy, the AI uses various medical data to figure out a strategy that can achieve a high probability of success.
The team decided to center this study effort around sepsis treatment since sepsis is one of the most frequent causes of death in intensive care.
The condition is also extremely difficult for healthcare professionals to detect early, despite treatment being critical for patient survival.
Additionally, there have not been many medical breakthroughs in this area– meaning that the identification of new treatments is even more crucial.
“For this reason, it is particularly interesting to investigate the extent to which artificial intelligence can contribute to improving medical care here. Using machine learning models and other AI technologies is an opportunity to improve the diagnosis and treatment of sepsis, ultimately increasing the chances of patient survival,” Heitzinger detailed.
According to the study’s analysis, AI capabilities were even found to outperform humans. The researchers showed that by using AI, the cure rate for sepsis patients in regards to 90-day mortality was increased by 3%– totaling an approximate 88% cure rate.
Now, this success does not mean that AI will be solely responsible for making medical decisions in the ICU.
However, the technology could be extremely helpful for medical staff consultations, allowing doctors to compare their own assessments and suggestions against the AI’s findings.
This possibility does raise various legal questions, though, such as who might be liable in the event an AI makes a medical error.
Heitzinger also pointed out how the converse problem could occur, too, in which the AI could make the correct decision, yet, a human could choose a different treatment option which results in the patient suffering harm.
“The research project shows that artificial intelligence can already be used successfully in clinical practice with today’s technology. But, a discussion about the social framework and clear legal rules are still urgently needed,” Heitzinger concluded.
To read the study’s complete findings, which have since been published in MDPI, visit the link here.
If true crime defines your free time, this is for you: join Chip Chick’s True Crime Tribe
In 2011, She Left For A Trip To Miami With Her Boyfriend And Never Returned Home
If You’re A Lover Of Anything Pink, This List Of Houseplants Will Make Your Day
Sign up for Chip Chick’s newsletter and get stories like this delivered to your inbox.
More About:Science