For example, “Doctor KI” increases the chance of surviving a blood poisoning

Artificial intelligence can increase the survival chances of patients with septicaemia. Researchers from the Vienna University of Technology (TU) report this in the journals “Plos One” and “Journal of Clinical Medicine”.

The new system takes into account more factors than human doctors and could improve their decisions. However, before «Doktor KI» can heal, legal aspects must be clarified.

What has been investigated?

A team led by Clemens Heitzinger of the Center for Artificial Intelligence and Machine Learning (CAIML) at the Vienna University of Technology used “extensive data from intensive care units in several hospitals” to teach a computer program how people with blood poisoning (sepsis) is best treated in intensive care, according to a university press release.

The computer makes treatment decisions that are applied to virtual patients in the hospital bed. If they do well, the computer is rewarded. If the condition worsens or death occurs, he will be punished.

“The computer program has the task of maximizing its virtual reward in every possible way,” says the expert: “In this way, a strategy can be automatically determined from extensive hospital data with a particularly high chance of success.”

How big are the differences if AI helps?

The medical staff make their decisions based on well-founded rules based on certain parameters to ensure the best patient care, the researchers explain and object:

“In simulations, we treated virtual patients with the strategy of the doctors and with the calculated strategy and compared the results,” Heitzinger explained to APA news agency: Without the use of artificial intelligence, the virtual patients survived 85 days, with the AI ​​strategy there are three more, namely 88.

What lessons are learned from this?

“Of course that doesn’t mean that you should leave the medical decisions in an intensive care unit to a computer alone,” he says, “But you can run artificial intelligence as an additional device at the bedside.” The medical staff can take advice from it and compare their own assessment with the AI’s suggestions. It would also be extremely helpful in training, he says.

Before “Doctor AI” is allowed to go to the clinic, legal questions must be cleared up: First, who is liable for any mistakes made by the AI. “The problem also occurs the other way around: what if the artificial intelligence had made the right decision, but the human had chosen a different option and the patient had suffered damage as a result?” Heitzinger says.

Clear rules are urgently needed here, because technically artificial intelligence could already be used in clinical practice for the benefit of patients.

Sources

(dsc/sda/apa)