Artificial intelligence can help ambulance workers save more lives by functioning as an “extra colleague”, a new study suggests.
Research conducted by Chalmers University of Technology, the University of Gothenburg and the University of Borås has found that artificial intelligence’s (AI) ability to make fast-paced, life-critical decisions will help paramedics to save many more lives.
First author Anna Bakidou said: “If severely injured people are transported directly to a university hospital, the chances of survival increase, as there are resources to take care of all types of injuries.
“Therefore, we need to be able to better say who is severely injured, and who is not, so that everyone receives the right care and that resources are used in the best way.”
- Fertility problems higher amongst women with bigger waist circumference
- Chatbots help people make better decisions about exercise, diet and sleep
- Patients prefer ChatGPT responses over doctors’ responses
A team of researchers have created five different mathematical models after analysing data from the Swedish Trauma Registry of people who received ambulance care between 2013 and 2020.
They found that AI models were better at making quick decisions at the time of a critical health incident than ambulance workers.
According to the report, 40% of people with serious injuries were not taken directly to a university hospital.
Meanwhile, 45% of individuals with non-serious injuries were sent to university hospitals, despite not needing urgent care.
Anna Bakidou said: “Ambulance personnel are constantly faced with difficult and quick decisions.
“Our hope is that a more objective decision support system will be able to function as an ‘extra colleague’ that makes staff see more complex connections and think twice in cases where injuries can be difficult to perceive or assess.”
Children and young people involved in a traffic accident are often judged to be more severely injured than they are.
Whereas older adults who have a fall accident are frequently labelled as mildly injured, but injuries caused by falling can be life-threating, such as internal bleeding.
“For example, can you talk to the tool to be able to have both hands free? How can existing routines and protocols be used to work together with the AI, and how can the advice to staff be updated when new data is added?” said Anna Bakidou.
- AI chat tools make people sound “more positive”
- One in three people have given up seeing a GP, poll shows
- Speaking to strangers can make us feel happier
She added: “We need to test and take these things into account when we proceed with more studies and prototype work.”
Large-scale clinical trials over time are required before AI services can be rolled out to support paramedics.
Joint author Professor Stefan Candefjord said: “The regulations mean that it takes time and there is also a fear of AI.
“There can be serious consequences if things go wrong. Everything that is to be introduced into healthcare must be validated.”
He continued: “At the same time, we know that some of the methods used today are not always the best.
“When it comes to ambulance care, there is not much research on AI, and we hope that our mathematical models will be able to contribute with support that is adapted to the work environment and that in the long run provides more equal care.”
The study has been published in the journal BMC Medical Informatics and Decision Making.
