Researchers at Imperial College London have developed an Artificial Intelligence (AI) Clinician which could soon be trialed in the UK intensive care units (ICUs) to improve the management of sepsis.
The system analysed the medical records of 96,000 US ICU patients with sepsis in intensive care units. The reinforcement learning technology extracted clinical information and treatment decisions and worked out the best strategy of keeping a patient alive. The system calculated 48 variables including age, vital signs and preexisting conditions.
The AI Clinician then predicted the best treatment strategy for each patient. The results revealed that 98% of the time, the AI system matched or was better than the human doctors’ decision.
The research, published in the journal Nature Medicine, also found that mortality was lowest in patients where the human doctor’s doses of fluids and vasopressor matched the AI system’s suggestion.
When the doctor’s decision varied from the AI Clinician’s suggestion, it was usually to administer too much fluid and too little vasopressor but, importantly, it varied between individual patients.
The team say the findings show the AI Clinician could help doctors decide the best treatment strategy for patients.
The researchers now hope to trial the system in ICUs in the United Kingdom.