London researchers set up AI tool—Photo: Courtesy of Sky News
London: Artificial intelligence (AI) can be used to predict future health-related situations for patients, according to research from UK institutions.
According to a Sky News report, researchers associated with King’s College London (KCL), University College London (UCL), King’s College Hospital NHS Foundation Trust and Guy’s and St Thomas NHS Foundation Trust called Forsyte. AI has created the tool.
According to the report, the tool is an AI model similar to ChatGPT but trained using information from NHS electronic records.
The technology could be used to monitor patients or help doctors diagnose disease, the researchers said.
They trained three different Forsyte models using data from more than 811,000 patients from NHS Trusts in London and publicly available data in the US.
According to the report, based on patient records, a patient was given 10 possible diseases and using material from NH hospitals, Forsyte was 68% accurate in identifying the condition and time wise. 76 percent were competent and 88 percent accurate with respect to timing using US material.
Zeljko Kraljevic, a research fellow in health informatics, biostatistics at KCL, said in a research paper published in The Lancet Digital Health that the results show that the device can achieve excellent results for predicting the nature of a patient’s illness and It can be used as a useful tool to support decision-making and informed clinical research.
Richard Dobson, Senior Informatics Officer at KCL and UCL, Senior Informatics Officer at the National Institute for Health and Care Research (NIHR) Professor at Mowdlesey Biomedical Research Center (BRC), said: It’s an exciting time for AI and to create effective tools, we must ensure that we use relevant data to train models and collaborate with patients towards the goal of innovation in the healthcare system.
The team of researchers is now looking to involve other hospitals in developing Forsyte Two, which Professor Dobson said would lead to a more accurate language model.
(function(d, s, id){
var js, fjs = d.getElementsByTagName(s)[0];
if (d.getElementById(id)) {return;}
js = d.createElement(s); js.id = id;
js.src = “//connect.facebook.net/en_US/sdk.js#xfbml=1&version=v2.3&appId=770767426360150”;
fjs.parentNode.insertBefore(js, fjs);
}(document, ‘script’, ‘facebook-jssdk’));
(function(d, s, id) {
var js, fjs = d.getElementsByTagName(s)[0];
if (d.getElementById(id)) return;
js = d.createElement(s); js.id = id;
js.src = “//connect.facebook.net/en_GB/sdk.js#xfbml=1&version=v2.7”;
fjs.parentNode.insertBefore(js, fjs);
}(document, ‘script’, ‘facebook-jssdk’));