The AI Clinician

The AI Clinician - Innovating Healthcare With The Latest Technology

What is the study about?

The AI Clinician is a study which explores whether the use of artificial intelligence (AI) applied to large medical databases can be used to assist doctors in treating sepsis; by recommending the correct medication doses for individual patients.

We demonstrated in proof-of-principle retrospective studies that our AI’s treatment strategy was, on average, better than clinicians: in an independent validation cohort, patient mortality was lowest where clinicians’ actual doses matched AI recommendations.  (The Artificial Intelligence Clinician learns optimal treatment strategies for sepsis in intensive care)

In this study we have developed a tool (The AI Clinician) capable of processing patient data within the electronic patient record of NHS hospitals in real-time to suggest a course of action. The AI Clinician will first be tested in a “shadow mode” whereby the result is not provided to the treating clinician. This will allow comparison of the decisions made by the treating clinician and the recommended decisions from the AI Clinician system. In the second stage of the clinical evaluation, we will display the recommendations to treating clinicians to assess the acceptability of the tool to clinicians and confirm the technical feasibility to inform future large-scale clinical trials.

The AI Clinician workflow
The AI Clinician workflow

 

Why is it important?

Sepsis, or overwhelming infection, is a common reason for intensive care unit (ICU) admission and death throughout the world. Despite advances in the way we treat this condition, it remains a significant economic and healthcare burden. A key part of the treatment of sepsis is the administration of IV fluids and blood pressure medication. However, there is huge uncertainty in the specific dosing of these drugs in different patients. The aim of the AI Clinician is to make recommendations for individual patients.


What are the benefits?

The long-term expected benefits of this project are numerous: improved patient survival, reduced use of precious intensive care resources and a reduction in healthcare costs.

Funders & Collaborators