Artificial Intelligence for Decision Making in Kidney Transplant
Research type
Research Study
Full title
Explainable machine learning models for clinical decision support in kidney transplant offering
IRAS ID
304542
Contact name
Simon Knight
Contact email
Sponsor organisation
University of Oxford / Research Governance, Ethics and Assurance
Duration of Study in the UK
1 years, 0 months, 1 days
Research summary
Research Summary
Around 2,500 deceased donor kidney transplants are performed in the UK each year. At any time, there are around 5,000 patients on the kidney transplant waiting list. The shortage of organs available for transplant means that some patients become too unwell for surgery or die whilst waiting. Because of this, doctors often consider kidneys from donors who are less ideal due to age or other medical problems.
These decisions are made by the transplant doctors based upon the information available at the time of offer. Details are rarely discussed with the patient. Doctors use their clinical experience, but do not have tools available to help them predict what would happen if they chose to accept or decline an offer and wait for the next one.
We plan to use data from twenty years of previous transplant offers and outcomes in the UK to train Artificial Intelligence (AI) models that will allow us to predict the outcome if an offered kidney is accepted and transplanted or declined and wait for another offer. We will test these predictions to see how accurate they are compared to existing methods.
During the study, we will interview patients and clinicians to gain insight into their opinions on how to present these predictions to help them to make the decision as to whether to accept or decline an organ offer. Ultimately, we hope to use this information to design a simple web-based tool that can be used by both patients and clinicians when considering organ transplant offers.
Initial work with patients at the Oxford Transplant Centre has shown that most patients would welcome more involvement in the decision to accept or decline an organ. We aim to present the results of our project at national and international conferences and publish them in peer reviewed journals.
Summary of Results
The activities of information-giving, decision-making, and waiting are central to the kidney transplant experience for both clinicians and patients but until now they have rarely been studied. It is known that clinicians may experience doubt around patient information giving, decision-making, and how newer tools using advanced computer programmes like Artificial Intelligence (AI) could help the process. Patients may experience misgivings around transplant information and waiting lists; they may also have questions around technology incorporated into the decision-making process. Qualitative research, which is a type of research that uses non number-based information to answer research questions, has the capacity to deepen understanding of these activities by generating understanding into clinician and patient experiences. This study used qualitative interviews to explore the clinician and patient experience in kidney transplant processes in the the UK.
Fourteen kidney transplant recipients and ten clinicians were interviewed in an outpatient clinic at a U.K. transplant centre. We used audio-recorded interviews to collect data.
Four main ideas emerged from the patient interviews: ‘Transplant information is challenging to understand,’ ‘Further information would be life-changing,’ ‘The waiting-game, fears and hopes on the waiting list,’ and ‘AI-driven tools could help transplant patients.’ The four main ideas that came from the clinician interviews included: ‘Challenges in clearly providing patients with transplant information,’ ‘The balancing act: whether to accept or decline an organ,’ ‘Team-approach to decision making,’ and ‘AI can be a friend to call on.’
Our results showed that patients and clinicians find the transfer of information around the transplant process challenging. The uncertainty in transplant can be a long process that encompasses hope but also fear in both the clinician and patient. The delicate balance of staying on the waiting list or accepting an organ involves many complex factors but using newer technology such as AI to help ease this burden would be welcomed by most patients and clinicians.
REC name
South East Scotland REC 02
REC reference
22/SS/0008
Date of REC Opinion
10 Feb 2022
REC opinion
Further Information Favourable Opinion