Challenges in Kidney Transplantation
End-stage renal disease, kidney failure, and chronic kidney disease are just a few of the many kidney diseases that are widely viewed as treatable through kidney transplants, offering patients the chance to resume a healthy, normal lifestyle. However, 12 out of every 100,000 people in the U.S. die on the kidney transplant waiting list every day.
The current organ donation system, managed by the United Network for Organ Sharing (UNOS), manually matches donors to patients. Due to the various factors that play a role in organ matching, such as blood type, HLA, and hemoglobin levels, this process is slow and highly inefficient—over 28,000 organs were wasted, and several thousand patients tragically died on the transplant waitlist.
Furthermore, the kidney transplantation process specifically lacks a coherent method to screen organ health before transplantation to determine future risks for kidney disease, resulting in 30% of patients with kidney transplants experiencing recurring issues.
This problem has become so prevalent that it has required Congress to intervene with the recent passing of the Organ Procurement and Transplantation Network Modernization Initiative—and we want to help.
Our Solution
To address these issues in the industry, KidneyChain leverages blockchain technology to automate the organ matching process, using the same metrics as UNOS clinicians. This results in efficient and faster matching.
Additionally, by incorporating artificial intelligence, KidneyChain screens organs pre-transplantation to predict potential risks for common kidney diseases such as chronic kidney disease (CKD), acute kidney injury (AKI), and polycystic kidney disease (PKD), aiming to prevent recurring issues in patients post-transplantation.
Furthermore, given the sensitive information the platform handles, including the personal health information of patients and donors, KidneyChain employs a novel TDL-CNN algorithm capable of recognizing malicious blocks added to the blockchain through a recurrent time series-based approach.
