2022 10th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO), Journal Year: 2024, Volume and Issue: unknown, P. 1 - 6

Published: March 14, 2024

Insufficient organ availability for donation fails to meet the increasing demand transplants, leading thousands of deaths annually among those awaiting organs. One donor has potential save eight lives and positively influence more than 75 others. While 50% children over 1 year old, who cease life-sustaining therapy, can donate organs after cardiac death, addressing gap between supply necessitates meticulous patient/donor selection matching. In our paper, we study how machine learning tools like Cox Proportional Hazard model, Random Forest, XGBoost be used in a centralized database. We also examine effectiveness Federated Learning survival analysis as enhance predictive modelling outcomes. Our research indicates that Transfer surpasses other techniques terms accuracy. These findings propose integrating federated transfer into repository significantly system's capabilities, offering promising approach advancing management allocation. This information is preserved future use predicting issues. The developed model demonstrates commendable accuracy donation, with value 0.998. Consequently, implementing such aid hospitals their mission lives.

Language: Английский