Authors:
Farrukh Arslan, S. Rubin Bose, J. Angelin Jeba, Shahid Ullah, Bushra Rehman, Kawsher Rahman, Mohamed Sameh Mohamed Elhadad, Mohamed Ibrahim Hamad Aborakika, Lorans Ashraf Botros Ajeep Rasan

Addresses:
Department of Computer Science, Purdue University, West Lafayette, Indiana, United States of America. School of Computer Science and Engineering, SRM Institute of Science and Technology, Ramapuram, Chennai, Tamil Nadu, India. Department of Electronics and Communication Engineering, S.A. Engineering College, Chennai, Tamil Nadu, India. Department of Bioinformatics and Biochemistry, S Khan Lab, Mardan, Khyber Pakhtunkhwa, Pakistan. Institute of Pathology and Diagnostic Medicine, Khyber Medical University, Peshawar, Khyber Pakhtunkhwa, Pakistan. Department of General Medicine, Beanibazar Cancer and General Hospital, Beanibazar, Sylhet, Bangladesh. Department of Biomedical Sciences, Zewail City of Science and Technology, October Gardens, Giza Governorate, Egypt.

Abstract:

Organ transplants have become one of the most important parts of health care, primarily because of the imbalance between those who need organs and the available organ donor pool. Due to this disparity, choosing the next organ recipient among other candidates can be quite challenging. This process largely relies on several medical criteria, including urgency, compatibility, severity, waiting period, and survival chances. Taking all these aspects into account and processing them manually could be problematic, even leading to biases during prioritisation. The proposed solution is a Smart Organ Transplant Priority Analyzer that facilitates the prioritization of patients waiting for an organ transplant using Machine Learning, SAHP, and SHAP. The tool evaluates patient information, assigns a priority score and category, and provides recommendations on who should be a top candidate to receive the organ. SAHP assigns weights to medical parameters to make sure that crucial factors play a greater role in determining the transplant recipient. Machine Learning algorithms, such as random forests, are used to estimate patients' transplant priority scores. SHAP provides interpretability of results by explaining why a particular outcome was achieved and the contribution of each criterion to that outcome.

Keywords: Organ Transplant Prioritisation; Machine Learning; SHAP and XGBoost; Random Forest; Support Vector Machine (SVM); Explainable AI; Health Care; Transplant Recipient.

Received on: 28/07/2025, Revised on: 05/10/2025, Accepted on: 04/12/2025, Published on: 18/08/2026

DOI: 10.69888/FTSHSL.2026.000733

FMDB Transactions on Sustainable Health Science Letters, 2026 Vol. 4 No. 3, Pages: 224-236

• Views : 21
• Downloads : 7

Download PDF