• KALPESH SANJAY BHOI
• Sudarshan Dilip Chole
• Dhiraj Tanaji Bhosale
• Aditya Suresh Jadhav
• Dhanishri Dixit

Liver transplantation is a life-saving procedure, but post-operative complications and disease recurrence remain major concerns for patient survival. Predicting post-transplant disease risks can significantly improve patient management, early intervention, and overall transplant success. In this study, we present a machine learning-based Post Liver Transplant Disease Prediction Model, leveraging clinical, biochemical, and donor-recipient data to assess the likelihood of post-transplant complications. Our approach integrates deep learning techniques, survival analysis, and natural language processing (NLP) to extract valuable insights from structured and unstructured medical records. We employed supervised learning models, including random forests, XGBoost, and deep neural networks, alongside DeepSurv, a deep learning-based survival analysis framework. Additionally, donor text narratives were analyzed using transformer-based NLP models to extract critical features influencing transplant outcomes. The model was trained and validated on a large multi-center dataset, achieving high predictive performance with an AUC of over 97% in identifying high-risk patients.

Liver Transplantation, Post-Transplant Complications, Machine Learning, Deep Learning, Python.

"Post Liver Transplant Disease Prediction Model", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 3, page no.a429-a435, March-2025, Available :http://www.jetir.org/papers/JETIR2503055.pdf

"Post Liver Transplant Disease Prediction Model", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 3, page no. ppa429-a435, March-2025, Available at : http://www.jetir.org/papers/JETIR2503055.pdf