Explainable Mortality Prediction for Liver Transplant Candidates with Hepatocellular Carcinoma: A Supervised
Abdelghani Halimi1,2, Nesma Houmani1, Sonia Garcia-Salicetti1
1SAMOVAR, Télécom SudParis, Institut Polytechnique de Paris, 91120 Palaiseau, France.
Insights
Predicting mortality for liver transplant candidates with hepatocellular carcinoma (HCC) is challenging. Our new machine learning model, using Ensemble Learning and SHAP, offers a more accurate risk assessment by considering both liver function and tumor progression.
Area of Science:
- Hepatology and Transplant Surgery
- Artificial Intelligence in Medicine
- Oncology
Background:
- Accurate mortality prediction for liver transplant candidates with hepatocellular carcinoma (HCC) is a significant clinical challenge.
- Existing scoring systems (Child-Pugh, MELD, etc.) often lack precision due to the dual burden of liver dysfunction and tumor progression.
- A comprehensive approach is needed to effectively manage HCC patients.
Purpose of the Study:
- To develop an advanced machine learning-based scoring system for improved mortality risk prediction in HCC patients.
- To leverage Ensemble Learning and SHapley Additive exPlanations (SHAP) for a deeper understanding of mortality risk factors.
- To identify latent patient subgroups for more granular risk assessment.
Main Methods:
- An advanced machine learning model utilizing Ensemble Learning and SHAP was developed.
- SHAP values were embedded in Uniform Manifold Approximation and Projection (UMAP) space for supervised clustering.
- Latent subgroups were inferred to provide granular insights into variable contributions to mortality risk.
Main Results:
- The LightGBM-based system outperformed conventional scores, utilizing only 8 key variables identified by SHAP analysis.
- These selected variables effectively addressed the dual risk challenge of liver dysfunction and tumor progression.
- Supervised clustering identified 7 distinct subgroups with increasing mortality risk levels and detailed risk factor contributions.
Conclusions:
- The proposed data-driven framework offers an integrative approach to the dual risk challenge in HCC patients with liver dysfunction.
- This method provides a more precise risk evaluation tool compared to existing studies.
- The findings may guide treatment decisions and improve patient progression monitoring.
Abstract:
Background: Accurate mortality prediction for liver transplant candidates with hepatocellular carcinoma (HCC) remains a critical challenge. Traditional scoring systems, including Child-Pugh, Albumin-Bilirubin, Model for End-Stage Liver Disease (MELD), MELD-Na, MELD 3.0, and Alpha-fetoprotein scores, are widely used but often fail to provide precise risk assessments. This limitation arises from the dual burden of liver dysfunction and tumor progression, which complicates prognosis. Consequently, there is a need for a comprehensive approach addressing both considerations to better manage HCC patients. Methods: We propose an advanced machine learning-based scoring system exploiting Ensemble Learning and SHapley Additive exPlanations (SHAP) for a better understanding of key mortality risk factors. SHAP offers valuable insights into the decision-making process by providing both global and local explanations. By embedding SHAP values in the Uniform Manifold Approximation and Projection space, we perform supervised clustering to infer latent subgroups, providing a higher granularity on the contribution of key variables for mortality risk assessment. Results: Our system based on LightGBM outperforms conventional scores leveraging only 8 relevant variables selected by SHAP analysis. These variables respond to the challenging dual risk problem set in this work. With supervised clustering, we uncover 7 subgroups showing an increasing mortality risk level and a fine assessment of risk factors' contribution. Conclusion: By contrast to existing studies, our approach offers an integrative data-driven framework for handling the dual risk challenge set by HCC patients with liver dysfunction. Also, it provides a valuable tool for a more precise risk evaluation that may guide treatment decisions and help monitoring patient progression.
