Abstract
Liver cancer is one of the main causes of cancer-related deaths worldwide. Due to the extreme heterogeneity of this disease, its prognosis and management are still not yet standardized. Different treatment modalities are available. However, the patient's response to each of them varies. Therefore, it is critical to establish a model to help physicians individualize the management of this aggressive tumor. This paper presents one of the first investigations into personalizing liver cancer treatment for patients with genotype 4 using their clinical and genetic data. In this study, we analyzed the data of 1427 Egyptian patients with liver cancer who were either treated by one of five different treatment methods or not treated. We proposed and compared between two pipelines, a Single-Model pipeline and a Multi-Model pipeline, for analyzing the patient's clinical and genetic data to recommend the best liver cancer treatment and, therefore, potentially improve their prognosis. We studied the performance of six regression methods in predicting the outcome of the treatment modalities for liver cancer patients. The best performing method was used in building the models in the proposed pipelines. Our results show a difference in performance among different regression models, which proves the importance of choosing an appropriate one in decision-making, especially when dealing with important issues such as liver cancer treatment recommendations. In our analysis, we also prove the crucial importance of genetic data and their effect on patients' prognosis and response to treatment. Finally, this study signifies the great potential that data-mining methods could have in improving healthcare especially for serious diseases such as liver cancer.