Machine Learning to Predict Overall Survival of Hepatocellular Carcinoma

22.11.2021
Machine Learning to Predict Overall Survival of Hepatocellular Carcinoma

 

Machine Learning to Predict Overall Survival of Hepatocellular Carcinoma

The aim of this project was to assess the ability of machine learning models to predict survival probability in HCC patients for different durations. A gradient boosting decision tree model; LightGBM was implemented to predict patient survival at 6 different durations.
The survival rate for 6, 12, 24, 36, 60, and 120 months was 88%, 81%, 67%, 60%, 40%, and 11%, respectively. The mean ROC area under the curve of the model prediction was 0.92 (0.061) for >6 months, 0.81 (0.107) for >12 months, 0.78 (0.11) for >24 months, 0.81 (0.083) for >36 months, 0.82 (0.079) for >60 months, and 0.66 (0.14) for >120 months.
The model was successful at predicting short and long term survival of HCC patients.

s