Artificial neural network model for predicting 5-year mortality after surgery for hepatocellular carcinoma: a
Hon-Yi Shi1, King-Teh Lee, Jhi-Joung Wang
1Department of Healthcare Administration and Medical Informatics, Kaohsiung Medical University, Kaohsiung, Taiwan.
Background:
To validate the use of artificial neural network (ANN) models for predicting 5-year mortality in HCC and to compare their predictive capability with that of logistic regression (LR) models.
Methods:
This study retrospectively compared LR and ANN models based on initial clinical data for 22,926 HCC surgery patients from 1998 to 2009. A global sensitivity analysis was also performed to assess the relative significance of input parameters in the system model and to rank the importance of variables.
Results:
Compared to the LR models, the ANN models had a better accuracy rate in 96.57 % of cases, a better Hosmer-Lemeshow statistic in 0.34 of cases, and a better receiver operating characteristic curves in 88.51 % of cases. Surgeon volume was the most influential (sensitive) parameter affecting 5-year mortality followed by hospital volume and Charlson co-morbidity index.
Conclusions:
In comparison with the conventional LR model, the ANN model in this study was more accurate in predicting 5-year mortality. Further studies of this model may consider the effect of a more detailed database that includes complications and clinical examination findings as well as more detailed outcome data.