Chong-Chi Chiu1,2,3, King-Teh Lee4,5, Hao-Hsien Lee1, Jhi-Joung Wang6, Ding-Ping Sun2, Chien-Cheng Huang7,8, Hon-Yi Shi9,10,11. 1. Department of General Surgery, Chi Mei Medical Center, Liouying, Taiwan. 2. Department of General Surgery, Chi Mei Medical Center, Tainan, Taiwan. 3. Department of Electrical Engineering, Southern Taiwan University of Science and Technology, Tainan, Taiwan. 4. Division of Hepatobiliary Surgery, Department of Surgery, Kaohsiung Medical University Hospital, Kaohsiung, Taiwan. 5. Department of Healthcare Administration and Medical Informatics, Kaohsiung Medical University, 100, Zihyou 1st Road, Kaohsiung, 807, Taiwan. 6. Department of Medical Research, Chi Mei Medical Center, Tainan, Taiwan. 7. Department of Emergency Medicine, Chi Mei Medical Center, Tainan, Taiwan. 8. Bachelor Program of Senior Service, Southern Taiwan University of Science and Technology, Tainan, Taiwan. 9. Department of Healthcare Administration and Medical Informatics, Kaohsiung Medical University, 100, Zihyou 1st Road, Kaohsiung, 807, Taiwan. hshi@kmu.edu.tw. 10. Department of Business Management, National Sun Yat-sen University, Kaohsiung, Taiwan. hshi@kmu.edu.tw. 11. Department of Medical Research, Kaohsiung Medical University Hospital, Kaohsiung, Taiwan. hshi@kmu.edu.tw.
Abstract
BACKGROUND: The essential issue of internal validity has not been adequately addressed in prediction models such as artificial neural network (ANN), support vector machine (SVM), Gaussian process regression (GPR), and multiple linear regression (MLR) models. METHODS: This prospective study compared the accuracy of these four models in predicting quality of life (QOL) after hepatic resection received by 332 patients with hepatocellular carcinoma (HCC) during 2012-2015. An estimation subset was used to train the models, and a validation subset was used to evaluate their performance. Sensitivity score approach was also used to assess the relative significance of input parameters in the system models. RESULTS: The ANN model had significantly higher performance indicators compared to the SVM, GPR, and MLR models (P < 0.05). Additionally, the ANN prediction of QOL at 6 months after hepatic resection significantly correlated with age, gender, marital status, Charlson comorbidity index (CCI) score, chemotherapy, radiotherapy, hospital volume, surgeon volume, and preoperational functional status (P < 0.05). Preoperational functional status was the most influential (sensitive) variable affecting sixth-month QOL followed by surgeon volume, hospital volume, age, and CCI score. CONCLUSIONS: The comparisons showed that, in preoperative and postoperative healthcare consultations with HCC surgery candidates, QOL at 6 months post-surgery should be estimated with an ANN model rather than with SVM, GPR, or MLR models. The best QOL predictors identified in this study can also be used to educate candidates for HCC surgery in the expected course of recovery and other surgical outcomes.
BACKGROUND: The essential issue of internal validity has not been adequately addressed in prediction models such as artificial neural network (ANN), support vector machine (SVM), Gaussian process regression (GPR), and multiple linear regression (MLR) models. METHODS: This prospective study compared the accuracy of these four models in predicting quality of life (QOL) after hepatic resection received by 332 patients with hepatocellular carcinoma (HCC) during 2012-2015. An estimation subset was used to train the models, and a validation subset was used to evaluate their performance. Sensitivity score approach was also used to assess the relative significance of input parameters in the system models. RESULTS: The ANN model had significantly higher performance indicators compared to the SVM, GPR, and MLR models (P < 0.05). Additionally, the ANN prediction of QOL at 6 months after hepatic resection significantly correlated with age, gender, marital status, Charlson comorbidity index (CCI) score, chemotherapy, radiotherapy, hospital volume, surgeon volume, and preoperational functional status (P < 0.05). Preoperational functional status was the most influential (sensitive) variable affecting sixth-month QOL followed by surgeon volume, hospital volume, age, and CCI score. CONCLUSIONS: The comparisons showed that, in preoperative and postoperative healthcare consultations with HCC surgery candidates, QOL at 6 months post-surgery should be estimated with an ANN model rather than with SVM, GPR, or MLR models. The best QOL predictors identified in this study can also be used to educate candidates for HCC surgery in the expected course of recovery and other surgical outcomes.
Entities:
Keywords:
Artificial neural network; Gaussian process regression; Hepatocellular carcinoma surgery; Multiple linear regression; Sixth-month quality of life; Support vector machine
Authors: Yuan He; An Pan; Ying Yang; Yuanyuan Wang; Jihong Xu; Ya Zhang; Dujia Liu; Qiaomei Wang; Haiping Shen; Yiping Zhang; Donghai Yan; Zuoqi Peng; Frank B Hu; Xu Ma Journal: Am J Public Health Date: 2016-12 Impact factor: 9.308
Authors: Ananya Das; Tamir Ben-Menachem; Gregory S Cooper; Amitabh Chak; Michael V Sivak; Judith A Gonet; Richard C K Wong Journal: Lancet Date: 2003-10-18 Impact factor: 79.321