PURPOSE: To stratify patients and aid clinical decision making, we developed machine learning models to predict treatment failure and radiation-induced toxicities after radiotherapy (RT) in patients with hepatocellular carcinoma across institutions. MATERIALS AND METHODS: The models were developed using linear and nonlinear algorithms, predicting survival, nonlocal failure, radiation-induced liver disease, and lymphopenia from baseline patient and treatment parameters. The models were trained on 207 patients from Massachusetts General Hospital. Performance was quantified using Harrell's c-index, area under the curve (AUC), and accuracy in high-risk populations. Models' structures were optimized in a nested cross-validation approach to prevent overfitting. A study analysis plan was registered before external validation using 143 patients from MD Anderson Cancer Center. Clinical utility was assessed using net-benefit analysis. RESULTS: The survival model stratified high-risk versus low-risk patients well in the external validation cohort (c-index = 0.75), better than existing risk scores. Predictions of 1-year survival and nonlocal failure were excellent (external AUC = 0.74 and 0.80, respectively), especially in the high-risk group (accuracy > 90%). Cause-of-death analysis showed differential modes of treatment failure in these cohorts and indicated that these models could be used to stratify RT patients for liver-sparing treatment regimen or combination approaches with systemic agents. Predictions of liver disease and lymphopenia were good but less robust (external AUC = 0.68 and 0.7, respectively), suggesting the need for more comprehensive consideration of dosimetry and better predictive biomarkers. The liver disease model showed excellent accuracy in the high-risk group (92%) and revealed possible interactions of platelet count with initial liver function. CONCLUSION: Machine learning approaches can provide reliable outcome predictions in patients with hepatocellular carcinoma after RT in diverse cohorts across institutions. The excellent performance, particularly in high-risk patients, suggests novel strategies for patient stratification and treatment selection.
PURPOSE: To stratify patients and aid clinical decision making, we developed machine learning models to predict treatment failure and radiation-induced toxicities after radiotherapy (RT) in patients with hepatocellular carcinoma across institutions. MATERIALS AND METHODS: The models were developed using linear and nonlinear algorithms, predicting survival, nonlocal failure, radiation-induced liver disease, and lymphopenia from baseline patient and treatment parameters. The models were trained on 207 patients from Massachusetts General Hospital. Performance was quantified using Harrell's c-index, area under the curve (AUC), and accuracy in high-risk populations. Models' structures were optimized in a nested cross-validation approach to prevent overfitting. A study analysis plan was registered before external validation using 143 patients from MD Anderson Cancer Center. Clinical utility was assessed using net-benefit analysis. RESULTS: The survival model stratified high-risk versus low-risk patients well in the external validation cohort (c-index = 0.75), better than existing risk scores. Predictions of 1-year survival and nonlocal failure were excellent (external AUC = 0.74 and 0.80, respectively), especially in the high-risk group (accuracy > 90%). Cause-of-death analysis showed differential modes of treatment failure in these cohorts and indicated that these models could be used to stratify RT patients for liver-sparing treatment regimen or combination approaches with systemic agents. Predictions of liver disease and lymphopenia were good but less robust (external AUC = 0.68 and 0.7, respectively), suggesting the need for more comprehensive consideration of dosimetry and better predictive biomarkers. The liver disease model showed excellent accuracy in the high-risk group (92%) and revealed possible interactions of platelet count with initial liver function. CONCLUSION: Machine learning approaches can provide reliable outcome predictions in patients with hepatocellular carcinoma after RT in diverse cohorts across institutions. The excellent performance, particularly in high-risk patients, suggests novel strategies for patient stratification and treatment selection.
Authors: Jennifer Pursley; Issam El Naqa; Nina N Sanford; Bridget Noe; Jennifer Y Wo; Christine E Eyler; Matthew Hwang; Kristy K Brock; Beow Y Yeap; John A Wolfgang; Theodore S Hong; Clemens Grassberger Journal: Int J Radiat Oncol Biol Phys Date: 2020-04-27 Impact factor: 7.038
Authors: Yi Luo; Daniel McShan; Dipankar Ray; Martha Matuszak; Shruti Jolly; Theodore Lawrence; Feng Ming Kong; Randall Ten Haken; Issam El Naqa Journal: IEEE Trans Radiat Plasma Med Sci Date: 2018-05-02
Authors: Philippe Lambin; Relinde I Y Lieverse; Franziska Eckert; Damiënne Marcus; Cary Oberije; Alexander M A van der Wiel; Chandan Guha; Ludwig J Dubois; Joseph O Deasy Journal: Semin Radiat Oncol Date: 2020-04 Impact factor: 5.934
Authors: Stephanie K Schaub; Smith Apisarnthanarax; Ryan G Price; Matthew J Nyflot; Tobias R Chapman; Manuela Matesan; Hubert J Vesselle; Stephen R Bowen Journal: Int J Radiat Oncol Biol Phys Date: 2018-08-28 Impact factor: 7.038
Authors: Young Seok Seo; Mi-Sook Kim; Sung Yul Yoo; Chul Koo Cho; Chul Won Choi; Jin Ho Kim; Chul Ju Han; Su Cheol Park; Byung Hee Lee; Young Han Kim; Dong Han Lee Journal: J Surg Oncol Date: 2010-09-01 Impact factor: 3.454
Authors: Clemens Grassberger; Susannah G Ellsworth; Moses Q Wilks; Florence K Keane; Jay S Loeffler Journal: Nat Rev Clin Oncol Date: 2019-06-26 Impact factor: 66.675