Predictive Modeling of Survival and Toxicity in Patients With Hepatocellular Carcinoma After Radiotherapy
Predictive Modeling of Survival and Toxicity in Patients With Hepatocellular Carcinoma After...
Chamseddine, Ibrahim; Kim, Yejin; De, Brian; El Naqa, Issam; Duda, Dan G.; Wolfgang, John; Pursley, Jennifer; Paganetti, Harald; Wo, Jennifer; Hong, Theodore; Koay, Eugene J.; Grassberger, Clemens
2022-02-22 00:00:00
PURPOSETo 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 METHODSThe 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.RESULTSThe 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.CONCLUSIONMachine 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.
http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.pngJCO: Clinical Cancer InformaticsWolters Kluwer Healthhttp://www.deepdyve.com/lp/wolters-kluwer-health/predictive-modeling-of-survival-and-toxicity-in-patients-with-ysUPZIgsi2
Predictive Modeling of Survival and Toxicity in Patients With Hepatocellular Carcinoma After Radiotherapy
PURPOSETo 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 METHODSThe 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.RESULTSThe 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.CONCLUSIONMachine 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.
Journal
JCO: Clinical Cancer Informatics
– Wolters Kluwer Health
Published: Feb 22, 2022
Recommended Articles
Loading...
References
Preliminary result of stereotactic body radiotherapy as a local salvage treatment for inoperable hepatocellular carcinoma
Seo, YS; Kim, MS; Yoo, SY
Stereotactic body radiation therapy as an ablative treatment for inoperable hepatocellular carcinoma
Huertas, A; Baumann, AS; Saunier-Kubs, F
Stereotactic body radiotherapy vs. TACE or RFA as a bridge to transplant in patients with hepatocellular carcinoma. An intention-to-treat analysis
Sapisochin, G; Barry, A; Doherty, M
Radiotherapy for liver tumors
Keane, FK; Tanguturi, SK; Zhu, AX
Phase I study of individualized stereotactic body radiotherapy for hepatocellular carcinoma and intrahepatic cholangiocarcinoma
Tse, RV; Hawkins, M; Lockwood, G
Liver-directed radiotherapy for hepatocellular carcinoma
Keane, FK; Wo, JY; Zhu, AX
Phase I feasibility trial of stereotactic body radiation therapy for primary hepatocellular carcinoma
Cárdenes, HR; Price, TR; Perkins, SM
Stereotactic body radiation therapy for inoperable hepatocellular carcinoma as a local salvage treatment after incomplete transarterial chemoembolization
Kang, JK; Kim, MS; Cho, CK
Sequential phase I and II trials of stereotactic body radiotherapy for locally advanced hepatocellular carcinoma
Bujold, A; Massey, CA; Kim, JJ
Clinical feasibility and efficacy of stereotactic body radiotherapy for hepatocellular carcinoma: A systematic review and meta-analysis of observational studies
Rim, CH; Kim, HJ; Seong, J
Evaluation of liver function after proton beam therapy for hepatocellular carcinoma
Mizumoto, M; Okumura, T; Hashimoto, T
Protons versus photons for unresectable hepatocellular carcinoma: Liver decompensation and overall survival
Sanford, NN; Pursley, J; Noe, B
Assessing the interactions between radiotherapy and antitumour immunity
Grassberger, C; Ellsworth, SG; Wilks, MQ
Lymphocyte-sparing radiotherapy: The rationale for protecting lymphocyte-rich organs when combining radiotherapy with immunotherapy
Lambin, P; Lieverse, RIY; Eckert, F
Radiation-associated lymphopenia and outcomes of patients with unresectable hepatocellular carcinoma treated with radiotherapy
De, B; Ng, SP; Liu, AY
A novel deep learning model using dosimetric and clinical information for grade 4 radiotherapy-induced lymphopenia prediction
Zhu, C; Lin, SH; Jiang, X
A tumor-immune interaction model for hepatocellular carcinoma based on measured lymphocyte counts in patients undergoing radiotherapy
Sung, W; Grassberger, C; McNamara, AL
Dosimetric analysis and normal-tissue complication probability modeling of Child-Pugh score and albumin-bilirubin grade increase after hepatic irradiation
Pursley, J; El Naqa, I; Sanford, NN
Stereotactic body radiation therapy for hepatocellular carcinoma: Prognostic factors of local control, overall survival, and toxicity
Bibault, JE; Dewas, S; Vautravers-Dewas, C
Survival and prognostic factors for patients with advanced hepatocellular carcinoma after stereotactic ablative radiotherapy
Lo, CH; Yang, JF; Liu, MY
Predicting radiotherapy outcomes in hepatocellular carcinoma
Chamseddine, I; Kim, Y; Paganetti, H
Clinical trial registration: A statement from the International Committee of Medical Journal Editors
De Angelis, C; Drazen, JM; Frizelle, FA
Registering study analysis plans (SAPs) before dissecting your data-updating and standardizing outcome modeling
Thor, M; Oh, JH; Apte, AP
Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): The TRIPOD statement
Collins, GS; Reitsma, JB; Altman, DG
Radiation-associated liver injury
Pan, CC; Kavanagh, BD; Dawson, LA
Development of a fully cross-validated Bayesian network approach for local control prediction in lung cancer
Luo, Y; McShan, D; Ray, D
Bias in error estimation when using cross-validation for model selection
Varma, S; Simon, R
mice: Multivariate imputation by chained equations in R
van Buuren, S; Groothuis-Oudshoorn, K
Wrappers for feature subset selection
Kohavi, R; John, GH
Bias in random forest variable importance measures: Illustrations, sources and a solution
Strobl, C; Boulesteix, AL; Zeileis, A
Predictive learning via rule ensembles
Friedman, JH; Popescu, BE
Multivariable prognostic models: Issues in developing models, evaluating assumptions and adequacy, and measuring and reducing errors
Harrell, FE; Lee, KL; Mark, DB
Calibration: The achilles heel of predictive analytics
Van Calster, B; McLernon, DJ; van Smeden, M
Net benefit approaches to the evaluation of prediction models, molecular markers, and diagnostic tests
Vickers, AJ; Van Calster, B; Steyerberg, EW
Comparison of 2 methods for prediction of liver dosimetric indices in hepatocellular cancer IMRT planning
Cui, W; Wang, W; Hu, Z
Radiotherapy for HCC: Ready for prime time?
Bang, A; Dawson, LA
Indications of external radiotherapy for hepatocellular carcinoma from updated clinical guidelines: Diverse global viewpoints
Park, S; Yoon, WS; Rim, CH
The quest for evidence for proton therapy: Model-based approach and precision medicine
Widder, J; van der Schaaf, A; Lambin, P
Pretreatment plasma HGF as potential biomarker for susceptibility to radiation-induced liver dysfunction after radiotherapy
Hong, TS; Grassberger, C; Yeap, BY
Modeling of normal tissue complications using imaging and biomarkers after radiation therapy for hepatocellular carcinoma
El Naqa, I; Johansson, A; Owen, D
Association of pro-inflammatory soluble cytokine receptors early during hepatocellular carcinoma stereotactic radiotherapy with liver toxicity
Ng, SSW; Zhang, H; Wang, L
Identification of a novel gene signature for the prediction of recurrence in HCC patients by machine learning of genome-wide databases
Shen, J; Qi, L; Zou, Z
Neural networks for deep radiotherapy dose analysis and prediction of liver SBRT outcomes
Ibragimov, B; Toesca, DAS; Yuan, Y
A deep survival interpretable radiomics model of hepatocellular carcinoma patients
Wei, L; Owen, D; Rosen, B
Functional liver imaging and dosimetry to predict hepatotoxicity risk in cirrhotic patients with primary liver cancer
Schaub, SK; Apisarnthanarax, S; Price, RG
Optimized planning using physical objectives and constraints
To get new article updates from a journal on your personalized homepage, please log in first, or sign up for a DeepDyve account if you don’t already have one.
All DeepDyve websites use cookies to improve your online experience. They were placed on your computer when you launched this website. You can change your cookie settings through your browser.
