Cong Zhu1,2, Radhe Mohan2, Steven H Lin3, Goo Jun2, Ashraf Yaseen4, Xiaoqian Jiang5, Qianxia Wang1, Wenhua Cao1, Brian P Hobbs6. 1. Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, TX. 2. Department of Epidemiology, Human Genetics, and Environmental Sciences, School of Public Health, The University of Texas Health Science Center at Houston, Houston, TX. 3. Department of Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX. 4. Department of Biostatistics and Data Science, School of Public Health, The University of Texas Health Science Center at Houston, Houston, TX. 5. School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX. 6. Department of Population Health, Dell Medical School, The University of Texas at Austin, Austin, TX.
Abstract
PURPOSE: Radiotherapy (RT)-induced lymphopenia (RIL) is commonly associated with adverse clinical outcomes in patients with cancer. Using machine learning techniques, a retrospective study was conducted for patients with esophageal cancer treated with proton and photon therapies to characterize the principal pretreatment clinical and radiation dosimetric risk factors of grade 4 RIL (G4RIL) as well as to establish G4RIL risk profiles. METHODS: A single-institution retrospective data of 746 patients with esophageal cancer treated with photons (n = 500) and protons (n = 246) was reviewed. The primary end point of our study was G4RIL. Clustering techniques were applied to identify patient subpopulations with similar pretreatment clinical and radiation dosimetric characteristics. XGBoost was built on a training set (n = 499) to predict G4RIL risks. Predictive performance was assessed on the remaining n = 247 patients. SHapley Additive exPlanations were used to rank the importance of individual predictors. Counterfactual analyses compared patients' risk profiles assuming that they had switched modalities. RESULTS: Baseline absolute lymphocyte count and volumes of lung and spleen receiving ≥ 15 and ≥ 5 Gy, respectively, were the most important G4RIL risk determinants. The model achieved sensitivitytesting-set 0.798 and specificitytesting-set 0.667 with an area under the receiver operating characteristics curve (AUCtesting-set) of 0.783. The G4RIL risk for an average patient receiving protons increased by 19% had the patient switched to photons. Reductions in G4RIL risk were maximized with proton therapy for patients with older age, lower baseline absolute lymphocyte count, and higher lung and heart dose. CONCLUSION: G4RIL risk varies for individual patients with esophageal cancer and is modulated by radiotherapy dosimetric parameters. The framework for machine learning presented can be applied broadly to study risk determinants of other adverse events, providing the basis for adapting treatment strategies for mitigation.
PURPOSE: Radiotherapy (RT)-induced lymphopenia (RIL) is commonly associated with adverse clinical outcomes in patients with cancer. Using machine learning techniques, a retrospective study was conducted for patients with esophageal cancer treated with proton and photon therapies to characterize the principal pretreatment clinical and radiation dosimetric risk factors of grade 4 RIL (G4RIL) as well as to establish G4RIL risk profiles. METHODS: A single-institution retrospective data of 746 patients with esophageal cancer treated with photons (n = 500) and protons (n = 246) was reviewed. The primary end point of our study was G4RIL. Clustering techniques were applied to identify patient subpopulations with similar pretreatment clinical and radiation dosimetric characteristics. XGBoost was built on a training set (n = 499) to predict G4RIL risks. Predictive performance was assessed on the remaining n = 247 patients. SHapley Additive exPlanations were used to rank the importance of individual predictors. Counterfactual analyses compared patients' risk profiles assuming that they had switched modalities. RESULTS: Baseline absolute lymphocyte count and volumes of lung and spleen receiving ≥ 15 and ≥ 5 Gy, respectively, were the most important G4RIL risk determinants. The model achieved sensitivitytesting-set 0.798 and specificitytesting-set 0.667 with an area under the receiver operating characteristics curve (AUCtesting-set) of 0.783. The G4RIL risk for an average patient receiving protons increased by 19% had the patient switched to photons. Reductions in G4RIL risk were maximized with proton therapy for patients with older age, lower baseline absolute lymphocyte count, and higher lung and heart dose. CONCLUSION: G4RIL risk varies for individual patients with esophageal cancer and is modulated by radiotherapy dosimetric parameters. The framework for machine learning presented can be applied broadly to study risk determinants of other adverse events, providing the basis for adapting treatment strategies for mitigation.
Authors: Peter S N van Rossum; Wei Deng; David M Routman; Amy Y Liu; Cai Xu; Yutaka Shiraishi; Max Peters; Kenneth W Merrell; Christopher L Hallemeier; Radhe Mohan; Steven H Lin Journal: Pract Radiat Oncol Date: 2019-07-29
Authors: Radhe Mohan; Amy Y Liu; Paul D Brown; Anita Mahajan; Jeffrey Dinh; Caroline Chung; Sarah McAvoy; Mary Frances McAleer; Steven H Lin; Jing Li; Amol J Ghia; Cong Zhu; Erik P Sulman; John F de Groot; Amy B Heimberger; Susan L McGovern; Clemens Grassberger; Helen Shih; Susannah Ellsworth; David R Grosshans Journal: Neuro Oncol Date: 2021-02-25 Impact factor: 12.300
Authors: Yutaka Shiraishi; Penny Fang; Cai Xu; Juhee Song; Sunil Krishnan; Eugene J Koay; Reza J Mehran; Wayne L Hofstetter; Mariela Blum-Murphy; Jaffer A Ajani; Ritsuko Komaki; Bruce Minsky; Radhe Mohan; Charles C Hsu; Brian P Hobbs; Steven H Lin Journal: Radiother Oncol Date: 2017-12-14 Impact factor: 6.280
Authors: Anirudh Yalamanchali; Hong Zhang; Ke Colin Huang; Radhe Mohan; Steven H Lin; Cong Zhu; Stuart A Grossman; Jian-Yue Jin; Susannah G Ellsworth Journal: Adv Radiat Oncol Date: 2020-08-10
Authors: Maximilian Knoll; Maria Waltenberger; Jennifer Furkel; Ute Wirkner; Aoife Ward Gahlawat; Ivana Dokic; Christian Schwager; Sebastian Adeberg; Stefan Rieken; Tobias Kessler; Felix Sahm; Laila König; Christel Herold-Mende; Stephanie E Combs; Jürgen Debus; Amir Abdollahi Journal: Cancers (Basel) Date: 2022-01-28 Impact factor: 6.639