1. Forecasting Individual Patient Response to Radiation Therapy in Head and Neck Cancer With a Dynamic Carrying Capacity Model
- Author
-
Abdallah S.R. Mohamed, Heiko Enderling, Mohammad U. Zahid, Louis B. Harrison, Clifton D. Fuller, Eduardo G. Moros, Jimmy J. Caudell, and Nuverah Mohsin
- Subjects
Oncology ,Conservation of Natural Resources ,Cancer Research ,medicine.medical_specialty ,medicine.medical_treatment ,Patient response ,Article ,Disease-Free Survival ,Accelerated fractionation ,Internal medicine ,Tumor Microenvironment ,Humans ,Medicine ,Volume reduction ,Radiology, Nuclear Medicine and imaging ,Tumor microenvironment ,Radiation ,business.industry ,Head and neck cancer ,medicine.disease ,Tumor Burden ,Radiation therapy ,Head and Neck Neoplasms ,Cohort ,Dose Fractionation, Radiation ,Personalized medicine ,business - Abstract
Purpose: In order for radiotherapy to enter the realm of personalized medicine it will be necessary to model and predict individual patient responses to radiotherapy. Methods and Materials: Here we model tumor dynamics as logistic growth and the effect of radiation as a reduction in the tumor carrying capacity, motivated by the impact of radiation on the tumor microenvironment. The model was assessed on weekly tumor volume data collected for two independent cohorts of head and neck cancer patients from XXXX1 and XXXX2 that received 66-70 Gy in standard daily fractions or with accelerated fractionation. To predict response to radiotherapy for individual patients, we developed a new forecasting framework that combined the learned tumor growth rate and carrying capacity reduction fraction (δ) distribution with weekly measurements of tumor volume reduction for a given test patient to estimate δ, which was used to predict patient-specific outcomes. Results: The model fit data from XXXX1 with high accuracy with patient-specific δ and a fixed tumor growth rate across all patients. The model fit data from an independent cohort from XXXX2 with comparable accuracy using the tumor growth rate learned from the XXXX1 cohort, demonstrating transferability of the growth rate. The forecasting framework predicted patient-specific outcomes with 76% sensitivity and 83% specificity for locoregional control and 68% sensitivity and 85% specificity for disease-free survival with the inclusion of four on-treatment tumor volume measurements. Conclusions: These results show that our simple mathematical model can describe a variety of tumor volume dynamics. Further, combining historically observed patient responses with a few patient-specific tumor volume measurements allows for the accurate prediction of patient outcomes, which may inform treatment adaptation and personalization.
- Published
- 2021
- Full Text
- View/download PDF