Integration of biological and statistical models toward personalized radiation therapy of cancer

Xiaonan Liu, Mirek Fatyga, Teresa Wu, Jing Li

Research output: Contribution to journalArticle

Abstract

Radiation Therapy (RT) is one of the most common treatments for cancer. To understand the impact of radiation toxicity on normal tissue, a Normal Tissue Complication Probability (NTCP) model is needed to link RT dose with radiation-induced complications. There are two types of NTCP models: biological and statistical models. Biological models have good generalizability but low accuracy, as they cannot factor in patient-specific information. Statistical models can incorporate patient-specific variables, but may not generalize well across different studies. We propose an integrated model that borrows strength from both biological and statistical models. Specifically, we propose a novel model formulation followed by an efficient parameter estimation algorithm, and investigate statistical properties of the estimator. We apply the integrated model to a real dataset of prostate cancer patients treated with Intensity Modulated RT at the Mayo Clinic Arizona, who are at risk of developing the grade 2+ acute rectal complication. The integrated model achieves an Area Under the Curve (AUC) level of 0.82 in prediction, whereas the AUCs for the biological and statistical models are only 0.66 and 0.76, respectively. The superior performance of the integrated model is also consistently observed over different simulation experiments.

Original languageEnglish (US)
JournalIISE Transactions
DOIs
StateAccepted/In press - Jan 1 2018

Fingerprint

Radiotherapy
Tissue
Radiation
Statistical Models
Parameter estimation
Dosimetry
Toxicity

Keywords

  • classification
  • Model integration
  • radiation toxicity

ASJC Scopus subject areas

  • Industrial and Manufacturing Engineering

Cite this

Integration of biological and statistical models toward personalized radiation therapy of cancer. / Liu, Xiaonan; Fatyga, Mirek; Wu, Teresa; Li, Jing.

In: IISE Transactions, 01.01.2018.

Research output: Contribution to journalArticle

@article{772bfa02269340eb989e13f18f17ccb6,
title = "Integration of biological and statistical models toward personalized radiation therapy of cancer",
abstract = "Radiation Therapy (RT) is one of the most common treatments for cancer. To understand the impact of radiation toxicity on normal tissue, a Normal Tissue Complication Probability (NTCP) model is needed to link RT dose with radiation-induced complications. There are two types of NTCP models: biological and statistical models. Biological models have good generalizability but low accuracy, as they cannot factor in patient-specific information. Statistical models can incorporate patient-specific variables, but may not generalize well across different studies. We propose an integrated model that borrows strength from both biological and statistical models. Specifically, we propose a novel model formulation followed by an efficient parameter estimation algorithm, and investigate statistical properties of the estimator. We apply the integrated model to a real dataset of prostate cancer patients treated with Intensity Modulated RT at the Mayo Clinic Arizona, who are at risk of developing the grade 2+ acute rectal complication. The integrated model achieves an Area Under the Curve (AUC) level of 0.82 in prediction, whereas the AUCs for the biological and statistical models are only 0.66 and 0.76, respectively. The superior performance of the integrated model is also consistently observed over different simulation experiments.",
keywords = "classification, Model integration, radiation toxicity",
author = "Xiaonan Liu and Mirek Fatyga and Teresa Wu and Jing Li",
year = "2018",
month = "1",
day = "1",
doi = "10.1080/24725854.2018.1486054",
language = "English (US)",
journal = "IISE Transactions",
issn = "2472-5854",
publisher = "Taylor and Francis Ltd.",

}

TY - JOUR

T1 - Integration of biological and statistical models toward personalized radiation therapy of cancer

AU - Liu, Xiaonan

AU - Fatyga, Mirek

AU - Wu, Teresa

AU - Li, Jing

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Radiation Therapy (RT) is one of the most common treatments for cancer. To understand the impact of radiation toxicity on normal tissue, a Normal Tissue Complication Probability (NTCP) model is needed to link RT dose with radiation-induced complications. There are two types of NTCP models: biological and statistical models. Biological models have good generalizability but low accuracy, as they cannot factor in patient-specific information. Statistical models can incorporate patient-specific variables, but may not generalize well across different studies. We propose an integrated model that borrows strength from both biological and statistical models. Specifically, we propose a novel model formulation followed by an efficient parameter estimation algorithm, and investigate statistical properties of the estimator. We apply the integrated model to a real dataset of prostate cancer patients treated with Intensity Modulated RT at the Mayo Clinic Arizona, who are at risk of developing the grade 2+ acute rectal complication. The integrated model achieves an Area Under the Curve (AUC) level of 0.82 in prediction, whereas the AUCs for the biological and statistical models are only 0.66 and 0.76, respectively. The superior performance of the integrated model is also consistently observed over different simulation experiments.

AB - Radiation Therapy (RT) is one of the most common treatments for cancer. To understand the impact of radiation toxicity on normal tissue, a Normal Tissue Complication Probability (NTCP) model is needed to link RT dose with radiation-induced complications. There are two types of NTCP models: biological and statistical models. Biological models have good generalizability but low accuracy, as they cannot factor in patient-specific information. Statistical models can incorporate patient-specific variables, but may not generalize well across different studies. We propose an integrated model that borrows strength from both biological and statistical models. Specifically, we propose a novel model formulation followed by an efficient parameter estimation algorithm, and investigate statistical properties of the estimator. We apply the integrated model to a real dataset of prostate cancer patients treated with Intensity Modulated RT at the Mayo Clinic Arizona, who are at risk of developing the grade 2+ acute rectal complication. The integrated model achieves an Area Under the Curve (AUC) level of 0.82 in prediction, whereas the AUCs for the biological and statistical models are only 0.66 and 0.76, respectively. The superior performance of the integrated model is also consistently observed over different simulation experiments.

KW - classification

KW - Model integration

KW - radiation toxicity

UR - http://www.scopus.com/inward/record.url?scp=85053805307&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85053805307&partnerID=8YFLogxK

U2 - 10.1080/24725854.2018.1486054

DO - 10.1080/24725854.2018.1486054

M3 - Article

AN - SCOPUS:85053805307

JO - IISE Transactions

JF - IISE Transactions

SN - 2472-5854

ER -