Literature DB >> 27664507

Prediction of lung cancer incidence on the low-dose computed tomography arm of the National Lung Screening Trial: A dynamic Bayesian network.

Panayiotis Petousis1, Simon X Han2, Denise Aberle2, Alex A T Bui2.   

Abstract

INTRODUCTION: Identifying high-risk lung cancer individuals at an early disease stage is the most effective way of improving survival. The landmark National Lung Screening Trial (NLST) demonstrated the utility of low-dose computed tomography (LDCT) imaging to reduce mortality (relative to X-ray screening). As a result of the NLST and other studies, imaging-based lung cancer screening programs are now being implemented. However, LDCT interpretation results in a high number of false positives. A set of dynamic Bayesian networks (DBN) were designed and evaluated to provide insight into how longitudinal data can be used to help inform lung cancer screening decisions.
METHODS: The LDCT arm of the NLST dataset was used to build and explore five DBNs for high-risk individuals. Three of these DBNs were built using a backward construction process, and two using structure learning methods. All models employ demographics, smoking status, cancer history, family lung cancer history, exposure risk factors, comorbidities related to lung cancer, and LDCT screening outcome information. Given the uncertainty arising from lung cancer screening, a cancer state-space model based on lung cancer staging was utilized to characterize the cancer status of an individual over time. The models were evaluated on balanced training and test sets of cancer and non-cancer cases to deal with data imbalance and overfitting.
RESULTS: Results were comparable to expert decisions. The average area under the curve (AUC) of the receiver operating characteristic (ROC) for the three intervention points of the NLST trial was higher than 0.75 for all models. Evaluation of the models on the complete LDCT arm of the NLST dataset (N=25,486) demonstrated satisfactory generalization. Consensus of predictions over similar cases is reported in concordance statistics between the models' and the physicians' predictions. The models' predictive ability with respect to missing data was also evaluated with the sample of cases that missed the second screening exam of the trial (N=417). The DBNs outperformed comparison models such as logistic regression and naïve Bayes.
CONCLUSION: The lung cancer screening DBNs demonstrated high discrimination and predictive power with the majority of cancer and non-cancer cases.
Copyright © 2016 Elsevier B.V. All rights reserved.

Entities:  

Keywords:  Annual NLST cancer risk; Cancer incidence; Dynamic Bayesian networks; Expert-driven networks; Individualized lung cancer screening; Lung stage cancer state-space; Structure learning

Mesh:

Year:  2016        PMID: 27664507      PMCID: PMC5082434          DOI: 10.1016/j.artmed.2016.07.001

Source DB:  PubMed          Journal:  Artif Intell Med        ISSN: 0933-3657            Impact factor:   5.326


  31 in total

1.  A risk model for prediction of lung cancer.

Authors:  Margaret R Spitz; Waun Ki Hong; Christopher I Amos; Xifeng Wu; Matthew B Schabath; Qiong Dong; Sanjay Shete; Carol J Etzel
Journal:  J Natl Cancer Inst       Date:  2007-05-02       Impact factor: 13.506

2.  Prognostic Bayesian networks II: an application in the domain of cardiac surgery.

Authors:  Marion Verduijn; Peter M J Rosseel; Niels Peek; Evert de Jonge; Bas A J M de Mol
Journal:  J Biomed Inform       Date:  2007-07-26       Impact factor: 6.317

3.  Lung cancer risk prediction to select smokers for screening CT--a model based on the Italian COSMOS trial.

Authors:  Patrick Maisonneuve; Vincenzo Bagnardi; Massimo Bellomi; Lorenzo Spaggiari; Giuseppe Pelosi; Cristiano Rampinelli; Raffaella Bertolotti; Nicole Rotmensz; John K Field; Andrea Decensi; Giulia Veronesi
Journal:  Cancer Prev Res (Phila)       Date:  2011-08-02

4.  A dynamic Bayesian network for estimating the risk of falls from real gait data.

Authors:  German Cuaya; Angélica Muñoz-Meléndez; Lidia Nuñez Carrera; Eduardo F Morales; Ivett Quiñones; Alberto I Pérez; Aldo Alessi
Journal:  Med Biol Eng Comput       Date:  2012-10-14       Impact factor: 2.602

5.  An automated lung segmentation approach using bidirectional chain codes to improve nodule detection accuracy.

Authors:  Shiwen Shen; Alex A T Bui; Jason Cong; William Hsu
Journal:  Comput Biol Med       Date:  2014-12-18       Impact factor: 4.589

6.  Validation of a model of lung cancer risk prediction among smokers.

Authors:  Kathleen A Cronin; Mitchell H Gail; Zhaohui Zou; Peter B Bach; Jarmo Virtamo; Demetrius Albanes
Journal:  J Natl Cancer Inst       Date:  2006-05-03       Impact factor: 13.506

7.  A Bayesian network approach for modeling local failure in lung cancer.

Authors:  Jung Hun Oh; Jeffrey Craft; Rawan Al Lozi; Manushka Vaidya; Yifan Meng; Joseph O Deasy; Jeffrey D Bradley; Issam El Naqa
Journal:  Phys Med Biol       Date:  2011-02-18       Impact factor: 3.609

8.  Sensitivity and specificity of needle biopsy in lung malignancy.

Authors:  R H Poe; R E Tobin
Journal:  Am Rev Respir Dis       Date:  1980-11

9.  Dynamic Bayesian networks as prognostic models for clinical patient management.

Authors:  Marcel A J van Gerven; Babs G Taal; Peter J F Lucas
Journal:  J Biomed Inform       Date:  2008-02-05       Impact factor: 6.317

10.  An expanded risk prediction model for lung cancer.

Authors:  Margaret R Spitz; Carol J Etzel; Qiong Dong; Christopher I Amos; Qingyi Wei; Xifeng Wu; Waun Ki Hong
Journal:  Cancer Prev Res (Phila)       Date:  2008-09
View more
  9 in total

Review 1.  Sensor, Signal, and Imaging Informatics.

Authors:  W Hsu; S Park; Charles E Kahn
Journal:  Yearb Med Inform       Date:  2017-09-11

2.  A Bayesian model for estimating multi-state disease progression.

Authors:  Shiwen Shen; Simon X Han; Panayiotis Petousis; Robert E Weiss; Frank Meng; Alex A T Bui; William Hsu
Journal:  Comput Biol Med       Date:  2016-12-22       Impact factor: 4.589

3.  Survivability Prognosis for Lung Cancer Patients at Different Severity Stages by a Risk Factor-Based Bayesian Network Modeling.

Authors:  Kung-Jeng Wang; Jyun-Lin Chen; Kun-Huang Chen; Kung-Min Wang
Journal:  J Med Syst       Date:  2020-02-10       Impact factor: 4.460

4.  Dynamic Bayesian network for predicting physiological changes, organ dysfunctions and mortality risk in critical trauma patients.

Authors:  Qi Chen; Bihan Tang; Jiaqi Song; Ying Jiang; Xinxin Zhao; Yiming Ruan; Fangjie Zhao; Guosheng Wu; Tao Chen; Jia He
Journal:  BMC Med Inform Decis Mak       Date:  2022-05-03       Impact factor: 3.298

5.  Analysis of survival for lung cancer resections cases with fuzzy and soft set theory in surgical decision making.

Authors:  José Carlos R Alcantud; Gonzalo Varela; Beatriz Santos-Buitrago; Gustavo Santos-García; Marcelo F Jiménez
Journal:  PLoS One       Date:  2019-06-19       Impact factor: 3.240

6.  Estimating survival benefit of adjuvant therapy based on a Bayesian network prediction model in curatively resected advanced gallbladder adenocarcinoma.

Authors:  Zhi-Min Geng; Zhi-Qiang Cai; Zhen Zhang; Zhao-Hui Tang; Feng Xue; Chen Chen; Dong Zhang; Qi Li; Rui Zhang; Wen-Zhi Li; Lin Wang; Shu-Bin Si
Journal:  World J Gastroenterol       Date:  2019-10-07       Impact factor: 5.742

7.  Copy number variation in plasma as a tool for lung cancer prediction using Extreme Gradient Boosting (XGBoost) classifier.

Authors:  Daping Yu; Zhidong Liu; Chongyu Su; Yi Han; XinChun Duan; Rui Zhang; Xiaoshuang Liu; Yang Yang; Shaofa Xu
Journal:  Thorac Cancer       Date:  2019-11-06       Impact factor: 3.500

8.  Deep Q-networks with web-based survey data for simulating lung cancer intervention prediction and assessment in the elderly: a quantitative study.

Authors:  Songjing Chen; Sizhu Wu
Journal:  BMC Med Inform Decis Mak       Date:  2022-01-04       Impact factor: 2.796

9.  Identifying Lung Cancer Risk Factors in the Elderly Using Deep Neural Networks: Quantitative Analysis of Web-Based Survey Data.

Authors:  Songjing Chen; Sizhu Wu
Journal:  J Med Internet Res       Date:  2020-03-17       Impact factor: 7.076

  9 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.