Dataset Information

Structure-Leveraged Methods in Breast Cancer Risk Prediction.

ABSTRACT: Predicting breast cancer risk has long been a goal of medical research in the pursuit of precision medicine. The goal of this study is to develop novel penalized methods to improve breast cancer risk prediction by leveraging structure information in electronic health records. We conducted a retrospective case-control study, garnering 49 mammography descriptors and 77 high-frequency/low-penetrance single-nucleotide polymorphisms (SNPs) from an existing personalized medicine data repository. Structured mammography reports and breast imaging features have long been part of a standard electronic health record (EHR), and genetic markers likely will be in the near future. Lasso and its variants are widely used approaches to integrated learning and feature selection, and our methodological contribution is to incorporate the dependence structure among the features into these approaches. More specifically, we propose a new methodology by combining group penalty and [Formula: see text] (1 ? p ? 2) fusion penalty to improve breast cancer risk prediction, taking into account structure information in mammography descriptors and SNPs. We demonstrate that our method provides benefits that are both statistically significant and potentially significant to people's lives.

SUBMITTER: Fan J

PROVIDER: S-EPMC5446896 | biostudies-literature | 2016 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Structure-Leveraged Methods in Breast Cancer Risk Prediction.

Fan Jun J Wu Yirong Y Yuan Ming M Page David D Liu Jie J Ong Irene M IM Peissig Peggy P Burnside Elizabeth E

Journal of machine learning research : JMLR 20161201

Predicting breast cancer risk has long been a goal of medical research in the pursuit of precision medicine. The goal of this study is to develop novel penalized methods to improve breast cancer risk prediction by leveraging structure information in electronic health records. We conducted a retrospective case-control study, garnering 49 mammography descriptors and 77 high-frequency/low-penetrance single-nucleotide polymorphisms (SNPs) from an existing personalized medicine data repository. Struc ...[more]

PMID: 28559747

Similar Datasets

Project description:Breast cancer is one of the most common invasive tumors causing high mortality among women. It is characterized by high heterogeneity regarding its biological and clinical characteristics. Several high-throughput assays have been used to collect genome-wide information for many patients in large collaborative studies. This knowledge has improved our understanding of its biology and led to new methods of diagnosing and treating the disease. In particular, system biology has become a valid approach to obtain better insights into breast cancer biological mechanisms. A crucial component of current research lies in identifying novel biomarkers that can be predictive for breast cancer patient prognosis on the basis of the molecular signature of the tumor sample. However, the high dimension and low sample size of data greatly increase the difficulty of cancer survival analysis demanding for the development of ad-hoc statistical methods. In this work, we propose novel screening-network methods that predict patient survival outcome by screening key survival-related genes and we assess the capability of the proposed approaches using METABRIC dataset. In particular, we first identify a subset of genes by using variable screening techniques on gene expression data. Then, we perform Cox regression analysis by incorporating network information associated with the selected subset of genes. The novelty of this work consists in the improved prediction of survival responses due to the different types of screenings (i.e., a biomedical-driven, data-driven and a combination of the two) before building the network-penalized model. Indeed, the combination of the two screening approaches allows us to use the available biological knowledge on breast cancer and complement it with additional information emerging from the data used for the analysis. Moreover, we also illustrate how to extend the proposed approaches to integrate an additional omic layer, such as copy number aberrations, and we show that such strategies can further improve our prediction capabilities. In conclusion, our approaches allow to discriminate patients in high-and low-risk groups using few potential biomarkers and therefore, can help clinicians to provide more precise prognoses and to facilitate the subsequent clinical management of patients at risk of disease.

Project description:PURPOSE:To update and expand the Rosner-Colditz breast cancer incidence model by evaluating the contributions of more recently identified risk factors as well as predicted percent mammographic density (MD) to breast cancer risk. METHODS:Using data from the Nurses' Health Study (NHS) and NHSII, we added adolescent somatotype (9 unit scale), vegetable intake (servings/day), breastfeeding (months), physical activity (MET-h/week), and predicted percent MD to the Rosner-Colditz model to determine whether these variables improved model discrimination. We evaluated all invasive as well as ER+/PR+, ER+/PR-, and ER-/PR- breast cancer. RESULTS:In the NHS/NHSII, we accrued over 5200 cases of invasive breast cancer over more than 20 years of follow-up with complete data on the risk factors. Adolescent somatotype and predicted percent MD significantly improved the original Rosner-Colditz model for all invasive breast cancer (change in age-adjusted AUC = 0.020, p < 0.001). The relative risk (RR) of invasive breast cancer for a 4-unit increase in adolescent somatotype was 0.62 (95% CI 0.56, 0.70), whereas the RR for a 20-unit increase in predicted percent MD was 1.32 (95% CI 1.28, 1.36). Adolescent somatotype and predicted percent MD also significantly improved the ER+/PR+model (change in age-adjusted AUC = 0.020, p < 0.001) as well as the ER+/PR- model (change in age-adjusted AUC = 0.012, p = 0.007). Adolescent somatotype, predicted percent MD, breastfeeding, and vegetable intake improved the ER-/PR- model (change in AUC = 0.031, p < 0.0001). The RR of ER-/PR- disease for 5 vegetable servings/day increase was 0.83 (95% CI 0.70, 0.99), while the RR for every 12 months of breastfeeding was 0.88 (95% CI 0.77, 1.01). Physical activity did not improve risk classification in any model. CONCLUSION:Adolescent somatotype and predicted percent MD significantly improved breast cancer risk classification using the Rosner-Colditz model. Further, risk factors specific to ER- disease, such as breastfeeding and vegetable intake, may also help improve risk prediction of this aggressive subtype.

Dataset Information

Structure-Leveraged Methods in Breast Cancer Risk Prediction.

Publications

Structure-Leveraged Methods in Breast Cancer Risk Prediction.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure