Bolette Mikela Vilmun1, Ilse Vejborg2, Elsebeth Lynge3, Martin Lillholm4, Mads Nielsen4, Michael Bachmann Nielsen2, Jonathan Frederik Carlsen2. 1. Department of Diagnostic Radiology, Copenhagen University Hospital, Rigshospitalet, Blegdamsvej 9, DK-2100 Copenhagen Ø, Denmark; Department of Clinical Medicine, University of Copenhagen, Blegdamsvej 3B, 2200 Copenhagen, Denmark. Electronic address: bolette.mikela.vilmun.01@regionh.dk. 2. Department of Diagnostic Radiology, Copenhagen University Hospital, Rigshospitalet, Blegdamsvej 9, DK-2100 Copenhagen Ø, Denmark; Department of Clinical Medicine, University of Copenhagen, Blegdamsvej 3B, 2200 Copenhagen, Denmark. 3. Nykøbing Falster Hospital, University of Copenhagen, Fjordvej 15, DK-4300 Nykøbing Falster, Denmark. 4. Biomediq, Fruebjergvej 3, DK-2100 Copenhagen Ø, Denmark; Department of Computer Science, University of Copenhagen, Universitetsparken 5, DK-2100 Copenhagen Ø, Denmark.
Abstract
PURPOSE: Assessment of a woman's risk of breast cancer is essential when moving towards personalized screening. Breast density is a well-known risk factor and has the potential to improve accuracy of risk prediction models. In this study we reviewed the impact on model performance of adding breast density to clinical breast cancer risk prediction models. METHODS: We conducted a systematic review using a pre-specified search strategy for PubMed, EMBASE, Web of Science, and Cochrane Library from January 2007 until November 2019. Studies were screened using the Covidence software. Eligible studies developed or modified existing breast cancer risk prediction models applicable to the general population of women by adding breast density to the model. Improvement in discriminatory accuracy was measured as an increase in the Area Under the Curve or concordance statistics. RESULTS: Eleven eligible studies were identified by the search and one by reference check. Four studies modified the Gail model, four modified the Tyrer-Cuzick model, and five studies developed new models. Several methods were used to measure breast density, including visual, semi- and fully automated methods. Eleven studies reported discriminatory accuracy and one study reported calibration. Seven studies found a statistically significantly increased discriminatory accuracy when including density in the model. The increase in AUC ranged 0.03 to 0.14. Four studies did not report on statistical significance, but reported an increased AUC ranging from 0.01 to 0.06. CONCLUSION: Including mammographic breast density has the potential to improve breast cancer risk prediction models. However, all models demonstrated limited discrimination accuracy.
PURPOSE: Assessment of a woman's risk of breast cancer is essential when moving towards personalized screening. Breast density is a well-known risk factor and has the potential to improve accuracy of risk prediction models. In this study we reviewed the impact on model performance of adding breast density to clinical breast cancer risk prediction models. METHODS: We conducted a systematic review using a pre-specified search strategy for PubMed, EMBASE, Web of Science, and Cochrane Library from January 2007 until November 2019. Studies were screened using the Covidence software. Eligible studies developed or modified existing breast cancer risk prediction models applicable to the general population of women by adding breast density to the model. Improvement in discriminatory accuracy was measured as an increase in the Area Under the Curve or concordance statistics. RESULTS: Eleven eligible studies were identified by the search and one by reference check. Four studies modified the Gail model, four modified the Tyrer-Cuzick model, and five studies developed new models. Several methods were used to measure breast density, including visual, semi- and fully automated methods. Eleven studies reported discriminatory accuracy and one study reported calibration. Seven studies found a statistically significantly increased discriminatory accuracy when including density in the model. The increase in AUC ranged 0.03 to 0.14. Four studies did not report on statistical significance, but reported an increased AUC ranging from 0.01 to 0.06. CONCLUSION: Including mammographic breast density has the potential to improve breast cancer risk prediction models. However, all models demonstrated limited discrimination accuracy.
Authors: Ritse M Mann; Alexandra Athanasiou; Pascal A T Baltzer; Julia Camps-Herrero; Paola Clauser; Eva M Fallenberg; Gabor Forrai; Michael H Fuchsjäger; Thomas H Helbich; Fleur Killburn-Toppin; Mihai Lesaru; Pietro Panizza; Federica Pediconi; Ruud M Pijnappel; Katja Pinker; Francesco Sardanelli; Tamar Sella; Isabelle Thomassin-Naggara; Sophia Zackrisson; Fiona J Gilbert; Christiane K Kuhl Journal: Eur Radiol Date: 2022-03-08 Impact factor: 7.034
Authors: Aimilia Gastounioti; Mikael Eriksson; Eric A Cohen; Walter Mankowski; Lauren Pantalone; Sarah Ehsan; Anne Marie McCarthy; Despina Kontos; Per Hall; Emily F Conant Journal: Cancers (Basel) Date: 2022-09-30 Impact factor: 6.575
Authors: John Heine; Erin Fowler; Christopher G Scott; Matthew R Jensen; John Shepherd; Carrie B Hruska; Stacey J Winham; Kathleen R Brandt; Fang F Wu; Aaron D Norman; Vernon S Pankratz; Diana L Miglioretti; Karla Kerlikowske; Celine M Vachon Journal: AJR Am J Roentgenol Date: 2021-06-23 Impact factor: 6.582
Authors: Elsebeth Lynge; Anna-Belle Beau; My von Euler-Chelpin; George Napolitano; Sisse Njor; Anne Helene Olsen; Walter Schwartz; Ilse Vejborg Journal: Breast Cancer Res Treat Date: 2020-08-30 Impact factor: 4.872