scholarly journals Comparison of Mammography Artificial Intelligence Algorithms for 5-year Breast Cancer Risk Prediction

2022 ◽  
Author(s):  
vignesh a arasu ◽  
laurel a habel ◽  
ninah s achacoso ◽  
diana s buist ◽  
jason b cord ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Artificial Intelligence ◽  
Cancer Risk ◽  
Risk Prediction ◽  
Risk Model ◽  
Interval Cancer ◽  
Area Under The Curve ◽  
Cancer Surveillance ◽  
Kaiser Permanente ◽  
Clinical Risk

PURPOSE: To examine the ability of 5 artificial intelligence (AI)-based computer vision algorithms, most trained to detect visible breast cancer on mammograms, to predict future risk relative to the Breast Cancer Surveillance Consortium clinical risk prediction model (BCSC v2). PATIENTS AND METHODS: In this case-cohort study, women who had a screening mammogram in 2016 at Kaiser Permanente Northern California with no evidence of cancer on final imaging assessment were followed through September 2021. Women with prior breast cancer or a known highly penetrant gene mutation were excluded. From the 329,814 total eligible women, a random subcohort of 13,881 women (4.2%) were selected, of whom 197 had incident cancer. All 4,475 additional incident cancers were also included. Continuous AI-predicted scores were generated from the index 2016 mammogram. Risk estimates were generated with the Kaplan-Meier method and time-varying area under the curve [AUC(t)]. RESULTS: For incident cancers at 0-1 year (interval cancer risk), BCSC demonstrated an AUC(t) of 0.62 (95% CI, 0.58-0.66), and the AI algorithms had AUC(t)s ranging from 0.66-0.71, all significantly higher than BCSC (P < .05). For incident cancers at 1 to 5 years (5-year future cancer risk), BCSC demonstrated an AUC(t) of 0.61 (95% CI, 0.60-0.62), and the AI algorithms had AUC(t)s ranging from 0.63 to 0.67, all significantly higher than BCSC. Combined BCSC and AI models demonstrated AUC(t)s for interval cancer risk of 0.67-0.73 and for 5-year future cancer risk of 0.66-0.68. CONCLUSION: The AI mammography algorithms we evaluated had significantly higher discrimination than the BCSC clinical risk model for interval and 5-year future cancer risk. Combined AI and BCSC models had slightly higher discrimination than AI alone.

scholarly journals Breast cancer risk prediction using a clinical risk model and polygenic risk score

2016 ◽  
Vol 159 (3) ◽  
pp. 513-525 ◽  
Author(s):  
Yiwey Shieh ◽  
Donglei Hu ◽  
Lin Ma ◽  
Scott Huntsman ◽  
Charlotte C. Gard ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Breast Cancer Risk ◽  
Cancer Risk ◽  
Risk Prediction ◽  
Risk Score ◽  
Risk Model ◽  
Polygenic Risk Score ◽  
Polygenic Risk ◽  
Clinical Risk

Development and Validation of a Breast Cancer Risk Prediction Model for Childhood Cancer Survivors Treated With Chest Radiation: A Report From the Childhood Cancer Survivor Study and the Dutch Hodgkin Late Effects and LATER Cohorts

2021 ◽  
pp. JCO.20.02244
Author(s):  
Chaya S. Moskowitz ◽  
Cécile M. Ronckers ◽  
Joanne F. Chou ◽  
Susan A. Smith ◽  
Danielle Novetsky Friedman ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Breast Cancer Risk ◽  
Cancer Risk ◽  
Cancer Survivors ◽  
Childhood Cancer ◽  
Risk Prediction ◽  
Area Under The Curve ◽  
Childhood Cancer Survivors ◽  
Degree Relative ◽  
Childhood Cancer Survivor Study

PURPOSE Women treated with chest radiation for childhood cancer have one of the highest risks of breast cancer. Models producing personalized breast cancer risk estimates applicable to this population do not exist. We sought to develop and validate a breast cancer risk prediction model for childhood cancer survivors treated with chest radiation incorporating treatment-related factors, family history, and reproductive factors. METHODS Analyses were based on multinational cohorts of female 5-year survivors of cancer diagnosed younger than age 21 years and treated with chest radiation. Model derivation was based on 1,120 participants in the Childhood Cancer Survivor Study diagnosed between 1970 and 1986, with median attained age 42 years (range 20-64) and 242 with breast cancer. Model validation included 1,027 participants from three cohorts, with median age 32 years (range 20-66) and 105 with breast cancer. RESULTS The model included current age, chest radiation field, whether chest radiation was delivered within 1 year of menarche, anthracycline exposure, age at menopause, and history of a first-degree relative with breast cancer. Ten-year risk estimates ranged from 2% to 23% for 30-year-old women (area under the curve, 0.63; 95% CI, 0.50 to 0.73) and from 5% to 34% for 40-year-old women (area under the curve, 0.67; 95% CI, 0.54 to 0.84). The highest risks were among premenopausal women older than age 40 years treated with mantle field radiation within a year of menarche who had a first-degree relative with breast cancer. It showed good calibration with an expected-to-observed ratio of the number of breast cancers of 0.92 (95% CI, 0.74 to 1.16). CONCLUSION Breast cancer risk varies among childhood cancer survivors treated with chest radiation. Accurate risk prediction may aid in refining surveillance, counseling, and preventive strategies in this population.

A breast cancer risk model as a predictor of interval cancer rate and tumor characteristics.

2018 ◽  
Vol 36 (15_suppl) ◽  
pp. 1506-1506
Author(s):  
Nickolas Dreher ◽  
Irene Acerbi ◽  
Edward Kenji Hadeler ◽  
Yiwey Shieh ◽  
Michelle E. Melisko ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Breast Cancer Risk ◽  
Cancer Risk ◽  
Risk Model ◽  
Interval Cancer ◽  
Tumor Characteristics ◽  
Cancer Rate ◽  
Interval Cancer Rate

scholarly journals A streamlined model for use in clinical breast cancer risk assessment maintains predictive power and is further improved with inclusion of a polygenic risk score

PLoS ONE ◽  
2021 ◽  
Vol 16 (1) ◽  
pp. e0245375
Author(s):  
Richard Allman ◽  
Erika Spaeth ◽  
John Lai ◽  
Susan J. Gross ◽  
John L. Hopper
Keyword(s):  
Breast Cancer ◽  
Risk Factors ◽  
African American ◽  
Breast Cancer Risk ◽  
Cancer Risk ◽  
Risk Score ◽  
Clinical Risk Factors ◽  
Polygenic Risk Score ◽  
Gail Model ◽  
Clinical Risk

Five-year absolute breast cancer risk prediction models are required to comply with national guidelines regarding risk reduction regimens. Models including the Gail model are under-utilized in the general population for various reasons, including difficulty in accurately completing some clinical fields. The purpose of this study was to determine if a streamlined risk model could be designed without substantial loss in performance. Only the clinical risk factors that were easily answered by women will be retained and combined with an objective validated polygenic risk score (PRS) to ultimately improve overall compliance with professional recommendations. We first undertook a review of a series of 2,339 Caucasian, African American and Hispanic women from the USA who underwent clinical testing. We first used deidentified test request forms to identify the clinical risk factors that were best answered by women in a clinical setting and then compared the 5-year risks for the full model and the streamlined model in this clinical series. We used OPERA analysis on previously published case-control data from 11,924 Gail model samples to determine clinical risk factors to include in a streamlined model: first degree family history and age that could then be combined with the PRS. Next, to ensure that the addition of PRS to the streamlined model was indeed beneficial, we compared risk stratification using the Streamlined model with and without PRS for the existing case-control datasets comprising 1,313 cases and 10,611 controls of African-American (n = 7421), Caucasian (n = 1155) and Hispanic (n = 3348) women, using the area under the curve to determine model performance. The improvement in risk discrimination from adding the PRS risk score to the Streamlined model was 52%, 46% and 62% for African-American, Caucasian and Hispanic women, respectively, based on changes in log OPERA. There was no statistically significant difference in mean risk scores between the Gail model plus risk PRS compared to the Streamlined model plus PRS. This study demonstrates that validated PRS can be used to streamline a clinical test for primary care practice without diminishing test performance. Importantly, by eliminating risk factors that women find hard to recall or that require obtaining medical records, this model may facilitate increased clinical adoption of 5-year risk breast cancer risk prediction test in keeping with national standards and guidelines for breast cancer risk reduction.

Sign in / Sign up

Export Citation Format

Share Document