scholarly journals Multidimensional Machine Learning Personalized Prognostic Model in an Early Invasive Breast Cancer Population-Based Cohort in China: Algorithm Validation Study

10.2196/19069 ◽  
2020 ◽  
Vol 8 (11) ◽  
pp. e19069
Author(s):  
Xiaorong Zhong ◽  
Ting Luo ◽  
Ling Deng ◽  
Pei Liu ◽  
Kejia Hu ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Disease Progression ◽  
Invasive Breast Cancer ◽  
Prognostic Model ◽  
The United States ◽  
Biomedical Ethics ◽  
Extreme Gradient Boosting ◽  
All Cause Mortality ◽  
Specific Mortality ◽  
Cancer Specific Mortality

Background Current online prognostic prediction models for breast cancer, such as Adjuvant! Online and PREDICT, are based on specific populations. They have been well validated and widely used in the United States and Western Europe; however, several validation attempts in non-European countries have revealed suboptimal predictions. Objective We aimed to develop an advanced breast cancer prognosis model for disease progression, cancer-specific mortality, and all-cause mortality by integrating tumor, demographic, and treatment characteristics from a large breast cancer cohort in China. Methods This study was approved by the Clinical Test and Biomedical Ethics Committee of West China Hospital, Sichuan University on May 17, 2012. Data collection for this project was started in May 2017 and ended in March 2019. Data on 5293 women diagnosed with stage I to III invasive breast cancer between 2000 and 2013 were collected. Disease progression, cancer-specific mortality, all-cause mortality, and the likelihood of disease progression or death within a 5-year period were predicted. Extreme gradient boosting was used to develop the prediction model. Model performance was assessed by calculating the area under the receiver operating characteristic curve (AUROC), and the model was calibrated and compared with PREDICT. Results The training, test, and validation sets comprised 3276 (499 progressions, 202 breast cancer-specific deaths, and 261 all-cause deaths within 5-year follow-up), 1405 (211 progressions, 94 breast cancer-specific deaths, and 129 all-cause deaths), and 612 (109 progressions, 33 breast cancer-specific deaths, and 37 all-cause deaths) women, respectively. The AUROC values for disease progression, cancer-specific mortality, and all-cause mortality were 0.76, 0.88, and 0.82 for training set; 0.79, 0.80, and 0.83 for the test set; and 0.79, 0.84, and 0.88 for the validation set, respectively. Calibration analysis demonstrated good agreement between predicted and observed events within 5 years. Comparable AUROC and calibration results were confirmed in different age, residence status, and receptor status subgroups. Compared with PREDICT, our model showed similar AUROC and improved calibration values. Conclusions Our prognostic model exhibits high discrimination and good calibration. It may facilitate prognosis prediction and clinical decision making for patients with breast cancer in China.

scholarly journals Multidimensional Machine Learning Personalized Prognostic Model in an Early Invasive Breast Cancer Population-Based Cohort in China: Algorithm Validation Study (Preprint)

2020 ◽  
Author(s):  
Xiaorong Zhong ◽  
Ting Luo ◽  
Ling Deng ◽  
Pei Liu ◽  
Kejia Hu ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Disease Progression ◽  
Invasive Breast Cancer ◽  
Prognostic Model ◽  
The United States ◽  
Biomedical Ethics ◽  
Extreme Gradient Boosting ◽  
All Cause Mortality ◽  
Specific Mortality ◽  
Cancer Specific Mortality

BACKGROUND Current online prognostic prediction models for breast cancer, such as Adjuvant! Online and PREDICT, are based on specific populations. They have been well validated and widely used in the United States and Western Europe; however, several validation attempts in non-European countries have revealed suboptimal predictions. OBJECTIVE We aimed to develop an advanced breast cancer prognosis model for disease progression, cancer-specific mortality, and all-cause mortality by integrating tumor, demographic, and treatment characteristics from a large breast cancer cohort in China. METHODS This study was approved by the Clinical Test and Biomedical Ethics Committee of West China Hospital, Sichuan University on May 17, 2012. Data collection for this project was started in May 2017 and ended in March 2019. Data on 5293 women diagnosed with stage I to III invasive breast cancer between 2000 and 2013 were collected. Disease progression, cancer-specific mortality, all-cause mortality, and the likelihood of disease progression or death within a 5-year period were predicted. Extreme gradient boosting was used to develop the prediction model. Model performance was assessed by calculating the area under the receiver operating characteristic curve (AUROC), and the model was calibrated and compared with PREDICT. RESULTS The training, test, and validation sets comprised 3276 (499 progressions, 202 breast cancer-specific deaths, and 261 all-cause deaths within 5-year follow-up), 1405 (211 progressions, 94 breast cancer-specific deaths, and 129 all-cause deaths), and 612 (109 progressions, 33 breast cancer-specific deaths, and 37 all-cause deaths) women, respectively. The AUROC values for disease progression, cancer-specific mortality, and all-cause mortality were 0.76, 0.88, and 0.82 for training set; 0.79, 0.80, and 0.83 for the test set; and 0.79, 0.84, and 0.88 for the validation set, respectively. Calibration analysis demonstrated good agreement between predicted and observed events within 5 years. Comparable AUROC and calibration results were confirmed in different age, residence status, and receptor status subgroups. Compared with PREDICT, our model showed similar AUROC and improved calibration values. CONCLUSIONS Our prognostic model exhibits high discrimination and good calibration. It may facilitate prognosis prediction and clinical decision making for patients with breast cancer in China.

The relationship between statins and breast cancer prognosis varies by statin type and exposure time: A meta-analysis.

2017 ◽  
Vol 35 (15_suppl) ◽  
pp. e21606-e21606
Author(s):  
Binliang Liu ◽  
Zongbi Yi ◽  
Xiuwen Guan ◽  
Fei Ma ◽  
Yi-Xin Zeng
Keyword(s):  
Breast Cancer ◽  
Protective Effect ◽  
Breast Cancer Prognosis ◽  
Cancer Prognosis ◽  
All Cause Mortality ◽  
Specific Mortality ◽  
Cancer Specific Mortality ◽  
The Relationship ◽  
Statin Use

e21606 Background:Breast cancer is the most common cancer in females. The effects of statins on breast cancer prognosis have long been controversial, so it is important to investigate the relationship between statin type, exposure time, and breast cancer prognosis. This study sought to explore the effect of statins on breast cancer prognosis. Methods:We searched the MEDLINE, EMBASE, Cochrane Library between October 15, 2016 and January 20, 2017. Searches combined the terms “breast neoplasms[MeSH]”, “statins”, “prognosis” or “survival” or “mortality” with no limit on publication date. Data were analyzed using Stata/SE 11.0. Results: 7 studies finally met the selection criteria and 197,048 included women. Overall statin use was associated with lower cancer-specific mortality and all-cause mortality (HR 0.73, 95% CI 0.59-0.92, P = 0.000 and HR 0.72, 95% CI 0.58-0.89, P = 0.000). Lipophilic statins were associated with decreased breast cancer-specific and all-cause mortality (HR 0.57, 95% CI 0.46-0.70, P = 0.000 and HR 0.57, 95% CI 0.48-0.69, P = 0.000); however, hydrophilic statins were weakly protective against only all-cause mortality (HR 0.79, 95% CI 0.65-0.97, P = 0.132) and not breast cancer-specific mortality (HR 0.94, 95% CI 0.76-1.17, P = 0.174). Of note, more than four years of follow-up did not show a significant correlation between statin use and cancer-specific mortality or all-cause mortality (HR 0.84, 95% CI 0.71-1.00, P = 0.616 and HR 0.95, 95% CI 0.75-1.19, P = 0.181), while groups with less than four years of follow-up still showed the protective effect of statins against cancer-specific mortality and all-cause mortality (HR 0.62, 95% CI 0.44-0.87, P = 0.000 and HR 0.61, 95% CI 0.45-0.80, P = 0.000). Conclusions:Although statins can reduce breast cancer patient mortality, the benefit appears to be constrained by statin type and follow-up time. Lipophilic statins showed a strong protective function in breast cancer patients, while hydrophilic statins only slightly improved all-cause mortality. Finally, the protective effect of statins could only be observed in groups with less than four years of follow-up.

scholarly journals A pre-operative prognostic model predicting all cause and cause specific mortality for women presenting with invasive breast cancer

The Breast ◽  
2022 ◽  
Vol 61 ◽  
pp. 11-21
Author(s):  
Huan Wang ◽  
Peter Donnan ◽  
E. Jane Macaskill ◽  
Lee Jordan ◽  
Alastair Thompson ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Invasive Breast Cancer ◽  
Prognostic Model ◽  
Specific Mortality

Mortgage Lending Bias and Breast Cancer Survival Among Older Women in the United States

2021 ◽  
pp. JCO.21.00112
Author(s):  
Kirsten M. M. Beyer ◽  
Yuhong Zhou ◽  
Purushottam W. Laud ◽  
Emily L. McGinley ◽  
Tina W. F. Yen ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Older Women ◽  
Cancer Survival ◽  
The United States ◽  
Mortgage Lending ◽  
Comorbid Conditions ◽  
Breast Cancer Specific Mortality ◽  
Specific Mortality ◽  
Cancer Specific Mortality ◽  
The Relationship

PURPOSE The objective was to examine the relationship between contemporary redlining (mortgage lending bias on the basis of property location) and survival among older women with breast cancer in the United States. METHODS A redlining index using Home Mortgage Disclosure Act data (2007-2013) was linked by census tract with a SEER-Medicare cohort of 27,516 women age 66-90 years with an initial diagnosis of stage I-IV breast cancer in 2007-2009 and follow-up through 2015. Cox proportional hazards models were used to examine the relationship between redlining and both all-cause and breast cancer–specific mortality, accounting for covariates. RESULTS Overall, 34% of non-Hispanic White, 57% of Hispanic, and 79% of non-Hispanic Black individuals lived in redlined tracts. As the redlining index increased, women experienced poorer survival. This effect was strongest for women with no comorbid conditions, who comprised 54% of the sample. For redlining index values of 1 (low), 2 (moderate), and 3 (high), as compared with 0.5 (least), hazard ratios (HRs) (and 95% CIs) for all-cause mortality were HR = 1.10 (1.06 to 1.14), HR = 1.27 (1.17 to 1.38), and HR = 1.39 (1.25 to 1.55), respectively, among women with no comorbidities. A similar pattern was found for breast cancer–specific mortality. CONCLUSION Contemporary redlining is associated with poorer breast cancer survival. The impact of this bias is emphasized by the pronounced effect even among women with health insurance (Medicare) and no comorbid conditions. The magnitude of this neighborhood level effect demands an increased focus on upstream determinants of health to support comprehensive patient care. The housing sector actively reveals structural racism and economic disinvestment and is an actionable policy target to mitigate adverse upstream health determinants for the benefit of patients with cancer.

scholarly journals Prognostic value of depression and anxiety on breast cancer recurrence and mortality: a systematic review and meta-analysis of 282,203 patients

2020 ◽  
Vol 25 (12) ◽  
pp. 3186-3197 ◽  
Author(s):  
Xuan Wang ◽  
Neng Wang ◽  
Lidan Zhong ◽  
Shengqi Wang ◽  
Yifeng Zheng ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Cancer Patients ◽  
Critical Role ◽  
Cancer Recurrence ◽  
Breast Cancer Recurrence ◽  
Depression And Anxiety ◽  
Breast Cancer Patients ◽  
All Cause Mortality ◽  
Specific Mortality ◽  
Cancer Specific Mortality

AbstractDepression and anxiety are common comorbidities in breast cancer patients. Whether depression and anxiety are associated with breast cancer progression or mortality is unclear. Herein, based on a systematic literature search, 17 eligible studies involving 282,203 breast cancer patients were included. The results showed that depression was associated with cancer recurrence [1.24 (1.07, 1.43)], all-cause mortality [1.30 (1.23, 1.36)], and cancer-specific mortality [1.29 (1.11, 1.49)]. However, anxiety was associated with recurrence [1.17 (1.02, 1.34)] and all-cause mortality [1.13 (1.07, 1.19)] but not with cancer-specific mortality [1.05 (0.82, 1.35)]. Comorbidity of depression and anxiety is associated with all-cause mortality [1.34 (1.24, 1.45)] and cancer-specific mortality [1.45 (1.11, 1.90)]. Subgroup analyses demonstrated that clinically diagnosed depression and anxiety, being female and of younger age (<60 years), and shorter follow-up duration (≤5 years) were related to a poorer prognosis. Our study highlights the critical role of depression/anxiety as an independent factor in predicting breast cancer recurrence and survival. Further research should focus on a favorable strategy that works best to improve outcomes among breast cancer patients with mental disorders.

scholarly journals Diabetes Mellitus and Obesity as Risk Factors for Bladder Cancer Prognosis: A Systematic Review and Meta-Analysis

2021 ◽  
Vol 12 ◽  
Author(s):  
Yu Lu ◽  
Jing Tao
Keyword(s):  
Diabetes Mellitus ◽  
Bladder Cancer ◽  
Body Weight ◽  
Disease Progression ◽  
Meta Analysis ◽  
Cancer Prognosis ◽  
Excess Body Weight ◽  
All Cause Mortality ◽  
Specific Mortality ◽  
Cancer Specific Mortality

BackgroundUrinary bladder carcinoma is common in developed settings, and prognosis may be impacted by lifestyle factors such as excess body weight and diabetes mellitus. The present meta-analysis aimed to systematically collate and analyze evidence on the impact of diabetes and excess BMI on bladder cancer outcomes.MethodsPubMed, Scopus, and Google Scholar databases were screened for relevant studies that examined the association between bladder cancer outcomes and diabetes and/or excess body weight. The primary outcomes for this study were mortality (both all-cause and cancer-specific), risk of cancer progression, and recurrence. Strength of association was presented in the form of pooled adjusted hazard ratios (HR). Statistical analysis was performed using STATA version 16.0.ResultsTwenty-five articles met inclusion criteria. Nine of these examined diabetes mellitus while 16 studied body mass index. All studies were retrospective. Diabetic patients had significantly higher risk for all-cause mortality (HR 1.24, 95% CI: 1.07, 1.44, n=3), cancer specific mortality (HR 1.67, 95% CI: 1.29, 2.16, n=7), disease progression (HR 1.54, 95% CI: 1.15, 2.06, n=8), and recurrence (HR 1.40, 95% CI: 1.32, 1.48, n=8) compared to non-diabetics. No statistically significant risk change for all-cause mortality, cancer specific mortality, disease progression, and recurrence was found for overweight patients. However, obese individuals were at higher risk for disease progression (HR 1.88, 95% CI: 1.41, 2.50, n=3) and recurrence (HR 1.60, 95% CI: 1.06, 2.40, n=7) compared to normal BMI patients.ConclusionsThese findings suggest that diabetes and excess body weight negatively influences bladder cancer prognosis and outcome. The increased risk of mortality due to diabetes was similar to that in the general population. Since retrospective studies are potentially susceptible to bias, future prospective studies on this subject are required.

Breast cancer specific mortality in patients with early-stage hormone receptor–positive invasive breast cancer and oncotype DX recurrence score results in the SEER database.

2016 ◽  
Vol 34 (7_suppl) ◽  
pp. 176-176 ◽  
Author(s):  
Steven Shak ◽  
Valentina Petkov ◽  
Dave P Miller ◽  
Nadia Howlader ◽  
Nathan Gliner ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Invasive Breast Cancer ◽  
Hormone Receptor ◽  
Early Stage ◽  
Recurrence Score ◽  
Oncotype Dx ◽  
Large Sample Size ◽  
Breast Cancer Specific Mortality ◽  
Specific Mortality ◽  
Cancer Specific Mortality

176 Background: NCI’s SEER Program provides cancer incidence and survival statistics for ~28% of the US. New research models are needed to characterize the use and impact of genomic tests on patient outcomes. Genomic Health and SEER collaborated to electronically supplement SEER registries with Recurrence Score (RS) results, and have evaluated breast cancer specific mortality (BCSM) in early stage hormone receptor (HR)+ HER2- invasive breast cancer. Methods: Pts were eligible for pre-specified node negative (N-) disease analysis if HR+, HER2- (by RT-PCR), no prior malignancy, 40-85 years of age, and diagnosed between Jan 2004 (Oncotype DX available Jan 2004) and Dec 2011 (SEER survival analysis complete through 2012). BCSM was defined as previously described (Howlader et al, JNCI 2010). Additional analyses of BCSM were performed for pts with N+ disease. Results: Of 169,158 eligible N- pts, 38,568 (23%) had a RS, increasing from 2% in 2004 to 35% in 2011. Pts with RS had median age of 57yr, were 99.4% female, 84% white, 29% grade 1 & 54% grade 2, 25% < 1cm & 53% 1-2cm. Median FU was 39mo. 8,239 pts had > 5yrs follow-up. Among RS < 18 (N = 21,023), RS 18-30 (N = 14,494) and RS ≥ 31 (N = 3,051) pts, chemotherapy use was reported in 7%, 34%, & 69%, respectively, and 5yr N- BCSM was 0.4% (95% CI, 0.3-0.6), 1.4% (95% CI, 1.1-1.7) and 4.4% (95% CI,3.4-5.6), respectively. Multivariate showed that RS was significantly associated with BCSM after adjusting for age, grade, and tumor size (p < 0.001), and when stratified by treatment (p < 0.001). BCSM results in additional N- subgroups (e.g., socioeconomic), and in > 60,000 N+ pts will be presented. Conclusions: 5yr survival outcomes are excellent in the over 21,000 N- pts with RS < 18 disease. RS ≥ 31 disease is associated with greater 5yr mortality despite addition of chemotherapy. The large sample size of this population-based observational study provides important information on prospective outcomes in subsets of pts that are often underrepresented in randomized clinical trials.

scholarly journals Postdiagnosis Changes in Cigarette Smoking and Survival Following Breast Cancer

2017 ◽  
Vol 1 (1) ◽  
Author(s):  
Humberto Parada ◽  
Patrick T. Bradshaw ◽  
Susan E. Steck ◽  
Lawrence S. Engel ◽  
Kathleen Conway ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Cox Regression ◽  
Smoking History ◽  
Term Survival ◽  
Breast Cancer Specific Mortality ◽  
All Cause Mortality ◽  
Specific Mortality ◽  
Cancer Specific Mortality ◽  
Never Smokers

Abstract Background The purpose of this study was to examine whether at-diagnosis smoking and postdiagnosis changes in smoking within five years after breast cancer were associated with long-term all-cause and breast cancer-specific mortality. Methods A population-based cohort of 1508 women diagnosed with first primary in situ or invasive breast cancer in 1996 to 1997 were interviewed shortly after diagnosis and again approximately five years later to assess smoking history. Participants were followed for vital status through December 31, 2014. After 18+ years of follow-up, 597 deaths were identified, 237 of which were breast cancer related. Multivariable Cox regression was used to estimate hazard ratios (HRs) and 95% confidence intervals (CIs). Results Compared with never smokers, risk of all-cause mortality was elevated among the 19% of at-diagnosis smokers (HR = 1.69, 95% CI = 1.36 to 2.11), those who smoked 20 or more cigarettes per day (HR = 1.85, 95% CI = 1.42 to 2.40), women who had smoked for 30 or more years (HR = 1.62, 95% CI = 1.28 to 2.05), and women who had smoked 30 or more pack-years (HR = 1.82, 95% CI = 1.39 to 2.37). Risk of all-cause mortality was further increased among the 8% of women who were at-/postdiagnosis smokers (HR = 2.30, 95% CI = 1.56 to 3.39) but was attenuated among the 11% women who quit smoking after diagnosis (HR = 1.83, 95% CI = 1.32 to 2.52). Compared with never smokers, breast cancer–specific mortality risk was elevated 60% (HR = 1.60, 95% CI = 0.79 to 3.23) among at-/postdiagnosis current smokers, but the confidence interval included the null value and elevated 175% (HR = 2.75, 95% CI = 1.26 to 5.99) when we considered postdiagnosis cumulative pack-years. Conclusions Smoking negatively impacts long-term survival after breast cancer. Postdiagnosis cessation of smoking may reduce the risk of all-cause mortality. Breast cancer survivors may benefit from aggressive smoking cessation programs starting as early as the time of diagnosis.

Prior DCIS and overall mortality in women with stage I breast cancer.

2021 ◽  
Vol 39 (15_suppl) ◽  
pp. e12593-e12593
Author(s):  
Rebecca A. Nelson ◽  
Lily L. Lai ◽  
Joanne E. Mortimer ◽  
Enrique Soto Perez De Celis ◽  
Rowan T. Chlebowski ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Invasive Breast Cancer ◽  
Tumor Grade ◽  
Breast Cancer Diagnosis ◽  
Stage I ◽  
Factors Associated ◽  
Breast Cancer Specific Mortality ◽  
Specific Mortality ◽  
Cancer Specific Mortality ◽  
Overall Mortality

e12593 Background: Whether a prior diagnosis of ductal carcinoma in situ (DCIS) impacts women later diagnosed with invasive breast cancer is unclear. If localized breast cancer following DCIS is more aggressive than localized breast cancer alone, this could inform therapy decisions. To our knowledge, no study has examined the impact of prior DCIS on overall mortality in women with stage I invasive breast cancer. The study objective was to determine if overall mortality for women with stage I breast cancer with prior DCIS is different from those with stage I disease without prior DCIS. Our hypothesis was that women with prior DCIS would have higher mortality compared to those without prior DCIS. Methods: 302,484 patients with stage I cancer diagnosed from 1998 to 2016 were ascertained from SEER. Of these, 5,011 (1.7%) had prior DCIS. Patients with DCIS were matched 1:2 to women with no prior DCIS based on age, year of diagnosis, race/ethnicity, marital status, and invasive breast cancer characteristics including histology, tumor grade, tumor size, T stage, N stage, ER/PR status, surgery type, radiation, and chemotherapy status. The primary study outcome was overall mortality. Cox proportional hazards models were used to compute hazard ratios (HR) and 95% confidence intervals (CI). Results: Cases and controls had similar demographics. Compared to women with stage I breast cancer without prior DCIS, overall mortality was statistically significantly lower in women with stage I breast cancer with prior DCIS (hazard ratio [HR] 0.89 95% confidence interval [CI]0.80-0.98). Other factors associated with overall mortality were bilateral mastectomy (adjusted HR: 0.62; 95% CI: 0.49-0.78), radiation therapy (adjusted HR: 0.64; 95% CI: 0.56-0.75) and chemotherapy (adjusted HR: 0.85; 95% CI: 0.72-0.99). Factors associated with higher overall mortality included age (trend p < 0.001), tumor grade (trend p = 0.003), and negative PR receptor status (adjusted HR: 1.29; 95% CI: 1.13-1.45). Breast cancer specific mortality, however, was statistically significantly higher in women with prior DCIS to their breast cancer diagnosis compared to women without prior DCIS to their breast cancer diagnosis (HR 1.24 95% CI 1.01-1.52). Conclusions: Contrary to our hypothesis, women with prior DCIS and subsequent stage I breast cancer have lower overall mortality compared to matched controls with stage I breast cancer without prior DCIS. In contrast, those with prior DCIS have higher breast cancer specific mortality than those without prior DCIS. Reasons for this discrepancy are unknown, but since DCIS is most commonly diagnosed on mammogram, differences may be related to sociodemographic characteristics that are associated with both higher screening adherence and higher overall survival, such as higher income, higher education achievement , and higher access to health care.

Sign in / Sign up

Export Citation Format

Share Document