scholarly journals Predicting local and distant metastasis for breast cancer patients using the Bayesian neural network

Author(s):  
Poh Lian Choong ◽  
C.J.S. deSilva ◽  
Y. Attikiouzel
1995 ◽  
Vol 13 (12) ◽  
pp. 2869-2878 ◽  
Author(s):  
R Arriagada ◽  
L E Rutqvist ◽  
A Mattsson ◽  
A Kramar ◽  
S Rotstein

PURPOSE To analyze different events that determine event-free survival (EFS) in a randomized trial on adjuvant radiotherapy in early breast cancer patients with more than 15 years of follow-up evaluation. PATIENTS AND METHODS The trial included 960 patients with a unilateral, operable breast cancer. Surgery consisted of a modified radical mastectomy. The trial compared three arms, as follows: preoperative radiotherapy, postoperative radiotherapy, and no adjuvant treatment. Events were analyzed by a competing-risk approach. A proportional hazards multiple regression model was used to analyze the effects of radiotherapy on the risk of distant metastasis. Similar analyses were performed separately for node-negative [N(-)] and node-positive [N(+)] patients in the two groups that did not include preoperative radiotherapy. RESULTS Radiotherapy produced a fivefold decrease of the risk of local recurrence (P < .0001). In N(+) patients, postoperative radiotherapy decreased the risk of distant dissemination (relative risk, 0.63). When local recurrence was introduced in the model as a time-dependent covariate, this factor was predictive of distant dissemination (P < .0001) and nullified the effect of postoperative radiotherapy. This finding suggests that the decrease of distant metastases was related to the prevention of local recurrence. A similar effect was found in models that used overall survival as an end point. CONCLUSION This study shows that postmastectomy radiotherapy in N(+) breast cancer patients may decrease the distant metastasis rate by preventing local recurrences and thus avoiding secondary dissemination.


2006 ◽  
Vol 24 (18_suppl) ◽  
pp. 594-594
Author(s):  
B. G. Haffty ◽  
Q. Yang ◽  
M. Reiss ◽  
T. Kearney ◽  
W. Hait ◽  
...  

594 Background: Triple negative (TN) basal-like breast cancers (Negative for ER,PR,HER2/neu) represent an aggressive phenotype, with unique clinical and pathologic features. The purpose of this study was to determine the prognostic significance of this classification with respect to local-regional relapse and distant metastasis in a cohort of conservatively managed breast cancer patients. Methods: A large data base of conservatively managed breast cancer patients with long term follow-up, in which all three immunhistochemical markers, ER,PR and HER2/neu were available was reviewed. Patients were classified as TN if they tested negative for all three markers. Of 442 patients in the data base with all three markers available, 100 were classified as TN. All clinical, pathologic, outcomes and molecular marker data were entered into a computerized database. Results: As of September 2005, with a median follow-up of 7 years, of the 442 patients in the study there have been 50 in-breast relapses, 10 nodal relapses, 68 distant relapses and 62 deaths. Compared with the other subtypes, the TN cohort had a poorer overall survival (67% vs 75%, p = .096), poorer distant metastasis-free rate (61% vs 75%, p = .002), poorer cause-specific survival (67% vs 78%, p = .03), and poorer nodal relapse-free rate (93% vs 99%, p = .021). In a multivariate Cox regression analysis, TN subtype was an independent predictor of distant metastasis (HR=2.6, CI 1.53–4.35, p = .004) and cause- specific survival (HR= 2.36, CI 1.28–4.38, p= .006). There was no significant difference in local (in-breast) control between the TN and other subtypes. BRCA testing was performed on 85 patients in this cohort, of whom 8 had deleterious mutations in BRCA1 and 6 had deleterious mutations in BRCA2. Of 8 BRCA1 mutant patients 7 were classified as TN, while only 1 of 6 BRCA2 patients were TN (p < .001). Conclusions: Patients classified as TN have a poor prognosis with respect to overall, disease free and cause specific survival. However there was no evidence that these patients are at higher risk for local relapse following conservative surgery and radiation. BRCA1 mutant patients develop predominantly TN tumors. No significant financial relationships to disclose.


2021 ◽  
Vol 22 (3) ◽  
pp. 757-766
Author(s):  
Kristanto Yarso ◽  
Monica Bellynda ◽  
Akhmad Azmiardi ◽  
Brian Wasita ◽  
Didik Heriyanto ◽  
...  

2021 ◽  
Author(s):  
Jingjing Gu ◽  
Dandan Chen ◽  
Zhiqiang li ◽  
Yongliang Yang ◽  
Zhaoming Ma ◽  
...  

Abstract Purpose: This meta-analysis investigated the relationships between the CD44+/CD24- phenotype and tumor size, lymph node metastasis, distant metastasis, disease-free survival (DFS), and overall survival (OS) in 8036 postoperative breast cancer patients enrolled in 23 studies.Methods: A literature search of PubMed, Medline, Cochrane, Embase, and PMC was conducted to identify eligible studies. The combined odds ratios (ORs) and 95% confidence intervals (95%CIs) were analyzed to evaluate the relationships between the CD44+/CD24- phenotype and the pathological and biological characteristics of breast cancer patients, and the combined hazard ratios (HRs) and 95% CIs were calculated to evaluate the relationships between CD44+/CD24- and DFS and OS of breast cancer petients using Stata12.0 software.Results: The CD44+/CD24- phenotype were not related to the tumor size (tumor size > 2.0 cm vs ≤ 2.0 cm, combined OR = 0.98, 95%CI: 0.68–1.34, p = 0.792) and didn’t promote lymph node metastasis (lymph node metastasis vs. no lymph node metastasis, combined OR = 0.94, 95% CI: 0.71–1.26, p = 0.692) and distant metastasis (distant metastasis vs no distant metastasis, combined OR = 3.88, 95% CI: 0.93–16.24, p = 0.064). The CD44+/CD24- phenotype was negatively correlated with postoperative DFS (HR = 1.67, 95% CI: 1.35–2.07, p <0.00001) and OS (combined HR = 1.52, 95%CI: 1.21–1.91, p = 0.0004).Conclusion: These results suggested expression of the CD44+/CD24- phenotype can be used as a reliable indicator of clinical prognosis and a potential therapeutic targets in breastcancer patients.


Sign in / Sign up

Export Citation Format

Share Document