UNASSIGNED: For several cancers, including those of the breast, young age at diagnosis is associated with an adverse prognosis. Although this effect is often attributed to heritable mutations such as BRCA1/2, the relationship between pathologic features, young age of onset, and prognosis for breast cancer remains unclear. In the present study, we highlight links between age of onset and lymph node metastasis (NM) in US women with breast cancer.
UNASSIGNED: Case listings from Surveillance, Epidemiology, and End Result (SEER) 18 registry data for women with breast cancer, which include information on race, were used. NM and its associated outcomes were evaluated for a subset of women with receptor subtype information and then compared against a larger, pre-subtype validation set of data from the same registry. Age of diagnosis was a 5-category variable; under 40 years, 40-49 years, 50-59 years, 60-69 years and 70+ years. Univariate and adjusted multivariate survival models were applied to both sets of data.
UNASSIGNED: As determined with adjusted logistic regression models, women under 40 years old at diagnosis had 1.55 times the odds of NM as women 60-69 years of age. The odds of NM for (HR = hormone receptor) HR+/HER2+, HR-/HER2+, and triple-negative breast cancer subtypes were significantly lower than those for HR+/HER2-. In subtype-stratified adjusted models, age of diagnosis had a consistent trend of decreasing odds of NM by age category, most noticeable for HR+ subtypes of luminal A and B. Univariate 5-year survival by age was worst for women under 40 years, with NM attributable for 49% of the hazard of death from cancer in adjusted multivariate models.
UNASSIGNED: Lymph node metastasis is age-dependent, yet not all molecular subtypes are clearly affected by this relationship. For <40-yr-old women, NM is a major cause for shorter survival. When stratified by subtype, the strongest associations were in HR+ groups, suggesting a possible hormonal connection between young age of breast cancer onset and NM.

Survival period prediction through early diagnosis of cancer has many benefits. It allows both patients and caregivers to plan resources, time and intensity of care to provide the best possible treatment path for the patients. In this paper, by focusing on lung cancer patients, we build several survival prediction models using deep learning techniques to tackle both cancer survival classification and regression problems. We also conduct feature importance analysis to understand how lung cancer patients\' relevant factors impact their survival periods. We contribute to identifying an approach to estimate survivability that are commonly and practically appropriate for medical use.
We have compared the performance across three of the most popular deep learning architectures - Artificial Neural Networks (ANN), Convolutional Neural Networks (CNN), and Recurrent Neural Networks (RNN) while comparing the performing of deep learning models against traditional machine learning models. The data was obtained from the lung cancer section of Surveillance, Epidemiology, and End Results (SEER) cancer registry.
The deep learning models outperformed traditional machine learning models across both classification and regression approaches. We obtained a best of 71.18 % accuracy for the classification approach when patients\' survival periods are segmented into classes of \'<=6 months\',\' 0.5 - 2 years\' and \'>2 years\' and Root Mean Squared Error (RMSE) of 13.5 % andR2 value of 0.5 for the regression approach for the deep learning models while the traditional machine learning models saturated at 61.12 % classification accuracy and 14.87 % RMSE in regression.
This approach can be a baseline for early prediction with predictions that can be further improved with more temporal treatment information collected from treated patients. In addition, we evaluated the feature importance to investigate the model interpretability, gaining further insight into the survival analysis models and the factors that are important in cancer survival period prediction.