Background:Breast cancer is the most common malignancy and a leading cause of cancer‐related deaths among women worldwide.Although treatment advances have improved outcomes,the 5‐year survival rate for metastatic br...Background:Breast cancer is the most common malignancy and a leading cause of cancer‐related deaths among women worldwide.Although treatment advances have improved outcomes,the 5‐year survival rate for metastatic breast cancer remains low.Understanding the anatomical distribution,associated risks,and prognostic features of metastases in patients with newly diagnosed stage IV breast cancer is essential for improving clinical management.This study aims to comprehensively investigate these aspects using data from the SEER database.Methods:This study utilized a retrospective cohort design,examining data from the Surveillance,Epidemiology,and End Results(SEER)database.The investigation considered patients diagnosed with stage IV breast cancer from SEER database.Using logistic regression,odds ratios(ORs)were calculated to determine the risk of various metastases,stratified based on sociodemographic and clinicopathological variables.Survival analyses were executed with Kaplan–Meier methodology in tandem with Cox regression analyses.Results:Out of 356,789 breast cancer patients considered,18,036(5.06%)were diagnosed with de novo stage IV disease.Bone metastasis predominated with a composition ratio of 42.6%.Patients with the HR−/HER2+subtype exhibited the highest metastasis incidence at the time of diagnosis,constituting 8.7%of the entire cohort.Male patients displayed heightened susceptibility to bone,lung,and brain metastases compared to female counterparts.Hispanic individuals exhibited the highest propensity for brain metastases.Relative to other subtypes,the HR−/HER2−patients were more inclined toward lung metastases.Those with bone metastasis had a median survival period of 27 months.Grade III patients with brain or liver metastases faced the most adverse prognoses.A comprehensive profile detailing metastasis patterns by demographics,tumor site and stage,biology,and treatment was presented.Conclusions:This study represents the most comprehensive analysis of metastasis'anatomical distribution and prognosis in breast cancer,offering invaluable insights into metastatic tendencies and characteristics.展开更多
In this paper,we utilize Physics-Informed Neural Networks(PINNs)without any labeled data to solve the fourth-order partial differential equation governing the bending of thin plates.We meticulously formulate and apply...In this paper,we utilize Physics-Informed Neural Networks(PINNs)without any labeled data to solve the fourth-order partial differential equation governing the bending of thin plates.We meticulously formulate and apply our framework to the bending problem of elastic thin plates.Our findings indicate that defining each solution variable through an independent network,meaning without shared network parameters,yields superior performance compared to a single-network model with multiple outputs.During the training process,we discovered that more accurate results were achieved by adjusting the network architecture to strictly satisfy the boundary conditions,rather than incorporating them as part of the loss function.Remarkably,the PINNs are capable of obtaining relatively good results without the use of any labeled data during training,irrespective of whether soft or hard constraints are applied.In the end,the neural network’s predictions for plate deflection,stress,strain,bending,and shear force all have errors less than 5% compared to the analytical solutions.In the algorithm implementation phase,we leverage the Python library DeepXDE,which facilitates the training of PINNs by providing an efficient and expedited process.展开更多
基金supported by the Noncommunicable Chronic Diseases‐National Science and Technology Major Project(No.2023ZD0502602)the CAMS Innovation Fund for Medical Sciences(CIFMS)(No.2024‐I2M‐C&T‐B‐057)+1 种基金the Beijing Natural Science Foundation(Grant No.L234043)the Natural Science Foundation of China(Grant Nos.81872160,82102887,82103047,and 82173328).
文摘Background:Breast cancer is the most common malignancy and a leading cause of cancer‐related deaths among women worldwide.Although treatment advances have improved outcomes,the 5‐year survival rate for metastatic breast cancer remains low.Understanding the anatomical distribution,associated risks,and prognostic features of metastases in patients with newly diagnosed stage IV breast cancer is essential for improving clinical management.This study aims to comprehensively investigate these aspects using data from the SEER database.Methods:This study utilized a retrospective cohort design,examining data from the Surveillance,Epidemiology,and End Results(SEER)database.The investigation considered patients diagnosed with stage IV breast cancer from SEER database.Using logistic regression,odds ratios(ORs)were calculated to determine the risk of various metastases,stratified based on sociodemographic and clinicopathological variables.Survival analyses were executed with Kaplan–Meier methodology in tandem with Cox regression analyses.Results:Out of 356,789 breast cancer patients considered,18,036(5.06%)were diagnosed with de novo stage IV disease.Bone metastasis predominated with a composition ratio of 42.6%.Patients with the HR−/HER2+subtype exhibited the highest metastasis incidence at the time of diagnosis,constituting 8.7%of the entire cohort.Male patients displayed heightened susceptibility to bone,lung,and brain metastases compared to female counterparts.Hispanic individuals exhibited the highest propensity for brain metastases.Relative to other subtypes,the HR−/HER2−patients were more inclined toward lung metastases.Those with bone metastasis had a median survival period of 27 months.Grade III patients with brain or liver metastases faced the most adverse prognoses.A comprehensive profile detailing metastasis patterns by demographics,tumor site and stage,biology,and treatment was presented.Conclusions:This study represents the most comprehensive analysis of metastasis'anatomical distribution and prognosis in breast cancer,offering invaluable insights into metastatic tendencies and characteristics.
基金supported by the Major scientific and technological innovation projects in Shandong Province(Grant No.2019SDZY01)the Science and Technology Innovation Development Project of Tai’an City(Grant No.2022GX075).
文摘In this paper,we utilize Physics-Informed Neural Networks(PINNs)without any labeled data to solve the fourth-order partial differential equation governing the bending of thin plates.We meticulously formulate and apply our framework to the bending problem of elastic thin plates.Our findings indicate that defining each solution variable through an independent network,meaning without shared network parameters,yields superior performance compared to a single-network model with multiple outputs.During the training process,we discovered that more accurate results were achieved by adjusting the network architecture to strictly satisfy the boundary conditions,rather than incorporating them as part of the loss function.Remarkably,the PINNs are capable of obtaining relatively good results without the use of any labeled data during training,irrespective of whether soft or hard constraints are applied.In the end,the neural network’s predictions for plate deflection,stress,strain,bending,and shear force all have errors less than 5% compared to the analytical solutions.In the algorithm implementation phase,we leverage the Python library DeepXDE,which facilitates the training of PINNs by providing an efficient and expedited process.
