Sources of Disparities in Surveillance Mammography Performance and Risk-Guided Recommendations for Supplemental Breast Imaging: A Simulation Study.

BACKGROUND: Surveillance mammography is recommended for all women with a history of breast cancer. Risk-guided surveillance incorporating advanced imaging modalities based on individual risk of a second cancer could improve cancer detection. However, personalized surveillance may also amplify disparities. METHODS: In simulated populations using inputs from the Breast Cancer Surveillance Consortium (BCSC), we investigated race- and ethnicity-based disparities. Disparities were decomposed into those due to primary breast cancer and treatment characteristics, social determinants of health (SDOH) and differential error in second cancer ascertainment by modeling populations with or without variation across race and ethnicity in the distribution of these characteristics. We estimated effects of disparities on mammography performance and supplemental imaging recommendations stratified by race and ethnicity. RESULTS: In simulated cohorts based on 65,446 BCSC surveillance mammograms, when only cancer characteristics varied by race and ethnicity, mammograms for Black women had lower sensitivity compared with the overall population (64.1% vs. 71.1%). Differences between Black women and the overall population were larger when both cancer characteristics and SDOH varied by race and ethnicity (53.8% vs. 71.1%). Basing supplemental imaging recommendations on high predicted second cancer risk resulted in less frequent recommendations for Hispanic (6.7%) and Asian/Pacific Islander women (6.4%) compared with the overall population (10.0%). CONCLUSIONS: Variation in cancer characteristics and SDOH led to disparities in surveillance mammography performance and recommendations for supplemental imaging. IMPACT: Risk-guided surveillance imaging may exacerbate disparities. Decision-makers should consider implications for equity in cancer outcomes resulting from implementing risk-guided screening programs. See related In the Spotlight, p. 1479.

Mathematical modeling of the lower urinary tract: A review.

AIMS: Understand what progress has been made toward a functionally predictive lower urinary tract (LUT) model, identify knowledge gaps, and develop from them a path forward. METHODS: We surveyed prominent mathematical models of the basic LUT components (bladder, urethra, and their neural control) and categorized the common modeling strategies and theoretical assumptions associated with each component. Given that LUT function emerges from the interaction of these components, we emphasized attempts to model their connections, and highlighted unmodeled aspects of LUT function. RESULTS: There is currently no satisfactory model of the LUT in its entirety that can predict its function in response to disease, treatment, or other perturbations. In particular, there is a lack of physiologically based mathematical descriptions of the neural control of the LUT. CONCLUSIONS: Based on our survey of the work to date, a potential path to a predictive LUT model is a modular effort in which models are initially built of individual tissue-level components using methods that are extensible and interoperable, allowing them to be connected and tested in a common framework. A modular approach will allow the larger goal of a comprehensive LUT model to be in sight while keeping individual efforts manageable, ensure new models can straightforwardly build on prior research, respect potential interactions between components, and incentivize efforts to model absent components. Using a modular framework and developing models based on physiological principles, to create a functionally predictive model is a challenge that the field is ready to undertake.

Cubature Kalman Filter Based Training of Hybrid Differential Equation Recurrent Neural Network Physiological Dynamic Models.

Modeling biological dynamical systems is challenging due to the interdependence of different system components, some of which are not fully understood. To fill existing gaps in our ability to mechanistically model physiological systems, we propose to combine neural networks with physics-based models. Specifically, we demonstrate how we can approximate missing ordinary differential equations (ODEs) coupled with known ODEs using Bayesian filtering techniques to train the model parameters and simultaneously estimate dynamic state variables. As a study case we leverage a well-understood model for blood circulation in the human retina and replace one of its core ODEs with a neural network approximation, representing the case where we have incomplete knowledge of the physiological state dynamics. Results demonstrate that state dynamics corresponding to the missing ODEs can be approximated well using a neural network trained using a recursive Bayesian filtering approach in a fashion coupled with the known state dynamic differential equations. This demonstrates that dynamics and impact of missing state variables can be captured through joint state estimation and model parameter estimation within a recursive Bayesian state estimation (RBSE) framework. Results also indicate that this RBSE approach to training the NN parameters yields better outcomes (measurement/state estimation accuracy) than training the neural network with backpropagation through time in the same setting.