AimTo evaluate maternal, neonatal and anesthetic outcomes according to BMI in women undergoing cesarean section.BackgroundIncreased incidence rates of obesity and morbid obesity have been reported in the United States. Pregnant obese patients are at increased risk of maternal and fetal complications, and obstetric and anesthetic management of these patients is especially challenging.MethodsA retrospective chart review of patients who underwent cesarean section in a single center between 2015 and 2016 was conducted. Anesthetic, obstetric and neonatal outcomes were analyzed in relation to levels of BMI.ResultsSeven hundred and seventy one patients underwent cesarean section during the study period. The number of patients with normal BMI, obesity and morbid obesity was 213 (27.6%), 365 (47.3%) and 193 (25%), respectively. Sixty-one percent of the patients in morbidly obese group had at least one comorbidity (p < 0.01). We found no significant differences with respect to perioperative obstetric complications. Intraoperative blood loss was significantly higher in the morbidly obese group.ConclusionIncreasing BMI is associated with comorbidities such as hypertension and diabetes mellitus, and with increased intraoperative blood loss. We were unable to detect differences in other obstetric, anesthetic and neonatal outcomes.

Objective: Robustness is an important aspect to consider, when developing methods for medical image analysis. This study investigated robustness properties of deep neural networks (DNNs) for a lung nodule classification problem based on CT images and proposed a solution to improve robustness. Approach: We firstly constructed a class of four DNNs with different widths, each predicting an output label (benign or malignant) for an input CT image cube containing a lung nodule. These networks were trained to achieve Area Under the Curve of 0.891-0.914 on a testing dataset. We then added to the input CT image cubes noise signals generated randomly using a realistic CT image noise model based on a noise power spectrum at 100 mAs, and monitored the DNN’s output change. We defined $SAR_{5} (\%)$ to quantify the robustness of the trained DNN model, indicating that for $5\%$ of CT image cubes, the noise can change the prediction results with a chance of at least $SAR_{5} (\%)$. To understand robustness, we viewed the information processing pipeline by the DNN as a two-step process, with the first step using all but the last layers to extract representations of the input CT image cubes in a latent space, and the second step employing the last fully-connected layer as a linear classifier to determine the position of the sample representations relative to a decision plane. To improve robustness, we proposed to retrain the last layer of the DNN with a Supporting Vector Machine (SVM) hinge loss function to enforce the desired position of the decision plane. Main results: $SAR_{5}$ ranged in $47.0\sim 62.0\%$ in different DNNs. The unrobustness behavior may be ascribed to the unfavorable placement of the decision plane in the latent representation space, which made some samples be perturbed to across the decision plane and hence susceptible to noise. The DNN-SVM model improved robustness over the DNN model and reduced $SAR_{5}$ by $8.8\sim 21.0\%$. Significance: This study provided insights about the potential reason for the unrobustness behavior of DNNs and the proposed DNN-SVM model improved model robustness.

No abstract

66 Background: The Oncology Care Model (OCM) is a 6-month, episode-based, Medicare value-based care program, which rewards practices for decreasing the total cost of care (TCOC) compared to a trend adjusted predicted baseline called the benchmark price. The predicted baseline and trend factor are a function of 14 covariates in a generalized linear model with a log link and gamma distribution. Select non-cancer comorbidities, represented by a subset of Hierarchical Condition Category (HCC) flags assigned to the episode in the calendar year when the episode initiates, is a major covariate of the linear model. Patient episodes with one or more HCC flags are expected to have higher episode expenditures and receive a higher adjustment to the benchmark. Here, we seek to describe the seasonality of HCC flags and its impact on the benchmark for OCM episodes in The US Oncology Network (The Network). Methods: All eligible OCM episodes data from 14 practices in The Network participating in the OCM for performance periods (PP) 3-9 were analyzed to measure the average number of HCC flags per episode. The relative contribution of HCC flags to the benchmark was calculated by unraveling the linear model. The difference of the average HCC flags, benchmark, and relative contribution of HCC flags to the benchmark for episodes starting in different quarters of the calendar year were evaluated. Results: Average HCC flags for episodes showed a seasonal decline during each calendar year, with episodes initiating during the first quarter of a calendar year having 16.25% higher HCC flags, compared to those in the last quarter (1.93 vs 1.66 flags). The benchmark and the relative contribution of the HCC flags to the episode benchmark were lower in the last quarter of the year (4% and 16.5% respectively) compared to the first quarter. Episode expenditures did not show a similar seasonality pattern. Conclusions: The assignment of HCC flags based on the episode initiation date, leads to a seasonality effect on the average HCC flags and benchmark for episodes initiating in different parts of the calendar year. The seasonality results from a progressively abbreviated period available to assign HCC flags for episodes initiating later in the calendar year. We also hypothesize that the annual reporting requirement for HCC flags, and risk adjustment coding by professionals at the start of each new calendar year, contributes to this seasonality. The financial impact of seasonality on episodic value-based care model benchmarks necessitates a modified, non-seasonal approach to comorbidity-based risk adjustment.