The Impact of Social Determinants of Health on the Time Between Diagnostic Breast Imaging and Biopsy at a Safety Net Hospital.

PURPOSE: Although social determinants of health (SDH) are thought to be associated with health outcomes, there is limited literature on the direct impact of SDH on delays in breast cancer diagnosis via breast imaging. Identifying SDH associated with longer lapses (defined in this study as a time interval between two events) between imaging and biopsy is essential to early-stage detection of breast cancer, which has a significant impact on survival. Previous work demonstrated associations between both housing and food insecurity with longer lapses between diagnostic imaging and biopsy. We aim to expand upon this retrospective analysis with a longer study period, more participants, and improved data cleaning techniques to better understand how SDH may affect the lapse between imaging and biopsy. METHODS: This retrospective study was institutional review board approved and HIPAA compliant. Informed consent was waived. Patients who underwent screening mammography between January 1, 2015, and January 1, 2020, were assessed for timing of recommended biopsy due to a BI-RADS category 4 or 5. SDH were assessed with the unique Tool for Health & Resilience in Vulnerable Environments screening questionnaire developed at Boston Medical Center. Associations between imaging and biopsy timing and eight explanatory SDH variables (food insecurity, housing insecurity, ability to pay for medications, transportation access, ability to pay for utilities, caretaking needs, employment, and desire for more education) were assessed with multivariate Cox proportional hazard modeling, as well as demographic data. RESULTS: There were 2,885 unique patients who underwent 3,142 unique diagnostic imaging studies and were included in the multivariate analysis. Of those 3,142 imaging studies, 196 (6.2%) had not yet been followed by the recommended biopsy by the end of the study period; 2,271 patients (78.7%) had SDH data in at least one domain; and the individual domains ranged from 962 patients (32.1%) with complete data for education to 2,175 patients (75.4%) with complete data for food insecurity. A positive screen for at least one SDH was associated with a longer lapse between diagnostic imaging and biopsy (P = .048). Furthermore, housing insecurity alone was nearly associated with longer lapses between diagnostic imaging and biopsy (P = .059). Those who desired more education were found to have shorter lapses between diagnostic imaging and biopsy (P = .037). CONCLUSIONS: Only a positive screen of the aggregate of all SDH (using a novel tool developed at our safety net hospital) was associated with a statistically significant lengthening of this lapse. Of the eight SDH screened, housing insecurity was the closest to association with longer lapses between diagnostic imaging and biopsy, whereas patients who desired more education were found to have statistically significant shorter lapses; however, this survey domain had the lowest completion rate. CLINICAL RELEVANCE: Identification of which SDH might affect the time from imaging to biopsy can potentially inform targeted programs to intervene. Government and health system interventions addressing SDH, notably housing insecurity, could allow for shorter time to breast cancer diagnosis and treatment.

Social determinants of health and the prediction of missed breast imaging appointments.

BACKGROUND: Predictive models utilizing social determinants of health (SDH), demographic data, and local weather data were trained to predict missed imaging appointments (MIA) among breast imaging patients at the Boston Medical Center (BMC). Patients were characterized by many different variables, including social needs, demographics, imaging utilization, appointment features, and weather conditions on the date of the appointment. METHODS: This HIPAA compliant retrospective cohort study was IRB approved. Informed consent was waived. After data preprocessing steps, the dataset contained 9,970 patients and 36,606 appointments from 1/1/2015 to 12/31/2019. We identified 57 potentially impactful variables used in the initial prediction model and assessed each patient for MIA. We then developed a parsimonious model via recursive feature elimination, which identified the 25 most predictive variables. We utilized linear and non-linear models including support vector machines (SVM), logistic regression (LR), and random forest (RF) to predict MIA and compared their performance. RESULTS: The highest-performing full model is the nonlinear RF, achieving the highest Area Under the ROC Curve (AUC) of 76% and average F1 score of 85%. Models limited to the most predictive variables were able to attain AUC and F1 scores comparable to models with all variables included. The variables most predictive of missed appointments included timing, prior appointment history, referral department of origin, and socioeconomic factors such as household income and access to caregiving services. CONCLUSIONS: Prediction of MIA with the data available is inherently limited by the complex, multifactorial nature of MIA. However, the algorithms presented achieved acceptable performance and demonstrated that socioeconomic factors were useful predictors of MIA. In contrast with non-modifiable demographic factors, we can address SDH to decrease the incidence of MIA.

Identifying Robust Radiomics Features for Lung Cancer by Using In-Vivo and Phantom Lung Lesions.

We propose a novel framework for determining radiomics feature robustness by considering the effects of both biological and noise signals. This framework is preliminarily tested in a study predicting the epidermal growth factor receptor (EGFR) mutation status in non-small cell lung cancer (NSCLC) patients. Pairs of CT images (baseline, 3-week post therapy) of 46 NSCLC patients with known EGFR mutation status were collected and a FDA-customized anthropomorphic thoracic phantom was scanned on two vendors' scanners at four different tube currents. Delta radiomics features were extracted from the NSCLC patient CTs and reproducible, non-redundant, and informative features were identified. The feature value differences between EGFR mutant and EGFR wildtype patients were quantitatively measured as the biological signal. Similarly, radiomics features were extracted from the phantom CTs. A pairwise comparison between settings resulted in a feature value difference that was quantitatively measured as the noise signal. Biological signals were compared to noise signals at each setting to determine if the distributions were significantly different by two-sample t-test, and thus robust. Four optimal features were selected to predict EGFR mutation status, Tumor-Mass, Sigmoid-Offset-Mean, Gabor-Energy and DWT-Energy, which quantified tumor mass, tumor-parenchyma density transition at boundary, line-like pattern inside tumor and intratumoral heterogeneity, respectively. The first three variables showed robustness across the majority of studied CT acquisition parameters. The textual feature DWT-Energy was less robust. The proposed framework was able to determine robustness of radiomics features at specific settings by comparing biological signal to noise signal. Identification of robust radiomics features may improve the generalizability of radiomics models in future studies.