Immigrants and refugees seeking admission to the United States must first undergo an overseas medical exam, overseen by the US Centers for Disease Control and Prevention (CDC), during which all persons ≥15 years old receive a chest x-ray to look for signs of tuberculosis. Although individual screening sites often implement quality control (QC) programs to ensure radiographs are interpreted correctly, the CDC does not currently have a method for conducting similar QC reviews at scale. We obtained digitized chest radiographs collected as part of the overseas immigration medical exam. Using radiographs from applicants 15 years old and older, we trained deep learning models to perform three tasks: identifying abnormal radiographs; identifying abnormal radiographs suggestive of tuberculosis; and identifying the specific findings (e.g., cavities or infiltrates) in abnormal radiographs. We then evaluated the models on both internal and external testing datasets, focusing on two classes of performance metrics: individual-level metrics, like sensitivity and specificity, and sample-level metrics, like accuracy in predicting the prevalence of abnormal radiographs. A total of 152,012 images (one image per applicant; mean applicant age 39 years) were used for model training. On our internal test dataset, our models performed well both in identifying abnormalities suggestive of TB (area under the curve [AUC] of 0.97; 95% confidence interval [CI]: 0.95, 0.98) and in estimating sample-level counts of the same (-2% absolute percentage error; 95% CIC: -8%, 6%). On the external test datasets, our models performed similarly well in identifying both generic abnormalities (AUCs ranging from 0.89 to 0.92) and those suggestive of TB (AUCs from 0.94 to 0.99). This performance was consistent across metrics, including those based on thresholded class predictions, like sensitivity, specificity, and F1 score. Strong performance relative to high-quality radiological reference standards across a variety of datasets suggests our models may make reliable tools for supporting chest radiography QC activities at CDC.

On August 29, 2021, the United States government oversaw the emergent establishment of Operation Allies Welcome (OAW), led by the U.S. Department of Homeland Security (DHS) and implemented by the U.S. Department of Defense (DoD) and U.S. Department of State (DoS), to safely resettle U.S. citizens and Afghan nationals from Afghanistan to the United States. Evacuees were temporarily housed at several overseas locations in Europe and Asia* before being transported via military and charter flights through two U.S. international airports, and onward to eight U.S. military bases,(†) with hotel A used for isolation and quarantine of persons with or exposed to certain infectious diseases.(§) On August 30, CDC issued an Epi-X notice encouraging public health officials to maintain vigilance for measles among Afghan evacuees because of an ongoing measles outbreak in Afghanistan (25,988 clinical cases reported nationwide during January-November 2021) (1) and low routine measles vaccination coverage (66% and 43% for the first and second doses, respectively, in 2020) (2).

We evaluated the association between socioeconomic status (SES) and community-associated Clostridioides difficile infection (CA-CDI) incidence across 2474 census tracts in 10 states. Highly correlated community-level SES variables were transformed into distinct factors using factor analysis. We found low SES communities were associated with higher CA-CDI incidence.

In August 2017, Hurricane Harvey caused unprecedented flooding and devastation to the Houston metropolitan area (1). Mold exposure was a serious concern because investigations after Hurricanes Katrina and Rita (2005) had documented extensive mold growth in flood-damaged homes (2,3). Because mold exposure can cause serious illnesses known as invasive mold infections (4,5), and immunosuppressed persons are at high risk for these infections (6,7), several federal agencies recommend that immunosuppressed persons avoid mold-contaminated sites (8,9). To assess the extent of exposure to mold and flood-damaged areas among persons at high risk for invasive mold infections after Hurricane Harvey, CDC and Texas health officials conducted a survey among 103 immunosuppressed residents in Houston. Approximately half of the participants (50) engaged in cleanup of mold and water-damaged areas; these activities included heavy cleanup (23), such as removing furniture or removing drywall, or light cleanup (27), such as wiping down walls or retrieving personal items. Among immunosuppressed persons who performed heavy cleanup, 43% reported wearing a respirator, as did 8% who performed light cleanup. One participant reported wearing all personal protective equipment (PPE) recommended for otherwise healthy persons (i.e., respirator, boots, goggles, and gloves). Immunosuppressed residents who are at high risk for invasive mold infections were exposed to mold and flood-damaged areas after Hurricane Harvey; recommendations from health care providers to avoid exposure to mold and flood-damaged areas could mitigate the risk to immunosuppressed persons.