Machine learning to predict risk for community-onset Staphylococcus aureus infections in children living in southeastern United States.

Staphylococcus aureus (S. aureus) is known to cause human infections and since the late 1990s, community-onset antibiotic resistant infections (methicillin resistant S. aureus (MRSA)) continue to cause significant infections in the United States. Skin and soft tissue infections (SSTIs) still account for the majority of these in the outpatient setting. Machine learning can predict the location-based risks for community-level S. aureus infections. Multi-year (2002-2016) electronic health records of children <19 years old with S. aureus infections were queried for patient level data for demographic, clinical, and laboratory information. Area level data (Block group) was abstracted from U.S. Census data. A machine learning ecological niche model, maximum entropy (MaxEnt), was applied to assess model performance of specific place-based factors (determined a priori) associated with S. aureus infections; analyses were structured to compare methicillin resistant (MRSA) against methicillin sensitive S. aureus (MSSA) infections. Differences in rates of MRSA and MSSA infections were determined by comparing those which occurred in the early phase (2002-2005) and those in the later phase (2006-2016). Multi-level modeling was applied to identify risks factors for S. aureus infections. Among 16,124 unique patients with community-onset MRSA and MSSA, majority occurred in the most densely populated neighborhoods of Atlanta's metropolitan area. MaxEnt model performance showed the training AUC ranged from 0.771 to 0.824, while the testing AUC ranged from 0.769 to 0.839. Population density was the area variable which contributed the most in predicting S. aureus disease (stratified by CO-MRSA and CO-MSSA) across early and late periods. Race contributed more to CO-MRSA prediction models during the early and late periods than for CO-MSSA. Machine learning accurately predicts which densely populated areas are at highest and lowest risk for community-onset S. aureus infections over a 14-year time span.

Space-time trends of community-onset Staphylococcus aureus infections in children: a group-based trajectory modeling approach.

PURPOSE: Staphylococcus aureus (S. aureus) remains a serious cause of infections in the United States and worldwide. In the United States, methicillin-resistant S. aureus (MRSA) is the leading cause of skin and soft tissue infections. This study identifies 'best' to 'worst' infection trends from 2002 to 2016, using group-based trajectory modeling approach. METHODS: Electronic health records of children living in the southeastern United States with S. aureus infections from 2002 to 2016 were retrospectively studied, by applying a group-based trajectory model to estimate infection trends (low, high, very high), and then assess spatial significance of these trends at the census tract level; we focused on community-onset infections and not those considered healthcare acquired. RESULTS: Three methicillin-susceptible S. aureus (MSSA) infection trends (low, high, very high) and three MRSA trends (low, high, very high) were identified from 2002 to 2016. Among census tracts with community-onset S. aureus cases, 29% of tracts belonged to the best trend (low infection) for both methicillin-resistant S. aureus and methicillin-susceptible S. aureus; higher proportions occurring in the less densely populated areas. Race disparities were seen with the worst methicillin-resistant S. aureus infection trends and were more often in urban areas. CONCLUSIONS: Group-based trajectory modeling identified unique trends of S. aureus infection rates over time and space, giving insight into the associated population characteristics which reflect these trends of community-onset infection.

Influence of Mask Wearing during COVID-19 Surge and Non-Surge Time Periods in Two K-12 Public School Districts in Georgia, USA.

BACKGROUND: Into the third year of the COVID-19 pandemic and the second year of in-person learning for many K-12 schools in the United States, the benefits of mitigation strategies in this setting are still unclear. We compare COVID-19 cases in school-aged children and adolescents between a school district with a mandatory mask-wearing policy to one with an optional mask-wearing policy, during and after the peak period of the Delta variant wave of infection. METHODS: COVID-19 cases during the Delta variant wave (August 2021) and post the wave (October 2021) were obtained from public health records. Cases of K-12 students, stratified by grade level (elementary, middle, and high school) and school districts across two counties, were included in the statistical and spatial analyses. COVID-19 case rates were determined and spatially mapped. Regression was performed adjusting for specific covariates. RESULTS: Mask-wearing was associated with lower COVID-19 cases during the peak Delta variant period; overall, regardless of the Delta variant period, higher COVID-19 rates were seen in older aged students. CONCLUSION: This study highlights the need for more layered prevention strategies and policies that take into consideration local community transmission levels, age of students, and vaccination coverage to ensure that students remain safe at school while optimizing their learning environment.

Molecular Epidemiologic and Geo-Spatial Characterization of Staphylococcus aureus Cultured from Skin and Soft Tissue Infections from United States-Born and Immigrant Patients Living in New York City.

(1) Background: With increasing international travel and mass population displacement due to war, famine, climate change, and immigration, pathogens, such as Staphylococcus aureus (S. aureus), can also spread across borders. Methicillin-resistant S. aureus (MRSA) most commonly causes skin and soft tissue infections (SSTIs), as well as more invasive infections. One clonal strain, S. aureus USA300, originating in the United States, has spread worldwide. We hypothesized that S. aureus USA300 would still be the leading clonal strain among US-born compared to non-US-born residents, even though risk factors for SSTIs may be similar in these two populations (2) Methods: In this study, 421 participants presenting with SSTIs were enrolled from six community health centers (CHCs) in New York City. The prevalence, risk factors, and molecular characteristics for MRSA and specifically clonal strain USA300 were examined in relation to the patients' self-identified country of birth. (3) Results: Patients born in the US were more likely to have S. aureus SSTIs identified as MRSA USA300. While being male and sharing hygiene products with others were also significant risks for MRSA SSTI, we found exposure to animals, such as owning a pet or working at an animal facility, was specifically associated with risk for SSTIs caused by MRSA USA300. Latin American USA300 variant (LV USA300) was most common in participants born in Latin America. Spatial analysis showed that MRSA USA300 SSTI cases were more clustered together compared to other clonal types either from MRSA or methicillin-sensitive S. aureus (MSSA) SSTI cases. (4) Conclusions: Immigrants with S. aureus infections have unique risk factors and S. aureus molecular characteristics that may differ from US-born patients. Hence, it is important to identify birthplace in MRSA surveillance and monitoring. Spatial analysis may also capture additional information for surveillance that other methods do not.

Prenatal Diagnosis Nomograms: A Novel Tool to Predict Fetal Chromosomal Abnormalities in High-Risk Patients.

BACKGROUND: Amniocentesis is an invasive prenatal diagnostic technique that can provide genetic information of fetus for pregnant women and give them a choice. A straightforward predictive tool can show pregnant women the need for amniocentesis prior to the procedure. METHODS: The information of patients who underwent amniocentesis from 2014 to 2019 at the Obstetrics Clinic, Shengjing Hospital of China Medical University was extracted, and important independent prognostic factors were determined by univariate and multivariate logistic regression analysis to construct nomograms with total abnormalities (TA) and chromosome number abnormalities (CNA). RESULTS: A total of 19,683 patients undergoing amniocentesis were included in this study. Among 1761 patients with abnormal results, 917 had abnormal chromosome numbers, 439 had abnormal chromosome structures, and 405 had polymorphic results. Nomograms of TA and CNA were created using data such as age, nuchal translucency value, ultrasound results, Oscar's testing and/or non-invasive prenatal testing abnormalities, parental chromosomes, and information whether they were twins. The nomogram has good predictive power and clinical practicality through the analysis of area under curve and decision curve analysis. Internal verification was performed for nomograms of TA and CNA, suggesting that the nomogram's predicted probability and actual probability of the two are consistent. CONCLUSION: The nomogram constructed is a good predictor of TA and CNA, which can be used in clinical practice to screen high-risk patients of chromosomal abnormalities.