Quantifying and correcting slide-to-slide variation in multiplexed immunofluorescence images.

MOTIVATION: Multiplexed imaging is a nascent single-cell assay with a complex data structure susceptible to technical variability that disrupts inference. These in situ methods are valuable in understanding cell-cell interactions, but few standardized processing steps or normalization techniques of multiplexed imaging data are available. RESULTS: We implement and compare data transformations and normalization algorithms in multiplexed imaging data. Our methods adapt the ComBat and functional data registration methods to remove slide effects in this domain, and we present an evaluation framework to compare the proposed approaches. We present clear slide-to-slide variation in the raw, unadjusted data and show that many of the proposed normalization methods reduce this variation while preserving and improving the biological signal. Furthermore, we find that dividing multiplexed imaging data by its slide mean, and the functional data registration methods, perform the best under our proposed evaluation framework. In summary, this approach provides a foundation for better data quality and evaluation criteria in multiplexed imaging. AVAILABILITY AND IMPLEMENTATION: Source code is provided at: https://github.com/statimagcoll/MultiplexedNormalization and an R package to implement these methods is available here: https://github.com/ColemanRHarris/mxnorm. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Influence of social determinants of health and county vaccination rates on machine learning models to predict COVID-19 case growth in Tennessee.

INTRODUCTION: The SARS-CoV-2 (COVID-19) pandemic has exposed health disparities throughout the USA, particularly among racial and ethnic minorities. As a result, there is a need for data-driven approaches to pinpoint the unique constellation of clinical and social determinants of health (SDOH) risk factors that give rise to poor patient outcomes following infection in US communities. METHODS: We combined county-level COVID-19 testing data, COVID-19 vaccination rates and SDOH information in Tennessee. Between February and May 2021, we trained machine learning models on a semimonthly basis using these datasets to predict COVID-19 incidence in Tennessee counties. We then analyzed SDOH data features at each time point to rank the impact of each feature on model performance. RESULTS: Our results indicate that COVID-19 vaccination rates play a crucial role in determining future COVID-19 disease risk. Beginning in mid-March 2021, higher vaccination rates significantly correlated with lower COVID-19 case growth predictions. Further, as the relative importance of COVID-19 vaccination data features grew, demographic SDOH features such as age, race and ethnicity decreased while the impact of socioeconomic and environmental factors, including access to healthcare and transportation, increased. CONCLUSION: Incorporating a data framework to track the evolving patterns of community-level SDOH risk factors could provide policy-makers with additional data resources to improve health equity and resilience to future public health emergencies.

Predictive modeling of COVID-19 case growth highlights evolving racial and ethnic risk factors in Tennessee and Georgia.

INTRODUCTION: The SARS-CoV-2 (COVID-19) pandemic has exposed the need to understand the risk drivers that contribute to uneven morbidity and mortality in US communities. Addressing the community-specific social determinants of health (SDOH) that correlate with spread of SARS-CoV-2 provides an opportunity for targeted public health intervention to promote greater resilience to viral respiratory infections. METHODS: Our work combined publicly available COVID-19 statistics with county-level SDOH information. Machine learning models were trained to predict COVID-19 case growth and understand the social, physical and environmental risk factors associated with higher rates of SARS-CoV-2 infection in Tennessee and Georgia counties. Model accuracy was assessed comparing predicted case counts to actual positive case counts in each county. RESULTS: The predictive models achieved a mean R2 of 0.998 in both states with accuracy above 90% for all time points examined. Using these models, we tracked the importance of SDOH data features over time to uncover the specific racial demographic characteristics strongly associated with COVID-19 incidence in Tennessee and Georgia counties. Our results point to dynamic racial trends in both states over time and varying, localized patterns of risk among counties within the same state. For example, we find that African American and Asian racial demographics present comparable, and contrasting, patterns of risk depending on locality. CONCLUSION: The dichotomy of demographic trends presented here emphasizes the importance of understanding the unique factors that influence COVID-19 incidence. Identifying these specific risk factors tied to COVID-19 case growth can help stakeholders target regional interventions to mitigate the burden of future outbreaks.

Predictive Modeling of COVID-19 Case Growth Highlights Evolving Demographic Risk Factors in Tennessee and Georgia.

The COVID-19 pandemic has exposed the need to understand the unique risk drivers that contribute to uneven morbidity and mortality in US communities. Addressing the community-specific social determinants of health that correlate with spread of SARS-CoV-2 provides an opportunity for targeted public health intervention to promote greater resilience to viral respiratory infections in the future. Our work combined publicly available COVID-19 statistics with county-level social determinants of health information. Machine learning models were trained to predict COVID-19 case growth and understand the unique social, physical and environmental risk factors associated with higher rates of SARS-CoV-2 infection in Tennessee and Georgia counties. Model accuracy was assessed comparing predicted case counts to actual positive case counts in each county. The predictive models achieved a mean r-squared (R2) of 0.998 in both states with accuracy above 90% for all time points examined. Using these models, we tracked the social determinants of health, with a specific focus on demographics, that were strongly associated with COVID-19 case growth in Tennessee and Georgia counties. The demographic results point to dynamic racial trends in both states over time and varying, localized patterns of risk among counties within the same state. Identifying the specific risk factors tied to COVID-19 case growth can assist public health officials and policymakers target regional interventions to mitigate the burden of future outbreaks and minimize long-term consequences including emergence or exacerbation of chronic diseases that are a direct consequence of infection.

Trust as a Predictor of Patient Perceptions Regarding Overlapping Surgery and Trainee Independence.

OBJECTIVES: To examine opinions on trainee independence and attending presence among a cross-section of the general population and explore how perceptions of trust, past experiences, and demographics interacted with comfort consenting to these surgical scenarios. STUDY DESIGN: Mixed-methods METHODS: Based on prior qualitative analysis, we designed a survey of patient preferences and values that focused on trust in healthcare practitioners and processes, which also included comfort ratings of three surgical scenarios (including overlapping surgery). The survey was administered to a sample from the general public using Mechanical Turk. We identified discreet domains of trust and examined the association of responses to these domains with comfort ratings, prior healthcare experiences, and demographics. RESULTS: We analyzed 225 surveys and identified four patient subgroups based on responses to the surgical scenarios. Subjects that were more comfortable with overlapping surgery were more trusting of trainees and delegation by the attending. Past experiences in healthcare (positive and negative) were associated with multiple domains of trust (in trainees, surgeons, and the healthcare system). Demographics were not predictive of trust responses or comfort ratings. CONCLUSION: Patients express varying degrees of comfort with overlapping surgery, and this is not associated with demographics. Past negative experiences have an impact on trust in the healthcare system overall, and trust in trainees specifically predicts comfort with attending absence from the operating room. Efforts to increase patient comfort with overlapping surgery and surgical training should include strategies to address past negative experiences and foster trust in trainees and the delegation process. LEVEL OF EVIDENCE: IV Laryngoscope, 130:2728-2735, 2020.

Sensing of NO2 with zirconium hydroxide via frequency-dependent electrical impedance spectroscopy.

Zirconium hydroxide has been investigated as a candidate nitrogen dioxide dielectric sensor using impedance spectroscopy analysis. Significant changes in electronic and physical properties down to our dosage minimum of 2 ppm h have been observed. Using disc-shaped pressed pellets of Zr(OH)4 in parallel plate geometry, we observe a maximum signal shift of 35% at 2 ppm h dosage, which increases six orders of magnitude as the dosage reaches 1000 ppm h. Changes in impedance correlate with nitrogen and oxygen atomic ratio increases observed via X-ray photoelectron spectroscopy (XPS) at higher NO2 dosages. In contrast to the sharp frequency-dependent features and net impedance decreases during NO2 exposures, Zr(OH)4 exhibits a large and broad impedance increase after exposure to humid air (water vapor). The results indicate that Zr(OH)4 could be used as a selective low-cost impedance-based NO2 detector by applying frequency-dependent impedance fingerprinting.