Disparities in Influenza, Pneumococcal, COVID-19 Vaccine Coverage in High-Risk Adults 19 to 64 Years of Age in Southeastern Minnesota, 2010-2021.

BACKGROUND: Despite effective vaccines against influenza, pneumococcus, and COVID-19, uptake has been suboptimal. RESEARCH QUESTION: Although disparities in vaccination by race and ethnicity have been observed, what is the role of other sociodemographic in US vaccine uptake? STUDY DESIGN AND METHODS: We conducted a population-based study using the Rochester Epidemiology Project (REP), a comprehensive medical records linkage system, to assess effects of sociodemographic factors including race, ethnicity, individual-level socioeconomic status (SES) via the housing-based socioeconomic status index, education, population density (urban or nonurban), and marital status with uptake of influenza, pneumococcal, and COVID-19 vaccination in high-risk adults. Adults at high risk of invasive pneumococcal disease residing in four counties in southeastern Minnesota who were 19 to 64 years of age were identified. Vaccination data were obtained from the Minnesota Immunization Information Connection and REP from January 1, 2010, through December 31, 2021. RESULTS: We identified 45,755 residents. Most were White (82%), non-Hispanic (94%), married (56%), and living in an urban setting (81%), with three-quarters obtaining at least some college education (74%). Although 45.1% were up-to-date on pneumococcal vaccines, 60.1% had completed the primary COVID-19 series. For influenza and COVID-19, higher SES, living in an urban setting, older age, and higher education positively correlated with vaccination. Magnitude of differences in race, education, and SES widened with booster vaccines. INTERPRETATION: This high-risk population is undervaccinated against preventable respiratory diseases, especially influenza and pneumococcus. Although national data reported improvement of disparities in COVID-19 vaccination uptake observed early in the pandemic, our data demonstrated gaps related to race, education level, SES, and age that widened with booster vaccines. Communities with high social vulnerabilities often show increased risk of severe disease outcomes, yet demonstrate lower uptake of preventive services. This highlights the need to understand better vaccine compliance and access in rural, lower SES, less-educated, Black, Hispanic, and younger populations, each of which were associated independently with decreased vaccination.

Clinical Needs Assessment of a Machine Learning-Based Asthma Management Tool: User-Centered Design Approach.

BACKGROUND: Personalized asthma management depends on a clinician's ability to efficiently review patient's data and make timely clinical decisions. Unfortunately, efficient and effective review of these data is impeded by the varied format, location, and workflow of data acquisition, storage, and processing in the electronic health record. While machine learning (ML) and clinical decision support tools are well-positioned as potential solutions, the translation of such frameworks requires that barriers to implementation be addressed in the formative research stages. OBJECTIVE: We aimed to use a structured user-centered design approach (double-diamond design framework) to (1) qualitatively explore clinicians' experience with the current asthma management system, (2) identify user requirements to improve algorithm explainability and Asthma Guidance and Prediction System prototype, and (3) identify potential barriers to ML-based clinical decision support system use. METHODS: At the "discovery" phase, we first shadowed to understand the practice context. Then, semistructured interviews were conducted digitally with 14 clinicians who encountered pediatric asthma patients at 2 outpatient facilities. Participants were asked about their current difficulties in gathering information for patients with pediatric asthma, their expectations of ideal workflows and tools, and suggestions on user-centered interfaces and features. At the "define" phase, a synthesis analysis was conducted to converge key results from interviewees' insights into themes, eventually forming critical "how might we" research questions to guide model development and implementation. RESULTS: We identified user requirements and potential barriers associated with three overarching themes: (1) usability and workflow aspects of the ML system, (2) user expectations and algorithm explainability, and (3) barriers to implementation in context. Even though the responsibilities and workflows vary among different roles, the core asthma-related information and functions they requested were highly cohesive, which allows for a shared information view of the tool. Clinicians hope to perceive the usability of the model with the ability to note patients' high risks and take proactive actions to manage asthma efficiently and effectively. For optimal ML algorithm explainability, requirements included documentation to support the validity of algorithm development and output logic, and a request for increased transparency to build trust and validate how the algorithm arrived at the decision. Acceptability, adoption, and sustainability of the asthma management tool are implementation outcomes that are reliant on the proper design and training as suggested by participants. CONCLUSIONS: As part of our comprehensive informatics-based process centered on clinical usability, we approach the problem using a theoretical framework grounded in user experience research leveraging semistructured interviews. Our focus on meeting the needs of the practice with ML technology is emphasized by a user-centered approach to clinician engagement through upstream technology design.

Rural Health Disparities in Allergy, Asthma, and Immunologic Diseases: The Current State and Future Direction for Clinical Care and Research.

Rural health disparities are well documented and continue to jeopardize the long-term health and wellness for the millions of individuals who live in rural America. The disparities observed between urban and rural residents encompass numerous morbidity and mortality measures for several chronic diseases and have been referred to as the "rural mortality penalty." Although the unmet health needs of rural communities are widely acknowledged, little is known about rural health disparities in allergies, asthma, and immunologic diseases. Furthermore, the intersection between rural health disparities and social determinants of health has not been fully explored. To achieve a more complete understanding of the factors that perpetuate rural health disparities, greater research efforts followed by improved practice and policy are needed that account for the complex social context within rural communities rather than a general comparison between urban and rural environments or focusing on biomedical factors. Moreover, research efforts must prioritize community inclusion throughout rural areas through meaningful engagement of stakeholders in both clinical care and research. In this review, we examine the scope of health disparities in the rural United States and the impact of social determinants of health. We then detail the current state of rural health disparities in the field of allergy, asthma, and immunology. To close, we offer future considerations to address knowledge gaps and unmet needs for both clinical care and research in addressing rural health disparities.

Application of Innovative Subject Recruitment System for Batch Enrollment: A Pilot Study.

INTRODUCTION: Using a digital process that leverages electronic health records (EHRs) can ease many of the challenges presented by the traditional enrollment process for clinical trials. We tested if automated batch enrollment using a technology-enabled subject recruitment system (TESRS) enhances recruitment while preserving representation of research subjects for the study population in our study setting. METHODS: An ongoing community-based prospective adult cohort study was used to randomize 600 subjects who were eligible by age and residential address to TESRS (n = 300) and standard mailing method (n = 300), respectively, for 3 months. Then, TESRS was initiated and included automatic identification of patients' preference for being contacted (online patient portal vs postal mail) from EHRs and automatic sending out of invitation letters followed by completion of a short online survey for checking eligibility and the digital consent process if eligible. We compared (1) median time to consent from invitation sent out per subject and total subjects recruited after a 3-month recruitment period, (2) the estimated study staff's time, and (3) representation of sociodemographic characteristics (e.g., age, sex, race, SES measured by HOUSES index, and rural residence) between subjects recruited via TESRS and those via traditional mailing methods. RESULTS: Median age of randomized subjects (n = 600) was 63 years with 52.0% female and 89.2% non-Hispanic White. Over a 3-month period, results showed consent rate via TESRS was 13% (39/297) similar to 11% (31/295) via standard mailing. However, recruitment was significantly faster with the TESRS approach (median 7 vs 26 days) given the study staff's effort. Study staff's time saved by using TESRS compared to standard mailing approach was estimated at 40 min per subject (equivalent to 200 h for 300 subjects). No significant differences in characteristics of research subjects from the study population were found. CONCLUSION: Our study demonstrated the utility of TESRS as a subject recruitment digital technology which significantly enhanced the recruitment effort while reducing the study staff burden of recruitment while maintaining the consistency of characteristics of recruited subjects. The strategy and support for implementing and testing TESRS in other study settings should be considered.

Rural and urban residents' attitudes and preferences toward COVID-19 prevention behaviors in a midwestern community.

Rural populations are more vulnerable to the impacts of COVID-19 compared to their urban counterparts as they are more likely to be older, uninsured, to have more underlying medical conditions, and live further from medical care facilities. We engaged the Southeastern MN (SEMN) community (N = 7,781, 51% rural) to conduct a survey of motivators and barriers to masking to prevent COVID-19. We also assessed preferences for types of and modalities to receive education/intervention, exploring both individual and environmental factors primarily consistent with Social Cognitive Theory. Our results indicated rural compared to urban residents performed fewer COVID-19 prevention behaviors (e.g. 62% rural vs. 77% urban residents reported wearing a mask all of the time in public, p<0.001), had more negative outcome expectations for wearing a mask (e.g. 50% rural vs. 66% urban residents thought wearing a mask would help businesses stay open, p<0.001), more concerns about wearing a mask (e.g. 23% rural vs. 14% urban were very concerned about being 'too hot', p<0.001) and lower levels of self-efficacy for masking (e.g. 13.9±3.4 vs. 14.9±2.8, p<0.001). It appears that masking has not become a social norm in rural SEMN, with almost 50% (vs. 24% in urban residents) disagreeing with the expectation 'others in my community will wear a mask to stop the spread of Coronavirus'. Except for people (both rural and urban) who reported not being at all willing to wear a mask (7%), all others expressed interest in future education/interventions to help reduce masking barriers that utilized email and social media for delivery. Creative public health messaging consistent with SCT tailored to rural culture and norms is needed, using emails and social media with pictures and videos from role models they trust, and emphasizing education about when masks are necessary.

Disproportionate increases in alcohol-associated hepatitis incidence in women and individuals of low socioeconomic status: A population-based study using the Rochester epidemiology project database.

BACKGROUND: Alcohol-associated hepatitis (AH) is among the deadliest liver diseases, but its incidence is poorly defined. The aim of our study was to define the incidence of AH meeting the National Institute on Alcohol Abuse and Alcoholism criteria and to identify risk factors for AH. METHODS: We conducted a retrospective cohort study using the Rochester epidemiology project database on adult patients hospitalized with AH between January 1, 2000 and December 31, 2018. Patients were screened using ICD-9 codes and then included if they met the National Institute on Alcohol Abuse and Alcoholism criteria on manual chart review. Baseline demographics, comorbidities, access to care, liver-related complications, and outcomes were obtained. The HOUsing-based index of SocioEconomic status index was used to measure socioeconomic status. Incidence rates were calculated in cases per 100,000 person-years of follow-up. RESULTS: Among 204 patients, the cumulative AH incidence was 6.8 per 100,000 person-years. Between 2000-2004 and 2015-2018, AH incidence among males increased from 8.4 to 14.7 per 100,000 py, whereas AH incidence among females increased by 7-fold from 0.8 to 5.9 per 100,000 py. Such increases among females were accompanied by increases in comorbid depression and anxiety. The proportion of patients with AH in the lower socioeconomic status quartiles increased from 62.9% between 2000 and 2004 to 73.3% between 2015 and 2019. CONCLUSIONS: The incidence of AH is increasing rapidly, especially among females and individuals of lower socioeconomic status. There are areas of unmet need in preventative measures and treatments for comorbid psychiatric disorders in patients at high risk of AH.

Paired Indoor and Outdoor Nitrogen Dioxide Associated With Childhood Asthma Outcomes in a Mixed Rural-Urban Setting: A Feasibility Study.

INTRODUCTION: Nitrogen dioxide (NO2) is known to be a trigger for asthma exacerbation. However, little is known about the role of seasonal variation in indoor and outdoor NO2 levels in childhood asthma in a mixed rural-urban setting of North America. METHODS: This prospective cohort study, as a feasibility study, included 62 families with children (5-17 years) that had diagnosed persistent asthma residing in Olmsted County, Minnesota. Indoor and outdoor NO2 concentrations were measured using passive air samples over 2 weeks in winter and 2 weeks in summer. We assessed seasonal variation in NO2 levels in urban and rural residential areas and the association with asthma control status collected from participants' asthma diaries during the study period. RESULTS: Outdoor NO2 levels were lower (median: 2.4 parts per billion (ppb) in summer, 3.9 ppb in winter) than the Environmental Protection Agency (EPA) annual standard (53 ppb). In winter, a higher level of outdoor NO2 was significantly associated with urban residential living area (P = .014) and lower socioeconomic status (SES) (P = .027). For both seasons, indoor NO2 was significantly higher (P < .05) in rural versus urban areas and in homes with gas versus electric stoves (P < .05). Asthma control status was not associated with level of indoor or outdoor NO2 in this cohort. CONCLUSIONS: NO2 levels were low in this mixed rural-urban community and not associated with asthma control status in this small feasibility study. Further research with a larger sample size is warranted for defining a lower threshold of NO2 concentration with health effect on asthma in mixed rural-urban settings.

Barriers to and solutions for representative inclusion across the lifespan and in life course research: The need for structural competency highlighted by the COVID-19 pandemic.

Exclusion of special populations (older adults; pregnant women, children, and adolescents; individuals of lower socioeconomic status and/or who live in rural communities; people from racial and ethnic minority groups; individuals from sexual or gender minority groups; and individuals with disabilities) in research is a pervasive problem, despite efforts and policy changes by the National Institutes of Health and other organizations. These populations are adversely impacted by social determinants of health (SDOH) that reduce access and ability to participate in biomedical research. In March 2020, the Northwestern University Clinical and Translational Sciences Institute hosted the "Lifespan and Life Course Research: integrating strategies" "Un-Meeting" to discuss barriers and solutions to underrepresentation of special populations in biomedical research. The COVID-19 pandemic highlighted how exclusion of representative populations in research can increase health inequities. We applied findings of this meeting to perform a literature review of barriers and solutions to recruitment and retention of representative populations in research and to discuss how findings are important to research conducted during the ongoing COVID-19 pandemic. We highlight the role of SDOH, review barriers and solutions to underrepresentation, and discuss the importance of a structural competency framework to improve research participation and retention among special populations.

The Role of Individual-Level Socioeconomic Status on Nursing Home Placement Accounting for Neighborhood Characteristics.

OBJECTIVE: Independent living is desirable for many older adults. Although several factors such as physical and cognitive functions are important predictors for nursing home placement (NHP), it is also reported that socioeconomic status (SES) affects the risk of NHP. In this study, we aimed to examine whether an individual-level measure of SES is associated with the risk of NHP after accounting for neighborhood characteristics. DESIGN: A population-based study (Olmsted County, Minnesota, USA). SETTING AND PARTICIPANTS: Older adults (age 65+ years) with no prior history of NHP. METHODS: Electronic health records (EHR) were used to identify individuals with any NHP between April 1, 2012 (baseline date) and April 30, 2019. Association between the (HOUsing-based index of SocioEconomic Status (HOUSES) index, an individual-level SES measure based on housing characteristics of current residence, and risk of NHP was tested using random effects Cox proportional hazard model adjusting for area deprivation index (ADI), an aggregated SES measure that captures neighborhood characteristics, and other pertinent confounders such as age and chronic disease burden. RESULTS: Among 15,031 older adults, 3341 (22.2%) experienced NHP during follow-up period (median: 7.1 years). At baseline date, median age was 73 years old with 55% female persons, 91% non-Hispanic Whites, and median number of chronic conditions of 4. Accounting for pertinent confounders, the HOUSES index was strongly associated with risk of NHP (hazard ratio 1.89; 95% confidence interval 1.66‒2.15 for comparing the lowest vs highest quartiles), which was not influenced by further accounting for ADI. CONCLUSIONS AND IMPLICATIONS: This study demonstrates that an individual-level SES measure capturing current individual-specific socioeconomic circumstances plays a significant role for predicting NHP independent of neighborhood characteristics where they reside. This study suggests that older adults who are at higher risk of NHP can be identified by utilizing the HOUSES index and potential individual-level intervention strategies can be applied to reduce the risk for those with higher risk.

Incidence of Respiratory Syncytial Virus Infection in Older Adults Before and During the COVID-19 Pandemic.

Importance: Little is known about the burden and outcomes of respiratory syncytial virus (RSV)-positive acute respiratory infection (ARI) in community-dwelling older adults. Objective: To assess the incidence of RSV-positive ARI before and during the COVID-19 pandemic, and to assess outcomes for RSV-positive ARI in older adults. Design, Setting, and Participants: This was a community-based cohort study of adults residing in southeast Minnesota that followed up with 2325 adults aged 50 years or older for 2 RSV seasons (2019-2021) to assess the incidence of RSV-positive ARI. The study assessed outcomes at 2 to 4 weeks, 6 to 7 months, and 12 to 13 months after RSV-positive ARI. Exposure: RSV-positive and -negative ARI. Main Outcomes and Measures: RSV status was the main study outcome. Incidence and attack rates of RSV-positive ARI were calculated during each RSV season, including before (October 2019 to April 2020) and during (October 2020 to April 2021) COVID-19 pandemic, and further calculated during non-RSV season (May to September 2021) for assessing impact of COVID-19. The self-reported quality of life (QOL) by Short-Form Health Survey-36 (SF-36) and physical functional measures (eg, 6-minute walk and spirometry) at each time point was assessed. Results: In this study of 2325 participants, the median (range) age of study participants was 67 (50-98) years, 1380 (59%) were female, and 2240 (96%) were non-Hispanic White individuals. The prepandemic incidence rate of RSV-positive ARI was 48.6 (95% CI, 36.9-62.9) per 1000 person-years with a 2.50% (95% CI, 1.90%-3.21%) attack rate. No RSV-positive ARI case was identified during the COVID-19 pandemic RSV season. Incidence of 10.2 (95% CI, 4.1-21.1) per 1000 person-years and attack rate of 0.42%; (95% CI, 0.17%-0.86%) were observed during the summer of 2021. Based on prepandemic RSV season results, participants with RSV-positive ARI (vs matched RSV-negative ARI) reported significantly lower QOL adjusted mean difference (limitations due to physical health, -16.7 [95% CI, -31.8 to -1.8]; fatigue, -8.4 [95% CI, -14.3 to -2.4]; and difficulty in social functioning, -11.9 [95% CI, -19.8 to -4.0] within 2 to 4 weeks after RSV-positive ARI [ie, short-term outcome]). Compared with participants with RSV-negative ARI, those with RSV-positive ARI also had lower QOL (fatigue: -4.0 [95% CI, -8.5 to -1.3]; difficulty in social functioning, -5.8 [95% CI, -10.3 to -1.3]; and limitation due to emotional problem, -7.0 [95% CI, -12.7 to -1.3] at 6 to 7 months after RSV-positive ARI [intermediate-term outcome]; fatigue, -4.4 [95% CI, -7.3 to -1.5]; difficulty in social functioning, -5.2 [95% CI, -8.7 to -1.7] and limitation due to emotional problem, -5.7 [95% CI, -10.7 to -0.6] at 12-13 months after RSV-positive ARI [ie, long-term outcomes]) independent of age, sex, race and/or ethnicity, socioeconomic status, and high-risk comorbidities. Conclusions and Relevance: In this cohort study, the burden of RSV-positive ARI in older adults during the pre-COVID-19 period was substantial. After a reduction of RSV-positive ARI incidence from October 2020 to April 2021, RSV-positive ARI re-emerged during the summer of 2021. RSV-positive ARI was associated with significant long-term lower QOL beyond the short-term lower QOL in older adults.

Disparities in vaccination rates in solid organ transplant patients.

INTRODUCTION: Vaccinations against preventable respiratory infections such as Streptococcus pneumoniae and influenza are important in immunosuppressed solid organ transplant (SOT) recipients. Little is known about the role of age, race, ethnicity, sex, and sociodemographic factors including rurality, or socioeconomic status (SES) associated with vaccine uptake in this population. METHODS: We conducted a population-based study using the Rochester Epidemiology Project, a medical records linkage system, to assess socioeconomic and demographic factors associated with influenza and pneumococcal vaccination rates among adult recipients of solid organ transplantation (aged 19-64 years) living in four counties in southeastern Minnesota. Vaccination data were obtained from the Minnesota Immunization Information Connection from June 1, 2010 to June 30, 2020. Vaccination rate was assessed with Poisson and logistic regression models. RESULTS: A total of 468 SOT recipients were identified with an overall vaccination rate of 57%-63% for influenza and 56% for pneumococcal vaccines. As expected, vaccination for pneumococcal vaccine positively correlated with influenza vaccination. Rural patients had decreased vaccination in both compared to urban patients, even after adjusting for age, sex, race, ethnicity, and SES. Although the population was mostly White and non-Hispanic, neither vaccination differed by race or ethnicity, but influenza vaccination did by SES. Among organ transplant groups, liver and lung recipients were least vaccinated for influenza, and heart recipients were least up-to-date on pneumococcal vaccines. CONCLUSIONS: Rates of vaccination were below national goals. Rurality was associated with undervaccination. Further investigation is needed to understand and address barriers to vaccination among transplant recipients.

Rates of Asymptomatic COVID-19 Infection and Associated Factors in Olmsted County, Minnesota, in the Prevaccination Era.

Objective: To estimate rates and identify factors associated with asymptomatic COVID-19 in the population of Olmsted County during the prevaccination era. Patients and Methods: We screened first responders (n=191) and Olmsted County employees (n=564) for antibodies to SARS-CoV-2 from November 1, 2020 to February 28, 2021 to estimate seroprevalence and asymptomatic infection. Second, we retrieved all polymerase chain reaction (PCR)-confirmed COVID-19 diagnoses in Olmsted County from March 2020 through January 2021, abstracted symptom information, estimated rates of asymptomatic infection and examined related factors. Results: Twenty (10.5%; 95% CI, 6.9%-15.6%) first responders and 38 (6.7%; 95% CI, 5.0%-9.1%) county employees had positive antibodies; an additional 5 (2.6%) and 10 (1.8%) had prior positive PCR tests per self-report or medical record, but no antibodies detected. Of persons with symptom information, 4 of 20 (20%; 95% CI, 3.0%-37.0%) first responders and 10 of 39 (26%; 95% CI, 12.6%-40.0%) county employees were asymptomatic. Of 6020 positive PCR tests in Olmsted County with symptom information between March 1, 2020, and January 31, 2021, 6% (n=385; 95% CI, 5.8%-7.1%) were asymptomatic. Factors associated with asymptomatic disease included age (0-18 years [odds ratio {OR}, 2.3; 95% CI, 1.7-3.1] and >65 years [OR, 1.40; 95% CI, 1.0-2.0] compared with ages 19-44 years), body mass index (overweight [OR, 0.58; 95% CI, 0.44-0.77] or obese [OR, 0.48; 95% CI, 0.57-0.62] compared with normal or underweight) and tests after November 20, 2020 ([OR, 1.35; 95% CI, 1.13-1.71] compared with prior dates). Conclusion: Asymptomatic rates in Olmsted County before COVID-19 vaccine rollout ranged from 6% to 25%, and younger age, normal weight, and later tests dates were associated with asymptomatic infection.

Influenza infection is not associated with phenotypical frailty in older patients, a prospective cohort study.

Background and Aims: Influenza is a challenging infectious illness for older adults. It is not completely clear whether influenza is associated with frailty or functional decline. We sought to determine the association between incident influenza infection and frailty and prefrailty in community patients over 50 years of age. We also investigated the association between influenza vaccination and frailty and prefrailty as a secondary aim. Methods: This was a prospective community cohort study from October 2019 to November 2020 in participants over 50 years. The primary outcome was the development of frailty as defined by three of five frailty criteria (slow gait speed, low grip strength, 5% weight loss, low energy, and low physical functioning). The primary predictor was a positive polymerase chain reaction (PCR) for influenza infection. Influenza vaccination was based on electronic health record reviewing 1 year before enrollment. We reported the relationship between influenza and frailty by calculating odds ratios (OR) with 95% confidence intervals (CI) after adjustment for age, sex, socioeconomic status, Charlson Comorbidity Index (CCI), influenza vaccine, and previous self-rated frailty from multinomial logistic regression model comparing frail and prefrail to nonfrail subjects. Results: In 1135 participants, the median age was 67 years (interquartile range  60-74), with 41% men. Eighty-one participants had PCR-confirmed influenza (7.1%). Frailty was not associated with influenza, with an OR of 0.50 (95% CI 0.17-1.43) for frail participants compared to nonfrail participants. Influenza vaccination is associated with frailty, with an OR of 1.69 (95% CI 1.09-2.63) for frail compared to nonfrail. Frailty was associated with a higher CCI with an OR of 1.52 (95% CI 1.31-1.76). Conclusion: We did not find a relationship between influenza infection and frailty. We found higher vaccination rates in participants with frailty compared to nonfrail participants While influenza was not associated with frailty, future work may involve longer follow-up.

A Technical Performance Study and Proposed Systematic and Comprehensive Evaluation of an ML-based CDS Solution for Pediatric Asthma.

Achieving optimal care for pediatric asthma patients depends on giving clinicians efficient access to pertinent patient information. Unfortunately, adherence to guidelines or best practices has shown to be challenging, as relevant information is often scattered throughout the patient record in both structured data and unstructured clinical notes. Furthermore, in the absence of supporting tools, the onus of consolidating this information generally falls upon the clinician. In this study, we propose a machine learning-based clinical decision support (CDS) system focused on pediatric asthma care to alleviate some of this burden. This framework aims to incorporate a machine learning model capable of predicting asthma exacerbation risk into the clinical workflow, emphasizing contextual data, supporting information, and model transparency and explainability. We show that this asthma exacerbation model is capable of predicting exacerbation with an 0.8 AUC-ROC. This model, paired with a comprehensive informatics-based process centered on clinical usability, emphasizes our focus on meeting the needs of the clinical practice with machine learning technology.

Role of geographic risk factors and social determinants of health in COVID-19 epidemiology: Longitudinal geospatial analysis in a midwest rural region.

Background: Studies examining the role of geographic factors in coronavirus disease-2019 (COVID-19) epidemiology among rural populations are lacking. Methods: Our study is a population-based longitudinal study based on rural residents in four southeast Minnesota counties from March through October 2020. We used a kernel density estimation approach to identify hotspots for COVID-19 cases. Temporal trends of cases and testing were examined by generating a series of hotspot maps during the study period. Household/individual-level socioeconomic status (SES) was measured using the HOUSES index and examined for association between identified hotspots and SES. Results: During the study period, 24,243 of 90,975 residents (26.6%) were tested for COVID-19 at least once; 1498 (6.2%) of these tested positive. Compared to other rural residents, hotspot residents were overall younger (median age: 40.5 vs 43.2), more likely to be minorities (10.7% vs 9.7%), and of higher SES (lowest HOUSES [SES] quadrant: 14.6% vs 18.7%). Hotspots accounted for 30.1% of cases (14.5% of population) for rural cities and 60.8% of cases (27.1% of population) for townships. Lower SES and minority households were primarily affected early in the pandemic and higher SES and non-minority households affected later. Conclusion: In rural areas of these four counties in Minnesota, geographic factors (hotspots) play a significant role in the overall burden of COVID-19 with associated racial/ethnic and SES disparities, of which pattern differed by the timing of the pandemic (earlier in pandemic vs later). The study results could more precisely guide community outreach efforts (e.g., public health education, testing/tracing, and vaccine roll out) to those residing in hotspots.

Assessing socioeconomic bias in machine learning algorithms in health care: a case study of the HOUSES index.

OBJECTIVE: Artificial intelligence (AI) models may propagate harmful biases in performance and hence negatively affect the underserved. We aimed to assess the degree to which data quality of electronic health records (EHRs) affected by inequities related to low socioeconomic status (SES), results in differential performance of AI models across SES. MATERIALS AND METHODS: This study utilized existing machine learning models for predicting asthma exacerbation in children with asthma. We compared balanced error rate (BER) against different SES levels measured by HOUsing-based SocioEconomic Status measure (HOUSES) index. As a possible mechanism for differential performance, we also compared incompleteness of EHR information relevant to asthma care by SES. RESULTS: Asthmatic children with lower SES had larger BER than those with higher SES (eg, ratio = 1.35 for HOUSES Q1 vs Q2-Q4) and had a higher proportion of missing information relevant to asthma care (eg, 41% vs 24% for missing asthma severity and 12% vs 9.8% for undiagnosed asthma despite meeting asthma criteria). DISCUSSION: Our study suggests that lower SES is associated with worse predictive model performance. It also highlights the potential role of incomplete EHR data in this differential performance and suggests a way to mitigate this bias. CONCLUSION: The HOUSES index allows AI researchers to assess bias in predictive model performance by SES. Although our case study was based on a small sample size and a single-site study, the study results highlight a potential strategy for identifying bias by using an innovative SES measure.

Risk of pneumonia in asthmatic children using inhaled corticosteroids: a nested case-control study in a birth cohort.

BACKGROUND: Inhaled corticosteroids (ICSs) are important in asthma management, but there are concerns regarding associated risk of pneumonia. While studies in asthmatic adults have shown inconsistent results, this risk in asthmatic children is unclear. OBJECTIVE: Our aim was to determine the association of ICS use with pneumonia risk in asthmatic children. METHODS: A nested case-control study was performed in the Mayo Clinic Birth Cohort. Asthmatic children (<18 years) with a physician diagnosis of asthma were identified from electronic medical records of children born at Mayo Clinic from 1997 to 2016 and followed until 31 December 2017. Pneumonia cases defined by Infectious Disease Society of America were 1:1 matched with controls without pneumonia by age, sex and asthma index date. Exposure was defined as ICS prescription at least 90 days prior to pneumonia. Associations of ICS use, type and dose (low, medium and high) with pneumonia risk were analysed using conditional logistic regression. RESULTS: Of the 2108 asthmatic children eligible for the study (70% mild intermittent and 30% persistent asthma), 312 children developed pneumonia during the study period. ICS use overall was not associated with risk of pneumonia (adjusted OR: 0.94, 95% CI: 0.62 to 1.41). Poorly controlled asthma was significantly associated with the risk of pneumonia (OR: 2.03, 95% CI: 1.35 to 3.05; p<0.001). No ICS type or dose was associated with risk of pneumonia. CONCLUSION: ICS use in asthmatic children was not associated with risk of pneumonia but poorly controlled asthma was. Future asthma studies may need to include pneumonia as a potential outcome of asthma management.

Atopic asthma as a potentially significant but unrecognized risk factor for Kawasaki disease in children.

OBJECTIVES: Childhood asthma is known to be associated with risks of both respiratory and non-respiratory infections. Little is known about the relationship between asthma and the risk of Kawasaki disease (KD). We assessed associations of asthma status and asthma phenotype (e.g. atopic asthma) with KD. METHODS: We performed a population-based retrospective case-control study, using KD cases between January 1, 1979, and December 31, 2016, and two matched controls per case. KD cases were defined by the American Heart Association diagnostic criteria. Asthma status prior to KD (or control) index dates was ascertained by the two asthma criteria, Predetermined Asthma Criteria (PAC) and Asthma Predictive Index (API, a surrogate phenotype of atopic asthma). We assessed whether 4 phenotypes (both PAC + and API+; PAC + only; API + only, and non-asthmatics) were associated with KD. RESULTS: There were 124 KD cases during the study period. The group having both PAC + and API + was significantly associated with the increased odds of KD, compared to non-asthmatics (odds ratio [OR] 4.3; 95% CI: 1.3 - 14.3). While asthma defined by PAC was not associated with KD, asthma defined by PAC positive with eosinophilia (≥4%) was significantly associated with the increased odds of KD (OR: 6.7; 95% CI: 1.6 - 28.6) compared to non-asthmatics. Asthma status defined by API was associated with KD (OR = 4.7; 95% CI: 1.4-15.1). CONCLUSIONS: Atopic asthma may be associated with increased odds of KD. Further prospective studies are needed to determine biological mechanisms underlying the association between atopic asthma and increased odds of KD.

Artificial Intelligence Assesses Clinicians' Adherence to Asthma Guidelines Using Electronic Health Records.

BACKGROUND: Clinicians' asthma guideline adherence in asthma care is suboptimal. The effort to improve adherence can be enhanced by assessing and monitoring clinicians' adherence to guidelines reflected in electronic health records (EHRs), which require costly manual chart review because many care elements cannot be identified by structured data. OBJECTIVE: This study was designed to demonstrate the feasibility of an artificial intelligence tool using natural language processing (NLP) leveraging the free text EHRs of pediatric patients to extract key components of the 2007 National Asthma Education and Prevention Program guidelines. METHODS: This is a retrospective cross-sectional study using a birth cohort with a diagnosis of asthma at Mayo Clinic between 2003 and 2016. We used 1,039 clinical notes with an asthma diagnosis from a random sample of 300 patients. Rule-based NLP algorithms were developed to identify asthma guideline-congruent elements by examining care description in EHR free text. RESULTS: Natural language processing algorithms demonstrated a sensitivity (0.82-1.0), specificity (0.95-1.0), positive predictive value (0.86-1.0), and negative predictive value (0.92-1.0) against manual chart review for asthma guideline-congruent elements. Assessing medication compliance and inhaler technique assessment were the most challenging elements to assess because of the complexity and wide variety of descriptions. CONCLUSIONS: Natural language processing technologies may enable the automated assessment of clinicians' documentation in EHRs regarding adherence to asthma guidelines and can be a useful population management and research tool to assess and monitor asthma care quality. Multisite studies with a larger sample size are needed to assess the generalizability of these NLP algorithms.