Preferred Information Source Correlates to COVID-19 Risk Misperception.

Inaccurate perceptions of COVID-19 (coronavirus disease 2019) risk may decrease compliance with public health mitigation practices, in turn increasing disease burden. The extent to which public perceptions of COVID-19 risk are inaccurate is not well studied. This study investigates the relationship between preferred information sources and inaccurate COVID-19 risk perception. A cross-sectional online survey of adults in the United States using online snowball techniques was administered between April 9, 2020 and July 12, 2020. Raking techniques were used to generate a representative U.S. sample from 10,650 respondents. Respondents who did not provide an answer to key questions were excluded. The remaining sample included 1,785 health care workers (HCW) and 4,843 non-HCW. Subjective risk was measured as the product of perceived likelihood of COVID-19 infection and perceived harm from infection. Objective risk was measured as a function of the presence of known COVID-19 risk factors. Discrepancies between subjective and objective risk were compared between respondents with different preferred information sources. Chi Square contingency tables and pair-wise correlation were used to evaluate differences to 95% confidence. For HCW and non-HCW, the greatest overestimation of personal COVID-19 risk assessment (p < .05 for all differences) were found in those whose preferred source of information was social media (HCW: 62.1%; non-HCW: 64.5%), followed by internet news sources (HCW: 59.6%, non-HCW%: 59.1%), government websites (HCW: 54%, non-HCW = 51.8%), other sources (HCW: 50.7%, non-HCW = 51.4%), and television news (HCW: 46.1%, non-HCW: 47.6%). Preferred information sources correlate with inaccuracies in personal COVID-19 risk assessment. Public health information campaigns should consider targeting groups whose preferred information sources correlate to higher inaccuracies in COVID-19 risk perceptions. [HLRP: Health Literacy Research and Practice. 2023;7(2):e105-e110.].

Latent class analysis of health, social, and behavioral profiles associated with psychological distress among pregnant and postpartum women during the COVID-19 pandemic in the United States.

BACKGROUND: There is a growing body of literature documenting negative mental health impacts from the COVID-19 pandemic. The purpose of this study was to identify risk and protective factors associated with mental health and well-being among pregnant and postpartum women during the pandemic. METHODS: This was a cross-sectional, anonymous online survey study distributed to pregnant and postpartum (within 6 months) women identified through electronic health records from two large healthcare systems in the Northeastern and Midwestern United States. Survey questions explored perinatal and postpartum experiences related to the pandemic, including social support, coping, and health care needs and access. Latent class analysis was performed to identify classes among 13 distinct health, social, and behavioral variables. Outcomes of depression, anxiety, and stress were examined using propensity-weighted regression modeling. RESULTS: Fit indices demonstrated a three-class solution as the best fitting model. Respondents (N = 616) from both regions comprised three classes, which significantly differed on sleep- and exercise-related health, social behaviors, and mental health: Higher Psychological Distress (31.8%), Moderate Psychological Distress (49.8%), and Lower Psychological Distress (18.4%). The largest discriminatory issue was support from one's social network. Significant differences in depression, anxiety, and stress severity scores were observed across these three classes. Reported need for mental health services was greater than reported access. CONCLUSIONS: Mental health outcomes were largely predicted by the lack or presence of social support, which can inform public health decisions and measures to buffer the psychological impact of ongoing waves of the COVID-19 pandemic on pregnant and postpartum women. Targeted early intervention among those in higher distress categories may help improve maternal and child health.

Virtual Recruitment Effects on Matched Residents in Family Medicine: Experiences From Central Pennsylvania.

Background and Objectives: As a result of the COVID-19 pandemic, interviews during the 2021 US residency match were conducted virtually, a practice again recommended and repeated by many programs in 2022. The impact of virtual interviews on recruitment and match outcomes has recently been of interest, with results showing the virtual format to be mostly well received by applicants due to cost, travel, and scheduling benefits. Few studies have looked at pre/posttransition comparisons of applicant geographic and demographic data. We compared objective match outcomes between in-person and virtual interviews across three residency programs. Methods: We conducted a retrospective cross-sectional analysis of National Residency Matching Program data between 2015-2022 across three family medicine residency programs. Primary outcomes were fill rate, average rank position, distance from program, and percentage of underrepresented in medicine demographic status for matched applicants. We compared aggregate in-person data (2015-2019) to aggregate virtual data (2020-2022) for each program using χ2, Fisher Exact test, or 2-tailed t tests to 95% confidence. Results: Saint Joseph Hospital in Reading, Pennsylvania, a 3-year community-based university affiliated program, had significantly more unfilled positions during virtual recruitment (P=.0058). Mount Nittany Medical Center in State College, Pennsylvania, a 3-year community based university-affiliated program, had a significant difference in distance of matched residents' current address (P=.048). Virtual interviews were not associated with significant differences in average position on rank list, average distance from permanent address zip code, or percentage of underrepresented in medicine (URiM) demographic status for matched applicants. Conclusions: The impact of virtual interviewing on unfilled positions and geographic data is likely site specific and generally small, as some programs had significant structural changes. Further research is needed to confirm the generalizability of these results and explore future comparisons of demographic and geographic characteristics of matched applicants pre/posttransition to the virtual format.

Longitudinal study of an emerging COVID-19 stigma: Media exposure, danger appraisal, and stress

Media coverage of coronavirus disease (COVID-19) has played a critical role throughout the pandemic: sharing news about the novel virus, policies and practices to mitigate it, and the race to create and distribute vaccines. The media coverage, however, has been critiqued as stigmatizing. Although this critique is not new, there is limited understanding of how and why new stigmas emerge from exposure to media coverage. Drawing upon the model of stigma communication (Smith et al., 2019) and the attribution model of stigma (Corrigan et al., 2003), we investigated a novel model of stigma emergence that delineates two kinds of longitudinal processes: (a) a message-effects process, in which exposure to mediated messages about COVID-19 leads to public stigma through danger appraisal and (b) a coping process in which stress and rumination shape later perceptions of public stigma. To test the model, we tracked an emerging COVID-19 stigma with a two-wave survey of a prospective, longitudinal cohort living in one county in a mid-Atlantic state (N = 883). The results supported this model. The longitudinal processes of stigma emergence and implications for COVID-19 stigma are discussed. (PsycInfo Database Record (c) 2023 APA, all rights reserved)

Race, employment, and the pandemic: An exploration of covariate explanations of COVID-19 case fatality rate variance.

We derive a simple asymptotic approximation for the long-run case fatality rate of COVID-19 (alpha and delta variants) and show that these estimations are highly correlated to the interaction between US State median age and projected US unemployment rate (Adj. r2 = 60%). We contrast this to the high level of correlation between point (instantaneous) estimates of per state case fatality rates and the interaction of median age, population density and current unemployment rates (Adj. r2 = 50.2%). To determine whether this is caused by a "race effect," we then analyze unemployment, race, median age and population density across US states and show that adding the interaction of African American population and unemployment explains 53.5% of the variance in COVID case fatality rates for the alpha and delta variants when considering instantaneous case fatality rate. Interestingly, when the asymptotic case fatality rate is used, the dependence on the African American population disappears, which is consistent with the fact that in the long-run COVID does not discriminate on race, but may discriminate on access to medical care which is highly correlated to employment in the US. The results provide further evidence of the impact inequality can have on case fatality rates in COVID-19 and the impact complex social, health and economic factors can have on patient survival.

Extending the Theory of Normative Social Behavior: Collective Norms, Opinion Leadership, and Masking During the COVID-19 Pandemic.

Novel, public behaviors, such as masking, should be susceptible to normative influence. This paper advances the theory of normative social behavior by considering a new set of moderators of normative influence - superdiffuser traits - and by clarifying the antecedents and consequences of exposure to collective norms. We use data from a two-wave survey of a cohort living in one U.S. county during the pandemic (N = 913) to assess normative effects on masking. We also used a bipartite network (based on people shopping for food in the same stores) to examine exposure to collective norms. The results show different superdiffuser traits have distinct effects on the relationship between perceived injunctive norms and masking intentions. Exposure to collective norms influences masking, but this influence depends on how people interact with their social environments. Network analysis shows that behavioral homophily is a significant predictor of selective exposure to collective norms earlier (but not later) in the pandemic. Implications for understanding normative influence in a context where opinion leadership matters are discussed.

External Validation of the COVID-NoLab and COVID-SimpleLab Prognostic Tools.

Our objective was to externally validate 2 simple risk scores for mortality among a mostly inpatient population with COVID-19 in Canada (588 patients for COVID-NoLab and 479 patients for COVID-SimpleLab). The mortality rates in the low-, moderate-, and high-risk groups for COVID-NoLab were 1.1%, 9.6%, and 21.2%, respectively. The mortality rates for COVID-SimpleLab were 0.0%, 9.8%, and 20.0%, respectively. These values were similar to those in the original derivation cohort. The 2 simple risk scores, now successfully externally validated, offer clinicians a reliable way to quickly identify low-risk inpatients who could potentially be managed as outpatients in the event of a bed shortage. Both are available online (https://ebell-projects.shinyapps.io/covid_nolab/ and https://ebell-projects.shinyapps.io/COVID-SimpleLab/).

Mixed-methods Analysis of Adults Likely versus Unlikely to Get a COVID-19 Vaccination.

Objectives: This mixed-methods study compared perspectives of those 'very likely' versus 'very unlikely' to receive a hypothetical COVID-19 vaccine. Methods: We used an explanatory, sequential, mixed- methods design to analyze quantitative data from a rural Pennsylvania sample. Of the 976 participants, 67 selected 'very unlikely' to get the COVID-19 vaccine. Responses to open-ended questions: "What worries you the most about the COVID 19 pandemic?" and "What are your thoughts about a potential COVID 19 vaccine?" were qualitatively compared to answers from the 67 participants who selected 'very likely' to get the COVID-19 vaccine. We used descriptive content analysis to compare themes across the 2 groups. Results: Both groups had thematic commonalities related to their concerns. Themes that were more common among those 'very unlikely' to get vaccinated included concern for politics overriding vaccine safety and rushed vaccine development timeline, whereas themes related to hope and optimism about vaccination were exclusive to the 'very likely' group. Conclusions: Shared beliefs existed across groups with different intents to vaccinate; yet, identification with vaccine spokespersons differed. Messaging campaigns can use these commonalities to address vaccine hesitancy.

Risks of Severe COVID-19 Outcomes Among Patients With Diabetic Polyneuropathy in the United States.

CONTEXT: Diabetic neuropathy (DN) affects more than 50% of diabetic patients who are also likely to have compromised immune system and respiratory function, both of which can make them susceptible to the SARS-CoV-2 virus. OBJECTIVE: To assess the risk of severe COVID-19 illness among adults with DN, compared with those with no DN and those with no diabetes. SETTING: The analysis utilized electronic health records from 55 US health care organizations in the TriNetX research database. DESIGN: A retrospective cohort study. PARTICIPANTS: The analysis included 882 650 adults diagnosed with COVID-19 in January 2020 to June 2021, including 16 641 with DN, 81 329 with diabetes with no neuropathy, and 784 680 with no diabetes. OUTCOME MEASURES: The presence of health care utilization (admissions to emergency department, hospital, intensive care unit), 30-day mortality, clinical presentation (cough, fever, hypoxemia, dyspnea, or acute respiratory distress syndrome), and diagnostic test results after being infected affected by COVID-19. RESULTS: The DN cohort was 1.19 to 2.47 times more likely than the non-DN cohorts to utilize care resources, receive critical care, and have higher 30-day mortality rates. Patients with DN also showed increased risk (1.13-2.18 times) of severe symptoms, such as hypoxemia, dyspnea, and acute respiratory distress syndrome. CONCLUSIONS: Patients with DN had a significantly greater risk of developing severe COVID-19-related complications than those with no DN. It is critical for the public health community to continue preventive measures, such as social distancing, wearing masks, and vaccination, to reduce infection rates, particularly in higher risk groups, such as those with DN.

Perceptions and knowledge regarding the COVID-19 pandemic between U.S. and China: a mixed methods study.

BACKGROUND: SARS-CoV-2, a new coronavirus first reported by China on December 31st, 2019, has led to a global health crisis that continues to challenge governments and public health organizations. Understanding COVID-19 knowledge, attitudes, and practices (KAP) is key for informing messaging strategies to contain the pandemic. Cross-national studies (e.g.: comparing China to the U.S.) are needed to better understand how trans-cultural differences may drive differences in pandemic response and behaviors. The goal of the study is to compare knowledge and perceptions of COVID-19 between adults in China and the U.S. These data will provide insight into challenges these nations may face in coordinating pandemic response. METHODS: This is a convergent mixed methods study comparing responses from China and the U.S. to a multinational COVID-19 KAP online survey. The survey included five quantitative constructs and five open-ended questions. Chinese respondents (n = 56) were matched for gender, age, education, perceived social standing, and time of survey completion with a U.S. cohort (n = 57) drawn from 10,620 U.S. RESPONDENTS: Quantitative responses were compared using T-test & Fisher-Exact tests. Inductive thematic analysis was applied to open-ended questions. RESULTS: Both U.S. and Chinese samples had relatively high intention to follow preventive behaviors overall. Differences in intended compliance with a specific recommendation appear to be driven by the different cultural norms in U.S. and China. Both groups expressed trepidation about the speed of COVID-19 vaccine development, driven by concern for safety among Chinese respondents, and concern for efficacy among U.S. RESPONDENTS: The Chinese cohort expressed worries about other countries' passive handling of the pandemic while the U.S. cohort focused on domestic responses from individuals and government. U.S. participants appeared more knowledgeable on some aspects of COVID-19. Different perspectives regarding COVID-19 origins were identified among the two groups. Participants from both samples reported high trust in health professionals and international health organizations. CONCLUSIONS: Mixed methods data from this cross-national analysis suggests sociocultural differences likely influence perceptions and knowledge of COVID-19 and its related public health policies. Discovering and addressing these culturally-based differences and perceptions are essential to coordinate a global pandemic response.

Skeptical Health Mavens May Limit COVID-19 Vaccine Diffusion: Using the Innovation Diffusion Cycle to Interpret Results of a Cross-sectional Survey among People Who are Socially Vulnerable.

We sought to identify barriers to COVID-19 vaccine uptake among persons who are socially vulnerable in light of the natural cycle of innovation diffusion. Widespread adoption of a health innovation requires a cadre of opinion leaders to build on successes experienced by early adopters. One type of opinion leader in healthcare are health mavens: members of a community who maintain up-to-date health knowledge and share their knowledge others. We surveyed 139 persons who are socially vulnerable regarding their COVID-19 vaccination intention, and evaluated their responses based on psychological traits captured by two scales: innovativeness and health mavenism. Health mavenism was not strongly correlated with COVID-19 vaccine intention. Health mavens often relied on their own healthcare providers (n = 46) and health agency websites (n = 42) for vaccine information. Those who relied on their faith leaders (n = 4) reported a lower likelihood of getting vaccinated (31.5% vs. 76.0%, p < .05). The observed lack of support by health mavens represents a critical barrier to COVID-19 vaccine uptake; targeting campaigns to health mavens may increase COVID-19 vaccine uptake in socially vulnerable communities.

Essential and non-essential US workers' health behaviors during the COVID-19 pandemic.

We seek to quantify the relationship between health behaviors and work-related experiences during the COVID-19 pandemic by predicting health behaviors as a function of essential worker status, job loss, change in work hours, and COVID-19 experiences. We use multivariate models and survey data from 913 employed adults in a semi-rural mid-Atlantic US county, and test whether essential worker results vary by gender, parenthood, and/or university employment. Multivariate models indicate that essential workers used tobacco on more days (4.5; p <.01) and were less likely to sleep 8 h (odds ratio [OR] 0.6; p <.01) than non-essential workers. The risk of sleeping less than 8 h is concentrated among essential workers in the service industry (OR 0.5; p <.05) and non-parents (OR 0.5; p <.05). Feminine essential workers exercised on fewer days (-0.8; p <.05) than feminine non-essential workers. Workers with reduced work hours consumed more alcoholic drinks (0.3; p <.05), while workers with increased work hours consumed alcohol (0.3; p <.05) and exercised (0.6; p <.05) on more days. Essential worker status and changes in work hours are correlated with unhealthy behaviors during the COVID-19 pandemic.

College students' COVID-19 vaccine beliefs and intentions: Implications for interventions.

On college campuses, effective management of vaccine-preventable transmissible pathogens requires understanding student vaccination intentions. This is necessary for developing and tailoring health messaging to maximize uptake of health information and vaccines. The current study explored students' beliefs and attitudes about vaccines in general, and the new COVID-19 vaccines specifically. This study provides insights into effective health messaging needed to rapidly increase COVID-19 vaccination on college campuses-information that will continue to be informative in future academic years across a broad scope of pathogens. Data were collected from 696 undergraduate students ages 18-29 years old enrolled in a large public university in the Northeast during fall 2020. Data were collected via an online survey. Overall, we found COVID-19 vaccine hesitancy in college students correlated strongly with some concerns about vaccines in general as well as with concerns specific to COVID-19 vaccines. Taken together, these results provide further insight for message development and delivery and can inform more effective interventions to advance critical public health outcomes on college campuses beyond the current pandemic.

Adjunctive osteopathic therapy for hospitalized COVID-19 patients: A feasibility-oriented chart review study with matched controls.

Background: Osteopathic manipulative treatment (OMT) may improve outcomes during COVID-related respiratory distress - the most common cause of death from novel coronavirus (SARS-CoV-2). Outcomes from OMT treatments of respiratory distress during the COVID-19 pandemic have not been reported. Objective: Assess adjunctive OMT in hospitalized patients with SARS-CoV-2 and respiratory distress. Design: Feasibility oriented retrospective observational cohort study. Setting: COVID-19 (non-ICU) ward in a tertiary academic medical center. Methods: Inpatients received daily OMT treatments of rib raising, abdominal diaphragm doming, thoracic pump and pedal pump. Primary outcomes were procedural acceptance, satisfaction, side effects, and adverse events. Secondary outcomes were patient-reported clinical change after therapy; number of hospital days; need during hospitalization for high-flow oxygen, C-PAP/BiPAP or intensive care; need for supplementary oxygen at discharge; and discharge disposition. Participants: Hospitalized adults with SARS-CoV-2 infection and respiratory distress. Results: OMT (n = 27) and Control (n = 152) groups were similar in demographics and most laboratory studies. 90% of patients accepted OMT and reported high satisfaction (4.26/±0.71 (maximum 5)), few negative effects, no adverse events, and positive clinical change (5.07 ± 0.96 (maximum 7)). Although no significant differences were found in secondary outcomes, OMT patients trended towards fewer hospital days than Controls (p = 0.053; Cohen's d = 0.22), a relationship that trended towards correlation with number of co-morbidities (p = 0.068). Conclusion: Hospitalized patients with respiratory distress and COVID-19 reported acceptance, satisfaction, and greater ease of breathing after a four-part OMT protocol, and appear to have a shorter length of hospitalization. Randomized controlled trials are needed to confirm these results.

Development and Validation of a Two-Step Predictive Risk Stratification Model for Coronavirus Disease 2019 In-hospital Mortality: A Multicenter Retrospective Cohort Study.

Objectives: An accurate prognostic score to predict mortality for adults with COVID-19 infection is needed to understand who would benefit most from hospitalizations and more intensive support and care. We aimed to develop and validate a two-step score system for patient triage, and to identify patients at a relatively low level of mortality risk using easy-to-collect individual information. Design: Multicenter retrospective observational cohort study. Setting: Four health centers from Virginia Commonwealth University, Georgetown University, the University of Florida, and the University of California, Los Angeles. Patients: Coronavirus Disease 2019-confirmed and hospitalized adult patients. Measurements and Main Results: We included 1,673 participants from Virginia Commonwealth University (VCU) as the derivation cohort. Risk factors for in-hospital death were identified using a multivariable logistic model with variable selection procedures after repeated missing data imputation. A two-step risk score was developed to identify patients at lower, moderate, and higher mortality risk. The first step selected increasing age, more than one pre-existing comorbidities, heart rate >100 beats/min, respiratory rate ≥30 breaths/min, and SpO2 <93% into the predictive model. Besides age and SpO2, the second step used blood urea nitrogen, absolute neutrophil count, C-reactive protein, platelet count, and neutrophil-to-lymphocyte ratio as predictors. C-statistics reflected very good discrimination with internal validation at VCU (0.83, 95% CI 0.79-0.88) and external validation at the other three health systems (range, 0.79-0.85). A one-step model was also derived for comparison. Overall, the two-step risk score had better performance than the one-step score. Conclusions: The two-step scoring system used widely available, point-of-care data for triage of COVID-19 patients and is a potentially time- and cost-saving tool in practice.

COVID-19 Mitigation Among College Students: Social Influences, Behavioral Spillover, and Antibody Results.

By fall 2020, students returning to U.S. university campuses were mandated to engage in COVID-19 mitigation behaviors, including masking, which was a relatively novel prevention behavior in the U.S. Masking became a target of university mandates and campaigns, and it became politicized. Critical questions are whether the influences of injunctive norms and response efficacy on one behavior (i.e. masking) spill over to other mitigation behaviors (e.g. hand-washing), and how patterns of mitigation behaviors are associated with clinical outcomes. We conducted a cross-sectional survey of college students who returned to campus (N = 837) to explore these questions, and conducted COVID-19 antibody testing on a subset of participants to identify correlations between behaviors and disease burden. The results showed that college students were more likely to intend to wear face masks as they experienced more positive injunctive norms, liberal political views, stronger response efficacy for masks, and less pessimism. Latent class analysis revealed four mitigation classes: Adherents who intended to wear face masks and engage in the other COVID-19 mitigation behaviors; Hygiene Stewards and Masked Symptom Managers who intended to wear masks but only some other behaviors, and Refusers who intended to engage in no mitigation behaviors. Importantly, the Hygiene Stewards and Refusers had the highest likelihood of positive antibodies; these two classes differed in their masking intentions, but shared very low likelihoods of physical distancing from others and avoiding crowds or mass gatherings. The implications for theories of normative influences on novel behaviors, spillover effects, and future messaging are discussed.

'Us-Versus-Them': Othering in COVID-19 public health behavior compliance.

OBJECTIVE: We explored public perceptions about the COVID-19 pandemic to learn how those attitudes may affect compliance with health behaviors. METHODS: Participants were Central Pennsylvania adults from diverse backgrounds purposively sampled (based on race, gender, educational attainment, and healthcare worker status) who responded to a mixed methods survey, completed between March 25-31, 2020. Four open-ended questions were analyzed, including: "What worries you most about the COVID-19 pandemic?" We applied a pragmatic, inductive coding process to conduct a qualitative, descriptive content analysis of responses. RESULTS: Of the 5,948 respondents, 538 were sampled for this qualitative analysis. Participants were 58% female, 56% with ≥ bachelor's degree, and 50% from minority racial backgrounds. Qualitative descriptive analysis revealed four themes related to respondents' health and societal concerns: lack of faith in others; fears of illness or death; frustration at perceived slow societal response; and a desire for transparency in communicating local COVID-19 information. An "us-versus-them" subtext emerged; participants attributed non-compliance with COVID-19 behaviors to other groups, setting themselves apart from those Others. CONCLUSION: Our study uncovered Othering undertones in the context of the COVID-19 pandemic, occurring between groups of like-minded individuals with behavioral differences in 'compliance' versus 'non-compliance' with public health recommendations. Addressing the 'us-versus-them' mentality may be important for boosting compliance with recommended health behaviors.

Underserved population acceptance of combination influenza-COVID-19 booster vaccines.

Recent data indicates increasing hesitancy towards both COVID-19 and influenza vaccination. We studied attitudes towards COVID-19 booster, influenza, and combination influenza-COVID-19 booster vaccines in a nationally representative sample of US adults between May and June 2021 (n = 12,887). We used pre-qualification quotes to ensure adequate sample sizes for minority populations. Overall vaccine acceptance was 45% for a COVID-19 booster alone, 58% for an influenza vaccine alone, and 50% for a combination vaccine. Logistic regression showed lower acceptance among female, Black/African American, Native American/American Indian, and rural respondents. Higher acceptance was found among those with college and post-graduate degrees. Despite these differences, our results suggest that a combination vaccine may provide a convenient method of dual vaccination that may increase COVID-19 vaccination coverage.

Developing and testing an automated qualitative assistant (AQUA) to support qualitative analysis.

Qualitative research remains underused, in part due to the time and cost of annotating qualitative data (coding). Artificial intelligence (AI) has been suggested as a means to reduce those burdens, and has been used in exploratory studies to reduce the burden of coding. However, methods to date use AI analytical techniques that lack transparency, potentially limiting acceptance of results. We developed an automated qualitative assistant (AQUA) using a semiclassical approach, replacing Latent Semantic Indexing/Latent Dirichlet Allocation with a more transparent graph-theoretic topic extraction and clustering method. Applied to a large dataset of free-text survey responses, AQUA generated unsupervised topic categories and circle hierarchical representations of free-text responses, enabling rapid interpretation of data. When tasked with coding a subset of free-text data into user-defined qualitative categories, AQUA demonstrated intercoder reliability in several multicategory combinations with a Cohen's kappa comparable to human coders (0.62-0.72), enabling researchers to automate coding on those categories for the entire dataset. The aim of this manuscript is to describe pertinent components of best practices of AI/machine learning (ML)-assisted qualitative methods, illustrating how primary care researchers may use AQUA to rapidly and accurately code large text datasets. The contribution of this article is providing guidance that should increase AI/ML transparency and reproducibility.