Evaluation of bias and gender/racial concordance based on sentiment analysis of narrative evaluations of clinical clerkships using natural language processing.

There is increasing interest in understanding potential bias in medical education. We used natural language processing (NLP) to evaluate potential bias in clinical clerkship evaluations. Data from medical evaluations and administrative databases for medical students enrolled in third-year clinical clerkship rotations across two academic years. We collected demographic information of students and faculty evaluators to determine gender/racial concordance (i.e., whether the student and faculty identified with the same demographic). We used a multinomial log-linear model for final clerkship grades, using predictors such as numerical evaluation scores, gender/racial concordance, and sentiment scores of narrative evaluations using the SentimentIntensityAnalyzer tool in Python. 2037 evaluations from 198 students were analyzed. Statistical significance was defined as P < 0.05. Sentiment scores for evaluations did not vary significantly by student gender, race, or ethnicity (P = 0.88, 0.64, and 0.06, respectively). Word choices were similar across faculty and student demographic groups. Modeling showed narrative evaluation sentiment scores were not predictive of an honors grade (odds ratio [OR] 1.23, P = 0.58). Numerical evaluation average (OR 1.45, P < 0.001) and gender concordance between faculty and student (OR 1.32, P = 0.049) were significant predictors of receiving honors. The lack of disparities in narrative text in our study contrasts with prior findings from other institutions. Ongoing efforts include comparative analyses with other institutions to understand what institutional factors may contribute to bias. NLP enables a systematic approach for investigating bias. The insights gained from the lack of association between word choices, sentiment scores, and final grades show potential opportunities to improve feedback processes for students.

Disparities in Eye Care Utilization Among Refugee and Migrant Populations.

Purpose: In this cross-sectional study, we examined refugee/migrant participants' health and eye care utilization compared to controls in San Diego County. Methods: Data were collected from electronic health records (EHRs) at UCSD Health-affiliated medical centers. Through a manual review of EHRs, eligibility criteria to identify a cohort were developed. A total of 64 refugee/migrant participants and 95 control participants matched based on country of origin, age, and sex were included in the analysis. Demographic characteristics, insurance type, and vision/eye care utilization were compared between the two groups. Results: A greater proportion of refugee/migrant participants were more likely to be enrolled in government-sponsored insurance programs, predominantly Medicaid when compared to controls (55% vs. 24%, P = < 0.01). When adjusting for age, history of ophthalmic procedure, and surgery, refugee status was associated with fewer encounters with ophthalmologists in a multivariable linear regression model (coefficient = -1.66 [95% confidence interval [CI] = -2.89 to -0.44], P = 0.009). Conclusions: This study highlights disparities in eye care utilization for refugee/migrant populations. When compared to controls, a larger proportion of refugees/migrants had government-funded insurance, and refugee status was associated with fewer encounters with ophthalmologists. These findings underscore the need for further research on this population to better understand potential healthcare barriers these individuals may encounter. Translational Relevance: This analysis of EHR data illustrates disparities in eye care experienced by refugees/migrants, highlighting potential gaps in care in a vulnerable population.

Proactive Decision Support for Glaucoma Treatment: Predicting Surgical Interventions with Clinically Available Data.

A longitudinal ophthalmic dataset was used to investigate multi-modal machine learning (ML) models incorporating patient demographics and history, clinical measurements, optical coherence tomography (OCT), and visual field (VF) testing in predicting glaucoma surgical interventions. The cohort included 369 patients who underwent glaucoma surgery and 592 patients who did not undergo surgery. The data types used for prediction included patient demographics, history of systemic conditions, medication history, ophthalmic measurements, 24-2 VF results, and thickness measurements from OCT imaging. The ML models were trained to predict surgical interventions and evaluated on independent data collected at a separate study site. The models were evaluated based on their ability to predict surgeries at varying lengths of time prior to surgical intervention. The highest performing predictions achieved an AUC of 0.93, 0.92, and 0.93 in predicting surgical intervention at 1 year, 2 years, and 3 years, respectively. The models were also able to achieve high sensitivity (0.89, 0.77, 0.86 at 1, 2, and 3 years, respectively) and specificity (0.85, 0.90, and 0.91 at 1, 2, and 3 years, respectively) at an 0.80 level of precision. The multi-modal models trained on a combination of data types predicted surgical interventions with high accuracy up to three years prior to surgery and could provide an important tool to predict the need for glaucoma intervention.

Gender Disparities in Depression, Stress, and Social Support Among Glaucoma Patients.

Purpose: To understand differences in measures of depression, stress, and social support by gender among those diagnosed with glaucoma. Methods: We obtained a cohort of glaucoma patients (any type) ages 18 years and over who answered the COVID-19 Participant Experience (COPE) survey of the NIH All of Us Research Program. We analyzed several measures of depression, stress, and social support by gender. Logistic regression was used to evaluate the association among reported stress associated with social distancing, depression (using Patient Health Questionnaire-9 [PHQ-9] scores), and measures of social support by self-reported gender, with men as the reference group. Multivariable models were adjusted for age, race and ethnicity, health insurance status, education, and income. Results: Of 3633 glaucoma patients, 56.8% were women. Many patients had a PHQ-9 score > 4 (33.3%), indicating mild, moderate, or severe depression. In multivariable models, women were significantly more likely to report a PHQ-9 score > 4 (odds ratio [OR] = 1.40; 95% confidence interval [CI], 1.20-1.62; P < 0.001) and some or a lot of stress (OR = 1.34; 95% CI, 1.14-1.57; P < 0.001) compared with men. Further, women were significantly less likely to report having help all or most of the time if they needed someone to prepare meals (OR = 0.78; 95% CI, 0.67-0.92; P = 0.002) or perform daily chores (OR = 0.79; 95% CI, 0.67-0.91; P = 0.003) than men. Conclusions: Women with glaucoma were more likely to experience depression and stress and were less likely to have social support on some measures than men. Translational Relevance: The disproportionate burden of psychosocial factors among women may complicate glaucoma management.

Social and Health Care Utilization Factors Associated With Ophthalmic Visit Nonadherence in Glaucoma: An All of Us Study.

PRCIS: In a diverse nationwide cohort, lower education and income levels, cost saving on medications, fewer past-year medical/specialist visits, and concerns regarding dissimilarity with health care providers were risk factors for ophthalmic visit nonadherence among glaucoma patients. PURPOSE: The purpose of this study was to characterize social and health care utilization factors associated with nonadherence with ophthalmic visits among patients with glaucoma. MATERIALS AND METHODS: Glaucoma patients in the All of Us database who completed the Healthcare Access and Utilization Survey were included and categorized into "visit" and "nonvisit" groups based on visit adherence, defined by self-reported past-year encounters with eyecare providers (yes/no). Data regarding potential factors affecting ophthalmic visit adherence, including past-year medical visits, inabilities to afford health care, and self-reported reasons for delayed care, were extracted. χ 2 tests and logistic regression were used to compare the 2 groups. Odds ratios (ORs) of visit adherence were analyzed for potential risk factors. RESULTS: Of 5739 glaucoma patients, 861 (15%) were in the nonvisit group. More participants in the visit group reported past-year general doctor/specialist visits (94%/65%; vs. nonvisit group: 89%/49.3%; P <0.05). The nonvisit group reported greater difficulty in affording medical care and learning about medical conditions, and higher rates of delayed/missed health care access for various concerns ( P <0.05). Older age (OR=1.02, 1.01-1.03), higher education (OR=1.25, 1.13-1.40), and income level (OR=1.06, 1.01-1.11), not employed for wages (OR=1.28, 1.08-1.53), and higher health care utilization in general medical/specialist visits (ORs range:1.08-1.90) were associated with visit adherence ( P <0.05). Visit nonadherence was associated with cost saving on medication (OR=0.62, 0.40-0.97) and delaying/avoiding seeing health care providers because of dissimilarity (OR=0.84, 0.71-0.99) ( P <0.05). CONCLUSIONS: This study builds on prior literature by identifying potentially modifiable factors associated with visit nonadherence and underutilization of eyecare in glaucoma. These may inform strategies to improve real-world ophthalmic visit adherence and identify patients who might benefit from additional support.

Racial, Ethnic, and Socioeconomic Disparities in Glaucoma Onset and Severity in a Diverse Nationwide Cohort in the United States.

PRCIS: Racial/ethnic minorities are diagnosed with glaucoma at younger ages, and Blacks are more likely to be diagnosed with moderate-to-severe glaucoma. In addition, we highlight a gap in the use of diagnosis codes. PURPOSE: The purpose of this study was to analyze patterns of diagnosis coding usage and validate epidemiologic patterns of glaucoma onset and severity among primary glaucoma patients within the National Institutes of Health All of Us database. PATIENTS AND METHODS: We used International Classification of Disease diagnosis codes to build 4 cohorts of patients with mild, moderate, severe, and unspecified stage glaucoma (N=2982). Descriptive analyses were stratified by disease stage, and mean age at diagnosis was compared across racial and ethnic groups. Multivariable ordinal regression was used to examine risk factors for increasing glaucoma severity. RESULTS: Of 2982 participants, 1714 (57%) had unspecified severity staging. Black/African Americans and other races were diagnosed with glaucoma at significantly younger ages compared with Whites (means 60 and 60 vs. 66 y; P <0.001). Hispanic/Latino participants also had an earlier mean age of diagnosis (61 vs. 65 y; P =0.001). Black/African Americans had higher odds of more severe glaucoma (odds ratio: 2.20, 95% CI, 1.62-3.30; P <0.001) than Whites when adjusting for socioeconomic characteristics. CONCLUSIONS: Black, Hispanic/Latino, and other minority participants are diagnosed with glaucoma at younger ages, and Blacks are more likely to be diagnosed with moderate-to-severe glaucoma. These findings validate prior population-based studies. Furthermore, we observed a gap in the use of diagnosis codes, as only 43% of participants had a specified severity stage in this national cohort. This may have implications for large-scale observational research concerning glaucoma severity, as electronic health records and claims databases typically lack other measures of disease progression, such as imaging and visual field data.

Epidemiology and factors associated with cannabis use among patients with glaucoma in the All of Us Research Program.

Purpose: To examine the epidemiology and factors of cannabis use among open-angle glaucoma (OAG) patients. Methods: In this cross-sectional study, OAG participants in the All of Us database were included. Cannabis ever-users were defined based on record of cannabis use. Demographic and socioeconomic data were collected and compared between cannabis ever-users and never-users using Chi-Square tests and logistic regression. Odds ratios (OR) of potential factors associated with cannabis use were examined in univariable and multivariable models. Results: Among 3723 OAG participants, 1436 (39%) were cannabis ever-users. The mean (SD) age of never-users and ever-users was 72.9 (10.4) and 69.2 (9.6) years, respectively (P < 0.001). Compared to never-users, Black (34%) and male (55%) participants were better represented in ever-users, while Hispanic or Latino participants (6%) were less represented (P < 0.001). Diversity was also observed in socioeconomic characteristics including marital status, housing security, and income/education levels. A higher percentage of ever-users had a degree ≥12 grades (91%), salaried employment (26%), housing insecurity (12%), and history of cigar smoking (48%), alcohol consumption (96%), and other substance use (47%) (P < 0.001). In the multivariable analysis, Black race (OR [95% CI] = 1.33 [1.06, 1.68]), higher education (OR = 1.19 [1.07, 1.32]), and history of nicotine product smoking (OR: 2.04-2.83), other substance use (OR = 8.14 [6.63, 10.04]), and alcohol consumption (OR = 6.80 [4.45, 10.79]) were significant factors associated with cannabis use. Increased age (OR = 0.96 [0.95, 0.97]), Asian race (OR = 0.18 [0.09, 0.33]), and Hispanic/Latino ethnicity (OR = 0.43 [0.27, 0.68]) were associated with decreased odds of use (P < 0.02). Conclusions: This study elucidated the previously uncharacterized epidemiology and factors associated with cannabis use among OAG patients, which may help to identify patients requiring additional outreach on unsupervised marijuana use.

Racial Disparities in Barriers to Care for Patients With Diabetic Retinopathy in a Nationwide Cohort.

Purpose: To ascertain specific barriers of care among patients with diabetic retinopathy (DR) from different racial/ethnic groups. Methods: In this cross-sectional study, we included adult participants in the National Institutes of Health All of Us Research Program with DR who answered questions in the Healthcare Access & Utilization survey and Social Determinants of Health (SDoH) survey. Logistic regression was used to study the association between barriers to care and race/ethnicity. Results: Our cohort included 885 DR patients who answered the Healthcare Access & Utilization survey and 385 DR patients who responded to the SDoH survey. After adjusting for confounders, Hispanic individuals were more likely than non-Hispanic White individuals to report delaying getting medical care due to not being able to get child care (odds ratio [OR] = 6.57 [95% confidence interval {CI}, 1.67-27.8]). Furthermore, compared to non-Hispanic White individuals, non-Hispanic Black individuals were significantly more likely to report being treated with less respect (OR = 2.62 [95% CI, 1.15-5.80]), treated with less courtesy (OR = 2.51 [95% CI, 1.01-5.92]), and receive poorer service than other people (OR = 2.85 [95% CI, 1.25-6.34]) when they go to a doctor's office or other healthcare provider. Conclusions: We found that Hispanic and non-Hispanic Black individuals with DR reported greater delays/barriers to care compared to non-Hispanic White individuals even after controlling for individualized socioeconomic factors. Translational Relevance: This study highlights the importance of taking steps to promote health equity, such as increasing access to child care resources and reducing implicit bias among eye care providers, to increase access to care and prevent vision loss from DR.

Associations between Socioeconomic Factors and Visit Adherence among Patients with Glaucoma in the All of Us Research Program.

PURPOSE: To identify socioeconomic factors associated with visit adherence among patients with glaucoma in a nationwide cohort. DESIGN: Cross-sectional study. SUBJECTS: All subjects were participants in the National Institutes of Health All of Us Research Program. This study cohort consists of participants who were diagnosed with glaucoma and who answered the question on the Health Care Access and Utilization Survey regarding whether they have seen an eye care provider in the last 12 months. METHODS: Descriptive analyses were conducted based on participant age, gender, race/ethnicity, insurance status, level of education, and income bracket. Multivariable logistic regression adjusting for these factors was used to generate odds ratios (ORs) for the association between socioeconomic factors and visit adherence. MAIN OUTCOME MEASURE: Visit adherence, defined as reporting seeing an eye care provider in the last 12 months. RESULTS: Among 4517 patients with glaucoma, 730 (16.3%) indicated that they had not seen or spoken to an eye doctor in the last 12 months. In multivariable models, those with some college education (OR: 1.91; 95% confidence interval [CI]: 1.19-3.04) and those with a college degree or advanced degree (OR: 2.25; 95% CI: 1.39-3.60) and those with the highest annual income of ≥ $200 000 (OR: 1.64; 95% CI: 1.10-2.45) were more likely to have seen an eye doctor in the past year compared with those in the lowest education and income categories, respectively. CONCLUSION: Lower income and education levels were significantly associated with lower odds of seeing an eye doctor in the past year among all patients with glaucoma in All of Us. This highlights an important health disparity and may inform subsequent interventions to promote improved adherence to clinical guidelines regarding eye care for glaucoma monitoring and management. FINANCIAL DISCLOSURE(S): Proprietary or commercial disclosure may be found after the references.

Evaluation of Depression and Anxiety in a Diverse Population With Thyroid Eye Disease Using the Nationwide NIH All of Us Database.

PURPOSE: To evaluate the prevalence of depression and anxiety among individuals with thyroid eye disease (TED) and identify sociodemographic risk factors using the NIH All of Us database. METHODS: Three hundred ninety eight cases with TED were compared with 1,592 controls with demographics matching the 2020 US Census. Primary outcomes were diagnosed depression or anxiety; Patient Health Questionnaire-9 (PHQ-9) scores and General Anxiety Disorder-7 (GAD-7) scores were included as secondary outcomes. We performed multivariable logistic regression to generate odds ratios (ORs) and 95% confidence intervals (CIs) for the association between TED and depression and anxiety. RESULTS: Patients with TED were more likely to have depression (OR 2.72, 95% CI 2.08-3.56, p < 0.001) and anxiety (OR 2.82, 95% CI 2.16-3.70, p < 0.001) than controls. In patients with TED, female gender was an independent risk factor for both depression (OR 1.72; 95% CI 1.00-5.07, p = 0.05) and anxiety (OR 2.17, 95% CI 1.25-3.85, p = 0.006). Unemployment (OR 1.72, 95% CI 1.03-2.94, p = 0.04) and lower income (OR 0.88 for income as a continuous variable, 95% CI 0.79-0.99, p = 0.03) were risk factors for anxiety. Risk factors for more severe depression as assessed by PHQ-9 included lower income (OR 0.70, 95% CI 0.57-0.85, p < 0.001), and protective factors included Black race (OR 0.12, 95% CI 0.02-0.45, p = 0.002). Lower income was associated with more severe anxiety as assessed by GAD-7 (OR 0.77, 95% CI 0.64-0.94, p = 0.009). CONCLUSIONS: Patients with TED were more likely to develop depression and anxiety compared with controls. This study highlights the psychosocial impact of TED and associated socioeconomic risk factors.

Mental health and social support among glaucoma patients enrolled in the NIH All of Us COVID-19 Participant Experience (COPE) survey.

BACKGROUND: The COVID-19 pandemic created many challenges for our society. In this study, we explore how measures of mental health, coping strategies, and social support during the pandemic varied by glaucoma status. METHODS: A cohort of patients aged 40 and over enrolled in the NIH All of Us Research Program, a nationwide longitudinal cohort, who answered the COVID-19 Participant Experience (COPE) survey was obtained. We analyzed several measures of mental health, coping strategies, and social support used during the early stages of the COVID-19 pandemic. Surveys were recurring and answered from May 2020 to February 2021. Demographics and the most recently answered survey responses were obtained and stratified by glaucoma status. Pearson's Chi-squared tests and multivariable logistic regressions adjusting for age, gender, race, ethnicity, and income were used to generate p-values, odds ratios (ORs) and 95% confidence intervals (CIs) between outcome measures and glaucoma status. RESULTS: Of 42,484 patients who responded to All of Us COPE survey items, 2912 (6.9%) had a diagnosis of glaucoma. On Pearson's Chi-squared tests glaucoma patients were less likely to report drinking alcohol (P = 0.003), eating more food than usual (P = 0.004), and using marijuana (P = 0.006) to cope with social distancing than those without a diagnosis of glaucoma. Further, glaucoma patients had lower rates of probable mild, moderate, or severe depression as calculated by Patient Health Questionnaire-9 (PHQ-9) scores (P < 0.001) and had lower rates of reporting some or a lot of stress from social distancing (P < 0.001). However, glaucoma patients were less likely to report having someone to help prepare meals (P = 0.005) or help with daily chores (P = 0.003) if they became sick with COVID-19. In multivariable logistic regression analyses adjusting for confounding factors, no differences were found for measures of mental health or social support. CONCLUSIONS: Glaucoma patients did not fare worse on many measures of mental health and coping strategies during the early stages of the COVID-19 pandemic compared those without glaucoma. However, a substantial proportion of glaucoma patients still endorsed stress, social isolation, and probable depression, representing challenges for disease management.

Associations Between Thyroid Eye Disease and Glaucoma Among Those Enrolled in the National Institutes of Health All of Us Research Program.

PURPOSE: To assess the association between thyroid eye disease (TED) and glaucoma. METHODS: Patients 18 years of age and over enrolled in the NIH All of Us Research Program, a nationwide cohort, were extracted. Those with conditions relating to TED were identified and compared with 2020 US Census-matched controls without a diagnosis of TED in a 1:4 ratio. The authors used Pearson's χ 2 tests to study demographics by TED status, and logistic regression to generate odds ratios and 95% confidence intervals to evaluate the association between TED and glaucoma (any type, including glaucoma suspect), using those without TED as the reference group. Multivariable models were adjusted for age, gender, race/ethnicity, eye doctor visits, and smoking status. RESULTS: A total of 393 cases of TED and 1,572 US Census-matched controls were identified. The median age of the cohort was 63 years (interquartile range: 48-73 years). Age, gender, and race/ethnicity varied by TED status ( p < 0.001). Overall, 114 (29.0%) of TED cases had a diagnosis of glaucoma, compared with 94 (6.0%) of non-TED controls. On bivariate logistic regression models, those diagnosed with TED were significantly more likely to be diagnosed with glaucoma compared with controls (odds ratio: 6.42; 95% confidence interval: 4.76-8.70; p < 0.001). This trend persisted on multivariable logistic regression controlling for confounding factors (odds ratio: 3.37; 95% confidence interval: 1.85-6.20 p < 0.001). CONCLUSIONS: Individuals with TED were significantly more likely to be diagnosed with glaucoma. Clinicians caring for patients with TED should be aware of this elevated risk and arrange glaucoma evaluation, accordingly.

Associations between healthcare utilization and access and diabetic retinopathy complications using All of Us nationwide survey data.

PURPOSE: Inadequacies in healthcare access and utilization substantially impact outcomes for diabetic patients. The All of Us database offers extensive survey data pertaining to social determinants that is not routinely available in electronic health records. This study assesses whether social determinants were associated with an increased risk of developing proliferative diabetic retinopathy or related complications (e.g. related diagnoses or procedures). METHODS: We identified 729 adult participants in the National Institutes of Health All of Us Research Program data repository with diabetic retinopathy (DR) who answered survey questions pertaining to healthcare access and utilization. Electronic health record data regarding co-morbidities, laboratory values, and procedures were extracted. Multivariable logistic regression with bi-directional stepwise variable selection was performed from a wide range of predictors. Statistical significance was defined as p<0.05. RESULTS: The mean (standard deviation) age of our cohort was 64.9 (11.4) years. 15.2% identified as Hispanic or Latino, 20.4% identified as Black, 60.6% identified as White, and 19.3% identified as Other. 10-20% of patients endorsed several reasons for avoiding or delaying care, including financial concerns and lack of access to transportation. Additional significant social determinants included race and religion discordance between healthcare provider and patient (odds ratio [OR] 1.20, 95% confidence interval [CI] 1.02-1.41, p = 0.03) and caregiver responsibilities toward others (OR 3.14, 95% CI 1.01-9.50, p = 0.04). CONCLUSIONS: Nationwide data demonstrate substantial barriers to healthcare access among DR patients. In addition to financial and social determinants, race and religion discordance between providers and patients may increase the likelihood of PDR and related complications.

Racial and Ethnic Disparities in Cost-Related Barriers to Medication Adherence Among Patients With Glaucoma Enrolled in the National Institutes of Health All of Us Research Program.

IMPORTANCE: Ability to afford medication is a major determinate of medication adherence among patients. OBJECTIVE: To determine cost-related barriers to medication adherence by race and ethnicity in a nationwide cohort of patients with glaucoma. DESIGN, SETTING, AND PARTICIPANTS: This cross-sectional study included patients with glaucoma enrolled in the National Institutes of Health All of Us Research Program, a nationwide longitudinal cohort of US adults, with more than 300 000 currently enrolled. Individuals with a diagnosis of glaucoma based on electronic health record diagnosis codes who participated in the Health Care Access and Utilization survey and had complete data on all covariates were studied. Data were collected from June 2016 to March 2021, and data were analyzed from August to November 2021. EXPOSURES: Race and ethnicity defined as non-Hispanic African American, non-Hispanic Asian, Hispanic, and non-Hispanic White. MAIN OUTCOMES AND MEASURES: Logistic regression was used to evaluate the association between reported cost-related barriers to medication adherence (could not afford prescription medication, skipped medication doses to save money, took less medication to save money, delayed filling a prescription to save money, asked for lower-cost medication to save money, bought prescriptions from another country to save money, and used alternative therapies to save money) and race and ethnicity, adjusting multivariable models by age, gender, health insurance status, education, and income. Odds ratios of these barriers were obtained by race and ethnicity, with non-Hispanic White race as the reference group. RESULTS: Of 3826 included patients with glaucoma, 481 (12.6%) were African American, 119 (3.1%) were non-Hispanic Asian, 351 (9.2%) were Hispanic, and 2875 (75.1%) were non-Hispanic White. The median (IQR) age was 69 (60-75) years, and 2307 (60.3%) were female. After adjusting for confounders, non-Hispanic African American individuals (odds ratio, 1.82; 95% CI, 1.34-2.44) and Hispanic individuals (odds ratio, 1.77; 95% CI, 1.25-2.49) were more likely than non-Hispanic White individuals to report not being able to afford medications. Further, despite having the lowest rate of endorsing difficulty affording medications, non-Hispanic White individuals were equally likely to ask for lower-cost medication from their clinicians as individuals of racial and ethnic minority groups. CONCLUSIONS AND RELEVANCE: In this study, there was significantly higher odds of self-reported difficulty affording medications among non-Hispanic African American and Hispanic individuals compared with non-Hispanic White individuals. Clinicians should be proactive and initiate discussions about costs in an effort to promote medication adherence and health equity among patients.

Social determinants associated with loss of an eye in the United States using the All of Us nationwide database.

PURPOSE: To identify common factors associated with the loss of an eye using the NIH All of Us database. METHODS: In this case-controlled study, we extracted electronic health record and socio-demographic data for 231 cases of eye loss from All of Us enrollment sites. Controls (N = 924) matched the demographic characteristics of the 2020 United States Census. Bivariate analyses and multivariable logistic regression identified variables significantly associated with increased odds of eye loss. OUTCOME MEASURES: Medical and social determinants associated with increased odds of losing an eye. RESULTS: Among cases, the average age (standard deviation) was 60.1 (14.4) years. The majority (125, 54.1%) were male. 87 (37.7%) identified as African American, and 49 (21.2%) identified as Hispanic or Latino. Loss of eye was more likely in those with ocular tumor (odds ratio [OR] 421.73, 25 95% confidence interval [CI] 129.81-1959.80, p < .001), trauma (OR 13.38, 95% CI 6.64-27.43, p < .001), infection (OR 11.46, 95% CI 4.11-32.26, p = .001) or glaucoma (OR 8.33, 95% CI 4.43- 15.81, p < .001). African American (OR 2.39, 95% CI 1.39-4.09, p = .002) and Hispanic or Latino (OR 1.80, 95% CI 1.01-3.15, p = .04) participants were disproportionately affected. CONCLUSIONS: Racial and ethnic disparities exist among those with loss of an eye from underlying conditions. Addressing health inequities may mitigate the risk of this morbid outcome.

Text Processing for Detection of Fungal Ocular Involvement in Critical Care Patients: Cross-Sectional Study.

BACKGROUND: Fungal ocular involvement can develop in patients with fungal bloodstream infections and can be vision-threatening. Ocular involvement has become less common in the current era of improved antifungal therapies. Retrospectively determining the prevalence of fungal ocular involvement is important for informing clinical guidelines, such as the need for routine ophthalmologic consultations. However, manual retrospective record review to detect cases is time-consuming. OBJECTIVE: This study aimed to determine the prevalence of fungal ocular involvement in a critical care database using both structured and unstructured electronic health record (EHR) data. METHODS: We queried microbiology data from 46,467 critical care patients over 12 years (2000-2012) from the Medical Information Mart for Intensive Care III (MIMIC-III) to identify 265 patients with culture-proven fungemia. For each fungemic patient, demographic data, fungal species present in blood culture, and risk factors for fungemia (eg, presence of indwelling catheters, recent major surgery, diabetes, immunosuppressed status) were ascertained. All structured diagnosis codes and free-text narrative notes associated with each patient's hospitalization were also extracted. Screening for fungal endophthalmitis was performed using two approaches: (1) by querying a wide array of eye- and vision-related diagnosis codes, and (2) by utilizing a custom regular expression pipeline to identify and collate relevant text matches pertaining to fungal ocular involvement. Both approaches were validated using manual record review. The main outcome measure was the documentation of any fungal ocular involvement. RESULTS: In total, 265 patients had culture-proven fungemia, with Candida albicans (n=114, 43%) and Candida glabrata (n=74, 28%) being the most common fungal species in blood culture. The in-hospital mortality rate was 121 (46%). In total, 7 patients were identified as having eye- or vision-related diagnosis codes, none of whom had fungal endophthalmitis based on record review. There were 26,830 free-text narrative notes associated with these 265 patients. A regular expression pipeline based on relevant terms yielded possible matches in 683 notes from 108 patients. Subsequent manual record review again demonstrated that no patients had fungal ocular involvement. Therefore, the prevalence of fungal ocular involvement in this cohort was 0%. CONCLUSIONS: MIMIC-III contained no cases of ocular involvement among fungemic patients, consistent with prior studies reporting low rates of ocular involvement in fungemia. This study demonstrates an application of natural language processing to expedite the review of narrative notes. This approach is highly relevant for ophthalmology, where diagnoses are often based on physical examination findings that are documented within clinical notes.