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

[This corrects the article DOI: 10.1371/journal.pone.0269231.].

Automated Detection of Posterior Vitreous Detachment on OCT Using Computer Vision and Deep Learning Algorithms.

Objective: To develop automated algorithms for the detection of posterior vitreous detachment (PVD) using OCT imaging. Design: Evaluation of a diagnostic test or technology. Subjects: Overall, 42 385 consecutive OCT images (865 volumetric OCT scans) obtained with Heidelberg Spectralis from 865 eyes from 464 patients at an academic retina clinic between October 2020 and December 2021 were retrospectively reviewed. Methods: We developed a customized computer vision algorithm based on image filtering and edge detection to detect the posterior vitreous cortex for the determination of PVD status. A second deep learning (DL) image classification model based on convolutional neural networks and ResNet-50 architecture was also trained to identify PVD status from OCT images. The training dataset consisted of 674 OCT volume scans (33 026 OCT images), while the validation testing set consisted of 73 OCT volume scans (3577 OCT images). Overall, 118 OCT volume scans (5782 OCT images) were used as a separate external testing dataset. Main Outcome Measures: Accuracy, sensitivity, specificity, F1-scores, and area under the receiver operator characteristic curves (AUROCs) were measured to assess the performance of the automated algorithms. Results: Both the customized computer vision algorithm and DL model results were largely in agreement with the PVD status labeled by trained graders. The DL approach achieved an accuracy of 90.7% and an F1-score of 0.932 with a sensitivity of 100% and a specificity of 74.5% for PVD detection from an OCT volume scan. The AUROC was 89% at the image level and 96% at the volume level for the DL model. The customized computer vision algorithm attained an accuracy of 89.5% and an F1-score of 0.912 with a sensitivity of 91.9% and a specificity of 86.1% on the same task. Conclusions: Both the computer vision algorithm and the DL model applied on OCT imaging enabled reliable detection of PVD status, demonstrating the potential for OCT-based automated PVD status classification to assist with vitreoretinal surgical planning. Financial Disclosures: Proprietary or commercial disclosure may be found after the references.

Healthcare Access and Utilization Among Glaucoma Patients in a Nationwide Cohort.

PRCIS: Despite having lower socioeconomic status on several measures, glaucoma patients do not report more barriers to healthcare access and utilization than non-glaucoma patients. PURPOSE: To characterize measures of socioeconomic status and barriers to healthcare access and utilization between patients with and without a diagnosis of glaucoma. METHODS: Patients aged 65 years and over who enrolled in the NIH All of Us Research Program, a nationwide longitudinal cohort, were extracted. We analyzed demographic information and several measures of socioeconomic status and healthcare access and utilization. Survey responses were compared by glaucoma status (any type) with Pearson χ 2 tests, univariable logistic regression, and multivariable logistic regression adjusting for age, gender, race/ethnicity, and insurance status. RESULTS: Of the 49,487 patients who answered at least 1 question on the All of Us Healthcare Access and Utilization Survey, 4441 (9.0%) had a diagnosis of glaucoma. Majority of the cohort was female (28,162, 56.9%) and nonHispanic White (42,008, 84.9%). Glaucoma patients were observed to have lower rates of education ( P =0.004), employment ( P <0.001), and home ownership ( P <0.001) on χ 2 tests. On multivariable logistic regression models, those with glaucoma were significantly more likely to speak to an eye doctor (Odds ratio: 2.46; 95% confidence interval: 2.16 to 2.81) and significantly less likely to have trouble affording eyeglasses (OR: 0.85 95% CI: 0.72 to 0.99) in the prior year than those without a diagnosis of glaucoma. No significant association was found for other measures of healthcare access and utilization by glaucoma status. CONCLUSION: Although glaucoma patients aged 65 years and over fared worse on several measures of socioeconomic status, no significant difference was found in measures of healthcare access and utilization.

Association of Electronic Health Record Inbasket Message Characteristics With Physician Burnout.

Importance: Physician burnout is an ongoing epidemic; electronic health record (EHR) use has been associated with burnout, and the burden of EHR inbasket messages has grown in the context of the COVID-19 pandemic. Understanding how EHR inbasket messages are associated with physician burnout may uncover new insights for intervention strategies. Objective: To evaluate associations between EHR inbasket message characteristics and physician burnout. Design, Setting, and Participants: Cross-sectional study in a single academic medical center involving physicians from multiple specialties. Data collection took place April to September 2020, and data were analyzed September to December 2020. Exposures: Physicians responded to a survey including the validated Mini-Z 5-point burnout scale. Main Outcomes and Measures: Physician burnout according to the self-reported burnout scale. A sentiment analysis model was used to calculate sentiment scores for EHR inbasket messages extracted for participating physicians. Multivariable modeling was used to model risk of physician burnout using factors such as message characteristics, physician demographics, and clinical practice characteristics. Results: Of 609 physicians who responded to the survey, 297 (48.8%) were women, 343 (56.3%) were White, 391 (64.2%) practiced in outpatient settings, and 428 (70.28%) had been in medical practice for 15 years or less. Half (307 [50.4%]) reported burnout (score of 3 or higher). A total of 1 453 245 inbasket messages were extracted, of which 630 828 (43.4%) were patient messages. Among negative messages, common words included medical conditions, expletives and/or profanity, and words related to violence. There were no significant associations between message characteristics (including sentiment scores) and burnout. Odds of burnout were significantly higher among Hispanic/Latino physicians (odds ratio [OR], 3.44; 95% CI, 1.18-10.61; P = .03) and women (OR, 1.60; 95% CI, 1.13-2.27; P = .01), and significantly lower among physicians in clinical practice for more than 15 years (OR, 0.46; 95% CI, 0.30-0.68; P < .001). Conclusions and Relevance: In this cross-sectional study, message characteristics were not associated with physician burnout, but the presence of expletives and violent words represents an opportunity for improving patient engagement, EHR portal design, or filters. Natural language processing represents a novel approach to understanding potential associations between EHR inbasket messages and physician burnout and may also help inform quality improvement initiatives aimed at improving patient experience.

Social Determinants of Health Data Availability for Patients with Eye Conditions.

Purpose: To quantify and characterize social determinants of health (SDoH) data coverage using single-center electronic health records (EHRs) and the National Institutes of Health All of Us research program. Design: Retrospective cohort study from June 2014 through June 2021. Participants: Adults 18 years of age or older with a diagnosis of diabetic retinopathy, glaucoma, cataracts, or age-related macular degeneration. Methods: For All of Us, research participants completed online survey forms as part of a nationwide prospective cohort study. In local EHRs, patients were selected based on diagnosis codes. Main Outcome Measures: Social determinants of health data coverage, characterized by the proportion of each disease cohort with available data regarding demographics and socioeconomic factors. Results: In All of Us, we identified 23 806 unique adult patients, of whom 2246 had a diagnosis of diabetic retinopathy, 13 448 had a diagnosis of glaucoma, 6634 had a diagnosis of cataracts, and 1478 had a diagnosis of age-related macular degeneration. Survey completion rates were high (99.5%-100%) across all cohorts for demographic information, overall health, income, education, and lifestyle. However, health care access (12.7%-29.4%), housing (0.7%-1.1%), social isolation (0.2%-0.3%), and food security (0-0.1%) showed significantly lower response rates. In local EHRs, we identified 80 548 adult patients, of whom 6616 had a diagnosis of diabetic retinopathy, 26 793 had a diagnosis of glaucoma, 40 427 had a diagnosis of cataracts, and 6712 had a diagnosis of age-related macular degeneration. High data coverage was found across all cohorts for variables related to tobacco use (82.84%-89.07%), alcohol use (77.45%-83.66%), and intravenous drug use (84.76%-93.14%). However, low data coverage (< 50% completion) was found for all other variables, including education, finances, social isolation, stress, physical activity, food insecurity, and transportation. We used chi-square testing to assess whether the data coverage varied across different disease cohorts and found that all fields varied significantly (P < 0.001). Conclusions: The limited and highly variable data coverage in both local EHRs and All of Us highlights the need for researchers and providers to develop SDoH data collection strategies and to assemble complete datasets.

Novel Association between Opioid Use and Increased Risk of Retinal Vein Occlusion Using the National Institutes of Health All of Us Research Program.

Purpose: To assess for risk factors for retinal vein occlusion (RVO) among participants in the National Institutes of Health All of Us database, particularly social risk factors that have not been well studied, including substance use. Design: Retrospective, case-control study. Participants: Data were extracted for 380 adult participants with branch retinal vein occlusion (BRVO), 311 adult participants with central retinal vein occlusion (CRVO), and 1520 controls sampled among 311 640 adult participants in the All of Us database. Methods: Data were extracted regarding demographics, comorbidities, income, housing, insurance, and substance use. Opioid use was defined by relevant diagnosis and prescription codes, with prescription use > 30 days. Controls were sampled at a 4:1 control to case ratio from a pool of individuals aged > 18 years without a diagnosis of RVO and proportionally matched to the demographic distribution of the 2019 U.S. census. Multivariable logistic regression identified medical and social determinants significantly associated with BRVO or CRVO. Statistical significance was defined as P < 0.05. Main Outcome Measure: Development of BRVO or CRVO based on diagnosis codes. Results: Among patients with BRVO, the mean (standard deviation) age was 70.1 (10.5) years. The majority (53.7%) were female. Cases were diverse; 23.7% identified as Black, and 18.4% identified as Hispanic or Latino. Medical risk factors including glaucoma (odds ratio [OR], 3.29; 95% confidence interval [CI], 2.22-4.90; P < 0.001), hypertension (OR, 2.15; 95% CI, 1.49-3.11; P < 0.001), and diabetes mellitus (OR, 1.68; 95% CI, 1.18-2.38; P = 0.004) were re-demonstrated to be associated with BRVO. Black race (OR, 2.64; 95% CI, 1.22-6.05; P = 0.017) was found to be associated with increased risk of BRVO. Past marijuana use (OR, 0.68; 95% CI, 0.50-0.92; P = 0.013) was associated with decreased risk of BRVO; however, opioid use (OR, 1.98; 95% CI, 1.41-2.78; P < 0.001) was associated with a significantly increased risk of BRVO. Similar associations were found for CRVO. Conclusions: Understanding RVO risk factors is important for primary prevention and improvement in visual outcomes. This study capitalizes on the diversity and scale of a novel nationwide database to elucidate a previously uncharacterized association between RVO and opioid use.

Assessing Usability of Smartwatch Digital Health Devices for Home Blood Pressure Monitoring among Glaucoma Patients.

Glaucoma is a leading cause of blindness worldwide. Blood pressure (BP) dysregulation is a known risk factor, and home-based BP monitoring is increasingly used, but the usability of digital health devices to measure BP among glaucoma patients is not well studied. There may be particular usability challenges among this group, given that glaucoma disproportionately affects the elderly and can cause visual impairment. Therefore, the goal of this mixed-methods study was to assess the usability of a smart watch digital health device for home BP monitoring among glaucoma patients. Adult participants were recruited and given a smartwatch blood pressure monitor for at-home use. The eHEALS questionnaire was used to determine baseline digital health literacy. After a week of use, participants assessed the usability of the BP monitor and related mobile app using the Post-study System Usability Questionnaire (PSSUQ) and the System Usability Scale (SUS), standardized instruments to measure usability in health information technology interventions. Variations in scores were evaluated using ANOVA and open-ended responses about participants' experience were analyzed thematically. Overall, usability scores corresponded to the 80th-84th percentile, although older patients endorsed significantly worse usability based on quantitative scores and additionally provided qualitative feedback describing some difficulty using the device. Usability for older patients should be considered in the design of digital health devices for glaucoma given their disproportionate burden of disease and challenges in navigating digital health technologies, although the overall high usability scores for the device demonstrates promise for future clinical applications in glaucoma risk stratification.

Predictive Analytics for Glaucoma Using Data From the All of Us Research Program.

PURPOSE: To (1) use All of Us (AoU) data to validate a previously published single-center model predicting the need for surgery among individuals with glaucoma, (2) train new models using AoU data, and (3) share insights regarding this novel data source for ophthalmic research. DESIGN: Development and evaluation of machine learning models. METHODS: Electronic health record data were extracted from AoU for 1,231 adults diagnosed with primary open-angle glaucoma. The single-center model was applied to AoU data for external validation. AoU data were then used to train new models for predicting the need for glaucoma surgery using multivariable logistic regression, artificial neural networks, and random forests. Five-fold cross-validation was performed. Model performance was evaluated based on area under the receiver operating characteristic curve (AUC), accuracy, precision, and recall. RESULTS: The mean (standard deviation) age of the AoU cohort was 69.1 (10.5) years, with 57.3% women and 33.5% black, significantly exceeding representation in the single-center cohort (P = .04 and P < .001, respectively). Of 1,231 participants, 286 (23.2%) needed glaucoma surgery. When applying the single-center model to AoU data, accuracy was 0.69 and AUC was only 0.49. Using AoU data to train new models resulted in superior performance: AUCs ranged from 0.80 (logistic regression) to 0.99 (random forests). CONCLUSIONS: Models trained with national AoU data achieved superior performance compared with using single-center data. Although AoU does not currently include ophthalmic imaging, it offers several strengths over similar big-data sources such as claims data. AoU is a promising new data source for ophthalmic research.

Predicting Mortality in Critical Care Patients with Fungemia Using Structured and Unstructured Data.

Fungemia is a life-threatening infection, but predictive models of in-patient mortality in this infection are few. In this study, we developed models predicting all-cause in-hospital mortality among 265 fungemic patients in the Medical Information Mart for Intensive Care (MIMIC-III) database using both structured and unstructured data. Structured data models included multivariable logistic regression, extreme gradient boosting, and stacked ensemble models. Unstructured data models were developed using Amazon Comprehend Medical and BioWordVec embeddings in logistic regression, convolutional neural networks (CNNs), and recurrent neural networks (RNNs). We evaluated models trained on all notes, notes from only the first three days of hospitalization, and models trained on only physician notes. The best-performing structured data model was a multivariable logistic regression model that achieved an accuracy of 0.74 and AUC of 0.76. Liver disease, acute renal failure, and intubation were some of the top features driving prediction in multiple models. CNNs using unstructured data achieved similar performance even when trained with notes from only the first three days of hospitalization. The best-performing unstructured data models used the Amazon Comprehend Medical document classifier and CNNs, achieving accuracy ranging from 0.99-1.00, and AUCs of 1.00. Therefore, unstructured data - particularly notes composed by physicians - offer added predictive value over models based on structured data alone.