Prediction Models for Glaucoma in a Multicenter Electronic Health Records Consortium: The Sight Outcomes Research Collaborative.

Purpose: Advances in artificial intelligence have enabled the development of predictive models for glaucoma. However, most work is single-center and uncertainty exists regarding the generalizability of such models. The purpose of this study was to build and evaluate machine learning (ML) approaches to predict glaucoma progression requiring surgery using data from a large multicenter consortium of electronic health records (EHR). Design: Cohort study. Participants: Thirty-six thousand five hundred forty-eight patients with glaucoma, as identified by International Classification of Diseases (ICD) codes from 6 academic eye centers participating in the Sight OUtcomes Research Collaborative (SOURCE). Methods: We developed ML models to predict whether patients with glaucoma would progress to glaucoma surgery in the coming year (identified by Current Procedural Terminology codes) using the following modeling approaches: (1) penalized logistic regression (lasso, ridge, and elastic net); (2) tree-based models (random forest, gradient boosted machines, and XGBoost), and (3) deep learning models. Model input features included demographics, diagnosis codes, medications, and clinical information (intraocular pressure, visual acuity, refractive status, and central corneal thickness) available from structured EHR data. One site was reserved as an "external site" test set (N = 1550); of the patients from the remaining sites, 10% each were randomly selected to be in development and test sets, with the remaining 27 999 reserved for model training. Main Outcome Measures: Evaluation metrics included area under the receiver operating characteristic curve (AUROC) on the test set and the external site. Results: Six thousand nineteen (16.5%) of 36 548 patients underwent glaucoma surgery. Overall, the AUROC ranged from 0.735 to 0.771 on the random test set and from 0.706 to 0.754 on the external test site, with the XGBoost and random forest model performing best, respectively. There was greatest performance decrease from the random test set to the external test site for the penalized regression models. Conclusions: Machine learning models developed using structured EHR data can reasonably predict whether glaucoma patients will need surgery, with reasonable generalizability to an external site. Additional research is needed to investigate the impact of protected class characteristics such as race or gender on model performance and fairness. Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Validation of Artificial Intelligence (AI)-Assisted Flow Cytometry Analysis for Immunological Disorders.

Flow cytometry is a vital diagnostic tool for hematologic and immunologic disorders, but manual analysis is prone to variation and time-consuming. Over the last decade, artificial intelligence (AI) has advanced significantly. In this study, we developed and validated an AI-assisted flow cytometry workflow using 379 clinical cases from 2021, employing a 3-tube, 10-color flow panel with 21 antibodies for primary immunodeficiency diseases and related immunological disorders. The AI software (DeepFlow™, version 2.1.1) is fully automated, reducing analysis time to under 5 min per case. It interacts with hematopatholoists for manual gating adjustments when necessary. Using proprietary multidimensional density-phenotype coupling algorithm, the AI model accurately classifies and enumerates T, B, and NK cells, along with important immune cell subsets, including CD4+ helper T cells, CD8+ cytotoxic T cells, CD3+/CD4-/CD8- double-negative T cells, and class-switched or non-switched B cells. Compared to manual analysis with hematopathologist-determined lymphocyte subset percentages as the gold standard, the AI model exhibited a strong correlation (r > 0.9) across lymphocyte subsets. This study highlights the accuracy and efficiency of AI-assisted flow cytometry in diagnosing immunological disorders in a clinical setting, providing a transformative approach within a concise timeframe.

Using Natural Language Processing to Identify Different Lens Pathology in Electronic Health Records.

PURPOSE: Nearly all published ophthalmology-related Big Data studies rely exclusively on International Classification of Diseases (ICD) billing codes to identify patients with particular ocular conditions. However, inaccurate or nonspecific codes may be used. We assessed whether natural language processing (NLP), as an alternative approach, could more accurately identify lens pathology. DESIGN: Database study comparing the accuracy of NLP versus ICD billing codes to properly identify lens pathology. METHODS: We developed an NLP algorithm capable of searching free-text lens exam data in the electronic health record (EHR) to identify the type(s) of cataract present, cataract density, presence of intraocular lenses, and other lens pathology. We applied our algorithm to 17.5 million lens exam records in the Sight Outcomes Research Collaborative (SOURCE) repository. We selected 4314 unique lens-exam entries and asked 11 clinicians to assess whether all pathology present in the entries had been correctly identified in the NLP algorithm output. The algorithm's sensitivity at accurately identifying lens pathology was compared with that of the ICD codes. RESULTS: The NLP algorithm correctly identified all lens pathology present in 4104 of the 4314 lens-exam entries (95.1%). For less common lens pathology, algorithm findings were corroborated by reviewing clinicians for 100% of mentions of pseudoexfoliation material and 99.7% for phimosis, subluxation, and synechia. Sensitivity at identifying lens pathology was better for NLP (0.98 [0.96-0.99] than for billing codes (0.49 [0.46-0.53]). CONCLUSIONS: Our NLP algorithm identifies and classifies lens abnormalities routinely documented by eye-care professionals with high accuracy. Such algorithms will help researchers to properly identify and classify ocular pathology, broadening the scope of feasible research using real-world data.

Impact of Type 2 diabetes mellitus and insulin use on progression to glaucoma surgery in primary open angle glaucoma.

PURPOSE: To investigate outcomes of primary open-angle glaucoma (POAG) patients with and without type 2 diabetes mellitus (T2DM). METHODS: Retrospective observational study using U.S. nationwide healthcare insurance claims database. Patients ≥40 years old with at least one HbA1c within one year of POAG diagnosis were included. Diabetic factors associated with POAG progression requiring glaucoma surgery were evaluated using multivariable Cox proportional hazards regression models adjusted for demographic, diabetic and glaucoma factors. T2DM diagnosis and use of either oral hypoglycaemic agents or insulin therapy were assessed in association with POAG progression requiring glaucoma surgery. RESULTS: 104,515 POAG patients were included, of which 70,315 (67%) had T2DM. The mean age was 68.9 years (Standard deviation 9.2) and 55% were female. Of those with T2DM, 93% were taking medication (65,468); 95% (62,412) taking oral hypoglycaemic agents, and 34% (22,028) were on insulin. In multivariable analyses, patients with T2DM had a higher hazard of requiring glaucoma surgery (Hazard ratio, HR 1.15, 95% CI 1.09-1.21, p < 0.001). Higher mean HbA1c was also a significant predictor of progression requiring glaucoma surgery (HR 1.02, 95% CI 1.01-1.03, p < 0.001). When evaluating only patients who were taking antidiabetic medication, after adjusting for confounders, insulin use was associated with a 1.20 higher hazard of requiring glaucoma surgery compared to oral hypoglycaemic agents (95% CI 1.14-1.27, p < 0.001), but when stratified by HbA1c, this effect was only significant for those with HbA1c > 7.5%. CONCLUSIONS: Higher baseline HbA1c, particularly in patients taking insulin may be associated with higher rates of glaucoma surgery in POAG.

Automated Recognition of Visual Acuity Measurements in Ophthalmology Clinical Notes Using Deep Learning.

Purpose: Visual acuity (VA) is a critical component of the eye examination but is often only documented in electronic health records (EHRs) as unstructured free-text notes, making it challenging to use in research. This study aimed to improve on existing rule-based algorithms by developing and evaluating deep learning models to perform named entity recognition of different types of VA measurements and their lateralities from free-text ophthalmology notes: VA for each of the right and left eyes, with and without glasses correction, and with and without pinhole. Design: Cross-sectional study. Subjects: A total of 319 756 clinical notes with documented VA measurements from approximately 90 000 patients were included. Methods: The notes were split into train, validation, and test sets. Bidirectional Encoder Representations from Transformers (BERT) models were fine-tuned to identify VA measurements from the progress notes and included BERT models pretrained on biomedical literature (BioBERT), critical care EHR notes (ClinicalBERT), both (BlueBERT), and a lighter version of BERT with 40% fewer parameters (DistilBERT). A baseline rule-based algorithm was created to recognize the same VA entities to compare against BERT models. Main Outcome Measures: Model performance was evaluated on a held-out test set using microaveraged precision, recall, and F1 score for all entities. Results: On the human-annotated subset, BlueBERT achieved the best microaveraged F1 score (F1 = 0.92), followed by ClinicalBERT (F1 = 0.91), DistilBERT (F1 = 0.90), BioBERT (F1 = 0.84), and the baseline model (F1 = 0.83). Common errors included labeling VA in sections outside of the examination portion of the note, difficulties labeling current VA alongside a series of past VAs, and missing nonnumeric VAs. Conclusions: This study demonstrates that deep learning models are capable of identifying VA measurements from free-text ophthalmology notes with high precision and recall, achieving significant performance improvements over a rule-based algorithm. The ability to recognize VA from free-text notes would enable a more detailed characterization of ophthalmology patient cohorts and enhance the development of models to predict ophthalmology outcomes. Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

The Association Between Frailty and Visual Field Loss in US Adults.

PURPOSE: To describe the association between visual field loss and frailty in a nationally representative cohort of US adults. DESIGN: Retrospective cross-sectional study. METHODS: The cohort included adults 40 years or older with complete eye examination data from the 2005-2006 and 2007-2008 National Health and Nutrition Examination Surveys (NHANES). Visual field loss (VFL) was determined by frequency doubling technology and a 2-2-1 algorithm. A 36-item deficit accumulation-based frailty index was used to divide subjects into 4 categories of increasing frailty severity. RESULTS: Of the 4897 participants, 4402 (93.2%) had no VFL, 301 (4.1%) had unilateral VFL, and 194 (2.73%) had bilateral VFL. Within the sample, 2 subjects197 (53.1%) were categorized as non-frail, 1659 (31.3%) as vulnerable, 732 (11.3%) as mildly frail, and 312 (4.3%) as most frail. In multivariable models adjusted for demographics, visual acuity, and history of cataract surgery, subjects with unilateral VFL had higher adjusted odds of being in a more frail category (adjusted odds ratio [aOR], 2.07; 95% CI, 1.42-3.02) than subjects without VFL. Subjects with bilateral VFL also had higher odds of a more frail category compared to subjects without VFL (aOR, 1.74; 95% CI, 1.20-2.52). CONCLUSIONS: In the 2005-2008 NHANES adult population, VFL is associated with higher odds of frailty, independent of central visual acuity loss. Frail individuals may be more susceptible to diseases that can cause VFL, and/or VFL may predispose to frailty. Additional studies are needed to determine the directionality of this relationship and to assess potential interventions.

Social Determinants of Health and Perceived Barriers to Care in Diabetic Retinopathy Screening.

Importance: Regular screening for diabetic retinopathy often is crucial for the health of patients with diabetes. However, many factors may be barriers to regular screening and associated with disparities in screening rates. Objective: To evaluate the associations between visiting an eye care practitioner for diabetic retinopathy screening and factors related to overall health and social determinants of health, including socioeconomic status and health care access and utilization. Design, Setting, and Participants: This retrospective cross-sectional study included adults aged 18 years or older with type 2 diabetes who answered survey questions in the All of Us Research Program, a national multicenter cohort of patients contributing electronic health records and survey data, who were enrolled from May 1, 2018, to July 1, 2022. Exposures: The associations between visiting an eye care practitioner and (1) demographic and socioeconomic factors and (2) responses to the Health Care Access and Utilization, Social Determinants of Health, and Overall Health surveys were investigated using univariable and multivariable logistic regressions. Main Outcome and Measures: The primary outcome was whether patients self-reported visiting an eye care practitioner in the past 12 months. The associations between visiting an eye care practitioner and demographic and socioeconomic factors and responses to the Health Care Access and Utilization, Social Determinants of Health, and Overall Health surveys in All of Us were investigated using univariable and multivariable logistic regression. Results: Of the 11 551 included participants (54.55% cisgender women; mean [SD] age, 64.71 [11.82] years), 7983 (69.11%) self-reported visiting an eye care practitioner in the past year. Individuals who thought practitioner concordance was somewhat or very important were less likely to have seen an eye care practitioner (somewhat important: adjusted odds ratio [AOR], 0.83 [95% CI, 0.74-0.93]; very important: AOR, 0.85 [95% CI, 0.76-0.95]). Compared with financially stable participants, individuals with food or housing insecurity were less likely to visit an eye care practitioner (food insecurity: AOR, 0.75 [95% CI, 0.61-0.91]; housing insecurity: AOR, 0.86 [95% CI, 0.75-0.98]). Individuals who reported fair mental health were less likely to visit an eye care practitioner than were those who reported good mental health (AOR, 0.84; 95% CI, 0.74-0.96). Conclusions and Relevance: This study found that food insecurity, housing insecurity, mental health concerns, and the perceived importance of practitioner concordance were associated with a lower likelihood of receiving eye care. Such findings highlight the self-reported barriers to seeking care and the importance of taking steps to promote health equity.

Real-world agreement of same-visit Tono-Pen vs Goldmann applanation intraocular pressure measurements using electronic health records.

Purpose: To compare intraocular pressure (IOP) obtained with Tono-Pen (TP) and Goldmann applanation (GAT) using large-scale electronic health records (EHR). Design: Retrospective cohort study. Methods: A single pair of eligible TP/GAT IOP readings was randomly selected from the EHR for each ophthalmology patient at an academic ophthalmology center (2013-2022), yielding 4550 eligible measurements. We used Bland-Altman analysis to describe agreement between TP/GAT IOP differences and mean IOP measurements. We also used multivariable logistic regression to identify factors associated with different IOP readings in the same eye, including demographics, glaucoma diagnosis, and central corneal thickness (CCT). Primary outcome metrics were discrepant measurements between TP and GAT as defined by two methods: Outcome A (normal TP despite elevated GAT measurements), and Outcome B (TP and GAT IOP differences ≥6 mmHg). Result: The mean TP/GAT IOP difference was 0.15 mmHg ( ± 5.49 mmHg 95% CI). There was high correlation between the measurements (r = 0.790, p < 0.001). We found that TP overestimated pressures at IOP <16.5 mmHg and underestimated at IOP >16.5 mmHg (Fig. 4). Discrepant measurements accounted for 2.6% (N = 116) and 5.2% (N = 238) for outcomes A and B respectively. Patients with thinner CCT had higher odds of discrepant IOP (OR 0.88 per 25 µm increase, CI [0.84-0.92], p < 0.0001; OR 0.88 per 25 µm increase, CI [0.84-0.92], p < 0.0001 for outcomes A and B respectively). Conclusion: In a real-world academic practice setting, TP and GAT IOP measurements demonstrated close agreement, although 2.6% of measurements showed elevated GAT IOP despite normal TP measurements, and 5.2% of measurements were ≥6 mmHg apart.

Comparison of Ophthalmologist and Large Language Model Chatbot Responses to Online Patient Eye Care Questions.

Importance: Large language models (LLMs) like ChatGPT appear capable of performing a variety of tasks, including answering patient eye care questions, but have not yet been evaluated in direct comparison with ophthalmologists. It remains unclear whether LLM-generated advice is accurate, appropriate, and safe for eye patients. Objective: To evaluate the quality of ophthalmology advice generated by an LLM chatbot in comparison with ophthalmologist-written advice. Design, Setting, and Participants: This cross-sectional study used deidentified data from an online medical forum, in which patient questions received responses written by American Academy of Ophthalmology (AAO)-affiliated ophthalmologists. A masked panel of 8 board-certified ophthalmologists were asked to distinguish between answers generated by the ChatGPT chatbot and human answers. Posts were dated between 2007 and 2016; data were accessed January 2023 and analysis was performed between March and May 2023. Main Outcomes and Measures: Identification of chatbot and human answers on a 4-point scale (likely or definitely artificial intelligence [AI] vs likely or definitely human) and evaluation of responses for presence of incorrect information, alignment with perceived consensus in the medical community, likelihood to cause harm, and extent of harm. Results: A total of 200 pairs of user questions and answers by AAO-affiliated ophthalmologists were evaluated. The mean (SD) accuracy for distinguishing between AI and human responses was 61.3% (9.7%). Of 800 evaluations of chatbot-written answers, 168 answers (21.0%) were marked as human-written, while 517 of 800 human-written answers (64.6%) were marked as AI-written. Compared with human answers, chatbot answers were more frequently rated as probably or definitely written by AI (prevalence ratio [PR], 1.72; 95% CI, 1.52-1.93). The likelihood of chatbot answers containing incorrect or inappropriate material was comparable with human answers (PR, 0.92; 95% CI, 0.77-1.10), and did not differ from human answers in terms of likelihood of harm (PR, 0.84; 95% CI, 0.67-1.07) nor extent of harm (PR, 0.99; 95% CI, 0.80-1.22). Conclusions and Relevance: In this cross-sectional study of human-written and AI-generated responses to 200 eye care questions from an online advice forum, a chatbot appeared capable of responding to long user-written eye health posts and largely generated appropriate responses that did not differ significantly from ophthalmologist-written responses in terms of incorrect information, likelihood of harm, extent of harm, or deviation from ophthalmologist community standards. Additional research is needed to assess patient attitudes toward LLM-augmented ophthalmologists vs fully autonomous AI content generation, to evaluate clarity and acceptability of LLM-generated answers from the patient perspective, to test the performance of LLMs in a greater variety of clinical contexts, and to determine an optimal manner of utilizing LLMs that is ethical and minimizes harm.

Predicting Glaucoma Progression to Surgery with Artificial Intelligence Survival Models.

Purpose: Prior artificial intelligence (AI) models for predicting glaucoma progression have used traditional classifiers that do not consider the longitudinal nature of patients' follow-up. In this study, we developed survival-based AI models for predicting glaucoma patients' progression to surgery, comparing performance of regression-, tree-, and deep learning-based approaches. Design: Retrospective observational study. Subjects: Patients with glaucoma seen at a single academic center from 2008 to 2020 identified from electronic health records (EHRs). Methods: From the EHRs, we identified 361 baseline features, including demographics, eye examinations, diagnoses, and medications. We trained AI survival models to predict patients' progression to glaucoma surgery using the following: (1) a penalized Cox proportional hazards (CPH) model with principal component analysis (PCA); (2) random survival forests (RSFs); (3) gradient-boosting survival (GBS); and (4) a deep learning model (DeepSurv). The concordance index (C-index) and mean cumulative/dynamic area under the curve (mean AUC) were used to evaluate model performance on a held-out test set. Explainability was investigated using Shapley values for feature importance and visualization of model-predicted cumulative hazard curves for patients with different treatment trajectories. Main Outcome Measures: Progression to glaucoma surgery. Results: Of the 4512 patients with glaucoma, 748 underwent glaucoma surgery, with a median follow-up of 1038 days. The DeepSurv model performed best overall (C-index, 0.775; mean AUC, 0.802) among the models studied in this article (CPH with PCA: C-index, 0.745; mean AUC, 0.780; RSF: C-index, 0.766; mean AUC, 0.804; GBS: C-index, 0.764; mean AUC, 0.791). Predicted cumulative hazard curves demonstrate how models could distinguish between patient who underwent early surgery and patients who underwent surgery after > 3000 days of follow-up or no surgery. Conclusions: Artificial intelligence survival models can predict progression to glaucoma surgery using structured data from EHRs. Tree-based and deep learning-based models performed better at predicting glaucoma progression to surgery than the CPH regression model, potentially because of their better suitability for high-dimensional data sets. Future work predicting ophthalmic outcomes should consider using tree-based and deep learning-based survival AI models. Additional research is needed to develop and evaluate more sophisticated deep learning survival models that can incorporate clinical notes or imaging. Financial Disclosures: Proprietary or commercial disclosure may be found after the references.

Predicting near-term glaucoma progression: An artificial intelligence approach using clinical free-text notes and data from electronic health records.

Purpose: The purpose of this study was to develop a model to predict whether or not glaucoma will progress to the point of requiring surgery within the following year, using data from electronic health records (EHRs), including both structured data and free-text progress notes. Methods: A cohort of adult glaucoma patients was identified from the EHR at Stanford University between 2008 and 2020, with data including free-text clinical notes, demographics, diagnosis codes, prior surgeries, and clinical information, including intraocular pressure, visual acuity, and central corneal thickness. Words from patients' notes were mapped to ophthalmology domain-specific neural word embeddings. Word embeddings and structured clinical data were combined as inputs to deep learning models to predict whether a patient would undergo glaucoma surgery in the following 12 months using the previous 4-12 months of clinical data. We also evaluated models using only structured data inputs (regression-, tree-, and deep-learning-based models) and models using only text inputs. Results: Of the 3,469 glaucoma patients included in our cohort, 26% underwent surgery. The baseline penalized logistic regression model achieved an area under the receiver operating curve (AUC) of 0.873 and F1 score of 0.750, compared with the best tree-based model (random forest, AUC 0.876; F1 0.746), the deep learning structured features model (AUC 0.885; F1 0.757), the deep learning clinical free-text features model (AUC 0.767; F1 0.536), and the deep learning model with both the structured clinical features and free-text features (AUC 0.899; F1 0.745). Discussion: Fusion models combining text and EHR structured data successfully and accurately predicted glaucoma progression to surgery. Future research incorporating imaging data could further optimize this predictive approach and be translated into clinical decision support tools.

PhacoTrainer: Deep Learning for Cataract Surgical Videos to Track Surgical Tools.

Purpose: The purpose of this study was to build a deep-learning model that automatically analyzes cataract surgical videos for the locations of surgical landmarks, and to derive skill-related motion metrics. Methods: The locations of the pupil, limbus, and 8 classes of surgical instruments were identified by a 2-step algorithm: (1) mask segmentation and (2) landmark identification from the masks. To perform mask segmentation, we trained the YOLACT model on 1156 frames sampled from 268 videos and the public Cataract Dataset for Image Segmentation (CaDIS) dataset. Landmark identification was performed by fitting ellipses or lines to the contours of the masks and deriving locations of interest, including surgical tooltips and the pupil center. Landmark identification was evaluated by the distance between the predicted and true positions in 5853 frames of 10 phacoemulsification video clips. We derived the total path length, maximal speed, and covered area using the tip positions and examined the correlation with human-rated surgical performance. Results: The mean average precision score and intersection-over-union for mask detection were 0.78 and 0.82. The average distance between the predicted and true positions of the pupil center, phaco tip, and second instrument tip was 5.8, 9.1, and 17.1 pixels. The total path length and covered areas of these landmarks were negatively correlated with surgical performance. Conclusions: We developed a deep-learning method to localize key anatomical portions of the eye and cataract surgical tools, which can be used to automatically derive metrics correlated with surgical skill. Translational Relevance: Our system could form the basis of an automated feedback system that helps cataract surgeons evaluate their performance.

Auto-segmentation of the tibia and femur from knee MR images via deep learning and its application to cartilage strain and recovery.

The ability to efficiently and reproducibly generate subject-specific 3D models of bone and soft tissue is important to many areas of musculoskeletal research. However, methodologies requiring such models have largely been limited by lengthy manual segmentation times. Recently, machine learning, and more specifically, convolutional neural networks, have shown potential to alleviate this bottleneck in research throughput. Thus, the purpose of this work was to develop a modified version of the convolutional neural network architecture U-Net to automate segmentation of the tibia and femur from double echo steady state knee magnetic resonance (MR) images. Our model was trained on a dataset of over 4,000 MR images from 34 subjects, segmented by three experienced researchers, and reviewed by a musculoskeletal radiologist. For our validation and testing sets, we achieved dice coefficients of 0.985 and 0.984, respectively. As further testing, we applied our trained model to a prior study of tibial cartilage strain and recovery. In this analysis, across all subjects, there were no statistically significant differences in cartilage strain between the machine learning and ground truth bone models, with a mean difference of 0.2 ± 0.7 % (mean ± 95 % confidence interval). This difference is within the measurement resolution of previous cartilage strain studies from our lab using manual segmentation. In summary, we successfully trained, validated, and tested a machine learning model capable of segmenting MR images of the knee, achieving results that are comparable to trained human segmenters.

The Predicted Position of the Knee Near the Time of ACL Rupture Is Similar Between 2 Commonly Observed Patterns of Bone Bruising on MRI.

BACKGROUND: Bone bruises observed on magnetic resonance imaging (MRI) can provide insight into the mechanisms of noncontact anterior cruciate ligament (ACL) injury. However, it remains unclear whether the position of the knee near the time of injury differs between patients evaluated with different patterns of bone bruising, particularly with regard to valgus angles. HYPOTHESIS: The position of the knee near the time of injury is similar between patients evaluated with 2 commonly occurring patterns of bone bruising. STUDY DESIGN: Descriptive laboratory study. METHODS: Clinical T2- and T1-weighted MRI scans obtained within 6 weeks of noncontact ACL rupture were reviewed. Patients had either 3 (n = 20) or 4 (n = 30) bone bruises. Patients in the 4-bone bruise group had bruising of the medial and lateral compartments of the femur and tibia, whereas patients in the 3-bone bruise group did not have a bruise on the medial femoral condyle. The outer contours of the bones and associated bruises were segmented from the MRI scans and used to create 3-dimensional surface models. For each patient, the position of the knee near the time of injury was predicted by moving the tibial model relative to the femoral model to maximize the overlap of the tibiofemoral bone bruises. Logistic regressions (adjusted for sex, age, and presence of medial collateral ligament injury) were used to assess relationships between predicted injury position (quantified in terms of knee flexion angle, valgus angle, internal rotation angle, and anterior tibial translation) and bone bruise group. RESULTS: The predicted injury position for patients in both groups involved a flexion angle <20°, anterior translation >20 mm, valgus angle <10°, and internal rotation angle <10°. The injury position for the 3-bone bruise group involved less flexion (odds ratio [OR], 0.914; 95% CI, 0.846-0.987; P = .02) and internal rotation (OR, 0.832; 95% CI, 0.739-0.937; P = .002) as compared with patients with 4 bone bruises. CONCLUSION: The predicted position of injury for patients displaying both 3 and 4 bone bruises involved substantial anterior tibial translation (>20 mm), with the knee in a straight position in both the sagittal (<20°) and the coronal (<10°) planes. CLINICAL RELEVANCE: Landing on a straight knee with subsequent anterior tibial translation is a potential mechanism of noncontact ACL injury.

Changes in glaucoma management following visual field testing and optical coherence tomography.

BACKGROUND: Optimal utilisation of investigations in glaucoma management remains unclear. We aimed to assess whether a temporal association exists between such testing and management changes. METHODS: Retrospective observational study using nationwide healthcare insurance claims database. Glaucoma outpatient encounters from patients aged ≥40 years with/without Humphrey visual field (HVF) and/or optical coherence tomography (OCT) were identified. An encounter was considered associated with an intervention if surgery occurred within 90 days, or if medication change or laser trabeculoplasty (LT) occurred within 30 days. RESULTS: 12 669 324 outpatient encounters of 1 863 748 individuals from 2003 to 2020 were included. HVF and OCT was performed during 32.8% and 22.2% of encounters respectively. Of the 36 763 (0.3%) encounters preceding surgery, 28.1% included HVF, 11.9% had OCT and 8.5% both. 79 181 (0.6%) visits preceded LT, of which 28.2% had HVF, 13.2% OCT and 9.3% both. Of the 515 899 (4.5%) encounters preceding medication changes, 29.1% had HVF, 16.7% OCT and 12.2% both. Compared with encounters with no investigations, those with HVF and/or OCT were associated with a 49% increased odds of a management change (p<0.001). In multivariate analyses, compared with encounters without investigations, visits with HVF alone had higher odds of subsequent surgery and LT, while HVF and/or OCT were associated with higher odds of medication change (p<0.001 for all). CONCLUSION: Glaucoma therapeutic changes occurred following approximately 5% of outpatient encounters. Surgery and LT were more likely to occur following a visit with a HVF rather than an OCT, while either investigation was associated with a higher odds of medication change.

Blood Pressure Measures and Incident Primary Open-Angle Glaucoma.

Purpose: To investigate the association of systemic blood pressure and incident primary open-angle glaucoma (POAG) using a large open-access database. Methods: Prospective cohort study included 484,268 participants from the UK Biobank without glaucoma at enrollment. Incident POAG events were recorded through assessment visits, hospital inpatient admissions, and primary care data. Blood pressure measures included systolic blood pressure (SBP), diastolic blood pressure (DBP), pulse pressure (PP), and mean arterial pressure (MAP). Repeated measurements throughout the study period were analyzed as time-varying covariables. The parameters were modeled as both categorical and continuous nonlinear variables. The primary outcome measure was the relative hazard of incident POAG. Results: There were 2390 incident POAG events over 5,715,480 person-years of follow-up. Median follow-up was 12.08 years. In multivariable analyses, compared to SBP and PP in the normal range (SBP, 120-130 mmHg; PP, 40-50 mmHg), higher SBP and PP were associated with an increased risk of incident POAG (linear trend P = 0.038 for SBP, P < 0.001 for PP). Specifically, SBP of 130 to 140 mmHg or 140 to 150 mmHg was associated with a 1.16 higher hazard of incident POAG (95% CI, 1.01-1.32 and 1.01-1.33, respectively), whereas a PP of greater than 70 mmHg was associated with a 1.13 higher hazard of incident glaucoma (95% CI, 1.00-1.29). In multivariable models, no statistically significant associations were found for DBP or MAP with incident glaucoma. These findings were similar when blood pressure measures were modeled as continuous variables. Conclusions: Higher SBP and PP were associated with an increased risk of incident POAG. Further studies are required to characterize these relationships better.

Real-World Outcomes of Glaucoma Filtration Surgery Using Electronic Health Records: An Informatics Study.

PRCIS: Utilizing an automated pipeline for data extraction from electronic health records provides real-world information on the success of various glaucoma procedures, with tube shunt implantation associated with increased failure rates compared with trabeculectomy. BACKGROUND: We aimed to evaluate the long-term survival of glaucoma surgeries using an automated pipeline for extraction of outcomes from electronic health records. METHODS: A retrospective observational study from a single academic center. Patients undergoing trabeculectomy, Ex-PRESS shunt, Baerveldt, and Ahmed tube shunt insertion from 2009 to 2018 were identified from electronic health record procedure codes. Patient characteristics were identified from structured and unstructured fields using a previously validated natural language processing pipeline. RESULTS: Five hundred twelve patients underwent 711 glaucoma surgeries: 287 trabeculectomies, 47 Ex-PRESS shunts, 274 Baerveldt and 103 Ahmed tube implantations. The Median follow-up was 359 days. The mean baseline IOP was 24.4 mm Hg (SD 10.9), and 73.1% were on ≥3 medications. Compared with trabeculectomy, tube shunt surgery had a higher risk of failure (Baerveldt: Hazard Ratio (HR) 1.44, 95% CI 1.02 to 2.02; Ahmed: HR 2.01, 95% CI 1.28 to 3.17). Previous glaucoma surgery was associated with increased failure (≥2 previous surgeries: HR 2.74, 95% CI 1.62 to 4.64), as were fewer baseline medications (<3 medications: HR 2.96, 95% CI 2.12 to 4.13) and male sex (HR 1.40, 95% CI 1.03 to 1.90). At 1 year, tube shunt patients had a 2.53 mm Hg ( P =0.002) higher IOP compared with trabeculectomy patients. CONCLUSIONS: Baerveldt and Ahmed tube shunt implantation was associated with increased failure compared with trabeculectomy. Fewer baseline medications, previous glaucoma surgeries, and male sex were also risk factors for failure. These results demonstrate the utility of applying an informatics pipeline to electronic health records to investigate key clinical questions using real-world evidence.