Comparison of Machine and Human Expert Evaluation of Capsulorrhexis Creation Performance Through Analysis of Surgical Video Recordings.

Purpose: Achieving competency in cataract surgery is an essential component of ophthalmology residency training. Video-based analysis of surgery can change training through its objective, reliable, and timely assessment of resident performance. Methods: Using the Image Labeler application in MATLAB, the capsulorrhexis step of 208 surgical videos, recorded at the University of Michigan, was annotated for subjective and objective analysis. Two expert surgeons graded the creation of the capsulorrhexis based on the International Council of Ophthalmology's Ophthalmology Surgical Competency Assessment Rubric:Phacoemulsification (ICO-OSCAR:phaco) rating scale and a custom rubric (eccentricity, roundness, size, centration) that focuses on the objective aspects of this step. The annotated rhexis frames were run through an automated analysis to obtain objective scores for these components. The subjective scores were compared using both intra and inter-rater analyses to assess the consistency of a human-graded scale. The subjective and objective scores were compared using intraclass correlation methods to determine relative agreement. Results: All rhexes were graded as 4/5 or 5/5 by both raters for both items 4 and 5 of the ICO-OSCAR:phaco rating scale. Only roundness scores were statistically different between the subjective graders (mean difference = -0.149, p-value = 0.0023). Subjective scores were highly correlated for all components (>0.6). Correlations between objective and subjective scores were low (0.09 to 0.39). Conclusion: Video-based analysis of cataract surgery presents significant opportunities, including the ability to asynchronously evaluate performance and provide longitudinal assessment. Subjective scoring between two raters was moderately correlated for each component.

Corneal Specialists' Confidence in Identifying Causal Organisms of Microbial Keratitis.

PURPOSE: Microbial keratitis (MK) is a potentially blinding corneal disease caused by an array of microbial etiologies. However, the lack of early organism identification is a barrier to optimal care. We investigated clinician confidence in their diagnosis of organism type on initial presentation and the relationship between confidence and presenting features. METHODS: This research presents secondary data analysis of 72 patients from the Automated Quantitative Ulcer Analysis (AQUA) study. Cornea specialists reported their confidence in organism identification. Presenting sample characteristics were recorded including patient demographics, health history, infection morphology, symptoms, and circumstances of infection. The association between confidence and presenting characteristics was investigated with 2-sample t-tests, Wilcoxon tests, and Chi-square or Fisher's exact tests. RESULTS: Clinicians reported being "confident or very confident" in their diagnosis of the causal organism in MK infections for 39 patients (54%) and "not confident" for 33 patients (46%). Confidence was not significantly associated with patient demographics, morphologic features, or symptoms related to MK. MK cases where clinicians reported they were confident, versus not confident in their diagnosis, showed significantly smaller percentages of previous corneal disease (0% versus 15%, p = 0.017), were not seen by an outside provider first (69% versus 94%, p = 0.015), or had no prior labs drawn (8% versus 33%, p = 0.046), and a significantly larger percentage of cases wore contact lenses (54% versus 28%, p = 0.029). CONCLUSION: In almost half of MK cases, cornea specialists reported lack of confidence in identifying the infection type. Confidence was related to ocular history and circumstances of infection but not by observable signs and symptoms or patient demographics. Tools are needed to assist clinicians with early diagnosis of MK infection type to expedite care and healing.

Microbial Keratitis Isolates at a Midwestern Tertiary Eye Care Center.

PURPOSE: The aim of the study was to describe the pathogen, antimicrobial susceptibility, and trends over time of microbial keratitis (MK) at a Midwestern tertiary eye center. METHODS: Patients with MK were identified in the electronic health record from August 2012 to December 2021. Diagnostic laboratory tests with an MK diagnosis were identified and classified as laboratory positive or laboratory negative. Laboratory-positive infections were categorized as bacterial (gram-positive, gram-negative, or acid-fast bacilli), fungal, viral, Acanthamoeba , or polymicrobial. Antimicrobial susceptibilities were obtained. Trends over time were assessed using linear regression. RESULTS: Of 3288 patients with MK identified, 1012 (30.8%) had laboratory tests performed. Laboratory-positive infections (n = 499, 49.3%) were bacterial in 73.5% (n = 367) of cases, fungal in 7.8% (n = 39), viral in 1.6% (n = 8), Acanthamoeba in 1.4% (n = 7), and polymicrobial in 15.6% (n = 78). Of bacterial infections, 70% (n = 257) were gram-positive, with coagulase-negative Staphylococcus (CoNS; 31%) and Staphylococcus aureus ( S. aureus ; 23%) as the most common pathogens. Bacteria were acid-fast bacilli in 1.9% (n = 7) of cases and gram-negative in 28.1% (n = 103), with Pseudomonas aeruginosa as the predominant pathogen (47.7%). S. aureus showed antibiotic resistance from 0% (vancomycin and gentamicin) to 50% (erythromycin); CoNS from 0% (vancomycin, gentamicin, and moxifloxacin) to 64% (erythromycin). The rate of laboratory-negative MK significantly increased over time (slope estimate = 2.1% per year, P = 0.034). Rates of bacterial, fungal, viral, Acanthamoeba , and polymicrobial infections were stable over time (all slope P > 0.05). CONCLUSIONS: Bacterial keratitis accounted for most MK cases. Gram-positive bacteria were the most common isolates. CoNS and S. aureus were universally susceptible to vancomycin. Rates of MK infection types were stable over time.

Prediction of Visual Acuity in Patients With Microbial Keratitis.

PURPOSE: The purpose of this study was to predict visual acuity (VA) 90 days after presentation for patients with microbial keratitis (MK) from data at the initial clinical ophthalmic encounter. METHODS: Patients with MK were identified in the electronic health record between August 2012 and February 2021. Random forest (RF) models were used to predict 90-day VA < 20/40 [visual impairment (VI)]. Predictors evaluated included age, sex, initial VA, and information documented in notes at presentation. Model diagnostics are reported with 95% confidence intervals (CIs) for area under the curve (AUC), misclassification rate, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). RESULTS: One thousand seven hundred ninety-one patients were identified. The presenting logMAR VA was on average 0.86 (Snellen equivalent and standard deviation = 20/144 ± 12.6 lines) in the affected or worse eye, and 43.6% with VI. VI at 90-day follow-up was present in the affected eye or worse eye for 26.9% of patients. The RF model for predicting 90-day VI had an AUC of 95% (CI: 93%-97%) and a misclassification rate of 9% (7%-12%). The percent sensitivity, specificity, PPV, and NPV were 86% (80%-91%), 92% (89%-95%), 81% (74%-86%), and 95% (92%-97%), respectively. Older age, worse presenting VA, and more mentions of "penetrating keratoplasty" and "bandage contact lens" were associated with increased probability of 90-day VI, whereas more mentions of "quiet" were associated with decreased probability of 90-day VI. CONCLUSIONS: RF modeling yielded good sensitivity and specificity to predict VI at 90 days which could guide clinicians about the risk of poor vision outcomes for patients with MK.

Analysis of Cataract Surgery Instrument Identification Performance of Convolutional and Recurrent Neural Network Ensembles Leveraging BigCat.

Purpose: To develop a method for accurate automated real-time identification of instruments in cataract surgery videos. Methods: Cataract surgery videos were collected at University of Michigan's Kellogg Eye Center between 2020 and 2021. Videos were annotated for the presence of instruments to aid in the development, validation, and testing of machine learning (ML) models for multiclass, multilabel instrument identification. Results: A new cataract surgery database, BigCat, was assembled, containing 190 videos with over 3.9 million annotated frames, the largest reported cataract surgery annotation database to date. Using a dense convolutional neural network (CNN) and a recursive averaging method, we were able to achieve a test F1 score of 0.9528 and test area under the receiver operator characteristic curve of 0.9985 for surgical instrument identification. These prove to be state-of-the-art results compared to previous works, while also only using a fraction of the model parameters of the previous architectures. Conclusions: Accurate automated surgical instrument identification is possible with lightweight CNNs and large datasets. Increasingly complex model architecture is not necessary to retain a well-performing model. Recurrent neural network architectures add additional complexity to a model and are unnecessary to attain state-of-the-art performance. Translational Relevance: Instrument identification in the operative field can be used for further applications such as evaluating surgical trainee skill level and developing early warning detection systems for use during surgery.

Development and Validation of a Model to Predict Anterior Segment Vision-Threatening Eye Disease Using Primary Care Clinical Notes.

PURPOSE: The purpose of this study was to develop a decision-support tool to predict anterior segment vision-threatening disease (asVTD) to aid primary care physicians (PCPs) with patient triage and referral. METHODS: The University of Michigan electronic health record data between January 1, 2016, and May 31, 2019, were obtained from patients presenting to a PCP with anterior eye symptoms and then saw an ophthalmologist within 30 days. asVTD included diagnosis of corneal ulcer, iridocyclitis, hyphema, anterior scleritis, or scleritis with corneal involvement by an ophthalmologist. Elastic net logistic regression with 10-fold cross-validation was used for prediction modeling of asVTD. Predictors evaluated included patient demographics and PCP notes processed using clinical natural language processing software (clinspacy). RESULTS: Two thousand nine hundred forty-two patients met the inclusion criteria, of which 133 patients (4.5%) had asVTD. The age was significantly lower among those with asVTD versus those without (median = 42 vs. 53 yrs, P < 0.001). Sex ( P = 0.8) and race ( P = 0.9) were not significantly different between groups. The final prediction model had an area under the curve of 0.72 (95% confidence interval 0.67-0.77). At a threshold achieving a sensitivity of 90%, the specificity was 30%, the positive predictive value was 5.8%, and the negative predictive value was 99%. CONCLUSIONS: The use of the prediction model increased the positive predictive value for asVTD compared with referral based on prevalence probabilities (17 patients vs. 22 patients needing to be evaluated to identify 1 case of asVTD). A prediction algorithm has potential to improve triage and initial management decision-making for PCPs because it performs better than probabilities in the absence of such a tool.

Opioid Prescribing Patterns for Ulcerative Keratitis.

PURPOSE: The purpose of this study was to characterize rates of opioid prescription for different ulcerative keratitis types. METHODS: This cohort study included patients diagnosed with ulcerative keratitis according to the University of Michigan electronic health record data between September 1, 2014 and December 22, 2020. Ulcerative keratitis was categorized by etiologic type (bacterial, fungal, viral, acanthamoeba, inflammatory, polymicrobial, or unspecified) using rule-based data classification that accounted for billing diagnosis code, antimicrobial or antiinflammatory medications prescribed, laboratory results, and manual chart review. Opioid prescriptions were converted to morphine milligram equivalent and summed over 90 days from diagnosis. Opioid prescription rate and amount were compared between ulcerative keratitis types. RESULTS: Of 3322 patients with ulcerative keratitis, 173 (5.2%) were prescribed at least 1 opioid for pain management within 90 days of diagnosis. More patients with acanthamoeba (32.4%), fungal (21.1%), and polymicrobial (25.0%) keratitis were treated with opioids compared with bacterial (6.7%), unspecified (2.9%), or viral (1.8%) keratitis (all Bonferroni adjusted P < 0.05). For the 173 patients who were prescribed opioids, a total of 353 prescriptions were given within 90 days of diagnosis, with half given within the first week after diagnosis. The quantity of opioid prescribed within 90 days from diagnosis was not significantly different between ulcerative keratitis types (P = 0.6559). Morphine milligram equivalent units prescribed ranged from 97.5 for acanthamoeba keratitis to 112.5 for fungal keratitis. CONCLUSIONS: The type of ulcerative keratitis may influence the opioid prescription rate. Providers can better serve patients needing opioids for pain management through improved characterization of pain and development of more tailored pain management regimens.

Bilateral Anterior Subcapsular Cataract Development Following Initiation of Enfortumab Vedotin.

Enfortumab vedotin is an antibody-drug conjugate that was recently granted accelerated US Food and Drug Administration approval for the treatment of locally advanced or metastatic urothelial cancer. Early clinical trials identified blurry vision, increased lacrimation and other events associated with dry eye as potential side effects. We report a case of bilateral anterior subcapsular cataract development following initiation of enfortumab vedotin. Enfortumab vedotin is not previously known to cause cataract development or progression and, thus, our patient's presentation may reflect the first report of an undocumented adverse effect of this novel agent.

Combination therapy of normobaric oxygen with hypothermia or ethanol modulates pyruvate dehydrogenase complex in thromboembolic cerebral ischemia.

Pyruvate dehydrogenase complex (PDH) is a brain mitochondrial matrix enzyme. PDH impairment after stroke is particularly devastating given PDH's critical role in the link between anaerobic and aerobic metabolism. This study evaluates the restoration of oxidative metabolism and energy regulation with a therapeutic combination of normobaric oxygen (NBO) plus either therapeutic hypothermia (TH) or ethanol. Sprague-Dawley rats were subjected to middle cerebral artery occlusion with an autologous embolus. One hour after occlusion, tissue-type plasminogen activator (t-PA) was administered alone or with NBO (60%), EtOH (1.0 g/kg), or TH (33°C), either singly or in combination. Neurological deficit score and infarct volume were assessed 24 hr after t-PA-induced reperfusion. PDH activity and reactive oxygen species (ROS) levels were measured 3 and 24 hr after t-PA. Western blotting was used to detect PDH and pyruvate dehydrogenase kinase (PDK) protein expression. After t-PA in ischemic rats, NBO combined with TH or EtOH most effectively decreased infarct volume and neurological deficit. The combined therapies produced greater increases in PDH activity and protein expression as well as greater decreases in PDK expression. Compared with the monotherapeutic approaches, the combined therapies provided the most significant declines in ROS generation. Reperfusion with t-PA followed by 60% NBO improves the efficacy of EtOH or TH in neuroprotection by ameliorating oxidative injury and improving PDH regulation. Comparable neuroprotective effects were found when treating with either EtOH or TH, suggesting a similar mechanism of neuroprotection and the possibility of substituting EtOH for TH in clinical settings. © 2016 Wiley Periodicals, Inc.

Pyruvate dehydrogenase complex in cerebral ischemia-reperfusion injury.

Pyruvate dehydrogenase (PDH) complex is a mitochondrial matrix enzyme that serves a critical role in the conversion of anaerobic to aerobic cerebral energy. The regulatory complexity of PDH, coupled with its significant influence in brain metabolism, underscores its susceptibility to, and significance in, ischemia-reperfusion injury. Here, we evaluate proposed mechanisms of PDH-mediated neurodysfunction in stroke, including oxidative stress, altered regulatory enzymatic control, and loss of PDH activity. We also describe the neuroprotective influence of antioxidants, dichloroacetate, acetyl-L-carnitine, and combined therapy with ethanol and normobaric oxygen, explained in relation to PDH modulation. Our review highlights the significance of PDH impairment in stroke injury through an understanding of the mechanisms by which it is modulated, as well as an exploration of neuroprotective strategies available to limit its impairment.