暂无摘要。

UNASSIGNED: The predictive factors for wheelchair dependence in patients with multiple system atrophy (MSA) are unclear. We aimed to explore the predictive factors for early-wheelchair dependence in patients with MSA focusing on clinical features and blood biomarkers.
UNASSIGNED: This is a prospective cohort study. This study included patients diagnosed with MSA between January 2014 and December 2019. At the deadline of October 2021, patients met the diagnosis of probable MSA were included in the analysis. Random forest (RF) was used to establish a predictive model for early-wheelchair dependence. Accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) were used to evaluate the performance of the model.
UNASSIGNED: Altogether, 100 patients with MSA including 49 with wheelchair dependence and 51 without wheelchair dependence were enrolled in the RF model. Baseline plasma neurofilament light chain (NFL) levels were higher in patients with wheelchair dependence than in those without (P = 0.037). According to the Gini index, the five major predictive factors were disease duration, age of onset, Unified MSA Rating Scale (UMSARS)-II score, NFL, and UMSARS-I score, followed by C-reactive protein (CRP) levels, neutrophil-to-lymphocyte ratio (NLR), UMSARS-IV score, symptom onset, orthostatic hypotension, sex, urinary incontinence, and diagnosis subtype. The sensitivity, specificity, accuracy, and AUC of the RF model were 70.82 %, 74.55 %, 72.29 %, and 0.72, respectively.
UNASSIGNED: Besides clinical features, baseline features including NFL, CRP, and NLR were potential predictive biomarkers of early-wheelchair dependence in MSA. These findings provide new insights into the trials regarding early intervention in MSA.

UNASSIGNED: No established biomarkers currently exist for therapeutic efficacy and durability of anti-VEGF therapy in neovascular age-related macular degeneration (nAMD). This study evaluated radiomic-based quantitative OCT biomarkers that may be predictive of anti-VEGF treatment response and durability.
UNASSIGNED: Assessment of baseline biomarkers using machine learning (ML) classifiers to predict tolerance to anti-VEGF therapy.
UNASSIGNED: Eighty-one participants with treatment-naïve nAMD from the OSPREY study, including 15 super responders (patients who achieved and maintained retinal fluid resolution) and 66 non-super responders (patients who did not achieve or maintain retinal fluid resolution).
UNASSIGNED: A total of 962 texture-based radiomic features were extracted from fluid, subretinal hyperreflective material (SHRM), and different retinal tissue compartments of OCT scans. The top 8 features, chosen by the minimum redundancy maximum relevance feature selection method, were evaluated using 4 ML classifiers in a cross-validated approach to distinguish between the 2 patient groups. Longitudinal assessment of changes in different texture-based radiomic descriptors (delta-texture features) between baseline and month 3 also was performed to evaluate their association with treatment response. Additionally, 8 baseline clinical parameters and a combination of baseline OCT, delta-texture features, and the clinical parameters were evaluated in a cross-validated approach in terms of association with therapeutic response.
UNASSIGNED: The cross-validated area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity were calculated to validate the classifier performance.
UNASSIGNED: The cross-validated AUC by the quadratic discriminant analysis classifier was 0.75 ± 0.09 using texture-based baseline OCT features. The delta-texture features within different OCT compartments between baseline and month 3 yielded an AUC of 0.78 ± 0.08. The baseline clinical parameters sub-retinal pigment epithelium volume and intraretinal fluid volume yielded an AUC of 0.62 ± 0.07. When all the baseline, delta, and clinical features were combined, a statistically significant improvement in the classifier performance (AUC, 0.81 ± 0.07) was obtained.
UNASSIGNED: Radiomic-based quantitative assessment of OCT images was shown to distinguish between super responders and non-super responders to anti-VEGF therapy in nAMD. The baseline fluid and SHRM delta-texture features were found to be most discriminating across groups.

UNASSIGNED: To develop a method for objective analysis of the reproducible steps in routine cataract surgery.
UNASSIGNED: Prospective study; machine learning.
UNASSIGNED: Deidentified faculty and trainee surgical videos.
UNASSIGNED: Consecutive cataract surgeries performed by a faculty or trainee surgeon in an ophthalmology residency program over 6 months were collected and labeled according to degrees of difficulty. An existing image classification network, ResNet 152, was fine-tuned for tool detection in cataract surgery to allow for automatic identification of each unique surgical instrument. Individual microscope video frame windows were subsequently encoded as a vector. The relation between vector encodings and perceived skill using k-fold user-out cross-validation was examined. Algorithms were evaluated using area under the receiver operating characteristic curve (AUC) and the classification accuracy.
UNASSIGNED: Accuracy of tool detection and skill assessment.
UNASSIGNED: In total, 391 consecutive cataract procedures with 209 routine cases were used. Our model achieved an AUC ranging from 0.933 to 0.998 for tool detection. For skill classification, AUC was 0.550 (95% confidence interval [CI], 0.547-0.553) with an accuracy of 54.3% (95% CI, 53.9%-54.7%) for a single snippet, AUC was 0.570 (0.565-0.575) with an accuracy of 57.8% (56.8%-58.7%) for a single surgery, and AUC was 0.692 (0.659-0.758) with an accuracy of 63.3% (56.8%-69.8%) for a single user given all their trials.
UNASSIGNED: Our research shows that machine learning can accurately and independently identify distinct cataract surgery tools in videos, which is crucial for comparing the use of the tool in a step. However, it is more challenging for machine learning to accurately differentiate overall and specific step skill to assess the level of training or expertise.
UNASSIGNED: The author(s) have no proprietary or commercial interest in any materials discussed in this article.

UNASSIGNED: Retinopathy of prematurity (ROP) is a leading cause of childhood blindness related to oxygen exposure in premature infants. Since oxygen monitoring protocols have reduced the incidence of treatment-requiring ROP (TR-ROP), it remains unclear whether oxygen exposure remains a relevant risk factor for incident TR-ROP and aggressive ROP (A-ROP), a severe, rapidly progressing form of ROP. The purpose of this proof-of-concept study was to use electronic health record (EHR) data to evaluate early oxygen exposure as a predictive variable for developing TR-ROP and A-ROP.
UNASSIGNED: Retrospective cohort study.
UNASSIGNED: Two hundred forty-four infants screened for ROP at a single academic center.
UNASSIGNED: For each infant, oxygen saturations and fraction of inspired oxygen (FiO2) were extracted manually from the EHR until 31 weeks postmenstrual age (PMA). Cumulative minimum, maximum, and mean oxygen saturation and FiO2 were calculated on a weekly basis. Random forest models were trained with 5-fold cross-validation using gestational age (GA) and cumulative minimum FiO2 at 30 weeks PMA to identify infants who developed TR-ROP. Secondary receiver operating characteristic (ROC) curve analysis of infants with or without A-ROP was performed without cross-validation because of small numbers.
UNASSIGNED: For each model, cross-validation performance for incident TR-ROP was assessed using area under the ROC curve (AUC) and area under the precision-recall curve (AUPRC) scores. For A-ROP, we calculated AUC and evaluated sensitivity and specificity at a high-sensitivity operating point.
UNASSIGNED: Of the 244 infants included, 33 developed TR-ROP, of which 5 developed A-ROP. For incident TR-ROP, random forest models trained on GA plus cumulative minimum FiO2 (AUC = 0.93 ± 0.06; AUPRC = 0.76 ± 0.08) were not significantly better than models trained on GA alone (AUC = 0.92 ± 0.06 [P = 0.59]; AUPRC = 0.74 ± 0.12 [P = 0.32]). Models using oxygen alone showed an AUC of 0.80 ± 0.09. ROC analysis for A-ROP found an AUC of 0.92 (95% confidence interval, 0.87-0.96).
UNASSIGNED: Oxygen exposure can be extracted from the EHR and quantified as a risk factor for incident TR-ROP and A-ROP. Extracting quantifiable clinical features from the EHR may be useful for building risk models for multiple diseases and evaluating the complex relationships among oxygen exposure, ROP, and other sequelae of prematurity.

UNASSIGNED: To investigate the effects of adjusting the ocular magnification during OCT-based angiography imaging on structure-function relationships and glaucoma detection.
UNASSIGNED: Cross-sectional study.
UNASSIGNED: A total of 96 healthy control participants and 90 patients with open-angle glaucoma were included.
UNASSIGNED: One eye of each patient in the control group and the patient group was evaluated. The layers comprising the macula vascular density (VD) and circumpapillary VD were derived from swept-source OCT angiography imaging. The mean sensitivity (MS) of the standard automated perimetry was measured using the Humphrey 24-2 test. Structure-function relationships were evaluated with simple and partial correlation coefficients. A receiver operating characteristic analysis was performed to evaluate the diagnostic accuracy for glaucoma using the area under the receiver operating characteristic curve (AUC). Ocular magnification was adjusted using Littmann\'s formula modified by Bennett.
UNASSIGNED: The association between the axial length and VD, structure-function relationships, and glaucoma detection with and without magnification correction.
UNASSIGNED: The superficial layer of the macular region was not significantly correlated to the axial length without magnification correction (r = 0.0011; P = 0.99); however, it was negatively correlated to the axial length with magnification correction (r = -0.22; P = 0.028). Regarding the nerve head layer in the circumpapillary region, a negative correlation to the axial length without magnification correction was observed (r = -0.22; P = 0.031); however, this significant correlation disappeared with magnification correction. The superficial layer of the macula and the nerve head layer of the circumpapillary region were significantly correlated to Humphrey 24-2 MS values without magnification correction (r = 0.22 and r = 0.32, respectively); however, these correlations did not improve after magnification correction (r = 0.20 and r = 0.33, respectively). Glaucoma diagnostic accuracy in the superficial layer (AUC, 0.63) and nerve head layer (AUC, 0.70) without magnification correction did not improve after magnification correction (AUC, 0.62 and 0.69, respectively).
UNASSIGNED: Adjustment of the ocular magnification is important for accurate VD measurements; however, it may not significantly impact structure-function relationships and glaucoma detection.

UNASSIGNED: To compare the efficacy and efficiency of training neural networks for medical image classification using comparison labels indicating relative disease severity versus diagnostic class labels from a retinopathy of prematurity (ROP) image dataset.
UNASSIGNED: Evaluation of diagnostic test or technology.
UNASSIGNED: Deep learning neural networks trained on expert-labeled wide-angle retinal images obtained from patients undergoing diagnostic ROP examinations obtained as part of the Imaging and Informatics in ROP (i-ROP) cohort study.
UNASSIGNED: Neural networks were trained with either class or comparison labels indicating plus disease severity in ROP retinal fundus images from 2 datasets. After training and validation, all networks underwent evaluation using a separate test dataset in 1 of 2 binary classification tasks: normal versus abnormal or plus versus nonplus.
UNASSIGNED: Area under the receiver operating characteristic curve (AUC) values were measured to assess network performance.
UNASSIGNED: Given the same number of labels, neural networks learned more efficiently by comparison, generating significantly higher AUCs in both classification tasks across both datasets. Similarly, given the same number of images, comparison learning developed networks with significantly higher AUCs across both classification tasks in 1 of 2 datasets. The difference in efficiency and accuracy between models trained on either label type decreased as the size of the training set increased.
UNASSIGNED: Comparison labels individually are more informative and more abundant per sample than class labels. These findings indicate a potential means of overcoming the common obstacle of data variability and scarcity when training neural networks for medical image classification tasks.

UNASSIGNED: To study the power of an 80-second multifocal pupillographic objective perimetry (mfPOP) test tailored to the ETDRS grid to diagnose age-related macular degeneration (AMD) by Age-Related Eye Disease Study (AREDS) severity grade.
UNASSIGNED: Evaluation of a diagnostic technology.
UNASSIGNED: We compared diagnostic power of acuity, ETDRS grid retinal thickness data, new 80-second M18 mfPOP test, and two wider-field 6-minute mfPOP tests (Macular-P131, Widefield-P129). The M18 stimuli match the size and shape of bifurcated ETDRS grid regions, allowing easy structure-function comparisons. M18, P129, and P131 stimuli test both eyes concurrently. We recruited 34 patients with early-stage AMD with a mean ± standard deviation (SD) age of 72.6 ± 7.06 years. The M18 and P129 plus P131 stimuli had 26 and 51 control participants, respectively with mean ± SD ages of 73.1 ± 8.17 years and 72.1 ± 5.83 years, respectively. Multifocal pupillographic objective perimetry testing used the Food and Drug Administration-cleared Objective FIELD Analyzer (OFA; Konan Medical USA).
UNASSIGNED: Percentage area under the receiver operator characteristic curve (AUC) and Hedge\'s g effect size.
UNASSIGNED: Acuity and OCT ETDRS grid thickness and volume produced reasonable diagnostic power (percentage AUC) for AREDS grade 4 eyes at 83.9 ± 9.98% and 90.2 ± 6.32% (mean ± standard error), respectively, but not for eyes with less severe disease. By contrast, M18 stimuli produced percentage AUCs from 72.8 ± 6.65% (AREDS grade 2) to 92.9 ± 3.93% (AREDS grade 4), and 82.9 ± 3.71% for all eyes. Hedge\'s g effect sizes ranged from 0.84 to 2.32 (large to huge). Percentage AUC for P131 stimuli performed similarly and for P129 performed somewhat less well.
UNASSIGNED: The rapid and objective M18 test provided diagnostic power comparable with that of wider-field 6-minute mfPOP tests. Unlike acuity or OCT ETDRS grid data, OFA tests produced reasonable diagnostic power in AREDS grade 1 to 3 eyes.

UNASSIGNED: Develop computer vision models for image-based differentiation of bacterial and fungal corneal ulcers and compare their performance against human experts.
UNASSIGNED: Cross-sectional comparison of diagnostic performance.
UNASSIGNED: Patients with acute, culture-proven bacterial or fungal keratitis from 4 centers in South India.
UNASSIGNED: Five convolutional neural networks (CNNs) were trained using images from handheld cameras collected from patients with culture-proven corneal ulcers in South India recruited as part of clinical trials conducted between 2006 and 2015. Their performance was evaluated on 2 hold-out test sets (1 single center and 1 multicenter) from South India. Twelve local expert cornea specialists performed remote interpretation of the images in the multicenter test set to enable direct comparison against CNN performance.
UNASSIGNED: Area under the receiver operating characteristic curve (AUC) individually and for each group collectively (i.e., CNN ensemble and human ensemble).
UNASSIGNED: The best-performing CNN architecture was MobileNet, which attained an AUC of 0.86 on the single-center test set (other CNNs range, 0.68-0.84) and 0.83 on the multicenter test set (other CNNs range, 0.75-0.83). Expert human AUCs on the multicenter test set ranged from 0.42 to 0.79. The CNN ensemble achieved a statistically significantly higher AUC (0.84) than the human ensemble (0.76; P < 0.01). CNNs showed relatively higher accuracy for fungal (81%) versus bacterial (75%) ulcers, whereas humans showed relatively higher accuracy for bacterial (88%) versus fungal (56%) ulcers. An ensemble of the best-performing CNN and best-performing human achieved the highest AUC of 0.87, although this was not statistically significantly higher than the best CNN (0.83; P = 0.17) or best human (0.79; P = 0.09).
UNASSIGNED: Computer vision models achieved superhuman performance in identifying the underlying infectious cause of corneal ulcers compared with cornea specialists. The best-performing model, MobileNet, attained an AUC of 0.83 to 0.86 without any additional clinical or historical information. These findings suggest the potential for future implementation of these models to enable earlier directed antimicrobial therapy in the management of infectious keratitis, which may improve visual outcomes. Additional studies are ongoing to incorporate clinical history and expert opinion into predictive models.

UNASSIGNED: To develop and validate an automated deep learning (DL)-based artificial intelligence (AI) platform for diagnosing and grading cataracts using slit-lamp and retroillumination lens photographs based on the Lens Opacities Classification System (LOCS) III.
UNASSIGNED: Cross-sectional study in which a convolutional neural network was trained and tested using photographs of slit-lamp and retroillumination lens photographs.
UNASSIGNED: One thousand three hundred thirty-five slit-lamp images and 637 retroillumination lens images from 596 patients.
UNASSIGNED: Slit-lamp and retroillumination lens photographs were graded by 2 trained graders using LOCS III. Image datasets were labeled and divided into training, validation, and test datasets. We trained and validated AI platforms with 4 key strategies in the AI domain: (1) region detection network for redundant information inside data, (2) data augmentation and transfer learning for the small dataset size problem, (3) generalized cross-entropy loss for dataset bias, and (4) class balanced loss for class imbalance problems. The performance of the AI platform was reinforced with an ensemble of 3 AI algorithms: ResNet18, WideResNet50-2, and ResNext50.
UNASSIGNED: Diagnostic and LOCS III-based grading prediction performance of AI platforms.
UNASSIGNED: The AI platform showed robust diagnostic performance (area under the receiver operating characteristic curve [AUC], 0.9992 [95% confidence interval (CI), 0.9986-0.9998] and 0.9994 [95% CI, 0.9989-0.9998]; accuracy, 98.82% [95% CI, 97.7%-99.9%] and 98.51% [95% CI, 97.4%-99.6%]) and LOCS III-based grading prediction performance (AUC, 0.9567 [95% CI, 0.9501-0.9633] and 0.9650 [95% CI, 0.9509-0.9792]; accuracy, 91.22% [95% CI, 89.4%-93.0%] and 90.26% [95% CI, 88.6%-91.9%]) for nuclear opalescence (NO) and nuclear color (NC) using slit-lamp photographs, respectively. For cortical opacity (CO) and posterior subcapsular opacity (PSC), the system achieved high diagnostic performance (AUC, 0.9680 [95% CI, 0.9579-0.9781] and 0.9465 [95% CI, 0.9348-0.9582]; accuracy, 96.21% [95% CI, 94.4%-98.0%] and 92.17% [95% CI, 88.6%-95.8%]) and good LOCS III-based grading prediction performance (AUC, 0.9044 [95% CI, 0.8958-0.9129] and 0.9174 [95% CI, 0.9055-0.9295]; accuracy, 91.33% [95% CI, 89.7%-93.0%] and 87.89% [95% CI, 85.6%-90.2%]) using retroillumination images.
UNASSIGNED: Our DL-based AI platform successfully yielded accurate and precise detection and grading of NO and NC in 7-level classification and CO and PSC in 6-level classification, overcoming the limitations of medical databases such as few training data or biased label distribution.