A foundation model for generalizable disease detection from retinal images.

Medical artificial intelligence (AI) offers great potential for recognizing signs of health conditions in retinal images and expediting the diagnosis of eye diseases and systemic disorders1. However, the development of AI models requires substantial annotation and models are usually task-specific with limited generalizability to different clinical applications2. Here, we present RETFound, a foundation model for retinal images that learns generalizable representations from unlabelled retinal images and provides a basis for label-efficient model adaptation in several applications. Specifically, RETFound is trained on 1.6 million unlabelled retinal images by means of self-supervised learning and then adapted to disease detection tasks with explicit labels. We show that adapted RETFound consistently outperforms several comparison models in the diagnosis and prognosis of sight-threatening eye diseases, as well as incident prediction of complex systemic disorders such as heart failure and myocardial infarction with fewer labelled data. RETFound provides a generalizable solution to improve model performance and alleviate the annotation workload of experts to enable broad clinical AI applications from retinal imaging.

Misspellings or "miscellings"-Non-verifiable and unknown cell lines in cancer research publications.

Reproducible laboratory research relies on correctly identified reagents. We have previously described gene research papers with wrongly identified nucleotide sequence(s), including papers studying miR-145. Manually verifying reagent identities in 36 recent miR-145 papers found that 56% and 17% of papers described misidentified nucleotide sequences and cell lines, respectively. We also found 5 cell line identifiers in miR-145 papers with misidentified nucleotide sequences and cell lines, and 18 cell line identifiers published elsewhere, that did not represent indexed human cell lines. These 23 identifiers were described as non-verifiable (NV), as their identities were unclear. Studying 420 papers that mentioned 8 NV identifier(s) found 235 papers (56%) that referred to 7 identifiers (BGC-803, BSG-803, BSG-823, GSE-1, HGC-7901, HGC-803, and MGC-823) as independent cell lines. We could not find any publications describing how these cell lines were established. Six cell lines were sourced from cell line repositories with externally accessible online catalogs, but these cell lines were not indexed as claimed. Some papers also stated that short tandem repeat (STR) profiles had been generated for three cell lines, yet no STR profiles could be identified. In summary, as NV cell lines represent new challenges to research integrity and reproducibility, further investigations are required to clarify their status and identities.

Developing a Continuous Severity Scale for Macular Telangiectasia Type 2 Using Deep Learning and Implications for Disease Grading.

PURPOSE: Deep learning (DL) models have achieved state-of-the-art medical diagnosis classification accuracy. Current models are limited by discrete diagnosis labels, but could yield more information with diagnosis in a continuous scale. We developed a novel continuous severity scaling system for macular telangiectasia (MacTel) type 2 by combining a DL classification model with uniform manifold approximation and projection (UMAP). DESIGN: We used a DL network to learn a feature representation of MacTel severity from discrete severity labels and applied UMAP to embed this feature representation into 2 dimensions, thereby creating a continuous MacTel severity scale. PARTICIPANTS: A total of 2003 OCT volumes were analyzed from 1089 MacTel Project participants. METHODS: We trained a multiview DL classifier using multiple B-scans from OCT volumes to learn a previously published discrete 7-step MacTel severity scale. The classifiers' last feature layer was extracted as input for UMAP, which embedded these features into a continuous 2-dimensional manifold. The DL classifier was assessed in terms of test accuracy. Rank correlation for the continuous UMAP scale against the previously published scale was calculated. Additionally, the UMAP scale was assessed in the κ agreement against 5 clinical experts on 100 pairs of patient volumes. For each pair of patient volumes, clinical experts were asked to select the volume with more severe MacTel disease and to compare them against the UMAP scale. MAIN OUTCOME MEASURES: Classification accuracy for the DL classifier and κ agreement versus clinical experts for UMAP. RESULTS: The multiview DL classifier achieved top 1 accuracy of 63.3% (186/294) on held-out test OCT volumes. The UMAP metric showed a clear continuous gradation of MacTel severity with a Spearman rank correlation of 0.84 with the previously published scale. Furthermore, the continuous UMAP metric achieved κ agreements of 0.56 to 0.63 with 5 clinical experts, which was comparable with interobserver κ values. CONCLUSIONS: Our UMAP embedding generated a continuous MacTel severity scale, without requiring continuous training labels. This technique can be applied to other diseases and may lead to more accurate diagnosis, improved understanding of disease progression, and key imaging features for pathologic characteristics. FINANCIAL DISCLOSURE(S): Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Large language models as tax attorneys: a case study in legal capabilities emergence.

Better understanding of Large Language Models' (LLMs) legal analysis abilities can contribute to improving the efficiency of legal services, governing artificial intelligence and leveraging LLMs to identify inconsistencies in law. This paper explores LLM capabilities in applying tax law. We choose this area of law because it has a structure that allows us to set up automated validation pipelines across thousands of examples, requires logical reasoning and maths skills, and enables us to test LLM capabilities in a manner relevant to real-world economic lives of citizens and companies. Our experiments demonstrate emerging legal understanding capabilities, with improved performance in each subsequent OpenAI model release. We experiment with retrieving and using the relevant legal authority to assess the impact of providing additional legal context to LLMs. Few-shot prompting, presenting examples of question-answer pairs, is also found to significantly enhance the performance of the most advanced model, GPT-4. The findings indicate that LLMs, particularly when combined with prompting enhancements and the correct legal texts, can perform at high levels of accuracy but not yet at expert tax lawyer levels. As LLMs continue to advance, their ability to reason about law autonomously could have significant implications for the legal profession and AI governance. This article is part of the theme issue 'A complexity science approach to law and governance'.

The role of emotion dysregulation in self-management behaviors among adults with type 2 diabetes.

Suboptimal disease self-management among adults with type 2 diabetes is associated with greater risk of diabetes related health complications and mortality. Emotional distress has been linked with poor diabetes self-management; however, few studies have examined the role of emotion dysregulation in diabetes management. The purpose of this study was to examine the relations between different facets of emotion dysregulation and diabetes self-management behaviors among a sample of 373 adults with type 2 diabetes. Separate median regression and binary logistic regression models were used to examine the association of emotion dysregulation facets and each diabetes self-care behavior (i.e., medication nonadherence, diet, exercise, self-monitoring of blood glucose (SMBG), foot care, and smoking). Generally, greater difficulties in emotion regulation were associated with poorer self-management behaviors. However, several facets of emotion dysregulation were linked with better self-management behaviors. Addressing emotion dysregulation among adults with type 2 diabetes has the potential to improve diabetes related self-management.

Psychometric Properties of the Short Scale Anxiety Sensitivity Index Among Adults with Chronic Respiratory Disease.

Approximately one-third of adults with chronic respiratory disease (CRD) have comorbid depressive and anxiety disorders; yet these disorders are often unrecognized in this patient population. Transdiagnostic processes such as anxiety sensitivity (AS) are useful for identifying mechanisms underlying psychological and heath conditions. The Short-Scale AS Index (SSASI) is a brief self-report measure of AS which has potential clinical utility among CRD populations to evaluate psychological distress and inform comprehensive care. The present study investigated the psychometric properties of the SSASI among adults with CRDs. Participants were recruited from a web-based panel of adults with CRDs (n = 768; 49.3% female; 57.8% White) including adults with asthma only (n = 230), COPD only (n = 321), or co-occurring asthma and COPD (n = 217). Participants completed a battery of self-report questionnaires assessing psychological and medical symptoms. Analyses were conducted to examine the factor structure and measurement invariance across CRD groups. Convergent validity and criterion validity of the SSASI were assessed within each group. Results supported partial measurement invariance across CRD groups. The SSASI demonstrated high reliability, convergent validity, and criterion validity with each CRD group. Findings from this study and existing work indicate that the SSASI is an effective and economical assessment tool for identifying patients CRD who may benefit from psychological interventions to reduce AS.

Frequency, Penetrance, and Variable Expressivity of Dilated Cardiomyopathy-Associated Putative Pathogenic Gene Variants in UK Biobank Participants.

BACKGROUND: There is a paucity of data regarding the phenotype of dilated cardiomyopathy (DCM) gene variants in the general population. We aimed to determine the frequency and penetrance of DCM-associated putative pathogenic gene variants in a general adult population, with a focus on the expression of clinical and subclinical phenotype, including structural, functional, and arrhythmic disease features. METHODS: UK Biobank participants who had undergone whole exome sequencing, ECG, and cardiovascular magnetic resonance imaging were selected for study. Three variant-calling strategies (1 primary and 2 secondary) were used to identify participants with putative pathogenic variants in 44 DCM genes. The observed phenotype was graded DCM (clinical or cardiovascular magnetic resonance diagnosis); early DCM features, including arrhythmia or conduction disease, isolated ventricular dilation, and hypokinetic nondilated cardiomyopathy; or phenotype-negative. RESULTS: Among 18 665 individuals included in the study, 1463 (7.8%) possessed ≥1 putative pathogenic variant in 44 DCM genes by the main variant calling strategy. A clinical diagnosis of DCM was present in 0.34% and early DCM features in 5.7% of individuals with putative pathogenic variants. ECG and cardiovascular magnetic resonance analysis revealed evidence of subclinical DCM in an additional 1.6% and early DCM features in an additional 15.9% of individuals with putative pathogenic variants. Arrhythmias or conduction disease (15.2%) were the most common early DCM features, followed by hypokinetic nondilated cardiomyopathy (4%). The combined clinical/subclinical penetrance was ≤30% with all 3 variant filtering strategies. Clinical DCM was slightly more prevalent among participants with putative pathogenic variants in definitive/strong evidence genes as compared with those with variants in moderate/limited evidence genes. CONCLUSIONS: In the UK Biobank, ≈1 of 6 of adults with putative pathogenic variants in DCM genes exhibited early DCM features potentially associated with DCM genotype, most commonly manifesting with arrhythmias in the absence of substantial ventricular dilation or dysfunction.

Optic radiations representing different eccentricities age differently.

The neural pathways that carry information from the foveal, macular, and peripheral visual fields have distinct biological properties. The optic radiations (OR) carry foveal and peripheral information from the thalamus to the primary visual cortex (V1) through adjacent but separate pathways in the white matter. Here, we perform white matter tractometry using pyAFQ on a large sample of diffusion MRI (dMRI) data from subjects with healthy vision in the U.K. Biobank dataset (UKBB; N = 5382; age 45-81). We use pyAFQ to characterize white matter tissue properties in parts of the OR that transmit information about the foveal, macular, and peripheral visual fields, and to characterize the changes in these tissue properties with age. We find that (1) independent of age there is higher fractional anisotropy, lower mean diffusivity, and higher mean kurtosis in the foveal and macular OR than in peripheral OR, consistent with denser, more organized nerve fiber populations in foveal/parafoveal pathways, and (2) age is associated with increased diffusivity and decreased anisotropy and kurtosis, consistent with decreased density and tissue organization with aging. However, anisotropy in foveal OR decreases faster with age than in peripheral OR, while diffusivity increases faster in peripheral OR, suggesting foveal/peri-foveal OR and peripheral OR differ in how they age.

Race, Ethnicity, Insurance, and Population Density Associations with Pediatric Strabismus and Strabismic Amblyopia in the IRIS® Registry.

PURPOSE: To evaluate the associations of sociodemographic factors with pediatric strabismus diagnosis and outcomes. DESIGN: Retrospective cohort study. PARTICIPANTS: American Academy of Ophthalmology IRIS® Registry (Intelligent Research in Sight) patients with strabismus diagnosed before the age of 10 years. METHODS: Multivariable regression models evaluated the associations of race and ethnicity, insurance, population density, and ophthalmologist ratio with age at strabismus diagnosis, diagnosis of amblyopia, residual amblyopia, and strabismus surgery. Survival analysis evaluated the same predictors of interest with the outcome of time to strabismus surgery. MAIN OUTCOME MEASURES: Age at strabismus diagnosis, rate of amblyopia and residual amblyopia, and rate of and time to strabismus surgery. RESULTS: The median age at diagnosis was 5 years (interquartile range, 3-7) for 106 723 children with esotropia (ET) and 54 454 children with exotropia (XT). Amblyopia diagnosis was more likely with Medicaid insurance than commercial insurance (odds ratio [OR], 1.05 for ET; 1.25 for XT; P < 0.01), as was residual amblyopia (OR, 1.70 for ET; 1.53 for XT; P < 0.01). For XT, Black children were more likely to develop residual amblyopia than White children (OR, 1.34; P < 0.01). Children with Medicaid were more likely to undergo surgery and did so sooner after diagnosis (hazard ratio [HR], 1.23 for ET; 1.21 for XT; P < 0.01) than those with commercial insurance. Compared with White children, Black, Hispanic, and Asian children were less likely to undergo ET surgery and received surgery later (all HRs < 0.87; P < 0.01), and Hispanic and Asian children were less likely to undergo XT surgery and received surgery later (all HRs < 0.85; P < 0.01). Increasing population density and clinician ratio were associated with lower HR for ET surgery (P < 0.01). CONCLUSIONS: Children with strabismus covered by Medicaid insurance had increased odds of amblyopia and underwent strabismus surgery sooner after diagnosis compared with children covered by commercial insurance. After adjusting for insurance status, Black, Hispanic, and Asian children were less likely to receive strabismus surgery with a longer delay between diagnosis and surgery compared with White children. FINANCIAL DISCLOSURE(S): Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Training Deep Learning Models to Work on Multiple Devices by Cross-Domain Learning with No Additional Annotations.

PURPOSE: To create an unsupervised cross-domain segmentation algorithm for segmenting intraretinal fluid and retinal layers on normal and pathologic macular OCT images from different manufacturers and camera devices. DESIGN: We sought to use generative adversarial networks (GANs) to generalize a segmentation model trained on one OCT device to segment B-scans obtained from a different OCT device manufacturer in a fully unsupervised approach without labeled data from the latter manufacturer. PARTICIPANTS: A total of 732 OCT B-scans from 4 different OCT devices (Heidelberg Spectralis, Topcon 1000, Maestro2, and Zeiss Plex Elite 9000). METHODS: We developed an unsupervised GAN model, GANSeg, to segment 7 retinal layers and intraretinal fluid in Topcon 1000 OCT images (domain B) that had access only to labeled data on Heidelberg Spectralis images (domain A). GANSeg was unsupervised because it had access only to 110 Heidelberg labeled OCTs and 556 raw and unlabeled Topcon 1000 OCTs. To validate GANSeg segmentations, 3 masked graders manually segmented 60 OCTs from an external Topcon 1000 test dataset independently. To test the limits of GANSeg, graders also manually segmented 3 OCTs from Zeiss Plex Elite 9000 and Topcon Maestro2. A U-Net was trained on the same labeled Heidelberg images as baseline. The GANSeg repository with labeled annotations is at https://github.com/uw-biomedical-ml/ganseg. MAIN OUTCOME MEASURES: Dice scores comparing segmentation results from GANSeg and the U-Net model with the manual segmented images. RESULTS: Although GANSeg and U-Net achieved comparable Dice scores performance as human experts on the labeled Heidelberg test dataset, only GANSeg achieved comparable Dice scores with the best performance for the ganglion cell layer plus inner plexiform layer (90%; 95% confidence interval [CI], 68%-96%) and the worst performance for intraretinal fluid (58%; 95% CI, 18%-89%), which was statistically similar to human graders (79%; 95% CI, 43%-94%). GANSeg significantly outperformed the U-Net model. Moreover, GANSeg generalized to both Zeiss and Topcon Maestro2 swept-source OCT domains, which it had never encountered before. CONCLUSIONS: GANSeg enables the transfer of supervised deep learning algorithms across OCT devices without labeled data, thereby greatly expanding the applicability of deep learning algorithms.

United States Population Disparities in Ophthalmic Care: Blindness and Visual Impairment in the IRIS® Registry (Intelligent Research in Sight).

PURPOSE: To evaluate associations of patient characteristics with United States eye care use and likelihood of blindness. DESIGN: Retrospective observational study. PARTICIPANTS: Patients (19 546 016) with 2018 visual acuity (VA) records in the American Academy of Ophthalmology's IRIS® Registry (Intelligent Research in Sight). METHODS: Legal blindness (20/200 or worse) and visual impairment (VI; worse than 20/40) were identified from corrected distance acuity in the better-seeing eye and stratified by patient characteristics. Multivariable logistic regressions evaluated associations with blindness and VI. Blindness was mapped by state and compared with population characteristics. Eye care use was analyzed by comparing population demographics with United States Census estimates and proportional demographic representation among blind patients versus a nationally representative US population sample (National Health and Nutritional Examination Survey [NHANES]). MAIN OUTCOME MEASURES: Prevalence and odds ratios for VI and blindness; proportional representation in the IRIS® Registry, Census, and NHANES by patient demographics. RESULTS: Visual impairment was present in 6.98% (n = 1 364 935) and blindness in 0.98% (n = 190 817) of IRIS patients. Adjusted odds of blindness were highest among patients ≥ 85 years old (odds ratio [OR], 11.85; 95% confidence interval [CI], 10.33-13.59 vs. those 0-17 years old). Blindness also was associated positively with rural location and Medicaid, Medicare, or no insurance vs. commercial insurance. Hispanic (OR, 1.59; 95% CI, 1.46-1.74) and Black (OR, 1.73; 95% CI, 1.63-1.84) patients showed a higher odds of blindness versus White non-Hispanic patients. Proportional representation in IRIS Registry relative to the Census was higher for White than Hispanic (2- to 4-fold) or Black (11%-85%) patients (P < 0.001). Blindness overall was less prevalent in NHANES than IRIS Registry; however, prevalence in adults aged 60+ was lowest among Black participants in the NHANES (0.54%) and second highest among comparable Black adults in IRIS (1.57%). CONCLUSIONS: Legal blindness from low VA was present in 0.98% of IRIS patients and associated with rural location, public or no insurance, and older age. Compared with US Census estimates, minorities may be underrepresented among ophthalmology patients, and compared with NHANES population estimates, Black individuals may be overrepresented among blind IRIS Registry patients. These findings provide a snapshot of US ophthalmic care and highlight the need for initiatives to address disparities in use and blindness. FINANCIAL DISCLOSURE(S): Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Headache and psychological variables as predictors of disability in individuals with primary headache disorders.

OBJECTIVE: To examine the relative contribution of headache symptoms and psychological factors to headache-related disability. BACKGROUND: Both headache symptoms and comorbid psychological factors (psychiatric symptoms and transdiagnostic constructs) negatively impact functioning among individuals with migraine and tension-type headache, but few studies have explored their relative contribution to headache-related disability. We hypothesized that psychiatric symptoms and transdiagnostic variables would afford incremental contribution to disability beyond headache symptoms, and we investigated the moderating role of headache diagnosis on these relationships. METHODS: This cross-sectional study examined data from a southern U.S. university online sample of 1818 young adults (mean [SD] age 19.0 [5.1] years; 74.6% female) who met the International Classification of Headache Disorders, third edition criteria for primary headache disorders (46.6% episodic migraine, 11.6% chronic migraine, 38.3% episodic tension-type headache, 3.5% chronic tension-type headache) and completed measures assessing psychological factors and headache-related disability. Headache, psychiatric symptoms, and transdiagnostic factors were examined in relation to headache-related disability, after controlling for sex. Moderation analyses examined the conditional effect of diagnosis on disability. RESULTS: As predicted, both psychiatric and transdiagnostic symptoms accounted for unique variance in headache-related disability beyond headache symptoms (R2 changes of 2.7% and 2.3%, respectively). Significant three-way interactions revealed the relationship between psychiatric symptoms and disability (b = -3.16, p = 0.002), and between transdiagnostic variables and disability (b = -2.37, p = 0.034). Tests of simple slopes showed greater psychiatric symptoms and transdiagnostic variables were associated with higher levels of disability. However, the associations of these variables with disability were strongest among individuals with chronic tension-type headache (B = 3.93 for psychiatric symptoms and B = 4.62 for transdiagnostic symptoms, both p < 0.001). CONCLUSION: Psychiatric and transdiagnostic factors contribute uniquely to headache-related functional impairment, which may be important for expanding targeted assessment and behavioral interventions.

Effects of Nystatin oral rinse on oral Candida species and Streptococcus mutans among healthy adults.

OBJECTIVES: To examine the effect of Nystatin oral rinse on oral Candida species and Streptococcus mutans carriage. MATERIALS AND METHODS: Twenty healthy adults with oral candidiasis participated in the single-arm clinical trial and received Nystatin oral rinse for 7 days, 4 applications/day, and 600,000 International Units/application. Demographic-socioeconomic-oral-medical conditions were obtained. Salivary and plaque Candida species and Streptococcus mutans were assessed at baseline and 1-week and 3-month follow-ups. Twenty-four salivary cytokines were assessed. Candida albicans isolates underwent Nystatin susceptibility test. RESULTS: Half of participants (10/20) were free of salivary C. albicans after using Nystatin rinse. Salivary S. mutans was significantly reduced at 3-month follow-up (p < 0.05). Periodontal status reflected by bleeding-on-probing was significantly improved at 1-week and 3-month follow-ups (p < 0.05). Plaque accumulation was significantly reduced at 1-week follow-up (p < 0.05). Interestingly, the responses to Nystatin oral rinse were not associated with race, gender, age, oral hygiene practice, adherence to Nystatin rinse, or sweet consumption (p > 0.05). No C. albicans isolates were resistant to Nystatin. Furthermore, salivary cytokine eotaxin and fractalkine were significantly reduced at 3-month follow-up among participants who responded to Nystatin rinse (p < 0.05). CONCLUSIONS: The study results indicate that oral antifungal treatment had an effect on S. mutans salivary carriage. Future clinical trials are warranted to comprehensively assess the impact of antifungal treatment on the oral flora other than S. mutans and Candida. CLINICAL RELEVANCE: Due to the potential cariogenic role of oral Candida species, antifungal approaches shed new light on the prevention and management of dental caries from a fungal perspective.

Clinical and genomic correlates of imatinib response in melanomas with KIT alterations.

BACKGROUND: Imatinib is an active agent for some patients with melanoma harbouring c-KIT alterations. However, the genetic and clinical features that correlate with imatinib sensitivity are not well-defined. METHODS: We retrospectively evaluated 38 KIT-altered melanoma patients from five medical centres who received imatinib, and pooled data from prospective studies of imatinib in 92 KIT-altered melanoma patients. Baseline patient and disease characteristics, and clinical outcomes were assessed. RESULTS: In the pooled analysis (N = 130), alterations in exons 11/13 had the highest response rates (38% and 33%); L576P (N = 23) and K642E (N = 12) mutations had ORR of 52% and 42%, respectively. ORR was 38% (mucosal), 25% (acral), and 8% (unknown-primary). PFS appeared longer in exon 11/13 vs. exon 17 alterations (median 4.3 and 4.5 vs. 1.1 months; p = 0.19), with similar superiority in OS (median 19.7 and 15.4 vs. 12.1 months; p = 0.20). By histology, median PFS was 4.5 months (mucosal), 2.7 (acral), and 5.0 (unknown-primary) [p = 0.36]. Median OS was 18.0 months (mucosal), 21.8 (acral), 11.5 (unknown-primary) [p = 0.26]. In multivariate analyses, mucosal melanoma was associated with higher PFS and exon 17 mutations were associated with reduced PFS. CONCLUSION: This multicenter study highlights KIT-alterations sensitive to imatinib and augments evidence for imatinib in subsets of KIT-altered melanoma.

Data Sources for Evaluating Health Disparities in Ophthalmology: Where We Are and Where We Need to Go.

Data provide an opportunity to discover disparities and inequities that may otherwise be unrecognized. Within the American Academy of Ophthalmology (AAO) Task Force on Disparities in Eye Care, the Leveraging Data Sub-task Force was charged with identifying data sources to study health disparities in eye care and to leverage data to advance health equity. We evaluated large data sources to determine their strengths, deficiencies, and relative accessibility in relation to the likelihood of identifying eye care disparities. We highlight the current challenges with these data sources and review key recommendations for improving future sources for studying health disparities in eye care.

Policy-Driven, Multimodal Deep Learning for Predicting Visual Fields from the Optic Disc and OCT Imaging.

PURPOSE: To develop and validate a deep learning (DL) system for predicting each point on visual fields (VFs) from disc and OCT imaging and derive a structure-function mapping. DESIGN: Retrospective, cross-sectional database study. PARTICIPANTS: A total of 6437 patients undergoing routine care for glaucoma in 3 clinical sites in the United Kingdom. METHODS: OCT and infrared reflectance (IR) optic disc imaging were paired with the closest VF within 7 days. EfficientNet B2 was used to train 2 single-modality DL models to predict each of the 52 sensitivity points on the 24-2 VF pattern. A policy DL model was designed and trained to fuse the 2 model predictions. MAIN OUTCOME MEASURES: Pointwise mean absolute error (PMAE). RESULTS: A total of 5078 imaging scans to VF pairs were used as a held-out test set to measure the final performance. The improvement in PMAE with the policy model was 0.485 (0.438, 0.533) decibels (dB) compared with the IR image of the disc alone and 0.060 (0.047, 0.073) dB with to the OCT alone. The improvement with the policy fusion model was statistically significant (P < 0.0001). Occlusion masking shows that the DL models learned the correct structure-function mapping in a data-driven, feature agnostic fashion. CONCLUSIONS: The multimodal, policy DL model performed the best; it provided explainable maps of its confidence in fusing data from single modalities and provides a pathway for probing the structure-function relationship in glaucoma.

From Data to Deployment: The Collaborative Community on Ophthalmic Imaging Roadmap for Artificial Intelligence in Age-Related Macular Degeneration.

OBJECTIVE: Health care systems worldwide are challenged to provide adequate care for the 200 million individuals with age-related macular degeneration (AMD). Artificial intelligence (AI) has the potential to make a significant, positive impact on the diagnosis and management of patients with AMD; however, the development of effective AI devices for clinical care faces numerous considerations and challenges, a fact evidenced by a current absence of Food and Drug Administration (FDA)-approved AI devices for AMD. PURPOSE: To delineate the state of AI for AMD, including current data, standards, achievements, and challenges. METHODS: Members of the Collaborative Community on Ophthalmic Imaging Working Group for AI in AMD attended an inaugural meeting on September 7, 2020, to discuss the topic. Subsequently, they undertook a comprehensive review of the medical literature relevant to the topic. Members engaged in meetings and discussion through December 2021 to synthesize the information and arrive at a consensus. RESULTS: Existing infrastructure for robust AI development for AMD includes several large, labeled data sets of color fundus photography and OCT images; however, image data often do not contain the metadata necessary for the development of reliable, valid, and generalizable models. Data sharing for AMD model development is made difficult by restrictions on data privacy and security, although potential solutions are under investigation. Computing resources may be adequate for current applications, but knowledge of machine learning development may be scarce in many clinical ophthalmology settings. Despite these challenges, researchers have produced promising AI models for AMD for screening, diagnosis, prediction, and monitoring. Future goals include defining benchmarks to facilitate regulatory authorization and subsequent clinical setting generalization. CONCLUSIONS: Delivering an FDA-authorized, AI-based device for clinical care in AMD involves numerous considerations, including the identification of an appropriate clinical application; acquisition and development of a large, high-quality data set; development of the AI architecture; training and validation of the model; and functional interactions between the model output and clinical end user. The research efforts undertaken to date represent starting points for the medical devices that eventually will benefit providers, health care systems, and patients.

Endophthalmitis Rate in Immediately Sequential versus Delayed Sequential Bilateral Cataract Surgery within the Intelligent Research in Sight (IRIS®) Registry Data.

PURPOSE: To compare the rate of postoperative endophthalmitis after immediately sequential bilateral cataract surgery (ISBCS) versus delayed sequential bilateral cataract surgery (DSBCS) using the American Academy of Ophthalmology Intelligent Research in Sight (IRIS®) Registry database. DESIGN: Retrospective cohort study. PARTICIPANTS: Patients in the IRIS Registry who underwent cataract surgery from 2013 through 2018. METHODS: Patients who underwent cataract surgery were divided into 2 groups: (1) ISBCS and (2) DSBCS (second-eye surgery ≥1 day after the first-eye surgery) or unilateral surgery. Postoperative endophthalmitis was defined as endophthalmitis occurring within 4 weeks of surgery by International Classification of Diseases (ICD) code and ICD code with additional clinical criteria. MAIN OUTCOME MEASURES: Rate of postoperative endophthalmitis. RESULTS: Of 5 573 639 IRIS Registry patients who underwent cataract extraction, 165 609 underwent ISBCS, and 5 408 030 underwent DSBCS or unilateral surgery (3 695 440 DSBCS, 1 712 590 unilateral surgery only). A total of 3102 participants (0.056%) met study criteria of postoperative endophthalmitis with supporting clinical findings. The rates of endophthalmitis in either surgery eye between the 2 surgery groups were similar (0.059% in the ISBCS group vs. 0.056% in the DSBCS or unilateral group; P = 0.53). Although the incidence of endophthalmitis was slightly higher in the ISBCS group compared with the DSBCS or unilateral group, the odds ratio did not reach statistical significance (1.08; 95% confidence interval, 0.87-1.31; P = 0.47) after adjusting for age, sex, race, insurance status, and comorbid eye disease. Seven cases of bilateral endophthalmitis with supporting clinical data in the DSBCS group and no cases in the ISBCS group were identified. CONCLUSIONS: Risk of postoperative endophthalmitis was not statistically significantly different between patients who underwent ISBCS and DSBCS or unilateral cataract surgery.

Impact of a Dyadic Intervention on Family Supporter Involvement in Helping Adults Manage Type 2 Diabetes.

BACKGROUND: Family support for adults' diabetes care is associated with improved self-management and outcomes, but healthcare providers lack structured ways to engage those supporters. OBJECTIVE: Assess the impact of a patient-supporter diabetes management intervention on supporters' engagement in patients' diabetes care, support techniques, and caregiving experience. DESIGN: Multivariate regression models examined between-group differences in support-related measures observed as part of a larger trial randomizing participants to a dyadic intervention versus usual care. PARTICIPANTS: A total of 239 adults with type 2 diabetes and either A1c >8% or systolic blood pressure >160mmHg enrolled with a family supporter. INTERVENTION: Health coaches provided training on positive support techniques and facilitated self-management information sharing and goal-setting. MAIN MEASURES: Patient and supporter reports at baseline and 12 months of supporter roles in diabetes care and caregiving experience. RESULTS: At 12 months, intervention-assigned patients had higher odds of reporting increased supporter involvement in remembering medical appointments (AOR 2.74, 95% CI 1.44, 5.21), performing home testing (AOR 2.40, 95% CI 1.29, 4.46), accessing online portals (AOR 2.34, 95% CI 1.29, 4.30), deciding when to contact healthcare providers (AOR 2.12, 95% CI 1.15, 3.91), and refilling medications (AOR 2.10, 95% CI 1.14, 3.89), but not with attending medical appointments or with healthy eating and exercise. Intervention-assigned patients reported increased supporter use of autonomy supportive communication (+0.27 points on a 7-point scale, p=0.02) and goal-setting techniques (+0.30 points on a 5-point scale, p=0.01). There were no differences at 12 months in change scores measuring supporter distress about patients' diabetes or caregiving burden. Intervention-assigned supporters had significantly larger increases in satisfaction with health system support for their role (+0.88 points on a 10-point scale, p=0.01). CONCLUSIONS: A dyadic patient-supporter intervention led to increased family supporter involvement in diabetes self-management and increased use of positive support techniques, without increasing caregiver stress.

Immune checkpoint inhibitors and their impact on liver enzymes and attenuation.

BACKGROUND: Immune related adverse events impacting the liver are common from immune checkpoint inhibitor (ICI) therapy; however, there is little data regarding the subclinical impact of ICIs on liver inflammation. The study aims to determine whether ICI therapy affects liver attenuation and liver enzymes in melanoma patients with and without hepatic steatosis. METHODS: A retrospective, cohort study was conducted of patients with advanced melanoma treated with ICI therapy who received serial PET-CT scans at the Vanderbilt University Medical Center (VUMC). Primary outcomes included: liver attenuation measured by PET-CT/non-contrast CT and liver enzymes. Hepatic steatosis was diagnosed by radiologists on clinical imaging. RESULTS: Among 839 patients with advanced melanoma treated with ICIs, 81 had serial PET-CT scans approximately 12 months apart and long-term survival; of these 11 patients had pre-existing steatosis/steatohepatitis. Overall, ICI was not associated with significant increases in liver enzymes in all patients; modest decreases in liver enzymes were observed in patients with pre-existing steatosis/steatohepatitis. Similarly, liver attenuation did not change from baseline to post-treatment (58.44 vs 60.60 HU, + 2.17, p = 0.055). CONCLUSIONS: ICIs may not chronically affect liver enzymes or liver attenuation, a non-invasive measure of liver fat content and inflammation, in the general population or in those with pre-existing steatosis/steatohepatitis.