Bacterial hemophilin homologs and their specific type eleven secretor proteins have conserved roles in heme capture and are diversifying as a family.

Cellular life relies on enzymes that require metals, which must be acquired from extracellular sources. Bacteria utilize surface and secreted proteins to acquire such valuable nutrients from their environment. These include the cargo proteins of the type eleven secretion system (T11SS), which have been connected to host specificity, metal homeostasis, and nutritional immunity evasion. This Sec-dependent, Gram-negative secretion system is encoded by organisms throughout the phylum Proteobacteria, including human pathogens Neisseria meningitidis, Proteus mirabilis, Acinetobacter baumannii, and Haemophilus influenzae. Experimentally verified T11SS-dependent cargo include transferrin-binding protein B (TbpB), the hemophilin homologs heme receptor protein C (HrpC), hemophilin A (HphA), the immune evasion protein factor-H binding protein (fHbp), and the host symbiosis factor nematode intestinal localization protein C (NilC). Here, we examined the specificity of T11SS systems for their cognate cargo proteins using taxonomically distributed homolog pairs of T11SS and hemophilin cargo and explored the ligand binding ability of those hemophilin cargo homologs. In vivo expression in Escherichia coli of hemophilin homologs revealed that each is secreted in a specific manner by its cognate T11SS protein. Sequence analysis and structural modeling suggest that all hemophilin homologs share an N-terminal ligand-binding domain with the same topology as the ligand-binding domains of the Haemophilus haemolyticus heme binding protein (Hpl) and HphA. We term this signature feature of this group of proteins the hemophilin ligand-binding domain. Network analysis of hemophilin homologs revealed five subclusters and representatives from four of these showed variable heme-binding activities, which, combined with sequence-structure variation, suggests that hemophilins are diversifying in function.IMPORTANCEThe secreted protein hemophilin and its homologs contribute to the survival of several bacterial symbionts within their respective host environments. Here, we compared taxonomically diverse hemophilin homologs and their paired Type 11 secretion systems (T11SS) to determine if heme binding and T11SS secretion are conserved characteristics of this family. We establish the existence of divergent hemophilin sub-families and describe structural features that contribute to distinct ligand-binding behaviors. Furthermore, we demonstrate that T11SS are specific for their cognate hemophilin family cargo proteins. Our work establishes that hemophilin homolog-T11SS pairs are diverging from each other, potentially evolving into novel ligand acquisition systems that provide competitive benefits in host niches.

Wireless, soft electronics for rapid, multisensor measurements of hydration levels in healthy and diseased skin.

Precise, quantitative measurements of the hydration status of skin can yield important insights into dermatological health and skin structure and function, with additional relevance to essential processes of thermoregulation and other features of basic physiology. Existing tools for determining skin water content exploit surrogate electrical assessments performed with bulky, rigid, and expensive instruments that are difficult to use in a repeatable manner. Recent alternatives exploit thermal measurements using soft wireless devices that adhere gently and noninvasively to the surface of the skin, but with limited operating range (∼1 cm) and high sensitivity to subtle environmental fluctuations. This paper introduces a set of ideas and technologies that overcome these drawbacks to enable high-speed, robust, long-range automated measurements of thermal transport properties via a miniaturized, multisensor module controlled by a long-range (∼10 m) Bluetooth Low Energy system on a chip, with a graphical user interface to standard smartphones. Soft contact to the surface of the skin, with almost zero user burden, yields recordings that can be quantitatively connected to hydration levels of both the epidermis and dermis, using computational modeling techniques, with high levels of repeatability and insensitivity to ambient fluctuations in temperature. Systematic studies of polymers in layered configurations similar to those of human skin, of porcine skin with known levels of hydration, and of human subjects with benchmarks against clinical devices validate the measurement approach and associated sensor hardware. The results support capabilities in characterizing skin barrier function, assessing severity of skin diseases, and evaluating cosmetic and medication efficacy, for use in the clinic or in the home.

Prospective Real-Time Validation of a Lung Ultrasound Deep Learning Model in the ICU.

OBJECTIVES: To evaluate the accuracy of a bedside, real-time deployment of a deep learning (DL) model capable of distinguishing between normal (A line pattern) and abnormal (B line pattern) lung parenchyma on lung ultrasound (LUS) in critically ill patients. DESIGN: Prospective, observational study evaluating the performance of a previously trained LUS DL model. Enrolled patients received a LUS examination with simultaneous DL model predictions using a portable device. Clip-level model predictions were analyzed and compared with blinded expert review for A versus B line pattern. Four prediction thresholding approaches were applied to maximize model sensitivity and specificity at bedside. SETTING: Academic ICU. PATIENTS: One-hundred critically ill patients admitted to ICU, receiving oxygen therapy, and eligible for respiratory imaging were included. Patients who were unstable or could not undergo an LUS examination were excluded. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: A total of 100 unique ICU patients (400 clips) were enrolled from two tertiary-care sites. Fifty-six patients were mechanically ventilated. When compared with gold standard expert annotation, the real-time inference yielded an accuracy of 95%, sensitivity of 93%, and specificity of 96% for identification of the B line pattern. Varying prediction thresholds showed that real-time modification of sensitivity and specificity according to clinical priorities is possible. CONCLUSIONS: A previously validated DL classification model performs equally well in real-time at the bedside when platformed on a portable device. As the first study to test the feasibility and performance of a DL classification model for LUS in a dedicated ICU environment, our results justify further inquiry into the impact of employing real-time automation of medical imaging into the care of the critically ill.

Acquisition and retention of lung ultrasound skills by respiratory therapists: A curriculum for respiratory therapists.

Purpose: Lung point-of-care ultrasound (POCUS) is a versatile bedside tool. The utility of POCUS has grown during the coronavirus disease 2019 pandemic, as it allows clinicians to obtain real-time images without requiring transport of the patient outside the intensive care unit. As respiratory therapists (RTs) are involved in caring for those with respiratory failure, there is a good rationale for their adoption of lung ultrasound. However, no training standards have been defined. Our objective was to develop and implement a training programme for RTs to achieve and sustain competence in lung ultrasound. Methods: This was a single-centre, prospective, single-cohort observational study. A total of 10 RTs completed our curriculum and were tasked with independently completing and interpreting 10 initial lung ultrasound exams and 3 subsequent exams after a 6-week interim period. All exams were blindly overread by a local expert in lung ultrasound. Results: After completing the curriculum, RTs were able to acquire and accurately interpret their images over 85% of the time. They were more successful in the upper lung zone image acquisition and interpretation compared with the lower lung zones. After 6 weeks, the RTs' lung POCUS skills remained stable, and their lower lung zone image interpretation improved. The RTs reported that their confidence improved throughout the study. Conclusion: The RTs in our study have demonstrated competence in acquisition and interpretation of upper lung zone images. They have also reported confidence in acquiring and interpreting upper lung zone images. More experience appears to be required to gain competence and confidence in lower lung zone ultrasound. Next steps would be to repeat the present study with a higher number of RTs completing at least 20 lung POCUS studies.

The Cerebellar Gene Database: a Collective Database of Genes Critical for Cerebellar Development.

This report presents the first comprehensive database that specifically compiles genes critical for cerebellar development and function. The Cerebellar Gene Database details genes that, when perturbed in mouse models, result in a cerebellar phenotype according to available data from both Mouse Genome Informatics and PubMed, as well as references to the corresponding studies for further examination. This database also offers a compilation of human genetic disorders with a cerebellar phenotype and their associated gene information from the Online Mendelian Inheritance in Man (OMIM) database. By comparing and contrasting the mouse and human datasets, we observe that only a small proportion of human mutant genes with a cerebellar phenotype have been studied in mouse knockout models. Given the highly conserved nature between mouse and human genomes, this surprising finding highlights how mouse genetic models can be more frequently employed to elucidate human disease etiology. On the other hand, many mouse genes identified in the present study that are known to lead to a cerebellar phenotype when perturbed have not yet been found to be pathogenic in the cerebellum of humans. This database furthers our understanding of human cerebellar disorders with yet-to-be-identified genetic causes. It is our hope that this gene database will serve as an invaluable tool for gathering background information, generating hypotheses, and facilitating translational research endeavors. Moreover, we encourage continual inputs from the research community in making this compilation a living database, one that remains up-to-date with the advances in cerebellar research.

Response to "The imaginary 'Asian Super Consumer': A critique of demand reduction campaigns for the illegal wildlife trade".

In a recent paper in Geoforum, Margulies et al. (2019) outline what they perceive as a bias toward an "Asian super consumer". They argue that wildlife trade demand reduction campaigns are unfocused, untargeted, and therefore have a tendency to place blame on people of colour and communities in the Global South as key actors in driving illegal wildlife trade. As researchers and practitioners, we have been studying the demand for wildlife and wildlife products for many years. While we agree that it is vitally important to consider the cultural nuances of illegal and unsustainable wildlife trade and to operate in a manner that is respectful toward different cultures, we believe that the authors have overlooked the fact that modern wildlife trade demand reduction campaigns are already conducting in-depth research and using it to target their campaigns to specific groups.

Deep Learning and Glaucoma Specialists: The Relative Importance of Optic Disc Features to Predict Glaucoma Referral in Fundus Photographs.

PURPOSE: To develop and validate a deep learning (DL) algorithm that predicts referable glaucomatous optic neuropathy (GON) and optic nerve head (ONH) features from color fundus images, to determine the relative importance of these features in referral decisions by glaucoma specialists (GSs) and the algorithm, and to compare the performance of the algorithm with eye care providers. DESIGN: Development and validation of an algorithm. PARTICIPANTS: Fundus images from screening programs, studies, and a glaucoma clinic. METHODS: A DL algorithm was trained using a retrospective dataset of 86 618 images, assessed for glaucomatous ONH features and referable GON (defined as ONH appearance worrisome enough to justify referral for comprehensive examination) by 43 graders. The algorithm was validated using 3 datasets: dataset A (1205 images, 1 image/patient; 18.1% referable), images adjudicated by panels of GSs; dataset B (9642 images, 1 image/patient; 9.2% referable), images from a diabetic teleretinal screening program; and dataset C (346 images, 1 image/patient; 81.7% referable), images from a glaucoma clinic. MAIN OUTCOME MEASURES: The algorithm was evaluated using the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity for referable GON and glaucomatous ONH features. RESULTS: The algorithm's AUC for referable GON was 0.945 (95% confidence interval [CI], 0.929-0.960) in dataset A, 0.855 (95% CI, 0.841-0.870) in dataset B, and 0.881 (95% CI, 0.838-0.918) in dataset C. Algorithm AUCs ranged between 0.661 and 0.973 for glaucomatous ONH features. The algorithm showed significantly higher sensitivity than 7 of 10 graders not involved in determining the reference standard, including 2 of 3 GSs, and showed higher specificity than 3 graders (including 1 GS), while remaining comparable to others. For both GSs and the algorithm, the most crucial features related to referable GON were: presence of vertical cup-to-disc ratio of 0.7 or more, neuroretinal rim notching, retinal nerve fiber layer defect, and bared circumlinear vessels. CONCLUSIONS: A DL algorithm trained on fundus images alone can detect referable GON with higher sensitivity than and comparable specificity to eye care providers. The algorithm maintained good performance on an independent dataset with diagnoses based on a full glaucoma workup.

Using a Deep Learning Algorithm and Integrated Gradients Explanation to Assist Grading for Diabetic Retinopathy.

PURPOSE: To understand the impact of deep learning diabetic retinopathy (DR) algorithms on physician readers in computer-assisted settings. DESIGN: Evaluation of diagnostic technology. PARTICIPANTS: One thousand seven hundred ninety-six retinal fundus images from 1612 diabetic patients. METHODS: Ten ophthalmologists (5 general ophthalmologists, 4 retina specialists, 1 retina fellow) read images for DR severity based on the International Clinical Diabetic Retinopathy disease severity scale in each of 3 conditions: unassisted, grades only, or grades plus heatmap. Grades-only assistance comprised a histogram of DR predictions (grades) from a trained deep-learning model. For grades plus heatmap, we additionally showed explanatory heatmaps. MAIN OUTCOME MEASURES: For each experiment arm, we computed sensitivity and specificity of each reader and the algorithm for different levels of DR severity against an adjudicated reference standard. We also measured accuracy (exact 5-class level agreement and Cohen's quadratically weighted κ), reader-reported confidence (5-point Likert scale), and grading time. RESULTS: Readers graded more accurately with model assistance than without for the grades-only condition (P < 0.001). Grades plus heatmaps improved accuracy for patients with DR (P < 0.001), but reduced accuracy for patients without DR (P = 0.006). Both forms of assistance increased readers' sensitivity moderate-or-worse DR: unassisted: mean, 79.4% [95% confidence interval (CI), 72.3%-86.5%]; grades only: mean, 87.5% [95% CI, 85.1%-89.9%]; grades plus heatmap: mean, 88.7% [95% CI, 84.9%-92.5%] without a corresponding drop in specificity (unassisted: mean, 96.6% [95% CI, 95.9%-97.4%]; grades only: mean, 96.1% [95% CI, 95.5%-96.7%]; grades plus heatmap: mean, 95.5% [95% CI, 94.8%-96.1%]). Algorithmic assistance increased the accuracy of retina specialists above that of the unassisted reader or model alone; and increased grading confidence and grading time across all readers. For most cases, grades plus heatmap was only as effective as grades only. Over the course of the experiment, grading time decreased across all conditions, although most sharply for grades plus heatmap. CONCLUSIONS: Deep learning algorithms can improve the accuracy of, and confidence in, DR diagnosis in an assisted read setting. They also may increase grading time, although these effects may be ameliorated with experience.

Development and Characterization of an 18F-labeled Ghrelin Peptidomimetic for Imaging the Cardiac Growth Hormone Secretagogue Receptor.

One-third of patients with heart disease develop heart failure, which is diagnosed through imaging and detection of circulating biomarkers. Imaging strategies reveal morphologic and functional changes but fall short of detecting molecular abnormalities that can lead to heart failure, and circulating biomarkers are not cardiac specific. Thus, there is critical need for biomarkers that are endogenous to myocardial tissues. The cardiac growth hormone secretagogue receptor 1a (GHSR1a), which binds the hormone ghrelin, is a potential biomarker for heart failure. We have synthesized and characterized a novel ghrelin peptidomimetic tracer, an 18F-labeled analogue of G-7039, for positron emission tomography (PET) imaging of cardiac GHSR1a. In vitro analysis showed enhanced serum stability compared to natural ghrelin and significantly increased cellular uptake in GHSR1a-expressing OVCAR cells. Biodistribution studies in mice showed that tissue uptake of the tracer was independent of circulating ghrelin levels, and there was negligible cardiac uptake and high uptake in the liver, intestines, and kidneys. Specificity of tracer uptake was assessed using ghsr -/- mice; both static and dynamic PET imaging revealed no difference in cardiac uptake, and there was no significant correlation between cardiac standardized uptake values and GHSR1a expression. Our study lays the groundwork for further refinement of peptidomimetic PET tracers targeting cardiac GHSR1a.

Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs.

Importance: Deep learning is a family of computational methods that allow an algorithm to program itself by learning from a large set of examples that demonstrate the desired behavior, removing the need to specify rules explicitly. Application of these methods to medical imaging requires further assessment and validation. Objective: To apply deep learning to create an algorithm for automated detection of diabetic retinopathy and diabetic macular edema in retinal fundus photographs. Design and Setting: A specific type of neural network optimized for image classification called a deep convolutional neural network was trained using a retrospective development data set of 128 175 retinal images, which were graded 3 to 7 times for diabetic retinopathy, diabetic macular edema, and image gradability by a panel of 54 US licensed ophthalmologists and ophthalmology senior residents between May and December 2015. The resultant algorithm was validated in January and February 2016 using 2 separate data sets, both graded by at least 7 US board-certified ophthalmologists with high intragrader consistency. Exposure: Deep learning-trained algorithm. Main Outcomes and Measures: The sensitivity and specificity of the algorithm for detecting referable diabetic retinopathy (RDR), defined as moderate and worse diabetic retinopathy, referable diabetic macular edema, or both, were generated based on the reference standard of the majority decision of the ophthalmologist panel. The algorithm was evaluated at 2 operating points selected from the development set, one selected for high specificity and another for high sensitivity. Results: The EyePACS-1 data set consisted of 9963 images from 4997 patients (mean age, 54.4 years; 62.2% women; prevalence of RDR, 683/8878 fully gradable images [7.8%]); the Messidor-2 data set had 1748 images from 874 patients (mean age, 57.6 years; 42.6% women; prevalence of RDR, 254/1745 fully gradable images [14.6%]). For detecting RDR, the algorithm had an area under the receiver operating curve of 0.991 (95% CI, 0.988-0.993) for EyePACS-1 and 0.990 (95% CI, 0.986-0.995) for Messidor-2. Using the first operating cut point with high specificity, for EyePACS-1, the sensitivity was 90.3% (95% CI, 87.5%-92.7%) and the specificity was 98.1% (95% CI, 97.8%-98.5%). For Messidor-2, the sensitivity was 87.0% (95% CI, 81.1%-91.0%) and the specificity was 98.5% (95% CI, 97.7%-99.1%). Using a second operating point with high sensitivity in the development set, for EyePACS-1 the sensitivity was 97.5% and specificity was 93.4% and for Messidor-2 the sensitivity was 96.1% and specificity was 93.9%. Conclusions and Relevance: In this evaluation of retinal fundus photographs from adults with diabetes, an algorithm based on deep machine learning had high sensitivity and specificity for detecting referable diabetic retinopathy. Further research is necessary to determine the feasibility of applying this algorithm in the clinical setting and to determine whether use of the algorithm could lead to improved care and outcomes compared with current ophthalmologic assessment.

Comparative metagenomics of tropical reef fishes show conserved core gut functions across hosts and diets with diet-related functional gene enrichments.

Fish gut microbial communities are important for the breakdown and energy harvesting of the host diet. Microbes within the fish gut are selected by environmental and evolutionary factors. To understand how fish gut microbial communities are shaped by diet, three tropical fish species (hawkfish, Paracirrhites arcatus; yellow tang, Zebrasoma flavescens; and triggerfish, Rhinecanthus aculeatus) were fed piscivorous (fish meal pellets), herbivorous (seaweed), and invertivorous (shrimp) diets, respectively. From fecal samples, a total of 43 metagenome assembled genomes (MAGs) were recovered from all fish diet treatments. Each host-diet treatment harbored distinct microbial communities based on taxonomy, with Proteobacteria, Bacteroidota, and Firmicutes being the most represented. Based on their metagenomes, microbial communities from all three host-diet treatments demonstrated a baseline ability to degrade proteinaceous, fatty acid, and simple carbohydrate inputs and carry out central carbon metabolism, lactate and formate fermentation, acetogenesis, nitrate respiration, and B vitamin synthesis. The herbivorous yellow tang harbored a more functionally diverse microbial community with some complex polysaccharide degradation specialists, while the piscivorous hawkfish's gut community was more specialized for the degradation of proteins. The invertivorous triggerfish's gut microbiome lacked many carbohydrate degrading capabilities, resulting in a more specialized, functionally uniform community. Across all treatments, several MAGs were able to participate in only individual steps of the degradation of complex polysaccharides, suggestive of microbial community networks that degrade complex inputs. These data suggest the existence of a functional core microbiome that is common among fish species, although the specific taxonomic identities of the associated bacteria may differ.

Medico-legal risks of point-of-care ultrasound: a closed-case analysis of Canadian Medical Protective Association medico-legal cases.

BACKGROUND: Point-of-care ultrasound (POCUS) has become a core diagnostic tool for many physicians due to its portability, excellent safety profile, and diagnostic utility. Despite its growing use, the potential risks of POCUS use should be considered by providers. We analyzed the Canadian Medical Protective Association (CMPA) repository to identify medico-legal cases arising from the use of POCUS. METHODS: We retrospectively searched the CMPA closed-case repository for cases involving diagnostic POCUS between January 1st, 2012 and December 31st, 2021. Cases included civil-legal actions, medical regulatory authority (College) cases, and hospital complaints. Patient and physician demographics, outcomes, reason for complaint, and expert-identified contributing factors were analyzed. RESULTS: From 2012 to 2021, there were 58,626 closed medico-legal cases in the CMPA repository with POCUS determined to be a contributing factor for medico-legal action in 15 cases; in all cases the medico-legal outcome was decided against the physicians. The most common reasons for patient complaints were diagnostic error, deficient assessment, and failure to perform a test or intervention. Expert analysis of these cases determined the most common contributing factors for medico-legal action was failure to perform POCUS when indicated (7 cases, 47%); however, medico-legal action also resulted from diagnostic error, incorrect sonographic approach, deficient assessment, inadequate skill, inadequate documentation, or inadequate reporting. CONCLUSIONS: Although the most common reason associated with the medico-legal action in these cases is failure to perform POCUS when indicated, inappropriate use of POCUS may lead to medico-legal action. Due to limitations in granularity of data, the exact number of civil-legal, College cases, and hospital complaints for each contributing factor is unavailable. To enhance patient care and mitigate risk for providers, POCUS should be carefully integrated with other clinical information, performed by providers with adequate skill, and carefully documented.

Biological Upcycling of Plastics Waste.

Plastic wastes accumulate in the environment, impacting wildlife and human health and representing a significant pool of inexpensive waste carbon that could form feedstock for the sustainable production of commodity chemicals, monomers, and specialty chemicals. Current mechanical recycling technologies are not economically attractive due to the lower-quality plastics that are produced in each iteration. Thus, the development of a plastics economy requires a solution that can deconstruct plastics and generate value from the deconstruction products. Biological systems can provide such value by allowing for the processing of mixed plastics waste streams via enzymatic specificity and using engineered metabolic pathways to produce upcycling targets. We focus on the use of biological systems for waste plastics deconstruction and upcycling. We highlight documented and predicted mechanisms through which plastics are biologically deconstructed and assimilated and provide examples of upcycled products from biological systems. Additionally, we detail current challenges in the field, including the discovery and development of microorganisms and enzymes for deconstructing non-polyethylene terephthalate plastics, the selection of appropriate target molecules to incentivize development of a plastic bioeconomy, and the selection of microbial chassis for the valorization of deconstruction products.

Automated Real-Time Detection of Lung Sliding Using Artificial Intelligence: A Prospective Diagnostic Accuracy Study.

BACKGROUND: Rapid evaluation for pneumothorax is a common clinical priority. Although lung ultrasound (LUS) often is used to assess for pneumothorax, its diagnostic accuracy varies based on patient and provider factors. To enhance the performance of LUS for pulmonary pathologic features, artificial intelligence (AI)-assisted imaging has been adopted; however, the diagnostic accuracy of AI-assisted LUS (AI-LUS) deployed in real time to diagnose pneumothorax remains unknown. RESEARCH QUESTION: In patients with suspected pneumothorax, what is the real-time diagnostic accuracy of AI-LUS to recognize the absence of lung sliding? STUDY DESIGN AND METHODS: We performed a prospective AI-assisted diagnostic accuracy study of AI-LUS to recognize the absence of lung sliding in a convenience sample of patients with suspected pneumothorax. After calibrating the model parameters and imaging settings for bedside deployment, we prospectively evaluated its diagnostic accuracy for lung sliding compared with a reference standard of expert consensus. RESULTS: Two hundred forty-one lung sliding evaluations were derived from 62 patients. AI-LUS showed a sensitivity of 0.921 (95% CI, 0.792-0.973), specificity of 0.802 (95% CI, 0.735-0.856), area under the receiver operating characteristic curve of 0.885 (95% CI, 0.828-0.956), and accuracy of 0.824 (95% CI, 0.766-0.870) for the diagnosis of absent lung sliding. INTERPRETATION: In this study, real-time AI-LUS showed high sensitivity and moderate specificity to identify the absence of lung sliding. Further research to improve model performance and optimize the integration of AI-LUS into existing diagnostic pathways is warranted.

Improving the Generalizability and Performance of an Ultrasound Deep Learning Model Using Limited Multicenter Data for Lung Sliding Artifact Identification.

Deep learning (DL) models for medical image classification frequently struggle to generalize to data from outside institutions. Additional clinical data are also rarely collected to comprehensively assess and understand model performance amongst subgroups. Following the development of a single-center model to identify the lung sliding artifact on lung ultrasound (LUS), we pursued a validation strategy using external LUS data. As annotated LUS data are relatively scarce-compared to other medical imaging data-we adopted a novel technique to optimize the use of limited external data to improve model generalizability. Externally acquired LUS data from three tertiary care centers, totaling 641 clips from 238 patients, were used to assess the baseline generalizability of our lung sliding model. We then employed our novel Threshold-Aware Accumulative Fine-Tuning (TAAFT) method to fine-tune the baseline model and determine the minimum amount of data required to achieve predefined performance goals. A subgroup analysis was also performed and Grad-CAM++ explanations were examined. The final model was fine-tuned on one-third of the external dataset to achieve 0.917 sensitivity, 0.817 specificity, and 0.920 area under the receiver operator characteristic curve (AUC) on the external validation dataset, exceeding our predefined performance goals. Subgroup analyses identified LUS characteristics that most greatly challenged the model's performance. Grad-CAM++ saliency maps highlighted clinically relevant regions on M-mode images. We report a multicenter study that exploits limited available external data to improve the generalizability and performance of our lung sliding model while identifying poorly performing subgroups to inform future iterative improvements. This approach may contribute to efficiencies for DL researchers working with smaller quantities of external validation data.

Impact of Adenotonsillectomy on Homework Performance in Children With Obstructive Sleep-Disordered Breathing.

OBJECTIVE: As a first line treatment for pediatric obstructive sleep-disordered breathing (SDB), adenotonsillectomy (AT) has been shown to confer physiologic and neurocognitive benefits to a child. However, there is a scarcity of data on how homework performance is affected postoperatively. Our objective was to evaluate the impact of AT on homework performance in children with SDB. METHODS: Children in grades 1 to 8 undergoing AT for SDB based on clinical criteria with or without preoperative polysomnography along with a control group of children undergoing surgery unrelated to the treatment of SDB were recruited. The primary outcome of interest was the differential change in homework performance between the study group and control at follow-up as measured by the validated Homework Performance Questionnaire (HPQ-P). Adjustments were made for demographics and Pediatric Sleep Questionnaire (PSQ) scores. RESULTS: 116 AT and 47 control subjects were recruited, and follow-up data was obtained in 99 AT and 35 control subjects. There were no significant differences between the general (total) HPQ-P scores and subscale scores between the AT and control subjects at entry and there were no significant differences in the change scores (follow-up minus initial scores) between the groups. Regression modeling also demonstrated that there were no group (AT vs control) by time interactions that predicted differential improvements in the HPQ-P (P > .10 for each model) although initial PSQ score was a significant predictor of lower HPQ-P scores for all models. CONCLUSIONS: Children with SDB experienced improvement in HPQ-P scores postoperatively, but the degree of change was not significant when compared to controls. Further studies incorporating additional educational metrics are encouraged to assess the true scholastic impact of AT in children with SDB.

Accurate assessment of the lung sliding artefact on lung ultrasonography using a deep learning approach.

Pneumothorax is a potentially life-threatening condition that can be rapidly and accurately assessed via the lung sliding artefact generated using lung ultrasound (LUS). Access to LUS is challenged by user dependence and shortage of training. Image classification using deep learning methods can automate interpretation in LUS and has not been thoroughly studied for lung sliding. Using a labelled LUS dataset from 2 academic hospitals, clinical B-mode (also known as brightness or two-dimensional mode) videos featuring both presence and absence of lung sliding were transformed into motion (M) mode images. These images were subsequently used to train a deep neural network binary classifier that was evaluated using a holdout set comprising 15% of the total data. Grad-CAM explanations were examined. Our binary classifier using the EfficientNetB0 architecture was trained using 2535 LUS clips from 614 patients. When evaluated on a test set of data uninvolved in training (540 clips from 124 patients), the model performed with a sensitivity of 93.5%, specificity of 87.3% and an area under the receiver operating characteristic curve (AUC) of 0.973. Grad-CAM explanations confirmed the model's focus on relevant regions on M-mode images. Our solution accurately distinguishes between the presence and absence of lung sliding artefacts on LUS.

Enhancing Annotation Efficiency with Machine Learning: Automated Partitioning of a Lung Ultrasound Dataset by View.

BACKGROUND: Annotating large medical imaging datasets is an arduous and expensive task, especially when the datasets in question are not organized according to deep learning goals. Here, we propose a method that exploits the hierarchical organization of annotating tasks to optimize efficiency. METHODS: We trained a machine learning model to accurately distinguish between one of two classes of lung ultrasound (LUS) views using 2908 clips from a larger dataset. Partitioning the remaining dataset by view would reduce downstream labelling efforts by enabling annotators to focus on annotating pathological features specific to each view. RESULTS: In a sample view-specific annotation task, we found that automatically partitioning a 780-clip dataset by view saved 42 min of manual annotation time and resulted in 55±6 additional relevant labels per hour. CONCLUSIONS: Automatic partitioning of a LUS dataset by view significantly increases annotator efficiency, resulting in higher throughput relevant to the annotating task at hand. The strategy described in this work can be applied to other hierarchical annotation schemes.

In-Office Corticosteroid Placement in the Management of Chronic Rhinosinusitis.

OBJECTIVES: Corticosteroids represent one of the mainstays of medical management of chronic rhinosinusitis (CRS) in both locally acting topical and systemic derivations. The application of topical corticosteroids is limited by a variety of factors including patient compliance, positioning, and nasal anatomy. Systemic corticosteroids confer a risk of medical complication that restricts their ability to be used repeatedly. The objective of this publication is to review the evolution of the in-office intranasal placement of corticosteroids in the management of CRS. The efficacy, outcomes, and safety of a variety of corticosteroid-containing devices meant to be placed in an office setting are reviewed. METHODS: Pertinent literature was reviewed and summarized beginning with the earliest reports of direct intralesional injection of corticosteroids up through manufactured modern-day bioresorbable implants that contain corticosteroids. RESULTS: The utilization of in-office placement of corticosteroid-containing material and implants has rapidly evolved since the concept was introduced, particularly in the last decade. Modern-day corticosteroid-eluting implants are reliably placed in the office, yield results across a range of objective and subjective outcomes, may decrease the need for revision endoscopic sinus surgery, and have a favorable safety profile. CONCLUSIONS: In-office placement of corticosteroid-containing stents are a viable treatment option for select patients, particularly those wishing to avoid revision surgery, and should be considered an important adjunct for treatment of refractory CRS in an otolaryngologist's armamentarium.

Development of a convolutional neural network to differentiate among the etiology of similar appearing pathological B lines on lung ultrasound: a deep learning study.

OBJECTIVES: Lung ultrasound (LUS) is a portable, low-cost respiratory imaging tool but is challenged by user dependence and lack of diagnostic specificity. It is unknown whether the advantages of LUS implementation could be paired with deep learning (DL) techniques to match or exceed human-level, diagnostic specificity among similar appearing, pathological LUS images. DESIGN: A convolutional neural network (CNN) was trained on LUS images with B lines of different aetiologies. CNN diagnostic performance, as validated using a 10% data holdback set, was compared with surveyed LUS-competent physicians. SETTING: Two tertiary Canadian hospitals. PARTICIPANTS: 612 LUS videos (121 381 frames) of B lines from 243 distinct patients with either (1) COVID-19 (COVID), non-COVID acute respiratory distress syndrome (NCOVID) or (3) hydrostatic pulmonary edema (HPE). RESULTS: The trained CNN performance on the independent dataset showed an ability to discriminate between COVID (area under the receiver operating characteristic curve (AUC) 1.0), NCOVID (AUC 0.934) and HPE (AUC 1.0) pathologies. This was significantly better than physician ability (AUCs of 0.697, 0.704, 0.967 for the COVID, NCOVID and HPE classes, respectively), p<0.01. CONCLUSIONS: A DL model can distinguish similar appearing LUS pathology, including COVID-19, that cannot be distinguished by humans. The performance gap between humans and the model suggests that subvisible biomarkers within ultrasound images could exist and multicentre research is merited.