Population-based incidence of psoriasis vulgaris in Germany: analysis of national statutory insurance data from 65 million population.

Information on the population-based incidence of psoriasis vulgaris was limited. This study was to provide a comprehensive understanding of the age-specific and sex-specific incidence of psoriasis vulgaris in Germany. The data were obtained in the context of a morbidity-based risk adjustment by statutory health insurance companies in Germany, comprising information regarding 65 million population. Psoriasis vulgaris diagnoses were made and coded according to the 10th edition of the International Statistical Classification of Diseases and Related Health Problems. Age-specific and sex-specific incidences were calculated using data from 2009 to 2011. There was a rise in the age- and sex-specific incidences of psoriasis vulgaris through midlife, reaching a peak at the age of 60 and subsequently declining for both genders. The peak incidence for men, at 130 cases per 100,000 person-years, slightly exceeded the peak incidence for women of 117 per 100,000 person-years. An increase in the overall incidence rate can also be observed over the course of the three-year period covered by the data. Considerable variations in the age- and sex-specific incidences of psoriasis vulgaris can be seen across the lifespan. Nevertheless, the overall age-standardized incidence for the German population was low compared to other European countries.

Acceptability and tolerability of alcohol-based hand rubs among health workers and concessionaires in Malaysia during the COVID pandemic: a hospital-wide cross-sectional study using a modified WHO protocol.

This study evaluated the acceptability and tolerability of three alcohol-based hand rubs (ABHRs) at Sarawak General Hospital, Malaysia. Conducted from 12-26 November 2021 using a modified WHO Protocol, it involved a survey among health workers and concessionaires, with a 35% response rate (1,598 of 4,628 participants). The majority were nurses (60.8%), with the medical division most represented (28.4%). Most respondents (93.2%) used ABHRs at least five days a week and found them easily accessible (72.3%). Product B was the preferred ABHR (65%), primarily for its color and fragrance, surpassing WHO's 50% approval rate in these aspects. However, no other product features met WHO criteria. There were no significant differences in self-reported skin tolerability across the products, and none achieved overall WHO approval. These results offer important insights for ABHR selection in developing countries and highlight the value of the WHO Protocol in assessing product acceptability and tolerability.

A population-based projection of psoriatic arthritis in Germany until 2050: analysis of national statutory health insurance data of 65 million German population.

The population-based prevalence of psoriatic arthritis (PsA) is still unclear and not well described globally. The aim of this study was to conduct a population-based prevalence projection and provide long-term future estimations of PsA patients in Germany until 2050, using the illness-death model and based on historical data. We analyzed the national statutory health insurance data of 65 million population in the German Institute for Medical Documentation and Information between January 2009 and December 2012. We constructed an estimation of the PsA burden among the German population using the relevant epidemiological parameters to project the numbers of patients with PsA in Germany until 2050 under five possible scenarios by varying the incidence and mortality. The overall conservatively estimated prevalence of PsA in Germany in 2019 was 0.31% (95% CI 0.28-0.36%). Women contribute a higher prevalence than men in all five scenarios. In the assumed scenarios with increased incidence, the prevalence of PsA at 60 years of age could rise from 1% in 2019 to more than 3% in 2050 for both genders, with the increase particularly pronounced for women, reaching around 3.5%. However, in the assumed scenarios with decreasing incidence, the prevalence curve may flatten and begin a decreasing trend from 2035 to 2050 for both genders, achieving a prevalence of less than 1% in 2050. Our research is to generate assumed population-based data on PsA in Germany that can serve as a reference for public health stakeholders to prepare an optional intervention. We would expect worryingly high numbers in the coming decades if preventive strategies are not implemented. In the long term, it will be necessary to implement preventive strategies to identify predictors and treat psoriasis symptoms early in order to delay or even prevent the transition of psoriasis to PsA.

Regional Deep Atrophy: a Self-Supervised Learning Method to Automatically Identify Regions Associated With Alzheimer's Disease Progression From Longitudinal MRI.

Longitudinal assessment of brain atrophy, particularly in the hippocampus, is a well-studied biomarker for neurodegenerative diseases, such as Alzheimer's disease (AD). In clinical trials, estimation of brain progressive rates can be applied to track therapeutic efficacy of disease modifying treatments. However, most state-of-the-art measurements calculate changes directly by segmentation and/or deformable registration of MRI images, and may misreport head motion or MRI artifacts as neurodegeneration, impacting their accuracy. In our previous study, we developed a deep learning method DeepAtrophy that uses a convolutional neural network to quantify differences between longitudinal MRI scan pairs that are associated with time. DeepAtrophy has high accuracy in inferring temporal information from longitudinal MRI scans, such as temporal order or relative inter-scan interval. DeepAtrophy also provides an overall atrophy score that was shown to perform well as a potential biomarker of disease progression and treatment efficacy. However, DeepAtrophy is not interpretable, and it is unclear what changes in the MRI contribute to progression measurements. In this paper, we propose Regional Deep Atrophy (RDA), which combines the temporal inference approach from DeepAtrophy with a deformable registration neural network and attention mechanism that highlights regions in the MRI image where longitudinal changes are contributing to temporal inference. RDA has similar prediction accuracy as DeepAtrophy, but its additional interpretability makes it more acceptable for use in clinical settings, and may lead to more sensitive biomarkers for disease monitoring in clinical trials of early AD.

Quality of systematic reviews on timing of complementary feeding for early childhood allergy prevention.

BACKGROUND: Only rigorously prepared analyses can provide the highest level of evidence to inform decision-making. Several recent systematic reviews (SRs) examined the hypothesis that the early introduction of specific allergenic complementary foods (CFs) to infants may lead to a lower incidence of one or more allergic outcomes. However, the methodological rigour and quality of reporting of SRs in this area has not yet been systematically evaluated. METHODS: We comprehensively searched PubMed, Medline (Ovid), and Web of Science Core Collection on 13th January 2022, using a pre-specified and tested search syntax for SRs with RCT evidence on the early introduction of allergenic CFs as a means for allergy prevention in infants and children. We examined the quality and risk of bias (RoB) using AMSTAR-2 and ROBIS tools, examined adherence to the Preferred Reporting Items for SRs and Meta-Analyses (PRISMA), and checked whether certainty of the evidence was assessed. RESULTS: Twelve SRs were included. Application of both tools resulted in similar overall judgements in terms of direction and extent for nine of the 12 SRs. Nine SRs were found to be of critically low to low quality according to AMSTAR-2 and to be at high RoB according to ROBIS. One SR received a moderate quality rating (AMSTAR-2) and high RoB rating (ROBIS). However, for two SRs, judgements between AMSTAR-2 and ROBIS were at stark variance. Only two SRs fully adhered to the PRISMA checklist. Six SRs evaluated the certainty of the body of RCT evidence. Several SRs failed to consider unpublished studies either by an explicit a priori exclusion or by inadequate search strategies. CONCLUSIONS: Well-conducted SRs are important for decision-making and informing guideline development, the quality of their methodology should therefore be considered. The methodological rigour and the reporting quality of SRs on the timing of CF for allergy prevention must be improved. REGISTRATION: https://osf.io/7cs4b .

Pesticide residues in rice planted in South and Southwest China.

In 2019 and 2020, 70 paddy and 70 brown rice samples were collected from South China and Southwest China, wherein the residues of 15 target pesticides were investigated. A gas chromatography-mass spectrometry (GC-MS) method was established for the simultaneous detection of 15 pesticides, which achieved good linear relationship with limits of detection (LODs) of 0.10-4.00 µg kg-1. The average recoveries and relative standard deviations (RSD) were satisfied for the pesticide residues detection. Analysis results showed that the detection rates of 15 typical pesticides in paddy and brown rice were 0%-12.9% and 0%-1.4%, respectively. None of the 15 pesticides exceed their maximum residue limit (MRL) stipulated by China. The pesticide with the highest detection rate and concentration was chlorpyrifos. This study can provide data support for the control of pesticide residues in rice and the realisation of the improving the efficiency of pesticide and fertiliser while reducing their application.

Deep label fusion: A generalizable hybrid multi-atlas and deep convolutional neural network for medical image segmentation.

Deep convolutional neural networks (DCNN) achieve very high accuracy in segmenting various anatomical structures in medical images but often suffer from relatively poor generalizability. Multi-atlas segmentation (MAS), while less accurate than DCNN in many applications, tends to generalize well to unseen datasets with different characteristics from the training dataset. Several groups have attempted to integrate the power of DCNN to learn complex data representations and the robustness of MAS to changes in image characteristics. However, these studies primarily focused on replacing individual components of MAS with DCNN models and reported marginal improvements in accuracy. In this study we describe and evaluate a 3D end-to-end hybrid MAS and DCNN segmentation pipeline, called Deep Label Fusion (DLF). The DLF pipeline consists of two main components with learnable weights, including a weighted voting subnet that mimics the MAS algorithm and a fine-tuning subnet that corrects residual segmentation errors to improve final segmentation accuracy. We evaluate DLF on five datasets that represent a diversity of anatomical structures (medial temporal lobe subregions and lumbar vertebrae) and imaging modalities (multi-modality, multi-field-strength MRI and Computational Tomography). These experiments show that DLF achieves comparable segmentation accuracy to nnU-Net (Isensee et al., 2020), the state-of-the-art DCNN pipeline, when evaluated on a dataset with similar characteristics to the training datasets, while outperforming nnU-Net on tasks that involve generalization to datasets with different characteristics (different MRI field strength or different patient population). DLF is also shown to consistently improve upon conventional MAS methods. In addition, a modality augmentation strategy tailored for multimodal imaging is proposed and demonstrated to be beneficial in improving the segmentation accuracy of learning-based methods, including DLF and DCNN, in missing data scenarios in test time as well as increasing the interpretability of the contribution of each individual modality.

Self-triggered fluorescent metal-organic framework mimic enzyme for competitive immunoassay of hypoglycemic drug in functional tea.

Colorimetric or fluorescent biosensors based on mimic enzymes have come into the spotlight in virtue of their visual detection. In traditional visual sensors, fluorescent-changing or color-changing substances should be introduced for the catalytic reaction with mimic enzymes. Herein, a mimic enzyme (Au@Fe-MIL-88B) with self-triggered fluorescent property was prepared. By incorporating Au nanoparticles (Au NPs) in Fe-MIL-88B, a higher peroxidase activity of Au@Fe-MIL-88B was monitored due to the synergistic effect between Au NPs and Fe-MIL-88B. Besides, Au NPs can change the valence of Fe ion in metal organic framework (MOF), thus lower background fluorescence was discovered, but the addition of H2O2 can trigger the self-fluorescence of Au@Fe-MIL-88B. By using Au@Fe-MIL-88B as a label to anchor secondary antibody, a competitive immunosensor based on fluorescence and photoelectrochemistry was constructed for the immunoassay of rosiglitazone (RSG), a kind of hypoglycemic drug. Finally, a portable instrument was homemade for the on-site and convenient detection of RSG in functional tea. This self-triggered fluorescent MOF may provide a possible route to design biosensors for the detection of hazardous materials.

Fully Automated Placental Volume Quantification From 3D Ultrasound for Prediction of Small-for-Gestational-Age Infants.

OBJECTIVES: Early placental volume (PV) has been associated with small-for-gestational-age infants born under the 10th/5th centiles (SGA10/SGA5). Manual or semiautomated PV quantification from 3D ultrasound (3DUS) is time intensive, limiting its incorporation into clinical care. We devised a novel convolutional neural network (CNN) pipeline for fully automated placenta segmentation from 3DUS images, exploring the association between the calculated PV and SGA. METHODS: Volumes of 3DUS obtained from singleton pregnancies at 11-14 weeks' gestation were automatically segmented by our CNN pipeline trained and tested on 99/25 images, combining two 2D and one 3D models with downsampling/upsampling architecture. The PVs derived from the automated segmentations (PVCNN ) were used to train multivariable logistic-regression classifiers for SGA10/SGA5. The test performance for predicting SGA was compared to PVs obtained via the semiautomated VOCAL (GE-Healthcare) method (PVVOCAL ). RESULTS: We included 442 subjects with 37 (8.4%) and 18 (4.1%) SGA10/SGA5 infants, respectively. Our segmentation pipeline achieved a mean Dice score of 0.88 on an independent test-set. Adjusted models including PVCNN or PVVOCAL were similarly predictive of SGA10 (area under curve [AUC]: PVCNN  = 0.780, PVVOCAL  = 0.768). The addition of PVCNN to a clinical model without any PV included (AUC = 0.725) yielded statistically significant improvement in AUC (P < .05); whereas PVVOCAL did not (P = .105). Moreover, when predicting SGA5, including the PVCNN (0.897) brought statistically significant improvement over both the clinical model (0.839, P = .015) and the PVVOCAL model (0.870, P = .039). CONCLUSIONS: First trimester PV measurements derived from our CNN segmentation pipeline are significantly associated with future SGA. This fully automated tool enables the incorporation of including placental volumetric biometry into the bedside clinical evaluation as part of a multivariable prediction model for risk stratification and patient counseling.

DeepAtrophy: Teaching a neural network to detect progressive changes in longitudinal MRI of the hippocampal region in Alzheimer's disease.

Measures of change in hippocampal volume derived from longitudinal MRI are a well-studied biomarker of disease progression in Alzheimer's disease (AD) and are used in clinical trials to track therapeutic efficacy of disease-modifying treatments. However, longitudinal MRI change measures based on deformable registration can be confounded by MRI artifacts, resulting in over-estimation or underestimation of hippocampal atrophy. For example, the deformation-based-morphometry method ALOHA (Das et al., 2012) finds an increase in hippocampal volume in a substantial proportion of longitudinal scan pairs from the Alzheimer's Disease Neuroimaging Initiative (ADNI) study, unexpected, given that the hippocampal gray matter is lost with age and disease progression. We propose an alternative approach to quantify disease progression in the hippocampal region: to train a deep learning network (called DeepAtrophy) to infer temporal information from longitudinal scan pairs. The underlying assumption is that by learning to derive time-related information from scan pairs, the network implicitly learns to detect progressive changes that are related to aging and disease progression. Our network is trained using two categorical loss functions: one that measures the network's ability to correctly order two scans from the same subject, input in arbitrary order; and another that measures the ability to correctly infer the ratio of inter-scan intervals between two pairs of same-subject input scans. When applied to longitudinal MRI scan pairs from subjects unseen during training, DeepAtrophy achieves greater accuracy in scan temporal ordering and interscan interval inference tasks than ALOHA (88.5% vs. 75.5% and 81.1% vs. 75.0%, respectively). A scalar measure of time-related change in a subject level derived from DeepAtrophy is then examined as a biomarker of disease progression in the context of AD clinical trials. We find that this measure performs on par with ALOHA in discriminating groups of individuals at different stages of the AD continuum. Overall, our results suggest that using deep learning to infer temporal information from longitudinal MRI of the hippocampal region has good potential as a biomarker of disease progression, and hints that combining this approach with conventional deformation-based morphometry algorithms may lead to improved biomarkers in the future.

Three-dimensional mapping of neurofibrillary tangle burden in the human medial temporal lobe.

Tau protein neurofibrillary tangles are closely linked to neuronal/synaptic loss and cognitive decline in Alzheimer's disease and related dementias. Our knowledge of the pattern of neurofibrillary tangle progression in the human brain, critical to the development of imaging biomarkers and interpretation of in vivo imaging studies in Alzheimer's disease, is based on conventional two-dimensional histology studies that only sample the brain sparsely. To address this limitation, ex vivo MRI and dense serial histological imaging in 18 human medial temporal lobe specimens (age 75.3 ± 11.4 years, range 45 to 93) were used to construct three-dimensional quantitative maps of neurofibrillary tangle burden in the medial temporal lobe at individual and group levels. Group-level maps were obtained in the space of an in vivo brain template, and neurofibrillary tangles were measured in specific anatomical regions defined in this template. Three-dimensional maps of neurofibrillary tangle burden revealed significant variation along the anterior-posterior axis. While early neurofibrillary tangle pathology is thought to be confined to the transentorhinal region, we found similar levels of burden in this region and other medial temporal lobe subregions, including amygdala, temporopolar cortex, and subiculum/cornu ammonis 1 hippocampal subfields. Overall, the three-dimensional maps of neurofibrillary tangle burden presented here provide more complete information about the distribution of this neurodegenerative pathology in the region of the cortex where it first emerges in Alzheimer's disease, and may help inform the field about the patterns of pathology spread, as well as support development and validation of neuroimaging biomarkers.

Retinal neovascularization induced by mutant Vldlr gene inhibited in an inherited retinitis pigmentosa mouse model: an in-vivo study.

AIM: To explore whether the retinal neovascularization (NV) in a genetic mutant mice model could be ameliorated in an inherited retinitis pigmentosa (RP) mouse, which would help to elucidate the possible mechanism and prevention of retinal NV diseases in clinic. METHODS: The Vldlr -/- mice, the genetic mutant mouse model of retinal NV caused by the homozygous mutation of Vldlr gene, with the rd1 mice, the inherited RP mouse caused by homozygous mutation of Pde6b gene were bred. Intercrossing of the above two mice led to the birth of the F1 hybrids, further inbreeding of which gave birth to the F2 offspring. The ocular genotypes and phenotypes of the mice from all generations were examined, with the F2 offspring grouped according to the genotypes. RESULTS: The rd1 mice exhibited the RP phenotype of outer retinal degeneration and loss of retinal function. The Vldlr -/- mice exhibited the phenotype of retinal NV obviously shown by the fundus fluorescein angiography. The F1 hydrides, with the heterozygote genotype, exhibited no phenotypes of RP or retinal NV. The F2 offspring with homozygous genotypes were grouped into four subgroups. They were the F2-I mice with the wild-type Pde6b and Vldlr genes (Pde6b+/+ -Vldlr+/+ ), which had normal ocular phenotypes; the F2-II mice with homozygous mutant Vldlr gene (Pde6b+/+ -Vldlr-/- ), which exhibited the retinal NV phenotype; the F2-III mice with homozygous mutant Pde6b gene (Pde6b-/- -Vldlr+/+ ), which exhibited the RP phenotype. Specifically, the F2-IV mice with homozygous mutant Vldlr and Pde6b gene (Pde6b-/- -Vldlr-/- ) showed only the RP phenotype, without the signs of retinal NV. CONCLUSION: The retinal NV can be inhibited by the RP phenotype, which implies the role of a hyperoxic state in treating retinal NV diseases.

Mortality associated with third generation cephalosporin-resistance in Enterobacteriaceae infections: a multicenter cohort study in Southern China.

Background: Emerging third-generation cephalosporin-resistant Enterobacteriaceae (3GCR-EB) pose global healthcare concern. This study assessed the in-hospital mortality attributed to 3GCR-EB.Methods: The study cohort comprised inpatients with community-onset or healthcare-associated infection caused by Enterobacteriaceae in three tertiary-care public hospitals in 2017. In-hospital mortality was compared between 3GCR-EB infected patients and third-generation cephalosporin-susceptible Enterobacteriaceae (3GCS-EB) infected patients using competing risk survival models.Results: Of 2,343 study patients (median age 60 years; 45.2% male), 1,481 (63.2%) had 3GCS-EB and 862 (36.8%) 3GCR-EB infection. 494 (57.0%) 3GCR-EB isolates were co-resistant to fluoroquinolones and 15 (1.7%) to carbapenems. In-hospital mortality was similar in 3GCS-EB and 3GCR-EB infections (2.4% vs. 2.8%; p = 0.601). No increase in the hazard of in-hospital mortality was detected for 3GCR-EB compared to 3GCS-EB infection (sub-distribution hazard ratio [HR] 0.80; 95%CI, 0.41-1.55) adjusting for patient age, sex, intensive care admission, origin of infection and site of infection. Analysis of cause-specific hazards showed that 3GCR-EB infections significantly decreased the daily rate of hospital discharge (cause-specific HR = 0.84; 95%CI, 0.76-0.92) leading to lengthier hospitalizations.Conclusion: 3GCR-EB infection per se was not associated with increased in-hospital mortality in this study, but placed significant healthcare burden by increasing the length of hospitalization.

The evidence for interventions in early childhood allergy prevention - towards a living systematic review: protocol.

Background: Research in early childhood allergy prevention (ECAP) is flourishing and new intervention strategies have proven to be promising. Due to the dynamic nature of ECAP, gaps between what is known and how guidelines inform practice are likely. A living systematic review (LSR) can narrow this gap by incorporating new evidence as it becomes available. No efficacy comparisons across various ECAP interventions for similar outcomes have been carried out. Networks of randomised clinical trials can be evaluated in the context of a network meta-analysis (NMA). We aim to establish a LSR on the efficacy and safety of any intervention investigated in randomised controlled trials (RCT) to prevent the occurrence of allergic sensitisation (AS), symptoms or diagnoses of allergic diseases in infancy and early childhood (0-3 years). Methods: A baseline SR will synthesise the evidence from existing SRs of RCTs as well as RCTs not yet considered in these. After completion of the baseline SR we propose to conduct a LSR. Using this methodology, we aim to undertake constant evidence surveillance, three-monthly search updates, and review updates every three months, should new evidence emerge. Conclusions: The ECAP evidence landscape has undergone dramatic transformations and this process is likely to continue. As a response to this, a LSR offers the potential to allow more timely synthesis of new evidence as it emerges. Long gaps between updates of SRs makes it harder for guidelines and recommendations to be up to date. Users of information, such as parents, may be confused if they encounter new evidence that is not part of a trusted guideline. A LSR approach allows us to continuously search the literature and update the evidence-base of existing ECAP interventions resulting in a decreased timespan from evidence accrual to informing clinical practice.

COVID-19 in Shanghai: IPC Policy Exploration in Support of Work Resumption Through System Dynamics Modeling.

PURPOSE: It is unclear how and to what extent various infection prevention and control (IPC) policies affect the spread of an epidemic during work resumption. In order to assess the impact of IPC policies, this research addresses the results of a policy simulation in Shanghai, China, which estimates the transmission dynamics of COVID-19 under various IPC policies and offers evidence-based outcomes of work resumption policies for the world. MATERIALS AND METHODS: This simulation research is based on a system dynamics (SD) model that integrates IPC work resumption policies implemented in Shanghai into the classical susceptible-exposed-infected-removed (SEIR) epidemiological model. Input data were obtained from official websites, the Baidu migration index and published literature. The SD model was validated by comparing results with real-world data. RESULTS: The simulations show that a non-quarantined and non-staged approach to work resumption (Policy 1) would bring a small secondary outbreak of COVID-19. The quarantined but non-staged approach (Policy 2) and the non-quarantined but staged approach (Policy 3) would not bring a secondary outbreak of COVID-19. However, they both would generate more newly confirmed cases than the staged and quarantined approach (Policy 4). Moreover, the 14-day quarantine policy alone appears to be more effective in reducing transmission risk than the staged work resumption policy alone. The combined staged and quarantined IPC policy led to the fewest confirmed cases caused by work resumption in Shanghai, and the spread of COVID-19 stopped (ie, the number of newly confirmed cases reduced to zero) at the earliest date. CONCLUSION: Conservative IPC policies can prevent a second outbreak of COVID-19 during work resumption. The dynamic systems model designed in this study can serve as a tool to test various IPC work resumption policies, facilitating decision-making in responses to combating the COVID-19 pandemic.

Artificial Intelligence System Approaching Neuroradiologist-level Differential Diagnosis Accuracy at Brain MRI.

Background Although artificial intelligence (AI) shows promise across many aspects of radiology, the use of AI to create differential diagnoses for rare and common diseases at brain MRI has not been demonstrated. Purpose To evaluate an AI system for generation of differential diagnoses at brain MRI compared with radiologists. Materials and Methods This retrospective study tested performance of an AI system for probabilistic diagnosis in patients with 19 common and rare diagnoses at brain MRI acquired between January 2008 and January 2018. The AI system combines data-driven and domain-expertise methodologies, including deep learning and Bayesian networks. First, lesions were detected by using deep learning. Then, 18 quantitative imaging features were extracted by using atlas-based coregistration and segmentation. Third, these image features were combined with five clinical features by using Bayesian inference to develop probability-ranked differential diagnoses. Quantitative feature extraction algorithms and conditional probabilities were fine-tuned on a training set of 86 patients (mean age, 49 years ± 16 [standard deviation]; 53 women). Accuracy was compared with radiology residents, general radiologists, neuroradiology fellows, and academic neuroradiologists by using accuracy of top one, top two, and top three differential diagnoses in 92 independent test set patients (mean age, 47 years ± 18; 52 women). Results For accuracy of top three differential diagnoses, the AI system (91% correct) performed similarly to academic neuroradiologists (86% correct; P = .20), and better than radiology residents (56%; P < .001), general radiologists (57%; P < .001), and neuroradiology fellows (77%; P = .003). The performance of the AI system was not affected by disease prevalence (93% accuracy for common vs 85% for rare diseases; P = .26). Radiologists were more accurate at diagnosing common versus rare diagnoses (78% vs 47% across all radiologists; P < .001). Conclusion An artificial intelligence system for brain MRI approached overall top one, top two, and top three differential diagnoses accuracy of neuroradiologists and exceeded that of less-specialized radiologists. © RSNA, 2020 Online supplemental material is available for this article. See also the editorial by Zaharchuk in this issue.