Molecular Epidemiology and Evolution of Coxsackievirus A14.

As the proportion of non-enterovirus 71 and non-coxsackievirus A16 which proportion of composition in the hand, foot, and mouth pathogenic spectrum gradually increases worldwide, the attention paid to other enteroviruses has increased. As a member of the species enterovirus A, coxsackievirus A14 (CVA14) has been epidemic around the world until now since it has been isolated. However, studies on CVA14 are poor and the effective population size, evolutionary dynamics, and recombination patterns of CVA14 are not well understood. In this study, 15 CVA14 strains were isolated from HFMD patients in mainland China from 2009 to 2019, and the complete sequences of CVA14 in GenBank as research objects were analyzed. CVA14 was divided into seven genotypes A-G based on an average nucleotide difference of the full-length VP1 coding region of more than 15%. Compared with the CVA14 prototype strain, the 15 CVA14 strains showed 84.0-84.7% nucleotide identity in the complete genome and 96.9-97.6% amino acid identity in the encoding region. Phylodynamic analysis based on 15 CVA14 strains and 22 full-length VP1 sequences in GenBank showed a mean substitution rate of 5.35 × 10-3 substitutions/site/year (95% HPD: 4.03-6.89 × 10-3) and the most recent common ancestor (tMRCA) of CVA14 dates back to 1942 (95% HPD: 1930-1950). The Bayesian skyline showed that the effective population size had experienced a decrease-increase-decrease fluctuation since 2004. The phylogeographic analysis indicated two and three possible migration paths in the world and mainland China, respectively. Four recombination patterns with others of species enterovirus A were observed in 15 CVA14 strains, among which coxsackievirus A2 (CVA2), coxsackievirus A4 (CVA4), coxsackievirus A6 (CVA6), coxsackievirus A8 (CVA8), and coxsackievirus A12 (CVA12) may act as recombinant donors in multiple regions. This study has filled the gap in the molecular epidemiological characteristics of CVA14, enriched the global CVA14 sequence database, and laid the epidemiological foundation for the future study of CVA14 worldwide.

A brain tumor computer-aided diagnosis method with automatic lesion segmentation and ensemble decision strategy.

Objectives: Gliomas and brain metastases (Mets) are the most common brain malignancies. The treatment strategy and clinical prognosis of patients are different, requiring accurate diagnosis of tumor types. However, the traditional radiomics diagnostic pipeline requires manual annotation and lacks integrated methods for segmentation and classification. To improve the diagnosis process, a gliomas and Mets computer-aided diagnosis method with automatic lesion segmentation and ensemble decision strategy on multi-center datasets was proposed. Methods: Overall, 1,022 high-grade gliomas and 775 Mets patients' preoperative MR images were adopted in the study, including contrast-enhanced T1-weighted (T1-CE) and T2-fluid attenuated inversion recovery (T2-flair) sequences from three hospitals. Two segmentation models trained on the gliomas and Mets datasets, respectively, were used to automatically segment tumors. Multiple radiomics features were extracted after automatic segmentation. Several machine learning classifiers were used to measure the impact of feature selection methods. A weight soft voting (RSV) model and ensemble decision strategy based on prior knowledge (EDPK) were introduced in the radiomics pipeline. Accuracy, sensitivity, specificity, and the area under the receiver operating characteristic curve (AUC) were used to evaluate the classification performance. Results: The proposed pipeline improved the diagnosis of gliomas and Mets with ACC reaching 0.8950 and AUC reaching 0.9585 after automatic lesion segmentation, which was higher than those of the traditional radiomics pipeline (ACC:0.8850, AUC:0.9450). Conclusion: The proposed model accurately classified gliomas and Mets patients using MRI radiomics. The novel pipeline showed great potential in diagnosing gliomas and Mets with high generalizability and interpretability.

Genetic characterization and molecular evolution of type 3 vaccine-derived polioviruses from an immunodeficient patient in China.

In 2013, a case of immunodeficiency vaccine-derived poliovirus (iVDPV) was identified in Jiangxi Province, China. In this study, we purified 14 type 3 original viral isolates from this case and characterized the molecular evolution of these iVDPVs for 298 days. Genetic variants were found in most of the original viral isolates, with complex genetic and evolutionary relationships among the variants. A phylogenetic tree constructed based on the P1 region showed that these iVDPVs were classified into lineage A and B. The dominant lineage B represents a major trend in virus evolution. The nucleotide substitution rate at the third codon position (3CP) estimated by the BEAST program was 1.76 × 10-2 substitutions/site/year (95% HPD: 1.23-2.39 × 10-2). The initial OPV dose was given dating back to March 2013, which was close to the time of the last OPV vaccination, suggesting that OPV infection may have originated with the last dose of vaccine. Recombinant analysis showed that these iVDPVs were inter-vaccine recombinants with two recombination patterns, S3/S2/S1 and S3/S2/S3/S2/S1. Whole genome sequence analysis revealed that key nucleotide sites (C472U, C2034U, U2493C) associated with the attenuated phenotype of Sabin 3 have been replaced. Temperature sensitivity test showed that all tested strains were temperature-sensitive, except for the variant Day11-5. Interestingly, we observed that the variant Day11-5 temperature resistance properties may be associated with the Lys to Met substitution at the VP2-162 site. Serological test and whole genome sequence analysis showed that the seropositivity rate remained high, and mutations in the antigenic sites did not significantly alter neutralization ability.

Artificial Intelligence-Assisted Left Ventricular Diastolic Function Assessment and Grading: Multiview Versus Single View.

BACKGROUND: Clinical assessment and grading of left ventricular diastolic function (LVDF) requires quantification of multiple echocardiographic parameters interpreted according to established guidelines, which depends on experienced clinicians and is time consuming. The aim of this study was to develop an artificial intelligence (AI)-assisted system to facilitate the clinical assessment of LVDF. METHODS: In total, 1,304 studies (33,404 images) were used to develop a view classification model to select six specific views required for LVDF assessment. A total of 2,238 studies (16,794 two-dimensional [2D] images and 2,198 Doppler images) to develop 2D and Doppler segmentation models, respectively, to quantify key metrics of diastolic function. We used 2,150 studies with definite LVDF labels determined by two experts to train single-view classification models by AI interpretation of strain metrics or video. The accuracy and efficiency of these models were tested in an external data set of 388 prospective studies. RESULTS: The view classification model identified views required for LVDF assessment with good sensitivity (>0.9), and view segmentation models successfully outlined key regions of these views with intersection over union > 0.8 in the internal validation data set. In the external test data set of 388 cases, AI quantification of 2D and Doppler images showed narrow limits of agreement compared with the two experts (e.g., left ventricular ejection fraction, -12.02% to 9.17%; E/e' ratio, -3.04 to 2.67). These metrics were used to detect LV diastolic dysfunction (DD) and grade DD with accuracy of 0.9 and 0.92, respectively. Concerning the single-view method, the overall accuracy of DD detection was 0.83 and 0.75 by strain-based and video-based models, and the accuracy of DD grading was 0.85 and 0.8, respectively. These models could achieve diagnosis and grading of LVDD in a few seconds, greatly saving time and labor. CONCLUSION: AI models successfully achieved LVDF assessment and grading that compared favorably with human experts reading according to guideline-based algorithms. Moreover, when Doppler variables were missing, AI models could provide assessment by interpreting 2D strain metrics or videos from a single view. These models have the potential to save labor and cost and to facilitate work flow of clinical LVDF assessment.

Examining Factors That Influence Learner Retention in MOOCs During the COVID-19 Pandemic Time.

Massive Open Online Courses have become a frequent platform for learners to acquire knowledge. This study aims to explore multiple factors influencing learner retention in MOOCs during the COVID-19 pandemic. To address this, we collected quantitative and qualitative data from questionnaires and qualitative data from interviews and then analyzed them through the Partial Least Square-Structural Equation Modeling to test 14 research hypotheses. The proposed research model and research hypotheses are empirically tested with 243 participants across the world. According to the results, support is found for all of the 14 research hypotheses. We confirmed 14 factors influencing learner retention in MOOCs. The result is beneficial for designers and manufacturers of MOOCs to improve the quality of the products and facilitate online or blended learning during this special time. It could also help students improve their learning experiences. Future research could examine influencing factors of learner retention in MOOCs with interdisciplinary cooperation.

A Two-Stage End-to-End Deep Learning Framework for Pathologic Examination in Skin Tumor Diagnosis.

Neurofibromas (NFs), Bowen disease (BD), and seborrheic keratosis (SK) are common skin tumors. Pathologic examination is the gold standard for diagnosis of these tumors. Current pathologic diagnosis is primarily based on microscopic observation, which is laborious and time-consuming. With digitization, artificial intelligence can be used to improve the efficiency of pathologic diagnosis. This research aims to develop an end-to-end extendable framework for the diagnosis of skin tumor based on pathologic slide images. NF, BD, and SK were selected as target skin tumors. A two-stage skin cancer diagnosis framework is proposed in this article, which consists of two parts: patches-wise diagnosis, and slide-wise diagnosis. Patches-wise diagnosis compares different convolutional neural networks to extract features and distinguish categories from patches generated in whole slide images. Slide-wise diagnosis combines attention graph gated network model prediction with post-processing algorithm. This approach can fuse information from feature-embedding learning and domain knowledge to draw conclusions. Training, validation, and testing were performed on NF, BD, SK, and negative samples. Accuracy and receiver operating characteristic curves were used to evaluate the classification performance. This study investigated the feasibility of skin tumor diagnosis from pathologic images and may be the first instance of applying deep learning to address these three types of tumor diagnoses in skin pathology.

Qualitative and quantitative analyses of artificial intelligence ethics in education using VOSviewer and CitNetExplorer.

The new decade has been witnessing the wide acceptance of artificial intelligence (AI) in education, followed by serious concerns about its ethics. This study examined the essence and principles of AI ethics used in education, as well as the bibliometric analysis of AI ethics for educational purposes. The clustering techniques of VOSviewer (n = 880) led the author to reveal the top 10 authors, sources, organizations, and countries in the research of AI ethics in education. The analysis of clustering solution through CitNetExplorer (n = 841) concluded that the essence of AI ethics for educational purposes included deontology, utilitarianism, and virtue, while the principles of AI ethics in education included transparency, justice, fairness, equity, non-maleficence, responsibility, and privacy. Future research could consider the influence of AI interpretability on AI ethics in education because the ability to interpret the AI decisions could help judge whether the decision is consistent with ethical criteria.

A deep learning framework assisted echocardiography with diagnosis, lesion localization, phenogrouping heterogeneous disease, and anomaly detection.

Echocardiography is the first-line diagnostic technique for heart diseases. Although artificial intelligence techniques have made great improvements in the analysis of echocardiography, the major limitations remain to be the built neural networks are normally adapted to a few diseases and specific equipment. Here, we present an end-to-end deep learning framework named AIEchoDx that differentiates four common cardiovascular diseases (Atrial Septal Defect, Dilated Cardiomyopathy, Hypertrophic Cardiomyopathy, prior Myocardial Infarction) from normal subjects with performance comparable to that of consensus of three senior cardiologists in AUCs (99.50% vs 99.26%, 98.75% vs 92.75%, 99.57% vs 97.21%, 98.52% vs 84.20%, and 98.70% vs 89.41%), respectively. Meanwhile, AIEchoDx accurately recognizes critical lesion regions of interest along with each disease by visualizing the decision-making process. Furthermore, our analysis indicates that heterogeneous diseases, like dilated cardiomyopathy, could be classified into two phenogroups with distinct clinical characteristics. Finally, AIEchoDx performs efficiently as an anomaly detection tool when applying handheld device-produced videos. Together, AIEchoDx provides a potential diagnostic assistant tool in either cart-based echocardiography equipment or handheld echocardiography device for primary and point-of-care medical personnel with high diagnostic performance, and the application of lesion region identification and heterogeneous disease phenogrouping, which may broaden the application of artificial intelligence in echocardiography.

Echocardiography-based AI detection of regional wall motion abnormalities and quantification of cardiac function in myocardial infarction.

Objective: To compare the performance of a newly developed deep learning (DL) framework for automatic detection of regional wall motion abnormalities (RWMAs) for patients presenting with the suspicion of myocardial infarction from echocardiograms obtained with portable bedside equipment versus standard equipment. Background: Bedside echocardiography is increasingly used by emergency department setting for rapid triage of patients presenting with chest pain. However, compared to images obtained with standard equipment, lower image quality from bedside equipment can lead to improper diagnosis. To overcome these limitations, we developed an automatic workflow to process echocardiograms, including view selection, segmentation, detection of RWMAs and quantification of cardiac function that was trained and validated on image obtained from bedside and standard equipment. Methods: We collected 4,142 examinations from one hospital as training and internal testing dataset and 2,811 examinations from other hospital as the external test dataset. For data pre-processing, we adopted DL model to automatically recognize three apical views and segment the left ventricle. Detection of RWMAs was achieved with 3D convolutional neural networks (CNN). Finally, DL model automatically measured the size of cardiac chambers and left ventricular ejection fraction. Results: The view selection model identified the three apical views with an average accuracy of 96%. The segmentation model provided good agreement with manual segmentation, achieving an average Dice of 0.89. In the internal test dataset, the model detected RWMAs with AUC of 0.91 and 0.88 respectively for standard and bedside ultrasound. In the external test dataset, the AUC were 0.90 and 0.85. The automatic cardiac function measurements agreed with echocardiographic report values (e. g., mean bias is 4% for left ventricular ejection fraction). Conclusion: We present a fully automated echocardiography pipeline applicable to both standard and bedside ultrasound with various functions, including view selection, quality control, segmentation, detection of the region of wall motion abnormalities and quantification of cardiac function.

Cardiac Adaptation to Prolonged High Altitude Migration Assessed by Speckle Tracking Echocardiography.

Objective: Exposure to high altitudes represents physiological stress that leads to significant changes in cardiovascular properties. However, long-term cardiovascular adaptions to high altitude migration of lowlanders have not been described. Accordingly, we measured changes in cardiovascular properties following prolonged hypoxic exposure in acclimatized Han migrants and Tibetans. Methods: Echocardiographic features of recently adapted Han migrant (3-12 months, n = 64) and highly adapted Han migrant (5-10 years, n = 71) residence in Tibet (4,300 m) using speckle tracking echocardiography were compared to those of age-matched native Tibetans (n = 75) and Han lowlanders living at 1,400 m (n = 60). Results: Short-term acclimatized migrants showed increased estimated pulmonary artery systolic pressure (PASP) (32.6 ± 5.1 mmHg vs. 21.1 ± 4.2 mmHg, p < 0.05), enlarged right ventricles (RVs), and decreased fractional area change (FAC) with decreased RV longitudinal strain (-20 ± 2.8% vs. -25.5 ± 3.9%, p < 0.05). While left ventricular ejection fraction (LVEF) was preserved, LV diameter (41.7 ± 3.1 mm vs. 49.7 ± 4.8 mm, p < 0.05) and LV longitudinal strain (-18.8 ± 3.2% vs. -22.9 ± 3.3%, p < 0.05) decreased. Compared with recent migrants, longer-term migrants had recovered RV structure and functions with slightly improved RV and LV longitudinal strain, though still lower than lowlander controls; LV size remained small with increased mass index (68.3 ± 12.7 vs. 59.3 ± 9.6, p < 0.05). In contrast, native Tibetans had slightly increased PASP (26.1 ± 3.4 mmHg vs. 21.1 ± 4.2 mmHg, p < 0.05) with minimally altered cardiac deformation compared to lowlanders. Conclusion: Right ventricular systolic function is impaired in recent (<1 year) migrants to high altitudes but improved during the long-term dwelling. LV remodeling persists in long-term migrants (>5 years) but without impairment of LV systolic or diastolic function. In contrast, cardiac size, structure, and function of native Tibetans are more similar to those of lowland dwelling Hans.

Automated Analysis of Doppler Echocardiographic Videos as a Screening Tool for Valvular Heart Diseases.

OBJECTIVES: This study sought to develop a deep learning (DL) framework to automatically analyze echocardiographic videos for the presence of valvular heart diseases (VHDs). BACKGROUND: Although advances in DL have been applied to the interpretation of echocardiograms, such techniques have not been reported for interpretation of color Doppler videos for diagnosing VHDs. METHODS: The authors developed a 3-stage DL framework for automatic screening of echocardiographic videos for mitral stenosis (MS), mitral regurgitation (MR), aortic stenosis (AS), and aortic regurgitation (AR) that classifies echocardiographic views, detects the presence of VHDs, and, when present, quantifies key metrics related to VHD severities. The algorithm was trained (n = 1,335), validated (n = 311), and tested (n = 434) using retrospectively selected studies from 5 hospitals. A prospectively collected set of 1,374 consecutive echocardiograms served as a real-world test data set. RESULTS: Disease classification accuracy was high, with areas under the curve of 0.99 (95% CI: 0.97-0.99) for MS; 0.88 (95% CI: 0.86-0.90) for MR; 0.97 (95% CI: 0.95-0.99) for AS; and 0.90 (95% CI: 0.88-0.92) for AR in the prospective test data set. The limits of agreement (LOA) between the DL algorithm and physician estimates of metrics of valve lesion severities compared to the LOAs between 2 experienced physicians spanned from -0.60 to 0.77 cm2 vs -0.48 to 0.44 cm2 for MV area; from -0.27 to 0.25 vs -0.23 to 0.08 for MR jet area/left atrial area; from -0.86 to 0.52 m/s vs -0.48 to 0.54 m/s for peak aortic valve blood flow velocity (Vmax); from -10.6 to 9.5 mm Hg vs -10.2 to 4.9 mm Hg for average peak aortic valve gradient; and from -0.39 to 0.32 vs -0.31 to 0.32 for AR jet width/left ventricular outflow tract diameter. CONCLUSIONS: The proposed deep learning algorithm has the potential to automate and increase efficiency of the clinical workflow for screening echocardiographic images for the presence of VHDs and for quantifying metrics of disease severity.

Development and Validation of an Artificial Intelligence-Based Image Classification Method for Pathological Diagnosis in Patients With Extramammary Paget's Disease.

Extramammary Paget's disease (EMPD) is a rare, malignant cutaneous adenocarcinoma with a high recurrence rate after surgical resection. Early diagnosis of EMPD is critical as 15%-40% of cases progress into an invasive form and resulting in a dismal prognosis. However, EMPD can be a diagnostic challenge to pathologists, especially in the grassroots hospital, because of its low incidence and nonspecific clinical presentation. Although AI-enabled computer-aided diagnosis solutions have been extensively used in dermatological pathological image analysis to diagnose common skin cancers such as melanoma and basal cell carcinoma, these techniques have yet been applied to diagnose EMPD. Here, we developed and verified a deep learning method with five different deep convolutional neural networks, named ResNet34, ResNet50, MobileNetV2, GoogLeNet, and VGG16, in Asian EMPD pathological image screening to distinguish between Paget's and normal cells. We further demonstrated that the results of the proposed method are quantitative, fast, and repeatable by a retrospective single-center study. The ResNet34 model achieved the best performance with an accuracy of 95.522% in pathological images collected at a magnification of ×40. We envision this method can potentially empower grassroots pathologists' efficiency and accuracy as well as to ultimately provide better patient care.

Deep learning for digitizing highly noisy paper-based ECG records.

Electrocardiography (ECG) is essential in many heart diseases. However, some ECGs are recorded by paper, which can be highly noisy. Digitizing the paper-based ECG records into a high-quality signal is critical for further analysis. We formulated the digitization problem as a segmentation problem and proposed a deep learning method to digitize highly noisy ECG scans. Our method extracts the ECG signal in an end-to-end manner and can handle different paper record layouts. In the experiment, our model clearly extracted the ECG waveform with a Dice coefficient of 0.85 and accurately measured the common ECG parameters with more than 0.90 Pearson's correlation. We showed that the end-to-end approach with deep learning can be powerful in ECG digitization. To the best of our knowledge, we provide the first approach to digitize the least informative noisy binary ECG scans and potentially be generalized to digitize various ECG records.