OBJECTIVE: To propose a convolutional neural network (EmbNet) for automatic pulmonary embolism detection on computed tomography pulmonary angiogram (CTPA) scans and to assess its diagnostic performance.
METHODS: 305 consecutive CTPA scans between January 2019 and December 2021 were enrolled in this study (142 for training, 163 for internal validation), and 250 CTPA scans from a public dataset were used for external validation. The framework comprised a preprocessing step to segment the pulmonary vessels and the EmbNet to detect emboli. Emboli were divided into three location-based subgroups for detailed evaluation: central arteries, lobar branches, and peripheral regions. Ground truth was established by three radiologists.
RESULTS: The EmbNet\'s per-scan level sensitivity, specificity, positive predictive value (PPV), and negative predictive value were 90.9%, 75.4%, 48.4%, and 97.0% (internal validation) and 88.0%, 70.5%, 42.7%, and 95.9% (external validation). At the per-embolus level, the overall sensitivity and PPV of the EmbNet were 86.0% and 61.3% (internal validation), and 83.5% and 57.5% (external validation). The sensitivity and PPV of central emboli were 89.7% and 52.0% (internal validation), and 94.4% and 43.0% (external validation); of lobar emboli were 95.2% and 76.9% (internal validation), and 93.5% and 72.5% (external validation); and of peripheral emboli were 82.6% and 61.7% (internal validation), and 80.2% and 59.4% (external validation). The average false positive rate was 0.45 false emboli per scan (internal validation) and 0.69 false emboli per scan (external validation).
CONCLUSIONS: The EmbNet provides high sensitivity across embolus locations, suggesting its potential utility for initial screening in clinical practice.

BACKGROUND: ICU readmissions and post-discharge mortality pose significant challenges. Previous studies used EHRs and machine learning models, but mostly focused on structured data. Nursing records contain crucial unstructured information, but their utilization is challenging. Natural language processing (NLP) can extract structured features from clinical text. This study proposes the Crucial Nursing Description Extractor (CNDE) to predict post-ICU discharge mortality rates and identify high-risk patients for unplanned readmission by analyzing electronic nursing records.
OBJECTIVE: Developed a deep neural network (NurnaNet) with the ability to perceive nursing records, combined with a bio-clinical medicine pre-trained language model (BioClinicalBERT) to analyze the electronic health records (EHRs) in the MIMIC III dataset to predict the death of patients within six month and two year risk.
METHODS: A cohort and system development design was used.
METHODS: Based on data extracted from MIMIC-III, a database of critically ill in the US between 2001 and 2012, the results were analyzed.
METHODS: We calculated patients\' age using admission time and date of birth information from the MIMIC dataset. Patients under 18 or over 89 years old, or who died in the hospital, were excluded. We analyzed 16,973 nursing records from patients\' ICU stays.
METHODS: We have developed a technology called the Crucial Nursing Description Extractor (CNDE), which extracts key content from text. We use the logarithmic likelihood ratio to extract keywords and combine BioClinicalBERT. We predict the survival of discharged patients after six months and two years and evaluate the performance of the model using precision, recall, the F1-score, the receiver operating characteristic curve (ROC curve), the area under the curve (AUC), and the precision-recall curve (PR curve).
RESULTS: The research findings indicate that NurnaNet achieved good F1-scores (0.67030, 0.70874) within six months and two years. Compared to using BioClinicalBERT alone, there was an improvement in performance of 2.05 % and 1.08 % for predictions within six months and two years, respectively.
CONCLUSIONS: CNDE can effectively reduce long-form records and extract key content. NurnaNet has a good F1-score in analyzing the data of nursing records, which helps to identify the risk of death of patients after leaving the hospital and adjust the regular follow-up and treatment plan of relevant medical care as soon as possible.

The purpose was to investigate relationships of cumulative load and cartilage turnover biomarkers with 2-year changes in cartilage in knee osteoarthritis. From participants with Kellgren-Lawrence (KL) grades of 1 to 3, cartilage thickness and transverse relaxation time (T2) were computed from 24-month (baseline) and 48-month magnetic resonance images. Cumulative load was the interaction term of the Physical Activity Scale for the Elderly (PASE) and body mass index (BMI). Serum cartilage oligomeric matrix protein (COMP) and the nitrated form of type II collagen (Coll2-1 NO2) were collected at baseline. Multiple regressions (adjusted for baseline age, KL grade, cartilage measures, pain, comorbidity) evaluated the relationships of cumulative load and biomarkers with 2-year changes. In 406 participants (63.7 (8.7) years), interactions of biomarkers with cumulative load weakly predicted 2-year cartilage changes: (i) COMP × cumulative load explained medial tibia thickness change (R2 increased 0.062 to 0.087, p < 0.001); (ii) Coll2-1 NO2 × cumulative load explained central medial femoral T2 change (R2 increased 0.177 to 0.210, p < 0.001); and (iii) Coll2-1 NO2 × cumulative load explained lateral tibia T2 change (R2 increased 0.166 to 0.188, p < 0.001). Moderate COMP or Coll2-1 NO2 at baseline appeared protective. High COMP or Coll2-1 NO2, particularly with high BMI and low PASE, associated with worsening cartilage. Moderate serum concentrations of cartilage turnover biomarkers, at high and low physical activity, associated with maintained cartilage outcomes over 2 years. In conclusion, high concentrations of cartilage turnover biomarkers, particularly with high BMI and low physical activity, associated with knee cartilage thinning and increasing T2 over 2 years. Key Points • Higher quality cartilage may be better able to tolerate a larger cumulative load than poor quality cartilage. • Among participants enrolled in the Osteoarthritis Initiative Biomarkers Consortium Project, a representation of cumulative load exposure and its interaction with cartilage turnover biomarkers were weakly related with 2-year change in knee cartilage. • These findings suggest that cartilage turnover is a factor that modifies the relationship between loading exposure and cartilage loss in knee OA.

Advancements in diagnostic methods and surgical techniques for keratoconus (KC) have increased non-invasive treatment options. Successful surgical planning for KC involves a combination of clinical science, empirical evidence, and surgical expertise. Assessment of disease progression is crucial, and halting the progression should be the focus if it is progressive. While surgeons used to rely on experience alone to decide the surgical method, comparing the network of primary factors, such as visual acuity, across studies can help them choose the most appropriate treatments for each patient and achieve optimal outcomes. Meticulous tabulation methods facilitate interpretation, highlighting the importance of selecting the correct surgical and rehabilitation approach based on each patient\'s condition and stage of the disease. We detail the outcomes of a comprehensive network meta-analysis comparing the effectiveness of various combined therapeutic refractive treatments for KC at identical stages of the disease, spanning 4 distinct follow-up intervals. Additionally, the comprehensive analysis suggests that for corneas with optimal best corrected visual acuity (BCVA) preoperatively (classified as regular), combining phakic intraocular lenses with intracorneal ring segments (ICRS) and corneal cross-linking (CXL) could offer the best therapeutic approach provided the disease stage does not exceed stage 3. For irregular corneas, although initial follow-ups show a significant difference in BCVA with surface ablation, longer-term follow-ups recommend combining surface ablation with ICRS and CXL, especially at higher stages.

This paper investigates the integration of augmented reality (AR) technology into English translation teaching for college students, emphasizing the pivotal role of innovative teaching methods in enhancing students\' translation skills and learning experiences. To address the issue of insufficient interest in English translation teaching, the paper initially assesses the purpose and significance of learning English translation through a questionnaire survey, elucidating challenges encountered in English language acquisition. Subsequently, adhering to AR principles, a teaching demonstration platform rooted in AR technology is conceived and developed, intricately aligned with English translation instruction. The platform serves as a solution to issues in English learning, such as inadequate course comprehension, low utilization of teaching resources, and instructors\' lack of experience. The research culminates in the analysis of survey results, wherein the quantitative disparities in translation ability between students utilizing the research platform and those subjected to traditional teaching methods are examined. The findings underscore the positive impact of the AR-based research platform on improving students\' translation proficiency. The AR platform heightens learners\' engagement in the learning process, contributes to constructing a robust knowledge framework, and enhances overall learning outcomes. The platform offers educators opportunities to optimize experimental courses and elevate teaching standards. The paper\'s outcomes present novel pedagogical scenarios for learners, propose technical solutions for other technical disciplines and furnish a theoretical foundation and application model for a new generation of experimental demonstration platforms.

Studies have shown that the digital divide affects students\' educational achievement across racial and ethnic groups. In light of this, the study investigates the effect of technology access at home on student learning hours during the COVID-19 pandemic and across racial and ethnic groups in the U.S. The Household Pulse Surveys (HPS), conducted by the United States Census Bureau and administered from August 19, 2020, to March 29, 2021, were used for the analysis. We compute a composite index of technology access using the principal component analysis (PCA). And for the empirical model, the study employed a Tobit regression model. The result shows that the estimated index of technology access based on PCA for the whole sample is about 0.92, indicating a higher level of access. However, the breakdown by race/ethnicity shows an average of about 0.93, 0.89, 0.90, 0.94, and 0.89 for students representing White, Black, Hispanic, Asia, and other races, respectively. This means the intensity at which households in the sample have access to technology is higher among the Asian and White students, followed by Hispanic, Black, and other races in that order. The estimated effect of technology access on the student learning hours during COVID-19 based on the Tobit regression model shows about a 3.1 unit points increase over the whole sample. And further analysis reveals variation at which access to the technology impacts learning hours across race and ethnicity groups. For example, we find that access to technology significantly increased learning hours by about 3.5, 1.6, 2.2, and 3.4 unit points among White, Black, Hispanic, and Asian students, respectively. The observed differing effect of access to technology on learning hours further highlights the racial disparities in American society\'s digital divide, which reveal how access to technology disproportionately impacts student learning hours during the COVID-19 pandemic across race and ethnicity.

BACKGROUND: The coronavirus disease 2019 (COVID-19) pandemic continues to pose significant challenges to the public health sector, including that of the United Arab Emirates (UAE). The objective of this study was to assess the efficiency and accuracy of various deep-learning models in forecasting COVID-19 cases within the UAE, thereby aiding the nation\'s public health authorities in informed decision-making.
METHODS: This study utilized a comprehensive dataset encompassing confirmed COVID-19 cases, demographic statistics, and socioeconomic indicators. Several advanced deep learning models, including long short-term memory (LSTM), bidirectional LSTM, convolutional neural network (CNN), CNN-LSTM, multilayer perceptron, and recurrent neural network (RNN) models, were trained and evaluated. Bayesian optimization was also implemented to fine-tune these models.
RESULTS: The evaluation framework revealed that each model exhibited different levels of predictive accuracy and precision. Specifically, the RNN model outperformed the other architectures even without optimization. Comprehensive predictive and perspective analytics were conducted to scrutinize the COVID-19 dataset.
CONCLUSIONS: This study transcends academic boundaries by offering critical insights that enable public health authorities in the UAE to deploy targeted data-driven interventions. The RNN model, which was identified as the most reliable and accurate for this specific context, can significantly influence public health decisions. Moreover, the broader implications of this research validate the capability of deep learning techniques in handling complex datasets, thus offering the transformative potential for predictive accuracy in the public health and healthcare sectors.

OBJECTIVE: Use a conference challenge format to compare machine learning-based gamma-aminobutyric acid (GABA)-edited magnetic resonance spectroscopy (MRS) reconstruction models using one-quarter of the transients typically acquired during a complete scan.
METHODS: There were three tracks: Track 1: simulated data, Track 2: identical acquisition parameters with in vivo data, and Track 3: different acquisition parameters with in vivo data. The mean squared error, signal-to-noise ratio, linewidth, and a proposed shape score metric were used to quantify model performance. Challenge organizers provided open access to a baseline model, simulated noise-free data, guides for adding synthetic noise, and in vivo data.
RESULTS: Three submissions were compared. A covariance matrix convolutional neural network model was most successful for Track 1. A vision transformer model operating on a spectrogram data representation was most successful for Tracks 2 and 3. Deep learning (DL) reconstructions with 80 transients achieved equivalent or better SNR, linewidth and fit error compared to conventional 320 transient reconstructions. However, some DL models optimized linewidth and SNR without actually improving overall spectral quality, indicating a need for more robust metrics.
CONCLUSIONS: DL-based reconstruction pipelines have the promise to reduce the number of transients required for GABA-edited MRS.

TA2Viewer is an open-access, web-based application and database for browsing anatomical terms and associated medical information on a computer or mobile device (https://ta2viewer.openanatomy.org/). It incorporates the official digital version of the second edition of Terminologia Anatomica (TA2) as published by the Federative International Programme for Anatomical Terminology (FIPAT), and adopted by the International Federation of Associations of Anatomists (IFAA) and other associations. It provides a dynamic and interactive view of the Latin and English nomenclatures. The organizational hierarchy of the terminology can be navigated by using a scrollable, expandable, and collapsible structured listing. Interactive search includes the official TA2 terms, synonyms, and related terms. TA2Viewer also uses TA2 term information to provide convenient access to other online resources, including Google web and image searches, PubMed, and Radiopaedia. Using cross-references from Wikidata, which were provided by the Wikipedia community, TA2Viewer offers links to Wikipedia, UBERON, UMLS, FMA, MeSH, NeuroNames, the public domain 20th edition of Gray\'s Anatomy, and other data sources. In addition, it can optionally use unofficial synonyms from Wikidata to provide multilingual term searches in hundreds of languages. By leveraging TA2, TA2Viewer provides free access to a curated anatomical nomenclature and serves as an index of online anatomical knowledge.

UNASSIGNED: New developments in artificial intelligence, particularly with promising results in early detection and management of keratoconus, have favorably altered the natural history of the disease over the last few decades. Features of artificial intelligence in different machine such as anterior segment optical coherence tomography, and femtosecond laser technique have improved safety, precision, effectiveness, and predictability of treatment modalities of keratoconus (from contact lenses to keratoplasty techniques). These options ingrained in artificial intelligence are already underway and allow ophthalmologist to approach disease in the most non-invasive way.
UNASSIGNED: This study comprehensively describes all of the treatment modalities of keratoconus considering machine learning strategies.
UNASSIGNED: A multidimensional comprehensive systematic narrative review.
UNASSIGNED: A comprehensive search was done in the five main electronic databases (PubMed, Scopus, Web of Science, Embase, and Cochrane), without language and time or type of study restrictions. Afterward, eligible articles were selected by screening the titles and abstracts based on main mesh keywords. For potentially eligible articles, the full text was also reviewed.
UNASSIGNED: Artificial intelligence demonstrates promise in keratoconus diagnosis and clinical management, spanning early detection (especially in subclinical cases), preoperative screening, postoperative ectasia prediction after keratorefractive surgery, and guiding surgical decisions. The majority of studies employed a solitary machine learning algorithm, whereas minor studies assessed multiple algorithms that evaluated the association of various keratoconus staging and management strategies. Last but not least, AI has proven effective in guiding the implantation of intracorneal ring segments in keratoconus corneas and predicting surgical outcomes.
UNASSIGNED: The efficient and widespread clinical translation of machine learning models in keratoconus management is a crucial goal of potential future approaches to better visual performance in keratoconus patients.
UNASSIGNED: The article has been registered through PROSPERO, an international database of prospectively registered systematic reviews, with the ID: CRD42022319338.
Keratoconus: from fundamentals to future Artificial intelligence has changed how we treat the eye disease keratoconus in recent years. This study examines the many keratoconus therapies available, including surgery and contact lens wear, and how artificial intelligence can improve the safety and accuracy of these procedures. We combed through numerous papers to locate this data. To achieve the best outcomes, several parameters and methods should be evaluated. According to the study, some elements from eye scans are more useful than others. The idea behind using artificial intelligence is to help patients see better and treat keratoconus more effectively.