Search

BackgroundMore than 79.2 million confirmed COVID-19 cases and 1.7 million deaths were caused by SARS-CoV-2; the disease was named COVID-19 by the World Health Organization. Control of the COVID-19 epidemic has become a crucial issue around the globe, but there are limited studies that investigate the global trend of the COVID-19 pandemic together with each country’s policy measures. ObjectiveWe aimed to develop an online artificial intelligence (AI) system to analyze the dynamic trend of the COVID-19 pandemic, facilitate forecasting and predictive modeling, and produce a heat map visualization of policy measures in 171 countries. MethodsThe COVID-19 Pandemic AI System (CPAIS) integrated two data sets: the data set from the Oxford COVID-19 Government Response Tracker from the Blavatnik School of Government, which is maintained by the University of Oxford, and the data set from the COVID-19 Data Repository, which was established by the Johns Hopkins University Center for Systems Science and Engineering. This study utilized four statistical and deep learning techniques for forecasting: autoregressive integrated moving average (ARIMA), feedforward neural network (FNN), multilayer perceptron (MLP) neural network, and long short-term memory (LSTM). With regard to 1-year records (ie, whole time series data), records from the last 14 days served as the validation set to evaluate the performance of the forecast, whereas earlier records served as the training set. ResultsA total of 171 countries that featured in both databases were included in the online system. The CPAIS was developed to explore variations, trends, and forecasts related to the COVID-19 pandemic across several counties. For instance, the number of confirmed monthly cases in the United States reached a local peak in July 2020 and another peak of 6,368,591 in December 2020. A dynamic heat map with policy measures depicts changes in COVID-19 measures for each country. A total of 19 measures were embedded within the three sections presented on the website, and only 4 of the 19 measures were continuous measures related to financial support or investment. Deep learning models were used to enable COVID-19 forecasting; the performances of ARIMA, FNN, and the MLP neural network were not stable because their forecast accuracy was only better than LSTM for a few countries. LSTM demonstrated the best forecast accuracy for Canada, as the root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE) were 2272.551, 1501.248, and 0.2723075, respectively. ARIMA (RMSE=317.53169; MAPE=0.4641688) and FNN (RMSE=181.29894; MAPE=0.2708482) demonstrated better performance for South Korea. ConclusionsThe CPAIS collects and summarizes information about the COVID-19 pandemic and offers data visualization and deep learning–based prediction. It might be a useful reference for predicting a serious outbreak or epidemic. Moreover, the system undergoes daily updates and includes the latest information on vaccination, which may change the dynamics of the pandemic.

Purpose: As HF progresses into advanced HF, patients experience a poor quality of life, distressing symptoms, intensive care use, social distress, and eventual hospital death. We aimed to investigate the relationship between morality and potential prognostic factors among in-patient and emergency patients with HF. Patients and Methods: A case series study: Data are collected from in-hospital and emergency care patients from 2014 to 2021, including their international classification of disease at admission, and laboratory data such as blood count, liver and renal functions, lipid profile, and other biochemistry from the hospital's electrical medical records. After a series of data pre-processing in the electronic medical record system, several machine learning models were used to evaluate predictions of HF mortality. The outcomes of those potential risk factors were visualized by different statistical analyses. Results: In total, 3871 hF patients were enrolled. Logistic regression showed that intensive care unit (ICU) history within 1 week (OR: 9.765, 95% CI: 6.65, 14.34; p-value < 0.001) and prothrombin time (OR: 1.193, 95% CI: 1.098, 1.296; < 0.001) were associated with mortality. Similar results were obtained when we analyzed the data using Cox regression instead of logistic regression. Random forest, support vector machine (SVM), Adaboost, and logistic regression had better overall performances with areas under the receiver operating characteristic curve (AUROCs) of > 0.87. Naïve Bayes was the best in terms of both specificity and precision. With ensemble learning, age, ICU history within 1 week, and respiratory rate (BF) were the top three compelling risk factors affecting mortality due to HF. To improve the explainability of the AI models, Shapley Additive Explanations methods were also conducted. Conclusion: Exploring HF mortality and its patterns related to clinical risk factors by machine learning models can help physicians make appropriate decisions when monitoring HF patients' health quality in the hospital. [ABSTRACT FROM AUTHOR]

Importance: Nasopharyngeal carcinoma (NPC) is closely linked to microorganisms, especially intra-tumoral microbiota. However, the role of commensal microbiota in NPC remains underexplored, with implications for understanding disease mechanisms. Objective: This study aims to analyze and compare the bacterial microbiota in the nasopharynx and middle meatus (MM) of individuals with NPC and those without NPC. Additionally, the study seeks to identify potential microbial biomarkers that can distinguish between NPC and non-NPC (nNPC) individuals. Design: Cross-sectional study. Setting: Study conducted in a clinical setting with NPC and non-NPC participants to evaluate microbial diversity relevant to NPC. Participants: Ten NPC cases and 15 non-NPC controls were recruited based on clinical eligibility. Main Outcome Measures: Bacterial microbiota sampling from the nasopharynx and MM was analyzed by 16S rRNA sequencing. Microbiota diversity (alpha and beta diversity indices), presence of bacterial taxa with biomarker potential, and prediction model accuracy [area under the curve (AUC)]. Results: Microbiota diversity was significantly lower in NPC patients versus controls. In nasopharyngeal samples, alpha diversity (Chao1 index, P =.02) and beta diversity (PERMANOVA, P =.001) differed notably between groups, though MM samples showed no significant difference (Chao1 index, P =.23). Machine learning identified Pseudomonas, Cutibacterium, and Finegoldia as potential NPC biomarkers (AUC = 0.86). Conclusions and Relevance: This pioneering study highlights dysbiosis in nasopharyngeal microbiota among NPC patients. Findings suggest that Pseudomonas, Cutibacterium, and Finegoldia may be useful biomarkers for NPC diagnosis, warranting further investigation into microbial roles in NPC pathogenesis. [ABSTRACT FROM AUTHOR]

Simple Summary: The tumor microenvironment (TME) influences treatment outcome, and analysis of immune cell composition plays an important role in establishing effective prognostic models. This study investigated cellular proportions decomposed from Rulk RNA expression data and immune profiles of patients with lung adenocarcinoma (LUAD) using publicly available data from TCGA and GEO. The results of the study showed a correlation between specific immune signatures, poor prognostic signatures (PPS) and patient outcomes such as progression-free survival and chemotherapy response. We integrated these features and used machine learning models to predict prognosis, with support vector machines (SVMs) having the highest accuracy. This study highlights the importance of immune profiling in advancing precision medicine for lung cancer patients. Background: The development of tumors is a highly complex process that entails numerous interactions and intricate relationships between the host immune system and cancer cells. It has been demonstrated in studies that the treatment response of patients can be correlated with the tumor microenvironment (TME). Consequently, the examination of diverse immune profiles within the TME can facilitate the elucidation of tumor development and the development of advantageous models for diagnoses and prognoses. Methods: In this study, we utilized a single-cell decomposition method to analyze the relationships between cell proportions and immune signatures in lung adenocarcinoma (LUAD) patients. Results: Our findings indicate that specific immune cell populations and immune signatures are significantly associated with patient prognosis. By identifying poor prognosis signatures (PPS), we reveal the critical role of immune profiles and cellular composition in disease outcomes, emphasizing their diagnostic potential for predicting patient prognosis. Conclusions: This study highlights the importance of immune signatures and cellular composition, which may serve as valuable biomarkers for disease prognosis in LUAD patients. [ABSTRACT FROM AUTHOR]

Our study explores the role of cancer-derived extracellular exosomes (EXs), particularly focusing on collagen alpha-3 (VI; COL6A3), in facilitating tumor dissemination and metastasis in epithelial ovarian cancer (EOC). We found that COL6A3 is expressed in aggressive ES2 derivatives, SKOV3 overexpressing COL6A3 (SKOV3/COL6A3), and mesenchymal-type ovarian carcinoma stromal progenitor cells (MSC-OCSPCs), as well as their EXs, but not in less aggressive SKOV3 cells or ES2 cells with COL6A3 knockdown (ES2/shCOL6A3). High COL6A3 expression correlates with worse overall survival among EOC patients, as evidenced by TCGA and GEO data analysis. In vitro experiments showed that EXs from MSC-OCSPCs or SKOV3/COL6A3 cells significantly enhance invasion ability in ES2 or SKOV3/COL6A3 cells, respectively (both, p <0.001). In contrast, ES2 cells with ES2/shCOL6A3 EXs exhibited reduced invasion ability (p < 0.001). In vivo, the average disseminated tumor numbers in the peritoneal cavity were significantly greater in mice receiving intraperitoneally injected SKOV3/COL6A3 cells than in SKOV3 cells (p < 0.001). Furthermore, mice intravenously (IV) injected with SKOV3/COL6A3 cells and SKOV3/COL6A3-EXs showed increased lung colonization compared to mice injected with SKOV3 cells and PBS (p = 0.007) or SKOV3/COL6A3 cells and PBS (p = 0.039). Knockdown of COL6A3 or treatment with EX inhibitor GW4869 or rapamycin-abolished COL6A3-EXs may suppress the aggressiveness of EOC. [ABSTRACT FROM AUTHOR]

Background and Objectives: Left ventricular hypertrophy (LVH) represents a significant cardiovascular risk in patients undergoing chronic hemodialysis (CHD). A large inferior vena cava diameter (IVCD), potentially indicative of fluid overload and a contributing factor to elevated cardiovascular risk, has not been sufficiently explored. Therefore, our study aims to gain further insights into this aspect. Materials and Methods: A retrospective cohort study enrolled patients receiving CHD in a single medical center with available echocardiography from October to December 2018. They were categorized into four groups based on LVH geometry and IVCD. Cox proportional hazard models assessed the risk of major adverse cardiovascular effects (MACEs) and cardiovascular and overall mortality after multivariate adjustments. Kaplan–Meier analysis depicted MACE-free events and survival during the follow-up time. Results: Of the 175 CHD patients, 38, 42, 45, and 50 exhibited small IVCD with eccentric and concentric LVH and large IVCD with eccentric and concentric LVH, respectively. Compared to small IVCD and eccentric LVH, large IVCD and eccentric LVH had the highest risk of MACEs, followed by large IVCD and concentric LVH (aHR: 4.40, 3.60; 95% CI: 1.58–12.23, 1.28–10.12, respectively). As for cardiovascular mortality, large IVCD and concentric LVH had the highest risk, followed by large IVCD and eccentric LVH, and small IVCD and concentric LVH. (aHR: 14.34, 10.23, 8.87; 95% CI: 1.99–103.35, 1.41–74.33; 1.01–77.87). The trend in overall mortality risk among the groups was similar to that of cardiovascular mortality. Conclusions: LVH geometry and IVCD co-modify the risk of MACEs and cardiovascular and overall mortality in CHD patients. The highest risk of MACEs is associated with large IVCD and eccentric LVH, while the highest risk of cardiovascular and overall mortality is linked with large IVCD and concentric LVH. [ABSTRACT FROM AUTHOR]

To evaluate the postoperative complications and mortality among patients with chronic kidney disease. Methods: Biochemical measurements, diagnosis codes for CKD and comorbid conditions for surgical patients aged ≥ 20 years were obtained from electronic medical records of three large hospitals in Taiwan in 2009– 2017. We conducted this retrospective cohort study by using propensity score-matching methods to balance the baseline characteristics between CKD and non-CKD groups. The multiple logistic regression analysis was used to estimate the odds ratios (ORs) and 95% confidence intervals (CIs) of risks of primary outcome (included postoperative mortality) and secondary outcome (included postoperative infectious complications and non-infectious complications) associated with CKD. Results: Among 31950 eligible surgical patients, the adjusted OR of in-hospital mortality in patients with CKD was 5.49 (95% CI 3.42– 8.81) compared with that in non-CKD controls. The adjusted ORs of postoperative septicemia, pneumonia and cellulitis in patients with CKD were 5.90 (95% CI 2.12– 16.5), 5.39 (95% CI 1.37– 21.16), and 4.42 (95% CI 1.57– 12.4), respectively, when compared with the non-CKD patients. CKD was also associated with postoperative stroke (OR 2.21, 95% CI 1.47– 3.31). Conclusion: Patients with CKD are at increased risk of postoperative stroke, infectious complications, and mortality. Our study implicated that it is crucial to improve the levels of hemoglobin and K+ in patients with CKD before surgery. Preventive strategies should be developed to improve clinical outcomes in these populations. [ABSTRACT FROM AUTHOR]

Background: Mobile phones, laptops, and computers have become an indispensable part of our lives in recent years. Workers may have an incorrect posture when using a computer for a prolonged period of time. Using these products with an incorrect posture can lead to neck pain. However, there are limited data on postures in real-life situations. Methods: In this study, we used a common camera to record images of subjects carrying out three different tasks (a typing task, a gaming task, and a video-watching task) on a computer. Different artificial intelligence (AI)-based pose estimation approaches were applied to analyze the head's yaw, pitch, and roll and coordinate information of the eyes, nose, neck, and shoulders in the images. We used machine learning models such as random forest, XGBoost, logistic regression, and ensemble learning to build a model to predict whether a subject had neck pain by analyzing their posture when using the computer. Results: After feature selection and adjustment of the predictive models, nested cross-validation was applied to evaluate the models and fine-tune the hyperparameters. Finally, the ensemble learning approach was utilized to construct a model via bagging, which achieved a performance with 87% accuracy, 92% precision, 80.3% recall, 95.5% specificity, and an AUROC of 0.878. Conclusions: We developed a predictive model for the identification of non-specific neck pain using 2D video images without the need for costly devices, advanced environment settings, or extra sensors. This method could provide an effective way for clinically evaluating poor posture during real-world computer usage scenarios. [ABSTRACT FROM AUTHOR]