Purpose: To compare the diagnostic performance of radiomic analysis with machine learning (ML) model with a convolutional neural network (CNN) in differentiating thymic epithelial tumors (TETs) from other prevascular mediastinal tumors (PMTs).Methods: A retrospective study was performed in patients with PMTs and undergoing surgical resection or biopsy in National Cheng Kung University Hospital, Tainan, Taiwan, E-Da Hospital, Kaohsiung, Taiwan, and Kaohsiung Veterans General Hospital, Kaohsiung, Taiwan between January 2010 and December 2019. Clinical data including age, sex, myasthenia gravis (MG) symptoms and pathologic diagnosis were collected. The datasets were divided into UECT (unenhanced computed tomography) and CECT (enhanced computed tomography) for analysis and modelling. Radiomics model and 3D CNN model were used to differentiate TETs from non-TET PMTs (including cyst, malignant germ cell tumor, lymphoma and teratoma). The macro F1-score and receiver operating characteristic (ROC) analysis were performed to evaluate the prediction models.Result: In the UECT dataset, there were 297 patients with TETs and 79 patients with other PMTs. The performance of radiomic analysis with machine learning model using LightGBM with Extra Tree (macro F1-Score = 83.95%, ROC-AUC = 0.9117) had better performance than the 3D CNN model (macro F1-score = 75.54%, ROC-AUC = 0.9015). In the CECT dataset, there were 296 patients with TETs and 77 patients with other PMTs. The performance of radiomic analysis with machine learning model using LightGBM with Extra Tree (macro F1-Score = 85.65%, ROC-AUC = 0.9464) had better performance than the 3D CNN model (macro F1-score = 81.01%, ROC-AUC = 0.9275).Conclusion: Our study revealed that the individualized prediction model integrating clinical information and radiomic features using machine learning demonstrated better predictive performance in the differentiation of TETs from other PMTs at chest CT scan than 3D CNN model.

Introduction: Bacteremia is a common but life-threatening infectious disease. However, a well-defined rule to assess patient risk of bacteremia and the urgency of blood culture is lacking. The aim of this study is to establish a predictive model for bacteremia in septic patients using available big data in the emergency department (ED) through logistic regression and other machine learning (ML) methods. Material and Methods: We conducted a retrospective cohort study at the ED of National Cheng Kung University Hospital in Taiwan from January 2015 to December 2019. ED adults (≥18 years old) with systemic inflammatory response syndrome and receiving blood cultures during the ED stay were included. Models I and II were established based on logistic regression, both of which were derived from support vector machine (SVM) and random forest (RF). Net reclassification index was used to determine which model was superior. Results: During the study period, 437,969 patients visited the study ED, and 40,395 patients were enrolled. Patients diagnosed with bacteremia accounted for 7.7% of the cohort. The area under the receiver operating curve (AUROC) in models I and II was 0.729 (95% CI, 0.718–0.740) and 0.731 (95% CI, 0.721–0.742), with Akaike information criterion (AIC) of 16,840 and 16,803, respectively. The performance of model II was superior to that of model I. The AUROC values of models III and IV in the validation dataset were 0.730 (95% CI, 0.713–0.747) and 0.705 (0.688–0.722), respectively. There is no statistical evidence to support that the performance of the model created with logistic regression is superior to those created by SVM and RF. Discussion: The advantage of the SVM or RF model is that the prediction model is more elastic and not limited to a linear relationship. The advantage of the LR model is that it is easy to explain the influence of the independent variable on the response variable. These models could help medical staff identify high-risk patients and prevent unnecessary antibiotic use. The performance of SVM and RF was not inferior to that of logistic regression. Conclusions: We established models that provide discrimination in predicting bacteremia among patients with sepsis. The reported results could inspire researchers to adopt ML in their development of prediction algorithms.

Background & Aims: Low plasma B12 and folate levels or hyperhomocysteinemia are related to cognitive impairment. This study explores the relationships among diet pattern, blood folate–B12–homocysteine levels, and cognition measurement in Alzheimer’s disease (AD) while exploring whether a gender effect may exist. Methods: This cross-sectional study enrolled 592 AD patients (246 males, 346 females) and the demographic data, blood biochemical profiles, Mini-Mental State Examination (MMSE), and a Food Frequency Questionnaire (FFQ) for quantitative assessment of dietary frequency were collected. Structural Equation Modeling (SEM) was employed to explore the associations among dietary patterns, blood profiles, and cognition. A least absolute shrinkage and selection operator regression model, stratified by gender, was constructed to analyze the weighting of possible confounders. Results: Higher MMSE scores were related to higher frequencies of coffee/tea and higher educational levels, body mass index, and younger age. The SEM model revealed a direct influence of dietary frequencies (skimmed milk, thin pork, coffee/tea) and blood profiles (homocysteine, B12, and folate) on cognitive outcomes. At the same time, the influence of dietary pattern on cognition was not mediated by folate–B12–homocysteine levels. In males, a direct influence on the MMSE is attributed to B12, while in females, homocysteine is considered a more critical factor. Conclusions: Dietary patterns and blood profiles are both associated with cognitive domains in AD, and there are gender differences in the associations of dietary patterns and the levels of B12 and homocysteine. To enhance the quality of dietary care and nutritional status for individuals with dementia, our study results still require future validations with multi-center and longitudinal studies.

Dietary pattern (DP) results in nutrition adequacy and may influence cognitive decline and cortical atrophy in Alzheimer’s disease (AD). The study explored DP in 248 patients with AD. Two neurobehavioral assessments (intervals 13.4 months) and two cortical thickness measurements derived from magnetic resonance images (intervals 26.5 months) were collected as outcome measures. Reduced rank regression was used to assess the groups of DPs and a linear mixed-effect model to explore the cortical neurodegenerative patterns. At screening, underweight body mass index (BMI) was related to significant higher lipid profile, impaired cognitive function, smaller cortical thickness, lower protein DP factor loading scores and the non-spouse caregiver status. Higher mini-mental state examination (MMSE) scores were related to the DP of coffee/tea, compared to the lipid/sugar or protein DP group. The underweighted-BMI group had faster cortical thickness atrophy in the pregenual and lateral temporal cortex, while the correlations between cortical thickness degeneration and high HbA1C or low B12 and folate levels were localized in the medial and lateral prefrontal cortex. The predictive model suggested that factors related to MMSE score were related to the caregiver status. In conclusion, normal or overweight BMI, coffee/tea DP group and living with a spouse were considered as protective factors for better cognitive outcomes in patients with AD. The influence of glucose, B12 and folate on the cortical degeneration was spatially distinct from the pattern of AD degeneration.

The study aimed to develop machine learning (ML) classification models for differentiating patients who needed direct surgery from patients who needed core needle biopsy among patients with prevascular mediastinal tumor (PMT). Patients with PMT who received a contrast-enhanced computed tomography (CECT) scan and initial management for PMT between January 2010 and December 2020 were included in this retrospective study. Fourteen ML algorithms were used to construct candidate classification models via the voting ensemble approach, based on preoperative clinical data and radiomic features extracted from the CECT. The classification accuracy of clinical diagnosis was 86.1%. The first ensemble learning model was built by randomly choosing seven ML models from a set of fourteen ML models and had a classification accuracy of 88.0% (95% CI = 85.8 to 90.3%). The second ensemble learning model was the combination of five ML models, including NeuralNetFastAI, NeuralNetTorch, RandomForest with Entropy, RandomForest with Gini, and XGBoost, and had a classification accuracy of 90.4% (95% CI = 87.9 to 93.0%), which significantly outperformed clinical diagnosis (p < 0.05). Due to the superior performance, the voting ensemble learning clinical–radiomic classification model may be used as a clinical decision support system to facilitate the selection of the initial management of PMT.

Corrigendum: Clinical radiomics-based machine learning versus three-dimension convolutional neural network analysis for differentiation of thymic epithelial tumors from other prevascular mediastinal tumors on chest computed tomography scan