C-X-C Chemokine Receptor Type 4 (CXCR4) and Programmed Death-Ligand 1 (PD-L1) Expression are Prognostic Biomarkers for Papillary Thyroid Carcinoma

Chemokines and immunomodulatory factors involve in tumor development. Papillary thyroid carcinoma (PTC) is considered to start from dendritic cell infiltration and then produce immunomodulatory factors. In this study, CXCR4 and PD-L1 biomarkers were used to explore their prognostic role in PTC survival. Confocal microscopy detected the transfection efficiency in tumor cells. 42 PTC patients and thyroiditis patients (control) were enrolled to measure the expressions of CXCR4 and PD-L1. Multi-factor analysis analyzed the effect of combined CXCR4 and PD-L1 expression on ROC. The two groups had no differences in the baseline characteristics. CTXCR4 and PD-L1 level in PTC patients was significantly higher than control. CXCR4 was lowly expressed in thyroid cancer tissue and PD-L1 was highly expressed in serological samples. Compared with single measurement, the combined detection of CXCR4 and PD-L1 showed more ROC area. In conclusion, reduced CXCR4 and increased PD-L1 level is found in thyroid cancer and their level might be used as predictive markers for PTC to improve the curative effect.

Towards a classification of sustainable software development process using manifold machine learning techniques

With the evaluation of the software industry, a huge number of software applications are designing, developing, and uploading to multiple online repositories. To find out the same type of category and resource utilization of applications, researchers must adopt manual working. To reduce their efforts, a solution has been proposed that works in two phases. In first phase, a semantic analysis-based keywords and variables identification process has been proposed. Based on the semantics, designed a dataset having two classes: one represents application type and the other corresponds to application keywords. Afterward, in second phase, input preprocessed dataset to manifold machine learning techniques (Decision Table, Random Forest, OneR, Randomizable Filtered Classifier, Logistic model tree) and compute their performance based on TP Rate, FP Rate, Precision, Recall, F1-Score, MCC, ROC Area, PRC Area, and Accuracy (%). For evaluation purposes, I have used an R language library called latent semantic analysis for creating semantics, and the Weka tool is used for measuring the performance of algorithms. Results show that the random forest depicts the highest accuracy which is 99.3% due to its parametric function evaluation and less misclassification error.

GIÁ TRỊ CỦA PHÂN LOẠI IOTA ADNEX TRONG ĐÁNH GIÁ KHỐI U BUỒNG TRỨNG BẰNG SIÊU ÂM TẠI BỆNH VIỆN K

Mục tiêu: Nghiên cứu nhằm đánh giá giá trị của mô hình IOTA ADNEX trong siêu âm chẩn đoán mức độ lành tính – ác tính của khối u buồng trứng tại bệnh viện K. Đối tượng và phương pháp: Nghiên cứu được thực hiện trên 54 bệnh nhân trong khoảng thời gian từ tháng 12 năm 2020 đến tháng 05 năm 2021 tại bệnh viện K với lâm sàng nghi ngờ u buồng trứng, được siêu âm trước phẫu thuật và thu thập số liệu theo mô hình IOTA ADNEX, được phẫu thuật với chẩn đoán sau phẫu thuật là u buồng trứng. Đối chiếu kết quả phẫu thuật, kết quả giải phẫu bệnh với mô hình IOTA ADNEX thu thập trước phẫu thuật. Từ đó đánh giá giá trị của mô hình IOTA ADNEX trong siêu âm chẩn đoán mức độ lành tính – ác tính u buồng trứng. Kết quả: Mô hình IOTA ADEX có CA 125 và mô hình IOTA ADNEX không có CA 125 có giá trịtốt trong chẩn đoán phân biệt u buồng trứng lành tính và ác tính với diện tích dưới đường cong ROC (Area under the curve – AUC) lần lượt là 0,977 và 0,968. Ngưỡng cắt tối ưu của mô hình IOTA ADNEX có CA 125 và mô hình IOTA ADNEX không có CA125 lần lượt là 24,5 và 25,2. Tại ngưỡng cắt tối ưu, cả hai mô hình này đều có độ nhạy, độ đặc hiệu, giá trị dự báo dương tính, giá trị dự báo âm tính, độ chính xác lần lượt là 92,3%, 96,8%,96%, 93,8%, 94,7%. Kết luận:Mô hình IOTA ADNEX có CA 125 và mô hình IOTA ADNEX không có CA 125 đều có giá trị cao và tương đồng trong chẩn đoán phân biệt u buồng trứng lành tính và ác tính ở bệnh viện K.

The salivary metatranscriptome as an accurate diagnostic indicator of oral cancer

Despite advances in cancer treatment, the 5-year mortality rate for oral cancers (OC) is 40%, mainly due to the lack of early diagnostics. To advance early diagnostics for high-risk and average-risk populations, we developed and evaluated machine-learning (ML) classifiers using metatranscriptomic data from saliva samples (n = 433) collected from oral premalignant disorders (OPMD), OC patients (n = 71) and normal controls (n = 171). Our diagnostic classifiers yielded a receiver operating characteristics (ROC) area under the curve (AUC) up to 0.9, sensitivity up to 83% (92.3% for stage 1 cancer) and specificity up to 97.9%. Our metatranscriptomic signature incorporates both taxonomic and functional microbiome features, and reveals a number of taxa and functional pathways associated with OC. We demonstrate the potential clinical utility of an AI/ML model for diagnosing OC early, opening a new era of non-invasive diagnostics, enabling early intervention and improved patient outcomes.

On the ROC Area of Ensemble Forecasts for Rare Events

The relative operating characteristic (ROC) curve is a popular diagnostic tool in forecast verification, with the area under the ROC curve (AUC) used as a verification metric measuring the discrimination ability of a forecast. Along with calibration, discrimination is deemed as a fundamental probabilistic forecast attribute. In particular, in ensemble forecast verification, AUC provides a basis for the comparison of potential predictive skill of competing forecasts. While this approach is straightforward when dealing with forecasts of common events (e.g. probability of precipitation), the AUC interpretation can turn out to be oversimplistic or misleading when focusing on rare events (e.g. precipitation exceeding some warning criterion). How should we interpret AUC of ensemble forecasts when focusing on rare events? How can changes in the way probability forecasts are derived from the ensemble forecast affect AUC results? How can we detect a genuine improvement in terms of predictive skill? Based on verification experiments, a critical eye is cast on the AUC interpretation to answer these questions. As well as the traditional trapezoidal approximation and the well-known bi-normal fitting model, we discuss a new approach which embraces the concept of imprecise probabilities and relies on the subdivision of the lowest ensemble probability category.

Paediatric pneumonia: deriving a model to identify severe disease

BackgroundCommunity-acquired pneumonia (CAP) is a leading cause of childhood hospitalisation. Limited data exist on factors predicting severe disease with no paediatric-specific predictive tools.MethodsRetrospective cohort (2011–2016) of hospitalised CAP cases. We analysed clinical variables collected at hospital presentation against outcomes. Stratified outcomes were mild (hospitalised), moderate (invasive drainage procedure, intensive care) or severe (mechanical ventilation, vasopressors, death).ResultsWe report 3330 CAP cases, median age 2.0 years (IQR 1–5 years), with 2950 (88.5%) mild, 305 (9.2%) moderate and 75 (2.3%) severe outcomes. Moderate-severe outcomes were associated with hypoxia (SaO2 <90%; OR 6.6, 95% CI 5.1 to 8.5), increased work of breathing (severe vs normal OR 5.8, 95% CI 4.2 to 8.0), comorbidities (4+ comorbidities vs nil; OR 8.8, 95% CI 5.5 to 14) and being indigenous (OR 4.7, 95% CI 2.6 to 8.4). Febrile children were less likely than afebrile children to have moderate-severe outcomes (OR 0.57 95% CI 0.44 to 0.74). The full model receiver operating characteristic (ROC) area under the curve (AUC) was 0.78. Sensitivity analyses showed similar results with clinical or radiological CAP definitions. We derived a clinical tool to stratify low, intermediate or high likelihood of severe disease (AUC 0.72). High scores (≥5) had nearly eight times higher odds of moderate-severe disease than those with a low (≤1) score (OR 7.7 95% CI 5.6 to 10.5).ConclusionsA clinical risk prediction tool is needed for child CAP. We have identified risk factors and derived a simple clinical tool using clinical variables at hospital presentation to determine a child’s risk of invasive or intensive care treatment with an ROC AUC comparable with adult pneumonia tools.

The roles of S100B , IL-1β and IL-2 as neuroinflammation biomarkers in Generalized Anxiety Disorder

Introduction: S100B is a neurotrophic factor regulates neuronal growth and plasticity via activating astrocytes and microglia through production of neuro-inflammatory molecules like interleukin (IL)-1β involved in many mental disorders, few studies have combined S100B and cytokines to explore their roles as neuro-inflammatory biomarkers in Generalized Anxiety Disorder (GAD). Methods: Serum S100B and cytokines (IL-1β , IL-2, IL-4 and IL-10) of 108 untreated GAD cases and 123 healthy controls were determined by enzyme linked-immuno-sorbent assay (ELISA) and then compared, while Hamilton Anxiety Rating Scale (HAMA) scores were measured to evaluate anxiety severity. Results: The serum S100B and IL-1β, IL-2 levels of GAD cases were lower than HC significantly (P<0.001), the IL-4 level of GAD were higher than HC (P<0.001), while IL-10 had no significant difference between two groups (P=0.215). The ROC area of S100B, IL-1β, IL-2 and IL-4 in diagnosis of GAD was (0.740 ± 0.032) , (0.900 ± 0.021) , (0.920 ± 0.018) and (0.696 ± 0.037) , all of them suggested a good predicting value (P < 0.001) , while the ROC area of IL-10 was (0.544 ± 0.038) (P = 0.251). The sensitivity of S-100B, IL-1β, IL-2 in diagnosis of GAD was 73.1%, 80.6%, 85.2%, while the specificity was 61.0%, 86.2%, 80.5%. The combination ROC area of S100B, IL-1β , IL-2 and IL-4 was (0.985 ± 0.006)(P < 0.001). Serum S100B was positively correlated with IL-2 and IL-4 (P <0.05)., while was negatively with HAMA scores (P <0.001). Conclusion: The serum S-100B, IL-1β, IL-2 levels of GAD were down-regulated while IL-4 was up-regulated, both IL-2 and IL-4 had a good diagnosis value in GAD separately while the combination of S100B and cytokines had a better diagnosis value which means the neuro-inflammation in GAD is a network regulated by many factors.

Serum exosomal lncRNA SNHG7 is increased in NSCLC and predicts unfavorable prognosis

BackgroundExosomal long non-coding RNAs (lncRNAs) are proposed as promising non-invasive biomarkers for clinical applications.AimsIn this study, we aimed to explore the potential of serum exosomal lncRNA SNHG7 for the diagnosis and prognosis prediction of non-small-cell lung cancer (NSCLC).MethodsA total of 128 patients with NSCLC and 80 healthy volunteers were enrolled. Quantitative real-time polymerase chain reaction (qRT-PCR) was performed to measure the expression level of serum exosomal lncRNA SNHG7 in all participants. Receiver operating characteristic (ROC) analysis was used to analyze the diagnostic value of serum exosomal lncRNA SNHG7 and CEA for NSCLC. The relationship between serum exosomal lncRNA SNHG7 expression and clinical characteristics of NSCLC was also assessed.ResultsSerum exosomal lncRNA SNHG7 levels were significantly upregulated in NSCLC patients compared to controls. In addition, serum exosomal lncRNA SNHG7 yield a ROC area under the curve (AUC) value of 0.856 with 77.34% sensitivity and 83.75% specificity for identifying NSCLC patients from normal controls. Combining serum exosomal lncRNA SNHG7 and CEA improved the diagnostic accuracy of NSCLC, with an AUC of 0.932 with 88.28% sensitivity and 86.25% specificity. Moreover, serum exosomal SNHG7 levels were significantly downregulated in post-operative blood samples whereas markedly higher in patients who experienced a relapse. Significant associations of elevated serum exosomal lncRNA SNHG7 expression with TNM stage, lymphatic invasion and lymph node metastasis were observed. High serum exosomal SNHG7 expression was associated with poorer survival and served as an independent prognostic factor for NSCLC.ConclusionsIn conclusion, our data demonstrates that serum exosomal SNHG7 expression might be a potential valuable biomarker for NSCLC detection and prognosis prediction.

A deep learning model for gastric diffuse-type adenocarcinoma classification in whole slide images

Gastric diffuse-type adenocarcinoma represents a disproportionately high percentage of cases of gastric cancers occurring in the young, and its relative incidence seems to be on the rise. Usually it affects the body of the stomach, and it presents shorter duration and worse prognosis compared with the differentiated (intestinal) type adenocarcinoma. The main difficulty encountered in the differential diagnosis of gastric adenocarcinomas occurs with the diffuse-type. As the cancer cells of diffuse-type adenocarcinoma are often single and inconspicuous in a background desmoplaia and inflammation, it can often be mistaken for a wide variety of non-neoplastic lesions including gastritis or reactive endothelial cells seen in granulation tissue. In this study we trained deep learning models to classify gastric diffuse-type adenocarcinoma from WSIs. We evaluated the models on five test sets obtained from distinct sources, achieving receiver operator curve (ROC) area under the curves (AUCs) in the range of 0.95–0.99. The highly promising results demonstrate the potential of AI-based computational pathology for aiding pathologists in their diagnostic workflow system.

Aspergillus Lateral Flow Assay with Digital Reader for the Diagnosis of COVID-19 Associated Pulmonary Aspergillosis (CAPA): A multicenter study

This multicenter study evaluated the IMMY Aspergillus Galactomannan Lateral Flow Assay (LFA) with automated reader for diagnosis of pulmonary aspergillosis in patients with COVID-19 associated acute respiratory failure (ARF) requiring intensive care unit (ICU) admission between 03/2020 and 04/2021. A total of 196 respiratory samples and 148 serum samples (n=344) from 238 patients were retrospectively included, with a maximum of one of each sample type per patient. Cases were retrospectively classified for COVID-19 associated pulmonary aspergillosis (CAPA) status following the 2020 consensus criteria, with the exclusion of LFA results as a mycological criterion. At the 1.0 cutoff, sensitivity of LFA for CAPA (proven/probable/possible) was 52%, 80% and 81%, and specificity was 98%, 88% and 67%, for bronchoalveolar lavage fluid (BALF), non-directed bronchoalveolar lavage (NBL), and tracheal aspiration (TA), respectively. At the 0.5 manufacturer’s cutoff, sensitivity was 72%, 90% and 100%, and specificity was 79%, 83% and 44%, for BALF, NBL and TA, respectively. When combining all respiratory samples, the receiver operating characteristic (ROC) area under the curve (AUC) was 0.823, versus 0.754, 0.890 and 0.814 for BALF, NBL and TA, respectively. Sensitivity and specificity of serum LFA were 20% and 93%, respectively, at the 0.5 ODI cutoff. Overall, the Aspergillus Galactomannan LFA showed good performances for CAPA diagnosis, when used from respiratory samples at the 1.0 cutoff, while sensitivity from serum was limited, linked to weak invasiveness during CAPA. As some false positive results can occur, isolated results slightly above the recommended cutoff should lead to further mycological investigations.