MCRWR: a new method to measure the similarity of documents based on semantic network.

BACKGROUND: Besides Boolean retrieval with medical subject headings (MeSH), PubMed provides users with an alternative way called "Related Articles" to access and collect relevant documents based on semantic similarity. To explore the functionality more efficiently and more accurately, we proposed an improved algorithm by measuring the semantic similarity of PubMed citations based on the MeSH-concept network model. RESULTS: Three article similarity networks are obtained using MeSH-concept random walk with restart (MCRWR), MeSH random walk with restart (MRWR) and PubMed related article (PMRA) respectively. The area under receiver operating characteristic (ROC) curve of MCRWR, MRWR and PMRA is 0.93, 0.90, and 0.67 respectively. Precisions of MCRWR and MRWR under various similarity thresholds are higher than that of PMRA. Mean value of P5 of MCRWR is 0.742, which is much higher than those of MRWR (0.692) and PMRA (0.223). In the article semantic similarity network of "Genes & Function of organ & Disease" based on MCRWR algorithm, four topics are identified according to golden standards. CONCLUSION: MeSH-concept random walk with restart algorithm has better performance in constructing article semantic similarity network, which can reveal the implicitly semantic association between documents. The efficiency and accuracy of retrieving semantic-related documents have been improved a lot.

Down-regulation of FTO promotes proliferation and migration, and protects bladder cancer cells from cisplatin-induced cytotoxicity.

BACKGROUND: FTO is known to be associated with body mass and obesity in humans and its over-expression affects the energy metabolism of cancer cells. The aim of the present study is to investigate the biological role of FTO in human bladder urothelial carcinoma. METHODS: PCR and western blotting are used to measure the levels of FTO in both tissues and cell lines (5637, T24, TCCSUP) of human bladder urothelial carcinoma. Raw RNA-Sequencing reads and the corresponding clinical information for bladder urothelial carcinoma are downloaded from TCGA. Cell Counting Kit-8 and wound healing assays are used to explore the effect of FTO on proliferation and migration of bladder cancer cells. RESULTS: The expression of FTO mRNA in bladder urothelial carcinoma decreases significantly compared with the normal controls from both the data of real-time PCR (p < 0.05) and TCGA (p < 0.01). Loss-of-function assays revealed that knockdown of FTO significantly promotes proliferation and migration of 5637 and T24 cells. Consistently, we found that the cisplatin-induced cytotoxicity of bladder cancer cell could be rescued by co-treatment with MA2, which was previously reported as a highly selective inhibitor of FTO, compared with the cisplatin-control group. CONCLUSIONS: These findings suggest that down-regulation of FTO plays an oncogenic role in bladder cancer. The further exploration of regulation of FTO expression may provide us a potential therapeutic target for the treatment of bladder cancer.

[International focuses in the studies of chronic pelvic pain syndrome: A social network analysis].

OBJECTIVE: To analyze the internationally published literature relevant to chronic pelvic pain syndrome (CPPS) using bibliometrics and social network analysis, and investigate the current status and focuses of CPPS studies. METHODS: We identified 692 publications on CPPS by searching PubMed up to December 2015, extracted their subject headings, calculated the frequencies of the headings, and constructed a co-occurrence network of the high-frequency (≥10) subject headings. Then we studied the features and structure of the co-occurrence network by analyzing its attributes and topological structure. RESULTS: The density of the constructed co-occurrence network was 0.111, with an average distance of 2.886 and a clustering coefficient of 0.685. Its low density, long average distance and high clustering coefficient indicated that it was a sparse network, with a slow speed of information spreading among nodes but a strong potential coherence, which suggested that the current topics in the study of CPPS were scattered and weakly correlated, with a high possibility of being integrated. Based on the topological structure of the co-occurrence network, the topics in the study of CPPS were divided into six aspects: diagnosis and classification, drug therapy, treatment, etiology, microbiology, psychology, and epidemiology, the more important of which were diagnosis and classification, drug therapy, treatment and etiology. CONCLUSIONS: A system has been formed in the studies of CPPS, focusing on the diagnosis, drug therapy, and etiology of the disease. However, the research topics are relatively scattered and frequently repeated. Therefore, more attention should be paid to the macrocosmic guidance and rational coordination of the researches on CPPS.

[A bibliometric investigation to research fronts of major sub-specialties in internal medicine].

OBJECTIVE: To outline the research fronts of ten major sub-specialties in internal medicine. METHODS: Based on their impact factor scores and the proportion of the journals of 10 subspecialties (endocrinology & metabolism, cardiac & cardiovascular systems, hematology, infectious diseases, nephrology, gastroenterology & hepatology, respiratory system, rheumatology, critical care medicine, clinical neurology) in Journal Citation Report (JCR), and careful consulation of expert clinicians, we identified 50 journals. Their bibliographic records (including references) published in 2011 were downloaded, and the frequency of the references (citations) in each sub-specialty was counted and the highly cited records were extracted. We performed a clustering analysis according to the co-cited times among any pairs of the highly cited records. To tag each cluster of highly cited records, we browsed the titles and abstracts of all highly cited records in the same cluster, and concluded the main topics of each cluster. Finally, we extracted the current published papers devoted to particular cluster by some clustering analysis indicators. The clusters of highly cited records were considered as the intelligence base, and the main topics in current papers which citing these highly cited papers were considered as research fronts. RESULTS: Totally 50 journals on 10 sub-specialties in internal medicine were identified. A total of 202 highly cited papers, 38 clusters (knowledge bases) , and 152 corresponding current citing papers presenting the research fronts were selected. CONCLUSIONS: We confirm and present research fronts in 10 major sub-specialties of internal medicine. This study provides a synchronic structure of contemporary research activities in internal medicine sub-specialties.

iPCa-Net: A CNN-based framework for predicting incidental prostate cancer using multiparametric MRI.

Incidental prostate cancer (iPCa) is an early stage of clinically significant prostate cancer (csPCa) and is typically asymptomatic, making it difficult to detect in clinical practice. The objective of this study is to predict iPCa by analyzing prostatic MRIs using deep convolutional neural network (CNN). While CNN-based models in medical image analysis have made significant advancements, the iPCa prediction task presents two challenging problems: subtler differences in MRIs that are imperceptible to human eyes and a lower incidence rate, resulting in a more pronounced sample imbalance compared to routine cancer prediction. To address these two challenges, we propose a new CNN-based framework called iPCa-Net, which is designed to jointly optimize two tasks: prostate transition zone segmentation and iPCa prediction. To evaluate the performance of our model, we construct a prostatic MRI dataset comprising 9536 prostate MRI slices from 448 patients diagnosed with benign prostatic hyperplasia (BPH) at our institution. In our study, the incidence rate of iPCa is 5.13% (23 out of 448) . We compare our model with eight state-of-the-art methods for segmentation task and nine established methods for prediction task respectively using our dataset, and experimental results demonstrate the superior performance of our model. Specifically, in the prostate transition zone segmentation task, our iPCa-Net outperforms the top-performing method by 1.23% with respect to mIoU. In the iPCa prediction task, our iPCa-Net surpasses the top-performing method by 2.06% with respect to F1 score. In conclusion, our iPCa-Net demonstrates superior performance in the early identification of iPCa patients compared to state-of-the-art methods. This advancement holds great significance for appropriate disease management and is highly beneficial for patients.

Automatic International Classification of Diseases Coding via Note-Code Interaction Network with Denoising Mechanism.

Clinical notes are comprehensive files containing explicit information about a patient's visit. However, accurately assigning medical codes from clinical documents can be a persistent challenge due to the complexity of clinical data and the vast range of medical codes. Moreover, the large volume of medical records, the noisy medical records, and the uneven quality of coders all negatively impact the quality of the final codes. Deep learning technology has recently been integrated into automatic International Classification of Diseases (ICD) coding tasks to improve accuracy. Nevertheless, the imbalanced class problem, the complexness of code associations, and the noise in lengthy records still restrict the advancement of ICD coding tasks in deep learning. Thus, we present the Note-code Interaction Denoising Network (NIDN) that employs the self-attention mechanism to pull critical semantic features in electronic medical records (EMRs). Our model utilizes the label attention mechanism for retaining code-specific text expression. We introduce Clinical Classifications Software coding for multitask learning, capturing the functional relationships of medical coding to oblige in model prediction. To minimize the impact of noise on model prediction and improve the label distribution imbalance, a denoising module is introduced to filter noise. Our practical consequences indicate that the model NIDN exceeds competitive models on a third version of Medical Information Mart for Intensive Care data set.

Tantalum-coated pedicle screws enhance implant integration.

Because titanium alloy (Ti) has the natural advantage of a low elastic modulus, it has become the most commonly used material for the manufacturing of pedicle screws. However, its poor shear strength and osteogenic ability are undesirable properties. The superior osteoinductivity demonstrated by tantalum (Ta) in oral and maxillofacial surgery and joint surgery leads us to assume that the tantalum-coated pedicle screws may have better osteogenic properties and bone anchoring strength. To verify this hypothesis, MC3T3-E1 cells and human mesenchymal stem cells (hBMSCs) were seeded on the surface of Ta and Ti disks to compare the effects of two different metals on cell adhesion, proliferation, and differentiation. At the same time, we observed the inhibitory effect of Ta on osteoclasts. As an in vivo study, conventional Ti pedicle screws and Ta-coated screws were implanted in bilateral pedicles of Bama pigs. The results showed that compared to titanium, tantalum promoted greater cell adhesion and proliferation and improved the level of hBMSC mineralization, and Ta-coated screws exerted an inhibitory effect on osteoclasts. More importantly, we found that the effect of tantalum on osteogenic differentiation was mediated through the Wnt/ß-catenin and TGF-ß/smad signaling pathways. Ta-coated screws significantly promoted trabecular bone growth compared with Ti as evidenced by micro-CT, histology and biomechanical examination. Our study clearly indicated that tantalum was a superior promoter of osteogenesis and proved that tantalum coating is an effective improvement for titanium alloy implants.