Background: Blood-based test for predicting disease progression and early diagnosis of Parkinson’s disease (PD) is an unmet need in the clinic. The profiles of microRNAs (miRNAs) are regarded as potential diagnostic biomarkers for human diseases, whereas miRNAs in the periphery are susceptible to the influence of various components. MiRNAs enriched in serum extracellular vesicles (EVs) have demonstrated disease-specific advantages in diagnosis due to their high abundance, stability and resistance to degradation. This study was aimed to screen differentially expressed EV-derived miRNAs between healthy controls and PD patients to aid in diagnosis of PD. Methods: A total of 31 healthy controls and 72 patients with a diagnosis of PD at different Hoehn and Yahr stages in Tangdu Hospital were included. In total, 185 differentially expressed miRNAs were obtained through RNA sequencing of serum EVs as well as edgeR and t-test analyses. Subsequently, the weighted gene co-expression network analysis (WGCNA) was utilized to identify the commonly expressed miRNAs in all stages of PD by constructing connections between modules, and specifically expressed miRNAs in each stage of PD by functional enrichment analysis. After aligning these miRNAs with PD-related miRNAs in Human miRNA Disease Database, the screened miRNAs were further validated by receiver operating characteristic (ROC) curves and quantitative real-time polymerase chain reaction (qRT-PCR) using peripheral blood EVs from 40 more participants. Results: WGCNA showed that 4 miRNAs were commonly associated with all stages of PD and 13 miRNAs were specifically associated with different stages of PD. Of the 17 obtained miRNAs, 7 were validated by ROC curve analysis and 7 were verified in 40 more participants by qRT-PCR. Six miRNAs were verified by both methods, which included 2 miRNAs that were commonly expressed in all stages of PD and 4 miRNAs that were specifically expressed in different stages of PD. Conclusions: The 6 serum EV-derived miRNAs, hsa-miR-374a-5p, hsa-miR-374b-5p, hsa-miR-199a-3p, hsa-miR-28-5p, hsa-miR-22-5p and hsa-miR-151a-5p, may potentially be used as biomarkers for PD progression and for early diagnosis of PD in populations.
Arabic is one of the most semantically and syntactically complex languages in the world. A key challenging issue in text mining is text summarization, so we propose an unsupervised score-based method which combines the vector space model, continuous bag of words (CBOW), clustering, and a statistically-based method. The problems with multidocument text summarization are the noisy data, redundancy, diminished readability, and sentence incoherency. In this study, we adopt a preprocessing strategy to solve the noise problem and use the word2vec model for two purposes, first, to map the words to fixed-length vectors and, second, to obtain the semantic relationship between each vector based on the dimensions. Similarly, we use a k-means algorithm for two purposes: (1) Selecting the distinctive documents and tokenizing these documents to sentences, and (2) using another iteration of the k-means algorithm to select the key sentences based on the similarity metric to overcome the redundancy problem and generate the initial summary. Lastly, we use weighted principal component analysis (W-PCA) to map the sentences’ encoded weights based on a list of features. This selects the highest set of weights, which relates to important sentences for solving incoherency and readability problems. We adopted Recall-Oriented Understudy for Gisting Evaluation (ROUGE) as an evaluation measure to examine our proposed technique and compare it with state-of-the-art methods. Finally, an experiment on the Essex Arabic Summaries Corpus (EASC) using the ROUGE-1 and ROUGE-2 metrics showed promising results in comparison with existing methods.
Patients’ discharge summaries (documents) are health sensors that are used for measuring the quality of treatment in medical centers. However, extracting information automatically from discharge summaries with unstructured natural language is considered challenging. These kinds of documents include various aspects of patient information that could be used to test the treatment quality for improving medical-related decisions. One of the significant techniques in literature for discharge summaries classification is feature extraction techniques from the domain of natural language processing on text data. We propose a novel sentiment analysis method for discharge summaries classification that relies on vector space models, statistical methods, association rule, and extreme learning machine autoencoder (ELM-AE). Our novel hybrid model is based on statistical methods that build the lexicon in a domain related to health and medical records. Meanwhile, our method examines treatment quality based on an idea inspired by sentiment analysis. Experiments prove that our proposed method obtains a higher F1 value of 0.89 with good TPR (True Positive Rate) and FPR (False Positive Rate) values compared with various well-known state-of-the-art methods with different size of training and testing datasets. The results also prove that our method provides a flexible and effective technique to examine treatment quality based on positive, negative, and neutral terms for sentence-level in each discharge summary.
Given the modest efficacy of docetaxel in advanced non-small cell lung cancer (NSCLC), this study assesses the therapeutic potential and safety profile of anlotinib in combination with docetaxel compared to docetaxel monotherapy as a second-line therapy for patients with advanced NSCLC. In this phase II study, patients with advanced NSCLC experiencing failure with first-line platinum-based regimens were randomized in a 1:1 ratio to receive either anlotinib plus docetaxel or docetaxel alone. Primary endpoint was progression-free survival (PFS), with overall survival (OS), objective response rate (ORR), disease control rate (DCR), and safety as secondary endpoints. A total of 83 patients were randomized. The combination of anlotinib and docetaxel significantly extended median PFS to 4.4 months compared to 1.6 months for docetaxel alone (hazard ratio [HR] = 0.38, 95 % confidence interval [CI]: 0.23-0.63, P = 0.0002), and also demonstrated superior ORR (32.5 % vs. 9.3 %, P = 0.0089) and DCR (87.5 % vs. 53.5 %, P = 0.0007). Median OS was observed at 12.0 months in the combination group vs. 10.9 months in the monotherapy group (HR = 0.82, 95 % CI: 0.47-1.43, P = 0.4803). For patients previously treated with immunotherapy, the median PFS was notably longer at 7.8 vs. 1.7 months (HR = 0.22, 95 % CI: 0.09-0.51, P = 0.0290). The incidence of grade ≥ 3 treatment-related adverse events, predominantly leukopenia (15.0 % vs. 7.0 %) and neutropenia (10.0 % vs. 5.0 %), was manageable across both groups. Anlotinib plus docetaxel offers a viable therapeutic alternative for patients with advanced NSCLC who failed first-line platinum-based treatments.
The Human Phenotype Ontology (HPO) is one of the most popular bioinformatics resources. Recently, HPO-based phenotype semantic similarity has been effectively applied to model patient phenotype data. However, the existing tools are revised based on the Gene Ontology (GO)-based term similarity. The design of the models are not optimized for the unique features of HPO. In addition, existing tools only allow HPO terms as input and only provide pure text-based outputs. We present PhenoSimWeb, a web application that allows researchers to measure HPO-based phenotype semantic similarities using four approaches borrowed from GO-based similarity measurements. Besides, we provide a approach considering the unique properties of HPO. And, PhenoSimWeb allows text that describes phenotypes as input, since clinical phenotype data is always in text. PhenoSimWeb also provides a graphic visualization interface to visualize the resulting phenotype network. PhenoSimWeb is an easy-to-use and functional online application. Researchers can use it to calculate phenotype similarity conveniently, predict phenotype associated genes or diseases, and visualize the network of phenotype interactions. PhenoSimWeb is available at http://120.77.47.2:8080.