Search

This document discusses the use of biomedical data mining and machine learning technologies in smart healthcare systems for disease diagnosis and health informatics. These technologies analyze large medical datasets to identify patterns and correlations that may be missed by human observation, helping to predict disease progression and provide personalized treatment plans. The document also highlights the impact of the COVID-19 pandemic on global public health and the importance of early detection and diagnosis in monitoring the spread of the virus. Various detection techniques for COVID-19 are described, including RT-PCR, RT-LAMP, immunoassay antibody detection, radiography imaging, and acoustic detection. The document also addresses the long-term effects of COVID-19, such as long COVID, and the potential use of biomedical data mining and machine learning technologies in monitoring and treating these effects. Overall, the document emphasizes the role of these technologies in improving healthcare quality and rehabilitation outcomes. [Extracted from the article]

Images uploaded to the cloud may be confidential or related to personal private information, so they need to be encrypted before uploading to the cloud storage. At the service provider side, appending additional information is usually required for transmission or database management. Reversible data hiding in encrypted images (RDHEI) serves as a technical solution. Recent RDHEI schemes successfully utilize the spatial correlation between image pixel values to vacate spare room for data hiding, however, the data payload can be further improved. This paper proposes a RDHEI scheme based on extended parameter binary tree labeling, which replaces non-reference pixel values with their prediction errors in a reduced length to vacate space. We further encode the prediction error of non-embeddable pixels to fit the space left from labeling. Thus, the space required to store the pixel bits replaced by labeling codes is saved. Experimental results show that the data payload of the extended parametric binary tree labeling outperforms state-of-the-art schemes. The embedding rates for the commonly applied datasets, including Bossbase, BOWS-2, and UCID, are 3.2305 bpp, 3.1619 bpp, and 2.8113 bpp, respectively. [ABSTRACT FROM AUTHOR]

Humans are able to detect an instantaneous change in correlation, demonstrating an ability to temporally process extremely rapid changes in interaural configurations. This temporal dynamic is correlated with human listeners' ability to store acoustic features in a transient auditory manner. The present study investigated whether the ability of transient auditory storage of acoustic features was affected by the interaural delay, which was assessed by measuring the sensitivity for detecting the instantaneous change in correlation for both wideband and narrowband correlated noise with various interaural delays. Furthermore, whether an instantaneous change in correlation between correlated interaural narrowband or wideband noise was detectable when introducing the longest interaural delay was investigated. Then, an auditory computational description model was applied to explore the relationship between wideband and narrowband simulation noise with various center frequencies in the auditory processes of lower-level transient memory of acoustic features. The computing results indicate that low-frequency information dominated perception and was more distinguishable in length than the high-frequency components, and the longest interaural delay for narrowband noise signals was highly correlated with that for wideband noise signals in the dynamic process of auditory perception. [ABSTRACT FROM AUTHOR]

Human epidermal growth factor receptor-2 (HER2) negative advanced gastric cancer (GC) has a high global incidence and mortality rate with limited options for second-line treatment. Monotherapy is not effective and the combination of chemotherapy and immunotherapy has not yet been included in the guidelines. The present study aimed to explore a new treatment approach by conducting a single-center, retrospective, observational real-world study. A total of 21 patients with advanced HER2-negative GC, who had progressed after receiving standard first-line regimens [tegafur, gimeracil and oteracil potassium capsules (S-1) or capecitabine plus oxaliplatin], were selected. The application of programmed cell death-1 (PD-1) inhibitor combined with taxanes was selected as the second-line treatment. The primary outcomes measured were progression-free survival (PFS), pathological complete response, objective response rate (ORR), disease control rate (DCR) and adverse reactions in the present patient cohort. The median (m)PFS in the overall population was 7.1 months, with a 95% confidence interval (CI) of 6.0-8.2 months and the median overall survival (mOS) was 11.3 months, with a 95% CI of 4.5-18.2 months. The ORR was 9.5% and the DCR was 90.5%. Univariate and multivariate analyses indicated that Ki67 <70% and tumor marker-positive status [one or two increases among carcinoembryogenic antigen (CEA), cancer antigen (CA) 199 and CA125] were independent prognostic factors for PFS and overall survival (OS) in second-line treatment. Significant statistical differences were noted in PFS (mPFS=5.3 months, 95% CI: 3.1-7.5 months vs. mPFS=9.1 months, 95% CI: 6.2-12.0 months; P=0.002) and OS (mOS=8.8 months, 95% CI: 7.0-10.7 months vs. mOS=17.2 months, 95% CI: 16.0-18.5 months; P=0.013) between the Ki67-high group (Ki67 ≥70%) and the Ki67-low group (Ki67 <70%). Significant statistical differences were noted in OS between tumor marker-negative status (CEA, CA199 and CA125 within normal range) and tumor marker-positive status (one or two increases among CEA, CA199 and CA125; mOS=17.2 months, 95% CI: 16.0-18.4 months vs. mOS=8.8 months, 95% CI: 5.3-12.4 months; P=0.018); however, no significant differences were noted in PFS between these two groups. The present study retrospectively analyzed the new second-line approach of PD-1 inhibitor combined with taxanes for HER2 negative GC which effectively improved patient PFS and OS compared with single-agent chemotherapy. The expression levels of Ki67 and the tumor marker-negative status possess potential clinical value in monitoring prognosis and guiding future individualized use of chemotherapy combined with immunotherapy. [ABSTRACT FROM AUTHOR]

Background The motion and interaction of social insects (such as ants) have been studied by many researchers to understand clustering mechanisms. Most studies in the field of ant behavior have focused only on indoor environments (a laboratory setup), while outdoor environments (natural environments) are still underexplored. Findings In this article, we collect 10 videos of 3 species of ant colonies from different scenes, including 5 indoor and 5 outdoor scenes. We develop an image sequence marking software named VisualMarkData, which enables us to provide annotations of the ants in the videos. (i) It offers comprehensive annotations of states at the individual-target and colony-target levels. (ii) It provides a simple matrix format to represent multiple targets and multiple groups of annotations (along with their IDs and behavior labels). (iii) During the annotation process, we propose a simple and effective visualization that takes the annotation information of the previous frame as a reference, and then a user can simply click on the center point of each target to complete the annotation task. (iv) We develop a user-friendly window-based GUI to minimize labor and maximize annotation quality. In all 5,354 frames, the location information and the identification number of each ant are recorded for a total of 712 ants and 114,112 annotations. Moreover, we provide visual analysis tools to assess and validate the technical quality and reproducibility of our data. Conclusions We provide a large-scale ant dataset with the accompanying annotation software. It is hoped that our work will contribute to a deeper exploration of the behavior of ant colonies. [ABSTRACT FROM AUTHOR]

Gastric cancer (GC) is the third most common cause of cancer-associated mortality in China. Aberrant microRNA (miR) expression can occur through multiple biological processes and has been implicated in cancer development. However, to the best of our knowledge, the function of miR-502-5p in GC is currently unclear. In the present study, the expression and function of miR-502-5p in GC was evaluated. Reverse transcription-quantitative (RT-q) PCR was used to measure the expression levels of miR-502-5p in GC tissues, normal adjacent tissues, a normal human gastric epithelial cell line (GES-1) and two GC cell lines. miR-502-5p expression levels were significantly lower in GC tissues and GC cell lines compared with those in adjacent normal tissues and GES-1 cells, respectively. Subsequently, the target genes of miR-502-5p were predicted, and it was demonstrated that the transcription factor SP1 was a direct target. SP1 expression, cell viability, migration and invasion, and SP1 protein levels were examined using RT-qPCR, an MTT assay, Transwell assay and western blotting, respectively. Human GC cells were then transfected with an miR-502-5p mimic to emulate miR-502-5p overexpression, resulting in inhibition of the proliferation, migration and invasion capacities of human GC cells. Compared with the negative control, cells overexpressing miR-502-5p had decreased levels of SP1 mRNA and protein. These data suggest that miR-502-5p serves as a tumor suppressor gene by targeting SP1 to regulate the proliferation, migration and invasion of GC cells. [ABSTRACT FROM AUTHOR]

Ensemble learning can achieve stronger generalization ability by training multiple weak classifier models and fusing the prediction results of these weak classifiers. However, with the increase in the number of weak classifier models, the complexity and training time of the model are also increasing. This paper introduces a heuristic parallel selective ensemble algorithm based on clustering and improved simulated annealing. First, the method uses selective clustering to remove similar weak classifiers, so as to reduce the number of weak models, and select the weak classifiers with large differences as candidate sets. Then, the optimal classifier sequence set is selected based on the improved simulated annealing heuristic selective ensemble algorithm, which improves the classification performance of the model. Moreover, the parallel integration strategy is adopted to improve the efficiency of selecting optimal subset of classifiers, thus effectively reducing the training time of the model. Experimental results show that the proposed algorithm exhibits better performance compared with traditional methods. [ABSTRACT FROM AUTHOR]

Intonation has many perceptually significant functions in language that contribute to speech recognition. This study aims to investigate whether intonation cues affect the unmasking of Mandarin Chinese speech in the presence of interfering sounds. Specifically, intelligibility of multi-tone Mandarin Chinese sentences with maskers consisting of either two-talker speech or steady-state noise was measured in three (flattened, typical, and exaggerated) intonation conditions. Different from most of the previous studies, the present study only manipulate and modify the intonation information but preserve tone information. The results showed that recognition of the final keywords in multi-tone Mandarin Chinese sentences was much better under the original F0 contour condition than the decreased F0 contour or exaggerated F0 contour conditions whenever there was a noise or speech masker, and an exaggerated F0 contour reduced the intelligibility of Mandarin Chinese more under the speech masker condition than that under the noise masker condition. These results suggested that speech in a tone language (Mandarin Chinese) is harder to understand when the intonation is unnatural, even if the tone information is preserved, and an unnatural intonation contour decreases releasing Mandarin Chinese speech from masking, especially in a multi-person talking environment. [ABSTRACT FROM AUTHOR]

Malignant ascites (MA) is a common manifestation of advanced gastric cancer (GC) with peritoneal metastasis (PM), which usually indicates a poor prognosis. The present study aimed to explore the effects of MA, a unique microenvironment of PM, on the proliferation of cancer cells and investigate the underlying mechanisms. Ex vivo experiments demonstrated that GC cells treated with MA exhibited enhanced proliferation. RNA sequencing indicated that asparagine synthetase (ASNS) was one of the differentially expressed genes in GC cells following incubation with MAs. Furthermore, the present study suggested that MA induced an upregulation of ASNS expression and the stimulatory effect of MA on cancer cell proliferation was alleviated upon ASNS downregulation. Activating transcription factor 4 (ATF4), a pivotal transcription factor regulating ASNS, was upregulated when cells were treated with MA supernatant. After ATF4 knockdown, the proliferation of MA-treated GC cells and the expression of ASNS decreased. In addition, the decline in the proliferation of the ATF4-downregulated AGS GC cell line was rescued by ASNS upregulation. The findings indicated that MA could promote the proliferation of GC cells via activation of the ATF4-ASNS axis. Hence, it may be a potential target for treating GC with PM and MA. [ABSTRACT FROM AUTHOR]

In order to retrieve similar trademarks from large-scale trademark databases, combining the characteristics of trademark images, this paper presents a trademark image retrieval method based on regional and border feature fusion. Based on the target image extraction, the proposed approach describes the target region and border features. The region feature description is mainly based on the concept of partition block statistics. The region is divided into equal-area unit using concentric circles, and feature extraction is performed in each small block unit. For the border feature description, this study first detect corners, and then construct a Delaunay graph and extract features by combining the corner detected and the Delaunay triangulation reconstruction. In the search process, the method also incorporates information such as the trademark's color characteristics, trademark classification, and trademark keywords. The present study carried out image retrieval experiment on CE-SHAPE-1 database containing 1400 MPEG-7 core experimental shape, a classification trademark database containing 2000 images, and a national trademark database containing approximately 4.89 million images. The experimental results show that the proposed approach combines the advantages of region and border feature description, and can choose the best among various local optimizations, which makes the retrieval result more effective, more in line with human visual perception, and improves the retrieval accuracy. [ABSTRACT FROM AUTHOR]

Nuclear respiratory factor-1 (Nrf1) and mitochondrial transcription factor A (TFAM) are involved in the regulation of a variety of mitochondrial functional genes, which are associated with decreased sensitivity of tumor cells to chemotherapy. However, the expression status of Nrf1 and TFAM, as well as their clinical significance in breast cancer, is unknown. In the present study, tumor tissues and corresponding adjacent normal tissues were collected from 336 patients with breast cancer, and Nrf1 and TFAM expression was analyzed by immunohistochemistry using a tissue microarray. Expression of Nrf1 and TFAM was significantly increased in breast cancer tissue compared with adjacent normal tissues. In addition, patients positive for Nrf1 or TFAM had a poorer clinical prognosis than patients who were negative, and those positive for Nrf1 and TFAM had the shortest survival time. These results suggest that Nrf1 and TFAM are potential biomarkers for the determination of individualized therapy and the prognosis of breast cancer, and molecular targeting of Nrf1 and TFAM is a promising strategy for the sensitization of breast cancer cells to chemotherapeutics. [ABSTRACT FROM AUTHOR]

Measuring stride variability and dynamics in children is useful for the quantitative study of gait maturation and neuromotor development in childhood and adolescence. In this paper, we computed the sample entropy (SampEn) and average stride interval (ASI) parameters to quantify the stride series of 50 gender-matched children participants in three age groups. We also normalized the SampEn and ASI values by leg length and body mass for each participant, respectively. Results show that the original and normalized SampEn values consistently decrease over the significance level of the Mann-Whitney U test (p<0.01) in children of 3–14 years old, which indicates the stride irregularity has been significantly ameliorated with the body growth. The original and normalized ASI values are also significantly changing when comparing between any two groups of young (aged 3–5 years), middle (aged 6–8 years), and elder (aged 10–14 years) children. Such results suggest that healthy children may better modulate their gait cadence rhythm with the development of their musculoskeletal and neurological systems. In addition, the AdaBoost.M2 and Bagging algorithms were used to effectively distinguish the children’s gait patterns. These ensemble learning algorithms both provided excellent gait classification results in terms of overall accuracy (≥90%), recall (≥0.8), and precision (≥0.8077). [ABSTRACT FROM AUTHOR]

tRNAScan-SE is a tRNA detection program that is widely used for tRNA annotation; however, the false positive rate of tRNAScan-SE is unacceptable for large sequences. Here, we used a machine learning method to try to improve the tRNAScan-SE results. A new predictor, tRNA-Predict, was designed. We obtained real and pseudo-tRNA sequences as training data sets using tRNAScan-SE and constructed three different tRNA feature sets. We then set up an ensemble classifier, LibMutil, to predict tRNAs from the training data. The positive data set of 623 tRNA sequences was obtained from tRNAdb 2009 and the negative data set was the false positive tRNAs predicted by tRNAscan-SE. Our in silico experiments revealed a prediction accuracy rate of 95.1 % for tRNA-Predict using 10-fold cross-validation. tRNA-Predict was developed to distinguish functional tRNAs from pseudo-tRNAs rather than to predict tRNAs from a genome-wide scan. However, tRNA-Predict can work with the output of tRNAscan-SE, which is a genome-wide scanning method, to improve the tRNAscan-SE annotation results. The tRNA-Predict web server is accessible at http://datamining.xmu.edu.cn/∼gjs/tRNA-Predict. [ABSTRACT FROM AUTHOR]

Background: Extrahepatic cholangiocarcinoma (EHCC) is the second most common primary hepatic malignancy, and is associated with high morbidity and mortality. We previously reported the decreased expression of WWOX in EHCC samples, but the underlying mechanism remained unclear. Methods: Immunoprecipitation and immunofluorescence were performed to examine the interaction of WWOX and P38 MAPK. Western blot was carried out to detect the expression of ATF2 and eIF-4E. MTT, colony formation, and Annexin V-FITC assays were performed to detect the cell proliferation and apoptosis. IHC was performed to detect the protein expression in clinical samples. Results: WWOX interacted with P38 and modulated its sub-cellular localization, leading to the cytoplasmic retention of P38. WWOX over-expression inhibited the phosphorylation of ATF2 and eIF-4E, while exogenous P38 reversed this reduction in phosphorylation. Ectopic expression of WWOX in EHCC cells led to inhibited proliferation and stimulated apoptosis in a P38 MAPK-dependent manner. In addition, we found a negative association of WWOX with nuclear localization of P38 and expression of phosphorylated ATF2 in EHCC samples. Conclusion: Our data demonstrated the role of WWOX in EHCC progression, revealing the potential of WWOX/p-ATF2 as a novel diagnostic and prognostic marker, and therapeutic target for EHCC. © 2015 S. Karger AG, Basel [ABSTRACT FROM AUTHOR]

High-resolution knee joint vibroarthrographic (VAG) signals can help physicians accurately evaluate the pathological condition of a degenerative knee joint, in order to prevent unnecessary exploratory surgery. Artifact cancellation is vital to preserve the quality of VAG signals prior to further computer-aided analysis. This paper describes a novel method that effectively utilizes ensemble empirical mode decomposition (EEMD) and detrended fluctuation analysis (DFA) algorithms for the removal of baseline wander and white noise in VAG signal processing. The EEMD method first successively decomposes the raw VAG signal into a set of intrinsic mode functions (IMFs) with fast and low oscillations, until the monotonic baseline wander remains in the last residue. Then, the DFA algorithm is applied to compute the fractal scaling index parameter for each IMF, in order to identify the anti-correlation and the long-range correlation components. Next, the DFA algorithm can be used to identify the anti-correlated and the long-range correlated IMFs, which assists in reconstructing the artifact-reduced VAG signals. Our experimental results showed that the combination of EEMD and DFA algorithms was able to provide averaged signal-to-noise ratio (SNR) values of 20.52 dB (standard deviation: 1.14 dB) and 20.87 dB (standard deviation: 1.89 dB) for 45 normal signals in healthy subjects and 20 pathological signals in symptomatic patients, respectively. The combination of EEMD and DFA algorithms can ameliorate the quality of VAG signals with great SNR improvements over the raw signal, and the results were also superior to those achieved by wavelet matching pursuit decomposition and time-delay neural filter. [ABSTRACT FROM AUTHOR]

Detection of dysphonia is useful for monitoring the progression of phonatory impairment for patients with Parkinson’s disease (PD), and also helps assess the disease severity. This paper describes the statistical pattern analysis methods to study different vocal measurements of sustained phonations. The feature dimension reduction procedure was implemented by using the sequential forward selection (SFS) and kernel principal component analysis (KPCA) methods. Four selected vocal measures were projected by the KPCA onto the bivariate feature space, in which the class-conditional feature densities can be approximated with the nonparametric kernel density estimation technique. In the vocal pattern classification experiments, Fisher’s linear discriminant analysis (FLDA) was applied to perform the linear classification of voice records for healthy control subjects and PD patients, and the maximum a posteriori (MAP) decision rule and support vector machine (SVM) with radial basis function kernels were employed for the nonlinear classification tasks. Based on the KPCA-mapped feature densities, the MAP classifier successfully distinguished 91.8% voice records, with a sensitivity rate of 0.986, a specificity rate of 0.708, and an area value of 0.94 under the receiver operating characteristic (ROC) curve. The diagnostic performance provided by the MAP classifier was superior to those of the FLDA and SVM classifiers. In addition, the classification results indicated that gender is insensitive to dysphonia detection, and the sustained phonations of PD patients with minimal functional disability are more difficult to be correctly identified. [ABSTRACT FROM AUTHOR]

Event-related potentials (ERPs) can reflect the high-level thinking activities of the brain. In ERP analysis, the superposition and averaging method is often used to estimate ERPs. However, the single-trial ERP estimation can provide researchers with more information on cognitive activities. In recent years, more and more researchers try to find an effective method to extract single-trial ERPs, because most of the existing methods have poor generalization ability or suffer from strong assumptions about the characteristics of ERPs, resulting in unsatisfactory results under the condition of a very low signal-to-noise ratio. In this paper, an EEG classification-based method for single-trial ERP detection and estimation was proposed. This study used a linear generated EEG model containing templates of ERP local descriptors which include amplitude and latency, and this model can avoid the invalid assumption about ERPs taken by other methods. The purpose of this method is not to recover the whole ERP waveform but to model the amplitude and latency of ERP components. This method afterwards examined the three machine learning models including logistic regression, neural network, and support vector machine in the EEG signal classification for ERP detection and selected the best performed MLPNN model for detection. To get the utmost out of information produced in the classification process, this study also used extra information to propose a new optimization model, with which outperformed detection results were obtained. Performance of the proposed method is evaluated on simulated N170 and real P50 data sets, and the results show that the model is more effective than the Woody filter and the SingleTrialEM algorithm. These results are also consistent with the conclusion of sensory gating, which demonstrated good generalization ability. [ABSTRACT FROM AUTHOR]

Analysis of quantified voice patterns is useful in the detection and assessment of dysphonia and related phonation disorders. In this paper, we first study the linear correlations between 22 voice parameters of fundamental frequency variability, amplitude variations, and nonlinear measures. The highly correlated vocal parameters are combined by using the linear discriminant analysis method. Based on the probability density functions estimated by the Parzen-window technique, we propose an interclass probability risk (ICPR) method to select the vocal parameters with small ICPR values as dominant features and compare with the modified Kullback-Leibler divergence (MKLD) feature selection approach. The experimental results show that the generalized logistic regression analysis (GLRA), support vector machine (SVM), and Bagging ensemble algorithm input with the ICPR features can provide better classification results than the same classifiers with the MKLD selected features. The SVM is much better at distinguishing normal vocal patterns with a specificity of 0.8542. Among the three classification methods, the Bagging ensemble algorithm with ICPR features can identify 90.77% vocal patterns, with the highest sensitivity of 0.9796 and largest area value of 0.9558 under the receiver operating characteristic curve. The classification results demonstrate the effectiveness of our feature selection and pattern analysis methods for dysphonic voice detection and measurement. [ABSTRACT FROM AUTHOR]

• Low temperature plasma titanium-nitriding (LPNTi) was primarily developed for 304 austenitic stainless steel. • The process efficiency was increased more than 4 times. • The surface hardness was enhanced from 978 HV 0.025 to 1300 HV 0.025. • The wear rate was decreased from 1.7 mg/cm2 to 0.6 mg/cm2. In order to improve the properties of 304 austenitic stainless steel, efficient low temperature plasma titanium-nitriding (LPNTi) was primarily developed at 420 °C for 4 h. The results show that comparing with traditional low temperature plasma nitriding (LPN), the surface hardness is dramatically enhanced from 978 HV 0.025 to 1300 HV 0.025 , the wear resistance is significantly improved, with much narrower and shallower wear marks, the friction coefficient decreasing from 0.96 to 0.42, the wear rate decreasing from 1.7 mg/cm2 to 0.6 mg/cm2. Meanwhile, the process efficiency is greatly improved as well, with the nitrided layer thickness increasing from 11.37 μm to 48.32 μm, more than 4 times comparing with LPN. [ABSTRACT FROM AUTHOR]