Search

Electronic health records (EHRs) contain critical information useful for clinical studies. Early assessment of patients' mortality in intensive care units is of great importance. In this paper, a Deep Rule-Based Fuzzy System (DRBFS) was proposed to develop an accurate in-hospital mortality prediction in the intensive care unit (ICU) patients employing a large number of input variables. Our main contribution is proposing a system, which is capable of dealing with big data with heterogeneous mixed categorical and numeric attributes. In DRBFS, the hidden layer in each unit is represented by interpretable fuzzy rules. Benefiting the strength of soft partitioning, a modified supervised fuzzy k-prototype clustering has been employed for fuzzy rule generation. According to the stacked approach, the same input space is kept in every base building unit of DRBFS. The training set in addition to random shifts, obtained from random projections of prediction results of the current base building unit is presented as the input of the next base building unit. A cohort of 10,972 adult admissions was selected from Medical Information Mart for Intensive Care (MIMIC-III) data set, where 9.31% of patients have died in the hospital. A heterogeneous feature set of first 48 h from ICU admissions, were extracted for in-hospital mortality rate. Required preprocessing and appropriate feature extraction were applied. To avoid biased assessments, performance indexes were calculated using holdout validation. We have evaluated our proposed method with several common classifiers including naïve Bayes (NB), decision trees (DT), Gradient Boosting (GB), Deep Belief Networks (DBN) and D-TSK-FC. The area under the receiver operating characteristics curve (AUROC) for NB, DT, GB, DBN, D-TSK-FC and our proposed method were 73.51%, 61.81%, 72.98%, 70.07%, 66.74% and 73.90% respectively. Our results have demonstrated that DRBFS outperforms various methods, while maintaining interpretable rule bases. Besides, benefiting from specific clustering methods, DRBFS can be well scaled up for large heterogeneous data sets. [ABSTRACT FROM AUTHOR]

[Display omitted] In recent years, the high-resolution manometry (HRM) technique has been increasingly used to study esophageal and colonic pressurization and has become a standard routine for discovering mobility disorders. In addition to evolving guidelines for the interpretation of HRM like Chicago standard, some complexities, such as the dependency of normative reference values on the recording device and other external variables, still remain for medical professions. In this study, a decision support framework is developed to aid the diagnosis of esophageal mobility disorders based on HRM data. To abstract HRM data, Spearman correlation is employed to model the spatio-temporal dependencies of pressure values of HRM components and convolutional graph neural networks are then utilized to embed relation graphs to the features vector. In the decision-making stage, a novel Expert per Class Fuzzy Classifier (EPC-FC) is presented that employs the ensemble structure and contains expertized sub-classifiers for recognizing a specific disorder. Training sub-classifiers using the negative correlation learning method makes the EPC-FC highly generalizable. Meanwhile, separating the sub-classifiers of each class gives flexibility and interpretability to the structure. The suggested framework is evaluated on a dataset of 67 patients in 5 different classes recorded in Shariati Hospital. The average accuracy of 78.03% for a single swallow and 92.54% for subject-level is achieved for distinguishing mobility disorders. Moreover, compared with the other studies, the presented framework has an outstanding performance considering that it imposes no limits on the type of classes or HRM data. On the other hand, the EPC-FC outperforms other comparative classifiers such as SVM and AdaBoost not only in HRM diagnosis but also on other benchmark classification problems. [ABSTRACT FROM AUTHOR]

This research was aimed to evaluate the in vitro antiviral effect and the mechanism of the effect of Peganum. harmala seeds extract against influenza A virus infection using Madin-Darby canine kidney (MDCK) cells. In this research, ethyl alcohol extract of P. harmala seeds and its total alkaloids was prepared. The potential antiviral activity of the extract and its total alkaloids against influenza A/Puerto Rico/8/34 (H1N1; PR8) virus was assessed. The mode of action of the extract to inhibit influenza replication was investigated using virucidal activity, hemagglutination inhibition assay, time of addition assays, RNA replication, western blot analysis and RNA polymerase blocking assay. The crud extract of P. harmala seed and its total alkaloids showed the best inhibitory effect against influenza A virus replication in MDCK cells using MTT assay, TCID 50 method and hemagglutination assay. Our results indicated that the extract inhibits viral RNA replication and viral polymerase activity but did not effect on hemagglutination inhibition and virucidal activity. This study showed that, in vitro antiviral activity of P. harmala seed extract against influenza virus is most probably associated with inhibiting viral RNA transcription. Therefore, this extract and its total alkaloid should be further characterized to be developed as anti-influenza A virus agent. [ABSTRACT FROM AUTHOR]

Uncertainty is one of the important facts of the medical knowledge. Medical prognosis and diagnosis, as the essential parts of medical knowledge, is affected by different aspects of uncertainty, which must be managed. In the previous studies, different theories such as Bayesian probability theory, evidence theory, and fuzzy set theory have been developed to represent and manage different aspects of uncertainty. Recently, hybrid frameworks are suggested to deal with various types of uncertainty in a single framework. Evidential networks are general frameworks for dealing explicitly with total and partial ignorance and offer powerful combination rule of contradictory evidence. In this framework, the fuzziness of linguistic variables is neglected while these variables commonly appear in the medical domain knowledge and different sources of medical information. In addition, the evidential network parameters are determined based on the experts' knowledge and no data-driven algorithm is provided to learn these parameters. In this study, a novel hybrid framework called fuzzy evidential network was suggested to manage the imprecision and epistemic uncertainty of medical prognosis and diagnosis. Also, a data-driven algorithm based on the fuzzy set theory and the fuzzy maximum likelihood is provided to learn the network parameters from clinical databases. The performance of the proposed framework as various prognosis and diagnosis models, compared with well-known machine learning algorithms and the results showed its superiority. Also, an evidential method is suggested to handle the missing values and its results were compared with KNN imputation method. [ABSTRACT FROM AUTHOR]

Clostridium difficile ( C.difficile ) infection is often established in the presence of antibiotics and probably antibiotics can influence surface layer protein A (slpA) expression as a colonization factor. The aim of this study is to evaluate the effect of vancomycin (VAN), clindamycin (CLI) alone and in combination with ceftazidime (CAZ) on slpA gene expression to determine whether such antibiotics can have any effect on slpA expression. About ∼10 6 CFU/mL was inoculated to medium containing an appropriate concentration of antibiotics alone and in combination. After 24 and 48 h incubation under anaerobic condition, 3 mL of culture was excluded and centrifuged in 8000 × g per 3 min. The pellet was washed and used for RNA extraction. The RNA extraction, Dnase I treatment and cDNA synthesis was performed by RNA extraction, Dnase I, and cDNA synthesis kits, respectively. The real–time PCR were carried out by sybrGreen methods and data were analyzed based on comparative ΔΔC T . All antibiotics alone and in combination, except VAN/CAZ in clinical isolate, decreased the level of slpA gene expression in the 24-h incubation. While the expression profile of slpA was different in the 48-h incubation period. The VAN and CLI decreased the slpA expression, although the template of expression is closed to control medium. CAZ alone and in combination increased slpA expression. C. difficile may down-regulate slpA expression in the early stages of growth in sub-inhibitory concentration of antibiotics. But, over time C. difficile increases or over expresses the slpA expression level. Consequently C. difficile binds strongly to epithelial cells and continues to survive in the presence of sub-MIC concentration of antibiotics. This effect is observed especially with regard to CAZ and probably other third generation cephalosporins or in combination therapy with VAN or CLI, which are prescribed in the clinic. CAZ can interfere with the anti-down regulatory feature of VAN, CLI, and maybe other antibiotics. [ABSTRACT FROM AUTHOR]

Toxin production in Clostridium difficile ( C. difficile ) is a key process for induction of diarrhea. Several factors such as sub-MIC of antibiotics impact on toxin production. The aim of this research is investigation of sub-minimum inhibitory concentration (sub-MIC) of vancomycin (VAN), clindamycin (CLI) separately and in combination with ceftazidime (CAZ) on toxin production in C. difficile . About ∼10 6 colony forming units (CFU) from 18-h culture of C. difficile ATCC 9689 and clinical isolates A + /B + /CTD − , were cultured anaerobically in the pre-reduced medium with appropriate concentration of separated and in combination antibiotics. After 24 and 48 h, 1 mL of culture was removed, centrifuged and the supernatant stored at-70 °C for later use. The evaluation of toxin production was carried out by the ELISA technique. All antibiotics alone and in combination formats inhibited toxin production over a period of 24 h. This effect is also observed in presence of VAN and CLI during a period of 48 h. Over a 4 h period, CAZ increased toxin production alone and in combination, especially with CLI. The data showed VAN and CLI decrease the level of toxins. In contrast, the CAZ not only increases the level of produced toxin, but also can interfere with VAN and CLI. Based on the results, combination therapy which is performed for treatment or prevention of other infections may cause toxin production and probably the severity of C. difficile AAD to increase. [ABSTRACT FROM AUTHOR]

Shigella is one of the important causes of diarrhea worldwide. Shigella has several virulence factors contributing in colonization and invasion of epithelial cells and eventually death of host cells. The present study was performed in order to investigate the distribution of virulence factors genes in Shigella spp. isolated from patients with acute diarrhea in Kerman, Iran as well as the genetic relationship of these isolates. A total of 56 isolates including 31 S. flexneri , 18 S. sonnei and 7 S. boydii were evaluated by polymerase chain reaction (PCR) for the presence of 11 virulence genes ( ipaH , ial , set1A , set1B , sen , virF , invE , sat , sigA , pic and sepA ). Then, the clonal relationship of these strains was analyzed by multilocus variable-number tandem repeat analysis (MLVA) method. All isolates were positive for ipaH gene. The other genes include ial , invE and virF were found in 80.4%, 60.7% and 67.9% of the isolates, respectively. Both set1A and set1B were detected in 32.3% of S. flexneri isolates, whereas 66.1% of the isolates belonging to different serogroup carried sen gene. The sat gene was present in all S. flexneri isolates, but not in the S. sonnei and S. boydii isolates. The result showed, 30.4% of isolates were simultaneously positive and the rest of the isolates were negative for sepA and pic genes. The Shigella isolates were divided into 29 MLVA types. This study, for the first time, investigated distribution of 11 virulence genes in Shigella spp. Our results revealed heterogeneity of virulence genes in different Shigella serogroups. Furthermore, the strains belonging to the same species had little diversity. [ABSTRACT FROM AUTHOR]