Tag: pubmed

Comput Biol Med. 2021 Aug 28;137:104813. doi: 10.1016/j.compbiomed.2021.104813. Online ahead of print.

ABSTRACT

BACKGROUND: This study sought to evaluate the performance of machine learning (ML) models and establish an explainable ML model with good prediction of 3-year all-cause mortality in patients with heart failure (HF) caused by coronary heart disease (CHD).

METHODS: We established six ML models using follow-up data to predict 3-year all-cause mortality. Through comprehensive evaluation, the best performing model was used to predict and stratify patients. The log-rank test was used to assess the difference between Kaplan-Meier curves. The association between ML risk and 3-year all-cause mortality was also assessed using multivariable Cox regression. Finally, an explainable approach based on ML and the SHapley Additive exPlanations (SHAP) method was deployed to calculate 3-year all-cause mortality risk and to generate individual explanations of the model’s decisions.

RESULTS: The best performing extreme gradient boosting (XGBoost) model was selected to predict and stratify patients. Subjects with a higher ML score had a high hazard of suffering events (hazard ratio [HR]: 10.351; P < 0.001), and this relationship persisted with a multivariable analysis (adjusted HR: 5.343; P < 0.001). Age, N-terminal pro-B-type natriuretic peptide, occupation, New York Heart Association classification, and nitrate drug use were important factors for both genders.

CONCLUSIONS: The ML-based risk stratification tool was able to accurately assess and stratify the risk of 3-year all-cause mortality in patients with HF caused by CHD. ML combined with SHAP could provide an explicit explanation of individualized risk prediction and give physicians an intuitive understanding of the influence of key features in the model.

PMID:34481185 | DOI:10.1016/j.compbiomed.2021.104813

J Fluency Disord. 2021 Aug 28;70:105866. doi: 10.1016/j.jfludis.2021.105866. Online ahead of print.

ABSTRACT

The Communication Attitude Test for Adults who stutter (BigCAT) is an established measure of cognitive traits in adults who stutter (AWS). The primary purpose of the present study was to adapt and validate the BigCAT to the Kannada language. The secondary purpose was to compare AWS’ and adults who do not stutter (AWNS) BigCAT-K scores and compare AWS’ score in sub-populations in terms of severity and age. The study included a purposive sample of 100 AWS and 317 AWNS. There was high test-retest reliability and solid construct validity, as made evident by the results of the discriminant analysis and cross-validation. Further, as in other investigations with the BigCAT (Vanryckeghem & Brutten, 2019), this self-report test revealed a statistically significant group mean difference between AWS and AWNS, suggesting the presence of a negative attitude towards communication in Kannada-speaking AWS. Further, individuals with severe stuttering had a significantly higher level of speech-associated negative attitude compared to those with mild stuttering. Age does not seem to influence the AWS’ speech-associated belief system. Both of these findings augment the existing scant literature on exploring the association between stuttering severity and age on the cognitive dimension of stuttering. The outcomes establish the BigCAT-K as an effective tool in the assessment and subsequent management of stuttering.

PMID:34481196 | DOI:10.1016/j.jfludis.2021.105866

Cognition. 2021 Sep 1;217:104891. doi: 10.1016/j.cognition.2021.104891. Online ahead of print.

ABSTRACT

Does semantic information-in particular, regularities in category membership across objects-influence visual working memory (VWM) processing? We predict that the answer is “yes”. Four experiments evaluating this prediction are reported. Experimental stimuli were images of real-world objects arranged in either one or two spatial clusters. On coherent trials, all objects belonging to a cluster also belonged to the same category. On incoherent trials, at least one cluster contained objects from different categories. Experiments using a change-detection paradigm (Experiments 1-3) and an experiment in which participants recalled the locations of objects in a scene (Experiment 4) yielded the same result: participants showed better memory performance on coherent trials than on incoherent trials. Taken as a whole, these experiments provide the best (perhaps only) data to date demonstrating that statistical regularities in semantic category membership improve VWM performance. Because a conventional perspective in cognitive science regards VWM as being sensitive solely to bottom-up visual properties of objects (e.g., shape, color, orientation), our results indicate that cognitive science may need to modify its conceptualization of VWM so that it is closer to “conceptual short-term memory”, a short-term memory store representing current stimuli and their associated concepts (Potter, 1993, 2012).

PMID:34481197 | DOI:10.1016/j.cognition.2021.104891

Leuk Res. 2021 Aug 31;110:106701. doi: 10.1016/j.leukres.2021.106701. Online ahead of print.

ABSTRACT

AML with myelodysplasia-related changes (AML-MRC) is a subtype of AML known to have adverse prognosis. The karyotype abnormalities in AML-MRC have been well established; however, relatively little has been known about the role of gene mutation profiles by next generation sequencing. 177 AML patients (72 AML-MRC and 105 non-MRC AML) were analyzed by NGS panel covering 53 AML related genes. AML-MRC showed statistically significantly higher frequency of TP53 mutation, but lower frequencies of mutations in NPM1, FLT3-ITD^Low, FLT3-ITD^High, FLT3-TKD, NRAS, and PTPN11 than non-MRC AML. Supervised tree-based classification models including Decision tree, Random forest, and XGboost, and logistic regression were used to evaluate if the mutation profiles could be used to aid the diagnosis of AML-MRC. All methods showed good accuracy in differentiating AML-MRC from non-MRC AML with AUC (area under curve) of ROC ranging from 0.69 to 0.78. Additionally, logistic regression indicated 3 independent factors (age and mutations of TP53 and FLT3) could aid the diagnosis AML-MRC. Using weighted factors, a AML-MRC risk scoring equation was established for potential application in clinical setting: +1x(Age ≥ 65) + 3 x (TP53 mutation) – 2 x (FLT3 mutation). Using a cutoff score of 0, the accuracy of the risk score was 0.76 with sensitivity of 0.77 and specificity of 0.75 for predicting the diagnosis of AML-MRC. Further studies with larger sample sizes are warranted to further evaluate the potential of using gene mutation profiles to aid the diagnosis of AML-MRC.

PMID:34481124 | DOI:10.1016/j.leukres.2021.106701

Comput Biol Chem. 2021 Aug 19;94:107558. doi: 10.1016/j.compbiolchem.2021.107558. Online ahead of print.

ABSTRACT

Classifying proteins into their respective enzyme class is an interesting question for researchers for a variety of reasons. The open source Protein Data Bank (PDB) contains more than 1,60,000 structures, with more being added everyday. This paper proposes an attention-based bidirectional-LSTM model (ABLE) trained on over sampled data generated by SMOTE to analyse and classify a protein into one of the six enzyme classes or a negative class using only the primary structure of the protein described as a string by the FASTA sequence as an input. We achieve the highest F1-score of 0.834 using our proposed model on a dataset of proteins from the PDB. We baseline our model against eighteen other machine learning and deep learning networks, including CNN, LSTM, Bi-LSTM, GRU, and the state-of-the-art DeepEC model. We conduct experiments with two different oversampling techniques, SMOTE and ADASYN. To corroborate the obtained results, we perform extensive experimentation and statistical testing.

PMID:34481129 | DOI:10.1016/j.compbiolchem.2021.107558

J Glob Antimicrob Resist. 2021 Sep 1:S2213-7165(21)00196-X. doi: 10.1016/j.jgar.2021.08.004. Online ahead of print.

ABSTRACT

INTRODUCTION: The discharge of drug-resistant, biofilm-forming pathogens from hospital effluent water into municipal wastewater treatment plants poses a public health concern. The present study examined the relationship between antibiotic resistance levels and biofilm formation of Acinetobacter baumannii strains isolated from hospital effluents.

METHODS: Antibiotic susceptibility of 71 A. baumannii isolates was evaluated using the Kirby Bauer disc diffusion method. The minimum inhibitory concentration was performed by the agar dilution method, while the minimum biofilm eradication concentration was performed by the broth dilution method. Genotyping was performed with plasmid DNA. Biofilm formation was evaluated by the microtitre plate method and quantified using crystal violet. P-values < 0.05 were regarded as statistically significant in all the tests conducted.

RESULTS: The extended spectrum resistant (XDR) strains made up 58% of the isolates while MDR and pan drug resistance (PDR) were observed in 50% of the isolates from the final effluent. The MBEC of ciprofloxacin increased by 255-fold while that of ceftazidime was as high as 63-1310-fold compared to their respective MICs. Isolates were classified into four plasmid pattern groups and no significance difference exists between biofilm formation and plasmid type (P = 0.0921). The degree of biofilm formation was independent of the level of antibiotic resistance, although MDRs, XDRs and PDRs produced significant biofilm biomass (P = 0.2580).

CONCLUSION: The results suggest that hospital effluent is a potential risk for multidrug-resistant biofilm-forming A. baumannii strains. Appropriate treatment and disposal for effluents are essential to prevent presence of drug resistance pathogens in waste water.

PMID:34481121 | DOI:10.1016/j.jgar.2021.08.004

J Magn Reson Imaging. 2021 Sep 4. doi: 10.1002/jmri.27914. Online ahead of print.

ABSTRACT

BACKGROUND: Noninvasive evaluation of the status of cerebral arteriole perfusion remains a practical challenge in murine stroke models, because conventional magnetic resonance imaging (MRI) is no longer capable of capturing these very small vessels.

PURPOSE: To investigate the feasibility of ultrasmall superparamagnetic iron oxide particles (USPIO)-based susceptibility weighted imaging (SWI)-MRI (USPIO-SWI) and T2* map-MRI (USPIO-T2* map) for monitoring angiographic perfusion in stroke rats.

STUDY TYPE: A preclinical randomized controlled trial.

ANIMAL MODEL: Normal rats (N = 9), embolic middle cerebral artery occlusion (eMCAO) rats (N = 66).

FIELD STRENGTH/SEQUENCE: 7 T; T2* map (multigradient echo), SWI (3D gradient echo).

ASSESSMENT: Experiment 1: To develop a method for angiographic reperfusion evaluation with USPIO-SWI. Normal rats were used to optimize the USPIO dosage (5.6, 16.8, and 56 mg/kg ferumoxytol) as well as scan time points for cerebral arterioles. Contrast-to-noise ratio (CNR) was measured. Stroke rats were further used and the number of visual cortical vessels were counted. Experiment 2: To examine whether fingolimod (lymphocytes inhibitor) enhances the action of tissue plasminogen activator (tPA) in eMCAO rats on cerebral angiographic reperfusion.

STATISTICAL TESTS: Mann-Whitney test and two way-ANOVA were used. P < 0.05 was considered statistically significant.

RESULTS: CNR values of cerebral cortical penetrating arteries in normal rats were significantly increased to 4.4 ± 0.5 (5.6 mg/kg), 6.1 ± 0.5 (16.8 mg/kg), and 3.4 ± 0.9 (56 mg/kg) after USPIO injection. The number of visual cortical vessels on USPIO-SWI images in ischemic regions was significantly less than in control regions (5 ± 2 vs. 56 ± 20) of eMCAO rats. Compared with eMCAO rats who received tPA only, eMCAO rats who received the combination of fingolimod and tPA exhibited significantly higher proportion of complete angiographic reperfusion (69% vs. 17%).

DATA CONCLUSION: This study supports the feasibility of angiographic perfusion evaluation with USPIO-SWI in stroke rats.

LEVEL OF EVIDENCE: 2 TECHNICAL EFFICACY STAGE: 1.

PMID:34480787 | DOI:10.1002/jmri.27914

Environ Sci Pollut Res Int. 2021 Sep 4. doi: 10.1007/s11356-021-16032-5. Online ahead of print.

ABSTRACT

The paper evaluates the species richness, material transfer, energy flow, and system function of the southwestern Yellow Sea Ecosystem (SYSE) indicating intensive human intervention affecting this large marine ecosystem. Twenty functional groups were chosen to represent the basic components of the SYSE for Ecopath modeling based on offshore surveys, annual bird observations, and the China Fisheries Statistical Yearbooks. Forty-nine species based on 15 functional groups of Ecopath model were assessed by stable isotopic analysis (SIA) to verify ecosystem features, energy flow, and trophic structure of the SYSE derived from Ecopath model. Results showed there was a clear correlation of the estimated trophic structure calculated from SIA and the Ecopath model with R²=0.7184. The SYSE Ecopath model was still at an immature and unstable stage according to outputs of the modeling parameters. This paper provides a verification method of detecting the ecosystem features and maturity, stability, and resilience of marine ecosystems by comparing outputs from Ecopath models with SIA.

PMID:34480702 | DOI:10.1007/s11356-021-16032-5

Cardiol Ther. 2021 Sep 4. doi: 10.1007/s40119-021-00239-1. Online ahead of print.

ABSTRACT

INTRODUCTION: Hypertension is a progressive cardiovascular condition arising from complex aetiologies. Progression is strongly associated with functional and structural abnormalities that lead to multi-organ dysfunction. Stroke and myocardial infarction are two of the major complications of hypertension in India. Various anti-hypertensive drugs, such as calcium channel blockers (CCBs), beta-blockers, diuretics, angiotensin-converting enzyme inhibitors and angiotensin receptor blockers, have been the medications of choice for disease management and are known to be effective in reducing the complications of hypertension. CCBs, such as amlodipine, are also currently being used and proven to be effective, although their beneficial effects in the management of complications of hypertension like stroke and myocardial infarction (MI) have yet to be proven. Therefore, the aim of this systematic review was to evaluate the effect of amlodipine on stroke and MI in hypertensive patients.

METHODS: A systematic search of English electronic databases was performed for studies with sufficient statistical power that were published between 2000 andl 30 August 2020, following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) criteria. A total of 676 papers were screened, and 13 were found eligible to be included in the meta-analysis. Studies that included patients who suffered from MI or stroke and were under amlodipine treatment were included in the analysis. The odds ratio and the risk ratio of amlodipine compared to active control/placebo were noted from the studies and statistically analyzed.

RESULTS: Amlodipine had a significant effect in reducing stroke and MI in hypertensive patients. Similar to results published in reports, this systematic review proved that the hazard ratio for amlodipine was < 1 for stroke (0.69-1.04) and MI (0.77-0.98), showing that amlodipine accounted for better prevention of stroke and MI.

CONCLUSION: In the pooled analysis of data from 12 randomised controlled trials and one double-blinded cohort study measuring the effect of CCBs, we found that the CCB amlodipine reduced the risk of stroke and MI in hypertensive patients. Superior results for amlodipine were found in ten of the 13 studies included in this meta-analysis.

PMID:34480745 | DOI:10.1007/s40119-021-00239-1

Biometrics. 2021 Sep 4. doi: 10.1111/biom.13556. Online ahead of print.

ABSTRACT

An accelerated failure time (AFT) model assuming a log-linear relationship between failure time and a set of covariates can be either parametric or semiparametric, depending on the distributional assumption for the error term. Both classes of AFT models have been popular in the analysis of censored failure time data. The semiparametric AFT model is more flexible and robust to departures from the distributional assumption than its parametric counterpart. However, the semiparametric AFT model is subject to producing biased results for estimating any quantities involving an intercept. Estimating an intercept requires a separate procedure. Moreover, a consistent estimation of the intercept requires stringent conditions. Thus, essential quantities such as mean failure times might not be reliably estimated using semiparametric AFT models, which can be naturally done in the framework of parametric AFT models. Meanwhile, parametric AFT models can be severely impaired by misspecifications. To overcome this, we propose a new type of AFT model using a nonparametric Gaussian scale mixture distribution. We also provide feasible algorithms to estimate the parameters and mixing distribution. The finite sample properties of the proposed estimators are investigated via an extensive stimulation study. The proposed estimators are illustrated using a real data set.

PMID:34480750 | DOI:10.1111/biom.13556