Categories
Nevin Manimala Statistics

Chronic stress in practice assistants: An analytic approach comparing four machine learning classifiers with a standard logistic regression model

PLoS One. 2021 May 4;16(5):e0250842. doi: 10.1371/journal.pone.0250842. eCollection 2021.

ABSTRACT

BACKGROUND: Occupational stress is associated with adverse outcomes for medical professionals and patients. In our cross-sectional study with 136 general practices, 26.4% of 550 practice assistants showed high chronic stress. As machine learning strategies offer the opportunity to improve understanding of chronic stress by exploiting complex interactions between variables, we used data from our previous study to derive the best analytic model for chronic stress: four common machine learning (ML) approaches are compared to a classical statistical procedure.

METHODS: We applied four machine learning classifiers (random forest, support vector machine, K-nearest neighbors’, and artificial neural network) and logistic regression as standard approach to analyze factors contributing to chronic stress in practice assistants. Chronic stress had been measured by the standardized, self-administered TICS-SSCS questionnaire. The performance of these models was compared in terms of predictive accuracy based on the ‘operating area under the curve’ (AUC), sensitivity, and positive predictive value.

FINDINGS: Compared to the standard logistic regression model (AUC 0.636, 95% CI 0.490-0.674), all machine learning models improved prediction: random forest +20.8% (AUC 0.844, 95% CI 0.684-0.843), artificial neural network +12.4% (AUC 0.760, 95% CI 0.605-0.777), support vector machine +15.1% (AUC 0.787, 95% CI 0.634-0.802), and K-nearest neighbours +7.1% (AUC 0.707, 95% CI 0.556-0.735). As best prediction model, random forest showed a sensitivity of 99% and a positive predictive value of 79%. Using the variable frequencies at the decision nodes of the random forest model, the following five work characteristics influence chronic stress: too much work, high demand to concentrate, time pressure, complicated tasks, and insufficient support by practice leaders.

CONCLUSIONS: Regarding chronic stress prediction, machine learning classifiers, especially random forest, provided more accurate prediction compared to classical logistic regression. Interventions to reduce chronic stress in practice personnel should primarily address the identified workplace characteristics.

PMID:33945572 | DOI:10.1371/journal.pone.0250842

Categories
Nevin Manimala Statistics

Poor sleep quality and its associated factors among pregnant women in Northern Ethiopia, 2020: A cross sectional study

PLoS One. 2021 May 4;16(5):e0250985. doi: 10.1371/journal.pone.0250985. eCollection 2021.

ABSTRACT

BACKGROUND: Sleep is a physiologic necessity for all humankind. Pregnant women, in particular, need adequate sleep to develop their fetuses as well as save energy required for delivery. A change in sleep quality and quantity is the most common phenomena during pregnancy due to mechanical and hormonal factors. However, there is a scarcity of data about poor sleep quality and its associated factors among pregnant mothers in Ethiopia. Therefore, this study aims to determine the prevalence of poor sleep quality and its associated factors among pregnant mothers at Wadila primary hospital, Ethiopia.

METHODS: Institution based cross-sectional study design was employed on 411 pregnant mothers. Data were collected using a pre-tested interviewer administered questionnaire. SPSS Version 23 for Windows software was used for data analyses. Bivariate analysis was conducted to detect the association between dependent and independent variables, and to choose candidate variables (p < 0.25) for multivariate logistic regression. Statistical significance was set at p-value <0.05.

RESULTS: A total of 411 participants were included in the study making a response rate of 97.4%. Overall, 68.4% of participants found to have poor sleep quality (PSQI>5). Age of the mother [age 20-30 years; AOR = 4.3 CI (1.8, 9.9), p = 0.001, and age >30 years; AOR = 4.7 CI (1.6, 13.9) p = 0.005], gestational age [second trimester, AOR = 2.46, CI (1.2, 4.9), p = 0.01 and third trimester, AOR = 7.5, CI (3.2, 17.8), p = 0.000] and parity [multiparous women; AOR = 2.1(1.24, 3.6) p = 0.006] were predictor variables for poor sleep quality among pregnant mothers.

CONCLUSION: More than two-third of pregnant mothers had poor sleep quality. Advanced maternal age, increased gestational age and multiparty are found to be predictors of poor sleep quality in pregnant women.

PMID:33945578 | DOI:10.1371/journal.pone.0250985

Categories
Nevin Manimala Statistics

Risk Factors Associated With Extended Length of Hospital Stay After Geriatric Hip Fracture

J Am Acad Orthop Surg Glob Res Rev. 2021 May 4;5(5):e21.00073. doi: 10.5435/JAAOSGlobal-D-21-00073.

ABSTRACT

INTRODUCTION: Within the geriatric hip fracture population, there exists a subset of patients whose length of inpatient hospital stay is excessive relative to the average. A better understanding of the risk factors associated with this group would be of value so that targeted prevention efforts can be properly directed. The goal of this study was to identify and characterize the risk factors associated with an extended length of hospital stay (eLOS) in the geriatric hip fracture population. In addition, a statistical model was created to predict the probability of eLOS in a geriatric hip fracture patient.

METHODS: The National Surgical Quality Improvement Program database (2005 to 2018) was searched for patients aged ≥65 years who underwent hip fracture surgery. Patients with a hospital stay greater than or equal to 14 days were considered to have an eLOS. A multivariate logistic regression model using 24 patient characteristics from two-thirds of the study population was created to determine independent risk factors predictive of having an eLOS; the remaining one-third of the population was used for internal model validation. Regression analyses were performed to determine preoperative and postoperative risk factors for having an eLOS.

RESULTS: A total of 77,144 patients were included in the study. Preoperatively, male sex, dyspnea, ventilator use, chronic obstructive pulmonary disease, American Society of Anesthesiologist class 3 and 4, and increased admission-to-operation time were among the factors associated with higher odds of having an eLOS (all P < 0.001). Postoperatively, patients with acute renal failure had the highest likelihood of eLOS (odds ratio [OR] 7.664), followed by ventilator use >48 hours (OR 4.784) and pneumonia (OR 4.332).

DISCUSSION: Among geriatric hip fracture patients, particular efforts should be directed toward optimizing those with preoperative risk factors for eLOS. Preemptive measures to target the postoperative complications with the strongest eLOS association may be beneficial for both the patient and the healthcare system as a whole.

PMID:33945514 | DOI:10.5435/JAAOSGlobal-D-21-00073

Categories
Nevin Manimala Statistics

MetaGSCA: A tool for meta-analysis of gene set differential coexpression

PLoS Comput Biol. 2021 May 4;17(5):e1008976. doi: 10.1371/journal.pcbi.1008976. Online ahead of print.

ABSTRACT

Analyses of gene set differential coexpression may shed light on molecular mechanisms underlying phenotypes and diseases. However, differential coexpression analyses of conceptually similar individual studies are often inconsistent and underpowered to provide definitive results. Researchers can greatly benefit from an open-source application facilitating the aggregation of evidence of differential coexpression across studies and the estimation of more robust common effects. We developed Meta Gene Set Coexpression Analysis (MetaGSCA), an analytical tool to systematically assess differential coexpression of an a priori defined gene set by aggregating evidence across studies to provide a definitive result. In the kernel, a nonparametric approach that accounts for the gene-gene correlation structure is used to test whether the gene set is differentially coexpressed between two comparative conditions, from which a permutation test p-statistic is computed for each individual study. A meta-analysis is then performed to combine individual study results with one of two options: a random-intercept logistic regression model or the inverse variance method. We demonstrated MetaGSCA in case studies investigating two human diseases and identified pathways highly relevant to each disease across studies. We further applied MetaGSCA in a pan-cancer analysis with hundreds of major cellular pathways in 11 cancer types. The results indicated that a majority of the pathways identified were dysregulated in the pan-cancer scenario, many of which have been previously reported in the cancer literature. Our analysis with randomly generated gene sets showed excellent specificity, indicating that the significant pathways/gene sets identified by MetaGSCA are unlikely false positives. MetaGSCA is a user-friendly tool implemented in both forms of a Web-based application and an R package “MetaGSCA”. It enables comprehensive meta-analyses of gene set differential coexpression data, with an optional module of post hoc pathway crosstalk network analysis to identify and visualize pathways having similar coexpression profiles.

PMID:33945541 | DOI:10.1371/journal.pcbi.1008976

Categories
Nevin Manimala Statistics

Pentoxifylline for the prevention of contrast-induced nephropathy: systematic review and meta-analysis of randomised controlled trials

BMJ Open. 2021 Apr 8;11(4):e043436. doi: 10.1136/bmjopen-2020-043436.

ABSTRACT

OBJECTIVES: To summarise current evidence on the use of pentoxifylline (PTX) to prevent contrast-induced nephropathy (CIN).

METHODS: The PubMed, Embase and CENTRAL databases were searched for randomised controlled trials including patients with and without PTX undergoing contrast media exposure. We analysed the incidence of CIN and serum creatinine changes before and after contrast media exposure. All statistical analyses were conducted with Review Manager V.5.3.

RESULTS: We finally enrolled in seven randomised controlled trials with a total of 1484 patients in this analysis. All of seven included studies were performed in patients undergoing angioplasty or stenting. The overall rates of CIN were 8.8% and 10.4% in the PTX groups and control groups, respectively. However, no significant reduction in the CIN rate was observed in the patients treated with PTX compared with the control groups (OR 0.81, 95% CI 0.57 to 1.13, I2=0, p=0.21). All studies reported no hospital mortality and the new requirement for dialysis during the trials.

CONCLUSION: Perioperative administration of PTX to patients undergoing angioplasty did not significantly reduce the development of CIN but showed some weak tendency of lower serum creatinine increase. Based on the available trials, the evidence does not support the administration of PTX for the prevention of CIN. More trials with larger sample sizes are needed to evaluate the role of PTX in CIN prevention.

PMID:33945499 | DOI:10.1136/bmjopen-2020-043436

Categories
Nevin Manimala Statistics

Research trends in rabies vaccine in the last three decades: a bibliometric analysis of global perspective

Hum Vaccin Immunother. 2021 May 4:1-9. doi: 10.1080/21645515.2021.1910000. Online ahead of print.

ABSTRACT

Introduction: Rabies is an infectious zoonotic viral disease which mainly occurs in Africa and Asia. Dogs are predominantly responsible for rabies transmission contributing up to 99% of all human rabies cases. Rabies is a vaccine preventable disease in both animals and humans.Objective: This study aimed to quantify and characterize the scientific literature and identify the top most cited studies in rabies vaccine research (RVR) from 1991 to 2020.Methods: The data used in this study were downloaded from Web of Science Core Collection (WoSCC), Science Citation Index-Expanded (SCI-E) database. Network visualization analysis was performed using VOSviewer software.Results: A total of 1,042 papers (article: n = 986, 94.6%, review: n = 56, 5.4%) were included in this study. These have been cited 17,390 times with an average citation per paper was 16.69 times. The most frequent publication year was 2019 (n = 75, 7.2%). More than 55% studies were published from the United State of America (USA) (n = 380, 36.5%), France (n = 128, 12.3%), and China (n = 97, 9.3%). The most studied Web of Science (WoS) category was immunology (n = 344, 33%). The most prolific author in RVR was Rupprecht CE (n = 55, 5.3%). ‘Vaccine’ was the leading journal (n = 218, 20.9%). Rabies was the most widely used keyword.Conclusion: Abundant literature has been published on RVR in developed countries. This study might provide a reference to understand the current and future research trends in RVR. In developing countries research collaboration and co-operation among institutes and researchers needs to be strengthened with developed countries.

PMID:33945433 | DOI:10.1080/21645515.2021.1910000

Categories
Nevin Manimala Statistics

Hybrid Spectral-IRDx: Near-IR and Ultrasound Attenuation System for Differentiating Breast Cancer from Adjacent Normal Tissue

IEEE Trans Biomed Eng. 2021 May 4;PP. doi: 10.1109/TBME.2021.3077582. Online ahead of print.

ABSTRACT

OBJECTIVE: While performing surgical excision for breast cancer (lumpectomy), it is important to ensure a clear margin of normal tissue around the cancer to achieve complete resection. The current standard is histopathology; however, it is time-consuming and labour-intensive requiring skilled personnel.

METHOD: We describe a Hybrid Spectral-IRDx – a combination of the previously reported Spectral-IRDx tool with multimodal ultrasound and NIR spectroscopy techniques. We show how this portable, cost-effective, minimal-contact tool could provide rapid diagnosis of cancer using formalin-fixed (FF) and deparaffinized (DP) breast biopsy tissues.

RESULTS: Using this new tool, measurements were performed on cancerous/fibroadenoma and its adjacent normal tissues from the same patients (N=14). The acoustic attenuation coefficient () and reduced scattering coefficient (s) (at 850, 940, and 1060 nm) for the cancerous/fibroadenoma tissues were reported to be higher compared to adjacent normal tissues, a basis of delineation. Comparing FF cancerous and adjacent normal tissue, the difference in s at 850 nm and 940 nm were statistically significant (p=3.17e-2 and 7.94e-3 respectively). The difference in between the cancerous and adjacent normal tissues for DP and FF tissues were also statistically significant (p=2.85e-2 and 7.94e-3 respectively). Combining multimodal parameters and s (at 940 nm) show highest statistical significance (p=6.72e-4) between FF cancerous/fibroadenoma and adjacent normal tissues.

CONCLUSION: We show that Hybrid Spectral-IRDx can accurately delineate between cancerous and adjacent normal breast biopsy tissue.

SIGNIFICANCE: The results obtained establish the proof-of-principle and large-scale testing of this multimodal breast cancer diagnostic platform for core biopsy diagnosis.

PMID:33945469 | DOI:10.1109/TBME.2021.3077582

Categories
Nevin Manimala Statistics

Image Inpainting by End-to-End Cascaded Refinement with Mask Awareness

IEEE Trans Image Process. 2021 May 4;PP. doi: 10.1109/TIP.2021.3076310. Online ahead of print.

ABSTRACT

Inpainting arbitrary missing regions is challenging because learning valid features for various masked regions is nontrivial. Though U-shaped encoder-decoder frameworks have been witnessed to be successful, most of them share a common drawback of mask unawareness in feature extraction because all convolution windows (or regions), including those with various shapes of missing pixels, are treated equally and filtered with fixed learned kernels. To this end, we propose our novel mask-aware inpainting solution. Firstly, a Mask-Aware Dynamic Filtering (MADF) module is designed to effectively learn multi-scale features for missing regions in the encoding phase. Specifically, filters for each convolution window are generated from features of the corresponding region of the mask. The second fold of mask awareness is achieved by adopting Point-wise Normalization (PN) in our decoding phase, considering that statistical natures of features at masked points differentiate from those of unmasked points. The proposed PN can tackle this issue by dynamically assigning point-wise scaling factor and bias. Lastly, our model is designed to be an end-to-end cascaded refinement one. Supervision information such as reconstruction loss, perceptual loss and total variation loss is incrementally leveraged to boost the inpainting results from coarse to fine. Effectiveness of the proposed framework is validated both quantitatively and qualitatively via extensive experiments on three public datasets including Places2, CelebA and Paris StreetView.

PMID:33945479 | DOI:10.1109/TIP.2021.3076310

Categories
Nevin Manimala Statistics

Does methylprednisolone reduce the mortality risk in hospitalized COVID-19 patients? A meta-analysis of randomized control trials

Expert Rev Respir Med. 2021 May 4. doi: 10.1080/17476348.2021.1925546. Online ahead of print.

ABSTRACT

OBJECTIVES: The questions remained if mortality benefits with dexamethasone seen in patients with coronavirus disease 2019 (COVID-19) also extend to other systemic corticosteroids such as methylprednisolone. This article presents a meta-analysis of randomized controlled trials (RCTs) to ascertain if methylprednisolone can be recommended for use in patients with COVID-19 to prevent deaths.

METHODS: Systematic literature search was performed in PubMed, Scopus, Cochrane Central Register of Controlled Trials, and preprint servers until 13th April 2021. The outcome of interest was all-cause mortality. The random-effects model for the meta-analysis was utilized to estimate the pooled odds ratio (OR) at 95% confidence intervals (CI).

RESULTS: Five RCTs were included in the meta-analysis. The pooled OR for all-cause mortality was 0.64 (95% CI: 0.29 -1.43, n=652) comparing methylprednisolone with the control, indicating no mortality benefits. A similar finding was noted with a sub-group analysis including four trials that used low-dose methylprednisolone. However, the only trial that administered high doses of methylprednisolone indicated a statistically significant mortality benefit (OR 0.08, 95% CI: 0.02-0.42).

CONCLUSIONS: A short duration (3 to 5 days) pulse therapy of high-dose methylprednisolone can be a promising alternative to the low-dose dexamethasone therapy in severely ill patients with COVID-19 to prevent deaths.

PMID:33945381 | DOI:10.1080/17476348.2021.1925546

Categories
Nevin Manimala Statistics

Prediction of stroke-associated pneumonia by the A2DS2, AIS-APS, and ISAN scores: a systematic review and meta-analysis

Expert Rev Respir Med. 2021 May 4. doi: 10.1080/17476348.2021.1923482. Online ahead of print.

ABSTRACT

BACKGROUND: Different scoring systems (A2DS2, AISAPS, ISAN) have been designed to predict the risk of in-hospital stroke-associated pneumonia (SAP). Studies have assessed the accuracy of these scores for predicting SAP. We performed this meta-analysis to consolidate the evidence on the predictive accuracies for SAP of the A2DS2, AISAPS, and ISAN scores.

MATERIALS AND METHODS: We conducted a systematic search for all studies reporting the SAP predictive accuracy of A2DS2, AISAPS, or ISAN scores in the databases of PubMed Central, SCOPUS, MEDLINE, Embase, and Cochrane from inception until December 2020. We used the STATA software for the meta-analysis.

RESULTS: : We included 19 studies with 35 849 patients. The pooled score sensitivities were 78% (95% CI, 71%-83%) for A2DS2, 79% (95% CI, 77%-81%) for AISAPS, and 79% (95% CI, 77%-81%) for ISAN. The pooled score specificities were 73% (95% CI, 65%-80%) for A2DS2, 74% (95% CI, 69%-79%) for AISAPS, and 74% (95% CI, 69%-79%) for ISAN. We found significant heterogeneity for all the scoring systems based on the chi-square test results and an I2 statistic > 75%. We performed meta-regression to explore the source of heterogeneity and found that patient selection (p<0.05) and reference standards (p<0.05) in the sensitivity model, index test standards (p<0.05), flow and timing of tests (p<0.01) in the specificity model, and mean age (p<0.001) in the joint model were the source of heterogeneity.

CONCLUSIONS: To summarize, we found that A2S2, AISAPS and ISAN have moderate predictive accuracy for SAP with A2S2 having a stable cut-off value.

PMID:33945394 | DOI:10.1080/17476348.2021.1923482