| 1. |
- Arian, Fatemeh, et al.
(författare)
-
Myocardial Function Prediction After Coronary Artery Bypass Grafting Using MRI Radiomic Features and Machine Learning Algorithms
- 2022
-
Ingår i: Journal of digital imaging. - : Springer Nature. - 0897-1889 .- 1618-727X. ; 35:6, s. 1708-1718
-
Tidskriftsartikel (refereegranskat)abstract
- The main aim of the present study was to predict myocardial function improvement in cardiac MR (LGE-CMR) images in patients after coronary artery bypass grafting (CABG) using radiomics and machine learning algorithms. Altogether, 43 patients who had visible scars on short-axis LGE-CMR images and were candidates for CABG surgery were selected and enrolled in this study. MR imaging was performed preoperatively using a 1.5-T MRI scanner. All images were segmented by two expert radiologists (in consensus). Prior to extraction of radiomics features, all MR images were resampled to an isotropic voxel size of 1.8 × 1.8 × 1.8 mm3. Subsequently, intensities were quantized to 64 discretized gray levels and a total of 93 features were extracted. The applied algorithms included a smoothly clipped absolute deviation (SCAD)–penalized support vector machine (SVM) and the recursive partitioning (RP) algorithm as a robust classifier for binary classification in this high-dimensional and non-sparse data. All models were validated with repeated fivefold cross-validation and 10,000 bootstrapping resamples. Ten and seven features were selected with SCAD-penalized SVM and RP algorithm, respectively, for CABG responder/non-responder classification. Considering univariate analysis, the GLSZM gray-level non-uniformity-normalized feature achieved the best performance (AUC: 0.62, 95% CI: 0.53–0.76) with SCAD-penalized SVM. Regarding multivariable modeling, SCAD-penalized SVM obtained an AUC of 0.784 (95% CI: 0.64–0.92), whereas the RP algorithm achieved an AUC of 0.654 (95% CI: 0.50–0.82). In conclusion, different radiomics texture features alone or combined in multivariate analysis using machine learning algorithms provide prognostic information regarding myocardial function in patients after CABG.
|
|
| 2. |
- Lin, Chung-Ying, et al.
(författare)
-
Using an integrated social cognition model to predict COVID-19 preventive behaviours
- 2020
-
Ingår i: British Journal of Health Psychology. - : John Wiley & Sons. - 1359-107X .- 2044-8287. ; 25:4, s. 981-1005
-
Tidskriftsartikel (refereegranskat)abstract
- Objectives Rates of novel coronavirus disease 2019 (COVID-19) infections have rapidly increased worldwide and reached pandemic proportions. A suite of preventive behaviours have been recommended to minimize risk of COVID-19 infection in the general population. The present study utilized an integrated social cognition model to explain COVID-19 preventive behaviours in a sample from the Iranian general population.Design The study adopted a three-wave prospective correlational design.Methods Members of the general public (N = 1,718, Mage = 33.34, SD = 15.77, male = 796, female = 922) agreed to participate in the study. Participants completed self-report measures of demographic characteristics, intention, attitude, subjective norm, perceived behavioural control, and action self-efficacy at an initial data collection occasion. One week later, participants completed self-report measures of maintenance self-efficacy, action planning and coping planning, and, a further week later, measures of COVID-19 preventive behaviours. Hypothesized relationships among social cognition constructs and COVID-19 preventive behaviours according to the proposed integrated model were estimated using structural equation modelling.Results The proposed model fitted the data well according to multiple goodness-of-fit criteria. All proposed relationships among model constructs were statistically significant. The social cognition constructs with the largest effects on COVID-19 preventive behaviours were coping planning (? = .575, p < .001) and action planning (? = .267, p < .001).Conclusions Current findings may inform the development of behavioural interventions in health care contexts by identifying intervention targets. In particular, findings suggest targeting change in coping planning and action planning may be most effective in promoting participation in COVID-19 preventive behaviours. Statement of contribution What is already known on this subject? Curbing COVID-19 infections globally is vital to reduce severe cases and deaths in at-risk groups. Preventive behaviours like handwashing and social distancing can stem contagion of the coronavirus. Identifying modifiable correlates of COVID-19 preventive behaviours is needed to inform intervention. What does this study add? An integrated model identified predictors of COVID-19 preventive behaviours in Iranian residents. Prominent predictors were intentions, planning, self-efficacy, and perceived behavioural control. Findings provide insight into potentially modifiable constructs that interventions can target. Research should examine if targeting these factors lead to changes in COVID-19 behaviours over time.
|
|
| 3. |
- Rajabi, Zahra, et al.
(författare)
-
Effect of addition of tin on the microstructure and machinability of alpha-brass
- 2018
-
Ingår i: Materials Science and Technology. - : Taylor & Francis. - 0267-0836 .- 1743-2847. ; 34:10, s. 1218-1227
-
Tidskriftsartikel (refereegranskat)abstract
- This study was aimed at developing lead-free brass alloys with the goal of substituting lead element with tin. For this purpose, lead-free alloys with tin were developed and the microstructure, hardness and machining behaviour of the Cu-30%Zn alloy was compared with Cu-30%Zn-x%Sn (x = 1.2, 3.2, 5.4, 8,11.4,13.9,17.4). The results showed that the addition of Sn to single-alpha phase brass led to the formation of duplex (alpha + beta') brass and then the formation of (beta' + gamma) brass both with increased hardness. In addition, the addition of Sn to Cu-30%Zn alloy led to the decrement of equivalent machining forces (F-m), surface roughness and also the promotion of chip fragmentation due to the formation of the beta' phase, which is an improvement in machinability.
|
|
