Osteosarcoma is a rare bone cancer which is more common in children than in adults and has a high chance of metastasizing to the patient’s lungs. Due to initiated cases, it is difficult to diagnose and hard to detect the nodule in a lung at the early state. Convolutional Neural Networks (CNNs) are effectively applied for early state detection by considering CT-scanned images. Transferring patients from small hospitals to the cancer specialized hospital, Lerdsin Hospital, poses difficulties in information sharing because of the privacy and safety regulations. CD-ROM media was allowed for transferring patients’ data to Lerdsin Hospital. Digital Imaging and Communications in Medicine (DICOM) files cannot be stored on a CD-ROM. DICOM must be converted into other common image formats, such as BMP, JPG and PNG formats. Quality of images can affect the accuracy of the CNN models. In this research, the effect of different image formats is studied and experimented. Three popular medical CNN models, VGG-16, ResNet-50 and MobileNet-V2, are considered and used for osteosarcoma detection. The positive and negative class images are corrected from Lerdsin Hospital, and 80% of all images are used as a training dataset, while the rest are used to validate the trained models. Limited training images are simulated by reducing images in the training dataset. Each model is trained and validated by three different image formats, resulting in 54 testing cases. F1-Score and accuracy are calculated and compared for the models’ performance. VGG-16 is the most robust of all the formats. PNG format is the most preferred image format, followed by BMP and JPG formats, respectively.
Objective: To develop and validate a prognostic scoring scheme for the prediction of microalbuminuria in type 2 diabetic patients of Thai descent. Methods: The clinical information from type 2 diabetic patients who were treated at community hospitals was used to develop a prediction model (derivation set). The model evaluated at a tertiary hospital (validation set). A stepwise logistic regression model was used to identify the independent risk variables from the derivation set and a simple point scoring system was derived from the beta-coefficients. The risk scoring scheme was validated by the validation set. Results: The risk scoring scheme is based on six risk predictors: the duration of diabetes, age at the onset of diabetes, systolic blood pressure, low density lipoprotein levels, creatinine levels, and alcohol consumption. The total score ranged from 0 to 11.5. The likelihood of microalbuminuria in patients with low risk (scores ≤ 2) was 0.28, with moderate risk (scores 2.5 to 5.5) was 0.86, and high risk (scores ≥ 6) was 7.36. The area under the ROC curve of the derivation set and validation set were 0.768 (95% CI 0.73 - 0.81) and 0.758 (95% CI 0.70 - 0.80), respectively. Conclusion: Our scoring system is a simple and reasonably accurate method for predicting the future presence of microalbuminuria in type 2 diabetic patients
Background Type 2 diabetes (T2D) is one of the most common chronic diseases in the world. In recent decades the prevalence of this disease has increased alarmingly in lower to middle income countries, where their resource-limited health care systems have struggled to meet this increased burden. Improving patient self-care by improving diabetes knowledge and diabetes management self-efficacy represents a feasible way of ameliorating the impact of T2D on the patient, and the health care system. Unfortunately, the relationships between self-efficacy, diabetes self-management, and thereafter, patient outcomes, are still far from well understood. Although a domain-specific measure of diabetes management self-efficacy, the Diabetes Management Self-Efficacy Scale (DMSES), has been validated in the Thai T2D population, more general measures of self-efficacy, such as the General Self-Efficacy scale (GSE) have not been validated in this population. In this paper we translate and examine the psychometric properties of the GSE in Thais living with T2D. Methods In this nation-wide study we examined the psychometric properties of the GSE in 749 Thais diagnosed with T2D within the last five years, and evaluated its relationship with the DMSES along with other patient characteristics. Reliability of GSE was assessed using Cronbach’s alpha, and the construct validity was examined using confirmatory factor analysis, along with GSE’s convergence and discrimination from DMSES. Results The Thai version of the GSE was shown to have good psychometric properties in Thais living with T2D. Cronbach’s alpha was shown to be 0.87 (95% CI [0.86, 0.88]). We also demonstrated the structural validity of the GSE (Tucker-Lewis Index = 0.994, Cumulative Fit Index = 0.995, Adjusted Goodness of Fit Index = 0.998, Root Mean Square Error of Approximations = 0.025, 95% CI [0.06–0.039]), and that this instrument has a similar structure in Thais as in other populations. GSE was also shown to have some overlap with the DMSES with correlations among GSE and the DMSES domains ranging from 0.18 to 0.26, but also the GSE has substantial discrimination from DMSES (Disattenuated correlation coefficient = 0.283, 95% CI [0.214–0.352], p < 0.001). This suggests that while general and diabetes management self-efficacy are somewhat associated, there are aspects of diabetes management self-efficacy not captured by the more stable general self-efficacy. Conclusions We demonstrate that the Thai GSE is a reliable and valid measure. We believe the GSE may represent a useful tool to examine the efficacy of proposed and existing diabetes self-management, and management self-efficacy interventions.
Background: Angiotensin-Converting Enzyme Inhibitors (ACEIs) and Angiotensin Receptor Blockers (ARBs) are popular first-line agents for delaying the onset of diabetic nephropathy and diabetic kidney disease in diabetic patients without nephropathy and for reducing all causes of mortality in diabetic patients with nephropathy. However, long-term data showing a reduction in mortality from all causes or renal failure in type 2 diabetes patients with undetermined nephropathy taking ACEIs/ARBs are not available. Objective: To compare renal and other causes of death between those treated and not treated with ACEIs/ARBs in type 2 diabetes patients who are non-nephropathic, nephropathic and have an undetermined nephropathy status. Methods: Type 2 diabetes patients (n = 7,946) who registered with the Thailand Diabetes Registry Project (TDRP) in 2003 were followed-up prospectively for 5 years until January 25, 2008. Baseline demographic data and diabetic nephropathy status were recorded when the patient registered in the TDRP. Living statuses were retrieved from the database of each study site and causes of death were retrieved from the death certificates from the Bureau of Registration Administration of Thailand. Results: There were 716 type 2 diabetic patients that died within 5 years of registration in the TPDR from all causes of death. Of these cases, 66 died from renal causes. The mortality incidence from renal causes in undetermined nephropathy patients who were treated and not treated with ACEIs/ARBs was 1.25 and 1.30 per 1000 person-years, respectively. After controlling for the propensity score, the competing risk analysis showed that treatment with ACEIs/ ARBs was not significantly associated with prevention of death from renal or other causes in type 2 diabetes patients with an undetermined nephropathy status (HR = 0.83, 95% CI: 0.33-2.09, p-value = 0.688 for renal causes; HR = 1.26, 95% CI: 0.97-1.63, p-value = 0.085 for other causes). Treatment with ACEIs/ARBs was significantly associated with the prevention of renal and other causes of death in type 2 diabetes patients with nephropathy (HR = 0.49, 95% CI: 0.25-0.95, p-value = 0.034 for renal causes; HR = 0.73, 95% CI: 0.56-0.95, p-value = 0.019 for other causes). Conclusions: Treatment with ACEIs or ARBs is not necessary for everyone, especially in type 2 diabetes patients with an undetermined nephropathy status. Healthcare services teams should screen for microalbuminuria before the treatment of all newly diagnosed type 2 diabetes patients with ACEIs or ARBs. J ou rna l o f D ia be tes & M e ta bolism
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.