Search

With the gradual marketization of energy trading, different economic entities such as the integrated energy service provider (IESP) and user aggregators (UAs) will form within the regional integrated energy system (RIES). The coordination of all entities to participate in joint planning for a globally optimal planning scheme while protecting privacy has posed a new challenge for RIES planning. First, the structure of the coupled electrical-gas-thermal RIES is clarified in this paper, and a mathematical model is constructed from IESP, UA, and electrical-gas-thermal network. Then, a RIES joint planning model considering IESP and multiple UAs is proposed with the objective of economical optimization. Afterwards, in order to adapt to the non-convexity of the sub-problem of the joint planning problem, the enhanced Benders algorithm is proposed to realize the distributed solution of the model, which protects the privacy of all entities to the greatest extent. Finally, the advantages of the joint planning scheme in terms of economy and energy efficiency are analyzed by comparing four sets of cases, and the good convergence of the proposed distributed algorithm is verified.

PURPOSE: To implement two Artificial Intelligence (AI) methods, radiomics and deep learning, to build diagnostic models for patients presenting with architectural distortion on Digital Breast Tomosynthesis (DBT) images. MATERIALS AND METHODS: A total of 298 patients were identified from a retrospective review, and all of them had confirmed pathological diagnoses, 175 malignant and 123 benign. The BI-RADS scores of DBT were obtained from the radiology reports, classified into 2, 3, 4A, 4B, 4C, and 5. The architectural distortion areas on craniocaudal (CC) and mediolateral oblique (MLO) views were manually outlined as the region of interest (ROI) for the radiomics analysis. Features were extracted using PyRadiomics, and then the support vector machine (SVM) was applied to select important features and build the classification model. Deep learning was performed using the ResNet50 algorithm, with the binary output of malignancy and benignity. The Gradient-weighted Class Activation Mapping (Grad-CAM) method was utilized to localize the suspicious areas. The predicted malignancy probability was used to construct the ROC curves, compared by the DeLong test. The binary diagnosis was made using the threshold of ≥ 0.5 as malignant. RESULTS: The majority of malignant lesions had BI-RADS scores of 4B, 4C, and 5 (148/175 = 84.6%). In the benign group, a substantial number of patients also had high BI-RADS ≥ 4B (56/123 = 45.5%), and the majority had BI-RADS ≥ 4A (102/123 = 82.9%). The radiomics model built using the combined CC+MLO features yielded an area under curve (AUC) of 0.82, the sensitivity of 0.78, specificity of 0.68, and accuracy of 0.74. If only features from CC were used, the AUC was 0.77, and if only features from MLO were used, the AUC was 0.72. The deep-learning model yielded an AUC of 0.61, significantly lower than all radiomics models (p

With the rapid development of society, the total education demand for higher vocational colleges and universities is growing at an extremely fast rate, and the original education management mode can no longer meet the needs of higher vocational education in the new era. The PDCA management model is a continuous improvement model that can achieve the objective of continuous improvement processes and perfectly fits the needs of higher vocational education management. This paper introduces the support vector machine, an algorithm suitable for high-dimensional classification problems, into the PDCA management model to carry out a multidimensional analysis of vocational high school students’ behavioral data, optimizing the checking part of the PDCA management model so that the cycle can continue to play an ideal role. The results of the application of the prediction of academically abnormal students show that the total number of academically normal students is 12,823, the total number of academically abnormal students is 2,981, and the proportion of abnormal students in different schools can be as high as 34.82%, and as low as 12%. The SVM algorithm, in the case of the imbalance between the proportion of academically abnormal and academically normal students, the model is still able to find out the majority of the students with abnormal studies, and it plays a central role in the PDCA management model to make the management of higher vocational education more perfect. By playing a central role, it enhances the management of higher education and creates a unique management path.

Purpose: To compare the accuracy of the Z CALC2 calculator and Barrett toric calculator in toric intraocular lens (IOL) calculation. Methods: Eighty-five eyes of 85 patients who underwent uneventful cataract surgery with toric IOL implantation were included. The accuracy was compared between the Z CALC2 calculator and Barrett toric calculator under two calculation modes: using simulated keratometry (SimK) from the IOLMaster 700 (Carl Zeiss Meditec AG) for posterior corneal astigmatism (PCA) prediction and employing total corneal astigmatism (total corneal refractive power [TCRP] or measured PCA) obtained from the Pentacam (Oculus Optikgeräte GmbH). The centroid of prediction errors, percentage of eyes with prediction errors within ±0.50 diopter (D), mean prediction error, and mean absolute prediction error were calculated. Subgroup analysis was conducted based on the orientation and magnitude of anterior corneal astigmatism and axial length. Results: When using SimK, the two calculators with predicted PCA showed comparable accuracy. When employing total corneal astigmatism, the Barrett toric calculator with measured PCA showed a lower centroid error (0.15 vs 0.38 D), a higher percentage of eyes with prediction errors within ±0.50 D (47.1% vs 32.9%, P =.018), and a lower mean prediction error (0.57 vs 0.71 D, P =.033) compared to the Z CALC2 calculator with TCRP in the 4-mm zone. In subgroup analysis, when employing total corneal astigmatism, the Barrett toric calculator with measured PCA exhibited superior accuracy, especially in the with-the-rule and anterior corneal astigmatism of 2.00 D or less subgroups. Conclusions: When using SimK, the Z CALC2 calculator and Barrett toric calculator yield comparable accuracy. The Barrett toric calculator with measured PCA may be more recommended when employing total corneal astigmatism. [J Refract Surg. 2024;40(10):e681–e691.] [ABSTRACT FROM AUTHOR]

Background: Captopril challenge test (CCT), seated saline infusion test (SSIT), oral sodium loading test (OSLT) and fludrocortisone suppression test (FST) are widely used diagnostic tests for primary aldosteronism (PA). These tests differ in terms of safety and complexity. Whether the simpler tests (CCT and SSIT) are comparable in diagnostic performance to the more complex ones (FST and OSLT) is unclear. Purpose: To compare the diagnostic accuracy of the four tests. Methods: This is a retrospective study of hypertensive patients who were screened for PA and completed at least one confirmatory test. The patients were divided into two cohorts: one including those who completed one to three tests was used for the estimation of sensitivity and specificity. The other including those who completed four tests was used for the comparison of accuracy. Bayesian method was used to obtain the sensitivity, specificity, and Youden index of each test. Results: The study included 1011 hypertensive patients. Among them, 895 patients completed one to three tests (including 889 CCT, 605 FST, 611 SSIT and 69 OSLT), and 116 patients completed four tests. SSIT had the highest sensitivity of 0.82(95% CI 0.78–0.86) but the lowest specificity of 0.76(0.70–0.80). OSLT had the lowest sensitivity of 0.65(0.56–0.75) but the highest specificity of 0.91(0.82–0.96). The sensitivity and specificity were 0.78 (95% CI, 0.75–0.82), 0.82 (95% CI, 0.78–0.85), for CCT, and 0.77 (95% CI, 0.73–0.81), 0.87 (95% CI, 0.82–0.91) for FST, respectively. The Youden index was not significantly different among the four tests[0.60(0.55–0.65) for CCT; 0.58(0.51–0.64) for SSIT; (0.64(0.57–0.69) for FST; 0.56(0.43–0.67) for OSLT]. Conclusion: The accuracy of simpler tests is comparable to the more complex ones. Considering the safety and simplicity of CCT, it may be a reasonable first choice when confirming the diagnosis of PA. [ABSTRACT FROM AUTHOR]

Purpose: Adrenal venous sampling (AVS) is recommended for subtyping primary aldosteronism (PA). However, in cases of PA, concurrent subclinical Cushing's syndrome (SCS) has the potential to confound AVS results. Pentixafor, a CXC chemokine receptor type 4–specific ligand, has been reported as a promising marker to evaluate functional nature of adrenal adenomas. This study aims to investigate the clinical value of Gallium-68 Pentixafor Positron Emission Tomography–Computed Tomography (68Ga-Pentixafor PET/CT) in the localization diagnosis of patients with PA plus SCS. Methods: Two patients with a confirmed diagnosis of PA plus SCS underwent AVS and 68Ga-Pentixafor PET/CT. Results: AVS results revealed no lateralization for both patients while 68Ga-Pentixafor PET/CT showed a unilateral adrenal nodule with increased uptake of 68Ga-Pentixafor. Unilateral adrenalectomy was performed based on the results of 68Ga-Pentixafor PET/CT. Subsequently, complete biochemical remission of autonomous aldosterone and cortisol secretion were achieved in both cases. Conclusions: 68Ga-Pentixafor PET/CT shows promising potential for the localization of aldosterone and cortisol co-secreting adrenal adenoma in patients with PA plus SCS. [ABSTRACT FROM AUTHOR]