Deep learning vs. robust federal learning for distinguishing adrenal metastases from benign lesions with multi-phase CT images.

Background: Differentiating adrenal adenomas from metastases poses a significant challenge, particularly in patients with a history of extra-adrenal malignancy. This study investigates the performance of three-phase computed tomography (CT) based robust federal learning algorithm and traditional deep learning for distinguishing metastases from benign adrenal lesions. Material and methods: This retrospective analysis includes 1187 instances who underwent three-phase CT scans between January 2008 and March 2021, comprising 720 benign lesions and 467 metastases. Utilizing the three-phase CT images, both a Robust Federal Learning Signature (RFLS) and a traditional Deep Learning Signature (DLS) were constructed using the Least Absolute Shrinkage and Selection Operator (LASSO) logistic regression. Their diagnostic capabilities were subsequently validated and compared using metrics such as the Areas Under the Receiver Operating Curve (AUCs), Net Reclassification Improvement (NRI), and Decision Curve Analysis (DCA). Results: Compared with DLS, the RFLS showed better capability in distinguishing metastases from benign adrenal lesions (average AUC: 0.816 vs.0.798, NRI = 0.126, P < 0.072; 0.889 vs.0.838, NRI = 0.209, P < 0.001; 0.903 vs.0.825, NRI = 0.643, p < 0.001) in the four-testing cohort, respectively. DCA showed that the RFLS added more net benefit than DLS for clinical utility. Moreover, Comparison with state-of-the-art federal learning methods, the results once again confirmed that the RFLS significantly improved the diagnostic performance based on three-phase CT (AUC: AP, 0.727 vs. 0.757 vs. 0.739 vs. 0.796; PCP, 0.781 vs. 0.851 vs. 0.790 vs. 0.882; VP, 0.789 vs. 0.814 vs. 0.779 vs. 0.886). Conclusion: RFLS was superior to DLS for preoperative distinguishing metastases from benign adrenal lesions with multi-phase CT Images.

Robustly federated learning model for identifying high-risk patients with postoperative gastric cancer recurrence.

The prediction of patient disease risk via computed tomography (CT) images and artificial intelligence techniques shows great potential. However, training a robust artificial intelligence model typically requires large-scale data support. In practice, the collection of medical data faces obstacles related to privacy protection. Therefore, the present study aims to establish a robust federated learning model to overcome the data island problem and identify high-risk patients with postoperative gastric cancer recurrence in a multicentre, cross-institution setting, thereby enabling robust treatment with significant value. In the present study, we collect data from four independent medical institutions for experimentation. The robust federated learning model algorithm yields area under the receiver operating characteristic curve (AUC) values of 0.710, 0.798, 0.809, and 0.869 across four data centres. Additionally, the effectiveness of the algorithm is evaluated, and both adaptive and common features are identified through analysis.

Motor imagery electroencephalogram classification algorithm based on joint features in the spatial and frequency domains and instance transfer.

Introduction: Motor imagery electroencephalography (MI-EEG) has significant application value in the field of rehabilitation, and is a research hotspot in the brain-computer interface (BCI) field. Due to the small training sample size of MI-EEG of a single subject and the large individual differences among different subjects, existing classification models have low accuracy and poor generalization ability in MI classification tasks. Methods: To solve this problem, this paper proposes a electroencephalography (EEG) joint feature classification algorithm based on instance transfer and ensemble learning. Firstly, the source domain and target domain data are preprocessed, and then common space mode (CSP) and power spectral density (PSD) are used to extract spatial and frequency domain features respectively, which are combined into EEG joint features. Finally, an ensemble learning algorithm based on kernel mean matching (KMM) and transfer learning adaptive boosting (TrAdaBoost) is used to classify MI-EEG. Results: To validate the effectiveness of the algorithm, this paper compared and analyzed different algorithms on the BCI Competition IV Dataset 2a, and further verified the stability and effectiveness of the algorithm on the BCI Competition IV Dataset 2b. The experimental results show that the algorithm has an average accuracy of 91.5% and 83.7% on Dataset 2a and Dataset 2b, respectively, which is significantly better than other algorithms. Discussion: The statement explains that the algorithm fully exploits EEG signals and enriches EEG features, improves the recognition of the MI signals, and provides a new approach to solving the above problem.

Single-channel EEG signal extraction based on DWT, CEEMDAN, and ICA method.

In special application scenarios, such as portable anesthesia depth monitoring, portable emotional state recognition and portable sleep monitoring, electroencephalogram (EEG) signal acquisition equipment is required to be convenient and easy to use. It is difficult to remove electrooculogram (EOG) artifacts when the number of EEG acquisition channels is small, especially when the number of observed signals is less than that of the source signals, and the overcomplete problem will arise. The independent component analysis (ICA) algorithm commonly used for artifact removal requires the number of basis vectors to be smaller than the dimension of the input data due to a set of standard orthonormal bases learned during the convergence process, so it cannot be used to solve the overcomplete problem. The empirical mode decomposition method decomposes the signal into several independent intrinsic mode functions so that the number of observed signals is more than that of the source signals, solving the overcomplete problem. However, when using this method to solve overcompleteness, the modal aliasing problem will arise, which is caused by abnormal events such as sharp signals, impulse interference, and noise. Aiming at the above problems, we propose a novel EEG artifact removal method based on discrete wavelet transform, complete empirical mode decomposition for adaptive noise (CEEMDAN) and ICA in this paper. First, the input signals are transformed by discrete wavelet (DWT), and then CEEMDAN is used to solve the overcomplete and mode aliasing problems, meeting the a priori conditions of the ICA algorithm. Finally, the components belonging to EOG artifacts are removed according to the sample entropy value of each independent component. Experiments show that this method can effectively remove EOG artifacts while solving the overcomplete and modal aliasing problems.

Association between smoking and COVID-19 severity: A multicentre retrospective observational study.

The relationship between smoking and coronavirus disease 2019 (COVID-19) severity remains unclear. This study aimed to investigate the effect of smoking status (current smoking and a smoking history) on the clinical severity of COVID-19. Data of all enrolled 588 patients, who were referred to 25 hospitals in Jiangsu province between January 10, 2020 and March 14, 2020, were retrospectively reviewed. Univariate and multivariate regression, random forest algorithms, and additive interaction were used to estimate the importance of selective predictor variables in the relationship between smoking and COVID-19 severity. In the univariate analysis, the proportion of patients with a current smoking status in the severe group was significantly higher than that in the non-severe group. In the multivariate analysis, current smoking remained a risk factor for severe COVID-19. Data from the interaction analysis showed a strong interaction between the number of comorbidities in patients with COVID-19 and smoking. However, no significant interaction was found between smoking and specific comorbidities, such as hypertension, diabetes, etc. In the random forest model, smoking history was ranked sixth in mean decrease accuracy. Active smoking may be significantly associated with an enhanced risk of COVID-19 progression towards severe disease. However, additional prospective studies are needed to clarify the complex relationship between smoking and COVID-19 severity.

Neuronal SH2B1 attenuates apoptosis in an MPTP mouse model of Parkinson's disease via promoting PLIN4 degradation.

The incidence of Parkinson's disease (PD) has increased tremendously, especially in the aged population and people with metabolic dysfunction; however, its underlying molecular mechanisms remain unclear. SH2B1, an intracellular adaptor protein, contributes to the signal transduction of several receptor tyrosine kinases and exerts beneficial metabolic effects for body weight regulation; however, whether SH2B1 plays a major role in pathological neurodegeneration in PD has not yet been investigated. This study aimed to investigate the effects of SH2B1 in 1-methyl-4-phenyl-1,2,3,6-tetrahydropyridine (MPTP)-induced PD mice with Sh2b1 deficiency or neuron-specific Sh2b1 overexpression. Cellular and molecular mechanisms were elucidated using human dopaminergic neuron SH-SY5Y cells analysed. We found that SH2B1 expression was confirmed to be downregulated in the blood samples of PD patients and in the brains of mice with MPTP-induced chronic PD. Sh2b1 deficiency caused marked exacerbation of behavioural defects and increased neuronal apoptosis in MPTP-treated mice, whereas restoration of neuron-specific Sh2b1 expression significantly reversed these effects. Similar results were observed in MPP + -treated SH-SY5Y cells. Mechanistically, upon binding to heat shock cognate 70 (HSC70), SH2B1 promotes HSC70-related recognition and PLIN4 lysosomal translocation and degradation, thus suppressing lipid peroxidation stress in the brains of PD mice. Adeno-associated virus-mediated rescue of neuronal HSC70 expression functionally alleviated the neuropathology of PD in wild-type but not in Sh2b1-deficient mice. This is the first study to examine the molecular underpinnings of SH2B1 against MPTP-induced neurodegeneration through cell autonomous promotion of neuronal survival in an in vivo PD model. Our findings reveal that SH2B1 antagonizes neurodegenerative pathology in PD via the SH2B1-HSC70-PLIN4 axis.

Classification of motor imagery electroencephalogram signals by using adaptive cross-subject transfer learning.

Introduction: Electroencephalogram (EEG)-based motor imagery (MI) classification is an important aspect in brain-computer interfaces (BCIs), which bridges between neural system and computer devices decoding brain signals into recognizable machine commands. However, due to the small number of training samples of MI electroencephalogram (MI-EEG) for a single subject and the great individual differences of MI-EEG among different subjects, the generalization and accuracy of the model on the specific MI task may be poor. Methods: To solve these problems, an adaptive cross-subject transfer learning algorithm is proposed, which is based on kernel mean matching (KMM) and transfer learning adaptive boosting (TrAdaBoost) method. First, the common spatial pattern (CSP) is used to extract the spatial features. Then, in order to make the feature distribution more similar among different subjects, the KMM algorithm is used to compute a sample weight matrix for aligning the mean between source and target domains and reducing distribution differences among different subjects. Finally, the sample weight matrix from KMM is used as the initialization weight of TrAdaBoost, and then TrAdaBoost is used to adaptively select source domain samples that are closer to the target task distribution to assist in building a classification model. Results: In order to verify the effectiveness and feasibility of the proposed method, the algorithm is applied to BCI Competition IV datasets and in-house datasets. The results show that the average classification accuracy of the proposed method on the public datasets is 89.1%, and the average classification accuracy on the in-house datasets is 80.4%. Discussion: Compared with the existing methods, the proposed method effectively improves the classification accuracy of MI-EEG signals. At the same time, this paper also applies the proposed algorithm to the in-house dataset, the results verify the effectiveness of the algorithm again, and the results of this study have certain clinical guiding significance for brain rehabilitation.

Brain MRI Radiomics Analysis of School-Aged Children with Tetralogy of Fallot.

INTRODUCTION: Radiomics could be potential imaging biomarkers by capturing and analyzing the features. Children and adolescents with CHD have worse neurodevelopmental and functional outcomes compared with their peers. Early diagnosis and intervention are the necessity to improve neurological outcomes in CHD patients. METHODS: School-aged TOF patients and their healthy peers were recruited for MRI and neurodevelopmental assessment. LASSO regression was used for dimension reduction. ROC curve graph showed the performance of the model. RESULTS: Six related features were finally selected for modeling. The final model AUC was 0.750. The radiomics features can be potential significant predictors for neurodevelopmental diagnoses. CONCLUSION: The radiomics on the conventional MRI can help predict the neurodevelopment of school-aged children and provide parents with rehabilitation advice as early as possible.

Association of Cigarette Smoking with Risk of Chronic Musculoskeletal Pain: A Meta-Analysis.

BACKGROUND: Chronic musculoskeletal pain (CMP) management is a major global public health goal owing to increased social and economic burdens. However, the risk of CMP in smokers compared with nonsmokers remains uncertain. OBJECTIVES: This study aims to determine the magnitude and importance of the relationship between cigarette smoking and risk of CMP. STUDY DESIGN: A meta-analysis of the CMP risk of cigarette smokers. METHODS: We systematically searched PubMed, Embase, and Cochrane library databases from inception to August 2020. Data extraction and quality assessment were performed by 2 independent reviewers using a standardized extraction checklist. Data were pooled using a random-effects model. RESULTS: In this meta-analysis of 32 studies involving 296,109 participants, current smoking was associated with increased CMP risk (OR: 1.23, 95% CI: 1.09-1.40), whereas ever and past smoking did not show such an association (OR: 1.14, 95% CI: 0.95-1.37; OR: 1.06, 95% CI: 0.83-1.35, respectively). Stratified analyses showed that there was a marked significance in almost all strata of current smokers compared with non-smokers, except for mean age (>= 50 years), location of pain (neck pain, sacral pain, and knee pain), smoking frequency (occasionally), study design (cross-sectional), mean follow-up (< 10 years), and adjustment for confounding factors (>= 6). Interestingly, there was statistically negative association between cigarette smoking and knee pain risk in current smokers, ever smokers, and past smokers. LIMITATIONS: The major limitation of this meta-analysis relates to the heterogeneities across included studies. CONCLUSIONS: Cigarette smoking was associated with increased risk of CMP. In view of the high prevalence of smoking in many countries and the increasing number of CMP patients worldwide, reducing tobacco use should be an important public health strategy to prevent and control the global epidemic of CMP. Future research should attempt to establish whether this association is causal and clarify its mechanisms.

Serum vitamin E concentration is negatively associated with body mass index change in girls not boys during adolescence.

BACKGROUND: Vitamin E is the most abundant lipid-soluble antioxidants present in plasma; however, the relationship between serum vitamin E and change in body mass index (BMI)-for-age Z scores in adolescents has not been well described. METHODS: This study is a cross-sectional study. Data were analyzed from 4014 adolescents who participated in the National Health and Nutrition Examination Survey. The nutritional status was calculated by BMI Z scores and was classified into normal weight, overweight, and obese. Multivariable-adjusted logistic regression was used to examine the association between serum vitamin E levels with overweight/obesity. Besides, the interaction effects between potential confounders and vitamin E on obesity were further evaluated. RESULTS: After adjusting potential confounders, serum vitamin E levels were negatively associated with overweight/obesity in girls but not in boys. Per standard deviation increment in vitamin E concentrations was associated with a 92% decreased risk of obesity in females. Besides, lower quartiles of serum vitamin E were associated with a higher risk of overweight/obesity in girls. Moreover, the inverse association between serum vitamin E levels and obesity was also found in most subgroups through subgroup analysis. CONCLUSIONS: Our study supports the negative association between serum vitamin E levels and overweight/obesity in adolescents. A higher serum vitamin E level may be associated with a reduced probability of obesity in girls, but not in boys.

The Effect of Abnormal Regional Homogeneity and Spontaneous Low-Frequency Brain Activity on Lower Cognitive Ability: A Cross-Sectional Study on Postoperative Children With Tetralogy of Fallot.

Despite intracardiac malformation correction, children with Tetralogy of Fallot (TOF) may still suffer from brain injury. This cross-sectional study was primarily designed to determine the relationship between blood oxygenation level-dependent (BOLD) signal changes after surgery and cognition in school-aged children with TOF. To evaluate the differences between TOF children (n = 9) and healthy children (n = 9), resting-state functional magnetic resonance imaging (rs-fMRI) and the Wechsler Intelligence Scale for Children-Chinese revised edition (WISC-CR) were conducted in this study. The results showed that TOF children had a lower full-scale intelligence quotient (FSIQ, 95.444 ± 5.354, p = 0.022) and verbal intelligence quotient (VIQ, 92.444 ± 4.708, p = 0.003) than healthy children (FSIQ = 118.500 ± 4.330;VIQ = 124.250 ± 4.404), and that significant differences in regional homogeneity (ReHo) and amplitude of low-frequency fluctuation (ALFF) existed between the two groups. Besides, VIQ had significantly positive correlations with the decreased ALFF value of the middle inferior occipital gyrus (MIOG, beta = 0.908, p = 0.012) after fully adjusting for all covariates. In addition, elevated ReHo values of the left and right precuneus were positively related to ALFF in the MIOG. This study revealed that brain injury substantially influences neural activity and cognition in postoperative TOF children, providing direct evidence of an association between BOLD signal changes and the VIQ and prompting further attention to language development in TOF children.

In vitro Assessment of Myocardial Protection following Hypothermia-Preconditioning in a Human Cardiac Myocytes Model.

Ischemia/reperfusion-derived myocardial dysfunction is a common clinical scenario in patients after cardiac surgery. In particular, the sensitivity of cardiomyocytes to ischemic injury is higher than that of other cell populations. At present, hypothermia affords considerable protection against an expected ischemic insult. However, investigations into complex hypothermia-induced molecular changes remain limited. Therefore, it is essential to identify a culture condition similar to in vivo conditions that can induce damage similar to that observed in the clinical condition in a reproducible manner. To mimic ischemia-like conditions in vitro, the cells in these models were treated by oxygen/glucose deprivation (OGD). In addition, we applied a standard time-temperature protocol used during cardiac surgery. Furthermore, we propose an approach to use a simple but comprehensive method for the quantitative analysis of myocardial injury. Apoptosis and expression levels of apoptosis-associated proteins were assessed by flow cytometry and using an ELISA kit. In this model, we tested a hypothesis regarding the effects of different temperature conditions on cardiomyocyte apoptosis in vitro. The reliability of this model depends on strict temperature control, controllable experimental procedures, and stable experimental results. Additionally, this model can be used to study the molecular mechanism of hypothermic cardioprotection, which may have important implications for the development of complementary therapies for use with hypothermia.

Targeting Epidermal Growth Factor Receptor in Non-Small-Cell-Lung Cancer: Current State and Future Perspective.

BACKGROUND: Lung cancer is one of the leading cause of cancer death worldwide, the most common histological type of lung cancer is non-small cell lung cancer (NSCLC), whose occurrence and development is closely related to the mutation and amplification of epidermal growth factor receptors (EGFR). Currently , a series of targeted drugs were developed on the inhibition of EGFR such as epidermal growth factor receptortyrosine kinase inhibitor EGFR-TKI and monoclonal antibody (McAb). OBJECTIVE: We sought to summarizes the current drugs targeting Epidermal Growth Factor Receptor in nonsmall- cell-lung. METHODS: We conducted a comprehensive review of the development and application of EGFR-TKI and McAb which targeted EGFR in NSCLC and compared the mechanisms of PROTAC with the traditional inhibitors. RESULTS: The drugs targeted EGFR in NSCLC have been widely used in clinic practices. Compared to traditional chemotherapy, these drugs excel with their clear and specific targeting, better curative effects, and less toxic and side effects. However, the mechanism comes with some insurmountable weaknesses like serious toxic and other side effects, as well as proneness to producing drug resistance. CONCLUSION: The emerging PROTAC (Proteolysis Targeting Chimera) technology has been successfully applied to selective degradation of multiple protein targets, including EGFR. It also highlights the potential and challenges of PROTAC therapy regarding future combination therapeutic options in NSCLC treatment.

Inhibition of an NAD⁺ salvage pathway provides efficient and selective toxicity to human pluripotent stem cells.

The tumorigenic potential of human pluripotent stem cells (hPSCs) is a major limitation to the widespread use of hPSC derivatives in the clinic. Here, we demonstrate that the small molecule STF-31 is effective at eliminating undifferentiated hPSCs across a broad range of cell culture conditions with important advantages over previously described methods that target metabolic processes. Although STF-31 was originally described as an inhibitor of glucose transporter 1, these data support the reclassification of STF-31 as a specific NAD⁺ salvage pathway inhibitor through the inhibition of nicotinamide phosphoribosyltransferase (NAMPT). These findings demonstrate the importance of an NAD⁺ salvage pathway in hPSC biology and describe how inhibition of NAMPT can effectively eliminate hPSCs from culture. These results will advance and accelerate the development of safe, clinically relevant hPSC-derived cell-based therapies.