ObjectiveTo summarize and analyze the clinical characteristics of patients with acute diffuse lung changes and respiratory failure.MethodsThe clinical data of patients in the Department of Critical Care Medicine, Dazhou Central Hospital between January 2016 and December 2018 were retrospectively collected, whose main clinical manifestation was acute respiratory distress syndrome with acute onset (<3 weeks) and main imaging manifestation was diffuse changes in both lungs. The clinical characteristics of patients were summarized, and the causes of the disease were explored.ResultsA total of 65 patients with acute diffuse lung changes and respiratory failure were enrolled, including 42 males (64.6%) and 23 females (35.4%). The average age was (57.1±18.4) years, the average time from onset to treatment was (7.5±5.9) d, and the average length of stay in the intensive care unit was (8.9±4.1) d. A total of 23 cases died, with a case-fatality rate of 35.4%. Among the 65 patients, there were 50 case (76.9%) of infectious diseases, including 36 cases of bacterial infections (including 4 cases of tuberculosis), 8 cases of viral infections (all were H1N1 infections), and 6 cases of fungal infections (including 1 case of pneumocystis infection); and there were 15 cases (23.1%) of non-infectious diseases, including 4 cases of acute left heart failure, 2 cases of interstitial pneumonia, 2 cases of vasculitis, 1 case of myositis dermatomyositis, 1 case of aspiration pneumonia, 1 case of acute pulmonary embolism, 1 case of acute drug lung injury, 1 case of neurogenic pulmonary edema, 1 case of drowning, and 1 case of unknown origin.ConclusionsInfectious diseases are the main cause of acute diffuse lung changes and respiratory failure, while among non-infectious diseases, acute heart failure and immune system diseases are common causes.
Magnetic resonance imaging(MRI) can obtain multi-modal images with different contrast, which provides rich information for clinical diagnosis. However, some contrast images are not scanned or the quality of the acquired images cannot meet the diagnostic requirements due to the difficulty of patient's cooperation or the limitation of scanning conditions. Image synthesis techniques have become a method to compensate for such image deficiencies. In recent years, deep learning has been widely used in the field of MRI synthesis. In this paper, a synthesis network based on multi-modal fusion is proposed, which firstly uses a feature encoder to encode the features of multiple unimodal images separately, and then fuses the features of different modal images through a feature fusion module, and finally generates the target modal image. The similarity measure between the target image and the predicted image in the network is improved by introducing a dynamic weighted combined loss function based on the spatial domain and K-space domain. After experimental validation and quantitative comparison, the multi-modal fusion deep learning network proposed in this paper can effectively synthesize high-quality MRI fluid-attenuated inversion recovery (FLAIR) images. In summary, the method proposed in this paper can reduce MRI scanning time of the patient, as well as solve the clinical problem of missing FLAIR images or image quality that is difficult to meet diagnostic requirements.
ObjectiveTo detect the expression of Krüppel like factor 8 (KLF8) in breast cancer tissues and cells and to explore the clinical significance of KLF8.Methods① The Oncomine database was used to analyze the differential expression of KLF8 mRNA in the breast cancer tissues. The Kaplan-Meier Plotter database was used to analyze the relationship between KLF8 mRNA expression and prognosis (relapse free survival, overall survival, post-progression survival, and distant metastasis-free survival) of patients with breast cancer. ② The quantitative real-time PCR (qRT-PCR) and Western blot were used to detect the KLF8 expression levels in the 16 clinical patients with breast cancer and 7 breast cancer cell lines (MDA-MB-231, MCF-12A, Hs-578T, MCF-7, BT-474, MDA-MB-453, ZR-75-30) and normal breast epithelial cell lines MCF-10A, and the immunofluorescence was used to further detect the localization of KLF8 expression in the 2 breast cancer cell lines with higher KLF8 expression level. ③ The immunohistochemistry was used to detect the expression of KLF8 protein in 135 cases of breast cancer tissue microarrays, and the relationships between KLF8 protein expression and clinicopathologic characteristics or overall survival were analyzed.Results① The Oncomine database showed that KLF8 mRNA expression in the breast cancer tissues was higher than that in the normal breast tissues (P<0.001). The median KLF8 mRNA expression level was taken as the cut-off point for high or low KLF8 expression. The results of Kaplan-Meier Plotter data analysis showed that the prognosis (relapse free survival, overall survival, postprogression survival, and distant metastasis-free survival) of patients with low KLF8 mRNA expression were better than those of patients with high KLF8 mRNA expression (P<0.05). ② The results of qRT-PCR and Western blot all showed that the KLF8 mRNA and protein expression levels in the breast cancer tissues were higher than those in the adjacent normal tissues (P=0.002, P<0.001). In addition, the Western blot results showed that the expression of KLF8 protein in the 7 breast cancer cell lines was higher than that in the normal breast epithelial cell lines MCF-10A respectively, and KLF8 protein mainly expressed in the cytoplasm of breast cancer cells and highly expressed in the nuclear of a few cells. ③ There were 63 cases of high KLF8 expression and 72 cases of low KLF8 expression by the immunohistochemical analysis of 135 patients with breast cancer tissue microarray (the H-score of the immunohistochemical test results was 75 as the cut-off point, H-score >75 was the high KLF8 expression and H-score ≤75 was the low KLF8 expression), the differences of statuses of estrogen receptor (ER) and progesterone receptor (PR) between the patient with high KLF8 expression and low KLF8 expression were significant (P<0.05). The Kaplan-Meier survival curve analysis showed that the prognosis of patients with high KLF8 expression was worse than that of patients with low KLF8 expression (P=0.002). The univariate analysis showed that the TNM stage, statuses of ER and PR, and KLF8 expression were related to the prognosis of patients with breast cancer (P<0.05), further multivariate Cox proportional hazards regression analysis indicated that the later stage of TNM and high KLF8 expression were the independent risk factors (P<0.05).ConclusionsThe results of this study suggest that KLF8 highly expresses in both breast cancer tissues and breast cancer cells, which is related to the statuses of ER and PR and prognosis of patients with breast cancer. KLF8 might be involved in the progression of breast cancer as an oncogenic gene, or it might provide a new direction for prognosis judgment and molecular targeted therapy of breast cancer.
Automated characterization of different vessel wall tissues including atherosclerotic plaques, branchings and stents from intravascular ultrasound (IVUS) gray-scale images was addressed. The texture features of each frame were firstly detected with local binary pattern (LBP), Haar-like and Gabor filter in the present study. Then, a Gentle Adaboost classifier was designed to classify tissue features. The methods were validated with clinically acquired image data. The manual characterization results obtained by experienced physicians were adopted as the golden standard to evaluate the accuracy. Results indicated that the recognition accuracy of lipidic plaques reached 94.54%, while classification precision of fibrous and calcified plaques reached 93.08%. High recognition accuracy can be reached up to branchings 93.20% and stents 93.50%, respectively.
Objective To explore the clinical and inflammatory characteristics and risk factors of severe asthma to improve clinicians' awareness of the disease. Methods The general information of patients with asthma who visited the Department of Respiratory Medicine, the First Hospital of Shanxi Medical University from May 2018 to May 2021, as well as the diagnosis and treatment of asthma, personal history, comorbidities, auxiliary examination, asthma control test (ACT) score were collected. A total of 127 patients were included, including 40 in the severe asthma group and 87 in the mild-to-moderate asthma group. Chi-square test, independent sample t test and logistic regression were used to analyze the clinical characteristics, inflammatory markers and risk factors of severe asthma. Results Compared with the patients with mild to moderate asthma, the patients with severe asthma were more older (51.0±12.0 years vs 40.7±12.8 years, P<0.05), had more smokers (32.5% vs. 14.9%, P<0.05), and more males (67.5% vs. 40.2%, P<0.05). The patients with severe asthma got poor FEV1%pred [(56.1±23.8)% vs. (93.2±18.0)%, P<0.05] and FEV1/FVC [(56.7±13.2)% vs. (75.8±9.0)%, P<0.05)], and more exacerbations in the previous year (2.7±3.1 vs. 0.1±0.4, P<0.05), lower ACT score (14.4±3.7 vs. 18.0±5.0, P<0.05), and higher blood and induced sputum eosinophil counts [(0.54±0.44)×109/L vs. (0.27±0.32)×109/L, P<0.05; (25.9±24.2)% vs. (9.8±17.5)%, P<0.05]. There was no significant difference in the proportion of neutrophils in the induced sputum or FeNO between the two groups (P>0.05). Analysis of related risk factors showed that smoking (OR=2.740, 95%CI 1.053 - 7.130), combined with allergic rhinitis (OR=14.388, 95%CI 1.486 - 139.296) and gastroesophageal reflux (OR=2.514, 95%CI 1.105 - 5.724) were risk factors for severe asthma. Conclusions Compared with patients with mild to moderate asthma, patients with severe asthma are characterized by poor lung function, more exacerbations, and a dominant eosinophil inflammatory phenotype, which is still poorly controlled even with higher level of treatment. Risk factors include smoking, allergic rhinitis, and gastroesophageal reflux, etc.
Existing emotion recognition research is typically limited to static laboratory settings and has not fully handle the changes in emotional states in dynamic scenarios. To address this problem, this paper proposes a method for dynamic continuous emotion recognition based on electroencephalography (EEG) and eye movement signals. Firstly, an experimental paradigm was designed to cover six dynamic emotion transition scenarios including happy to calm, calm to happy, sad to calm, calm to sad, nervous to calm, and calm to nervous. EEG and eye movement data were collected simultaneously from 20 subjects to fill the gap in current multimodal dynamic continuous emotion datasets. In the valence-arousal two-dimensional space, emotion ratings for stimulus videos were performed every five seconds on a scale of 1 to 9, and dynamic continuous emotion labels were normalized. Subsequently, frequency band features were extracted from the preprocessed EEG and eye movement data. A cascade feature fusion approach was used to effectively combine EEG and eye movement features, generating an information-rich multimodal feature vector. This feature vector was input into four regression models including support vector regression with radial basis function kernel, decision tree, random forest, and K-nearest neighbors, to develop the dynamic continuous emotion recognition model. The results showed that the proposed method achieved the lowest mean square error for valence and arousal across the six dynamic continuous emotions. This approach can accurately recognize various emotion transitions in dynamic situations, offering higher accuracy and robustness compared to using either EEG or eye movement signals alone, making it well-suited for practical applications.
ObjectiveTo explore the association of pretreatment hyponatremia with clinicopathological and prognostic characteristics of non-small cell lung cancer (NSCLC) patients. MethodsThe PubMed, EMbase, Web of Science, VIP, CNKI and WanFang databases were searched from the inception to July 12, 2021 for relevant literatures. The quality of included studies was assessed by the Newcastle-Ottawa Scale (NOS) score. The relative risk (RR) and hazard ratio (HR) with 95% confidence interval (CI) were combined to assess the relationship between pretreatment hyponatremia and clinicopathological and prognostic characteristics. The prognostic indicators included the overall survival (OS) and progression-free survival (PFS). All statistical analysis was conducted by the STATA 15.0 software. ResultsA total of 10 high-quality studies (NOS score≥6 points) involving 10 045 patients were enrolled and all participants were from Asian or European regions. The pooled results demonstrated that male [RR=1.18, 95%CI (1.02, 1.36), P=0.026], non-adenocarcinoma [RR=0.86, 95%CI (0.81, 0.91), P＜0.001] and TNM Ⅲ-Ⅳ stage [RR=1.17, 95%CI (1.12, 1.21), P＜0.001] patients were more likely to experience hyponatremia. Besides, pretreatment hyponatremia was significantly related to worse OS [HR=1.83, 95%CI (1.53, 2.19), P＜0.001] and PFS [HR=1.54, 95%CI (1.02, 2.34), P=0.040]. Pretreatment hyponatremia was a risk factor for poor prognosis of NSCLC patients. ConclusionMale, non-adenocarcinoma and advance stage NSCLC patients are more likely to experience hyponatremia. Meanwhile, the pretreatment sodium level can be applied as one of the prognostic evaluation indicators in NSCLC and patients with hyponatremia are more likely to have poor survival. However, more researches are still needed to verify above findings.
Deep learning method can be used to automatically analyze electrocardiogram (ECG) data and rapidly implement arrhythmia classification, which provides significant clinical value for the early screening of arrhythmias. How to select arrhythmia features effectively under limited abnormal sample supervision is an urgent issue to address. This paper proposed an arrhythmia classification algorithm based on an adaptive multi-feature fusion network. The algorithm extracted RR interval features from ECG signals, employed one-dimensional convolutional neural network (1D-CNN) to extract time-domain deep features, employed Mel frequency cepstral coefficients (MFCC) and two-dimensional convolutional neural network (2D-CNN) to extract frequency-domain deep features. The features were fused using adaptive weighting strategy for arrhythmia classification. The paper used the arrhythmia database jointly developed by the Massachusetts Institute of Technology and Beth Israel Hospital (MIT-BIH) and evaluated the algorithm under the inter-patient paradigm. Experimental results demonstrated that the proposed algorithm achieved an average precision of 75.2%, an average recall of 70.1% and an average F1-score of 71.3%, demonstrating high classification accuracy and being able to provide algorithmic support for arrhythmia classification in wearable devices.
ObjectiveTo compare the clinicopathological characteristics of breast invasive micropapillary carcinoma (IMPC) with different composition ratios, and analyze the relationship between proportion of micropapillary carcinoma components and the prognosis of IMPC. Methods The related data of 121 patients with invasive ductal carcinoma (IDC) complicated with IMPC who were treated in the Department of Breast Surgery, Affiliated Hospital of Southwest Medical University from August 2016 to August 2020 were collected. With micropapillary carcinoma accounting for 50%, the patients were divided into IMPC <50% group and IMPC ≥50% group. The correlation between related clinicopathological features and prognosis of patients was analyzed. Results There were 85 patients in the IMPC <50% group and 36 patients in the IMPC ≥50% group. The analysis results showed that there was no significant differences between the two groups in menstrual status, histological grade, molecular typing, TNM stage, age, immunohistochemical expression, neoadjuvant therapy, nerve invasion, nipple invasion, and skin invasion (P>0.05). The rate of lymphatic vessel invasion (LVI) in the IMPC ≥50% group was 83.33% (30/36), which was significantly higher than 61.18% (52/85) in the IMPC <50% group, and the difference between the two groups was statistically significant (χ2=5.684, P=0.017). Kaplan-Meier survival curve was drawn, and the analysis results showed that the 3-year cumulative disease-free survival (DFS) of IMPC patients was correlated with the number of lymph node metastasis and LVI (P<0.05). And with the estrogen receptor, progesterone receptor, human epidermal growth factor receptor 2, Ki-67, molecular typing, proportion of micropapillary carcinoma components and histological grade were unrelated (P>0.05). The results of multivariate Cox risk regression analysis showed that the number of lymph node metastases and LVI were independent prognostic factors affecting DFS in patients. Conclusions When the proportion of IMPC component is ≥50%, the LVI rate of tumor is higher than that of IMPC component <50%. The number of lymph node metastasis and LVI are independent prognostic factors affecting DFS in IMPC patients.
目的:探讨成人麻疹的流行病学与临床特征。方法:回顾性分析196例成人麻疹的临床资料。结果:患者以外来流动人员及本地农村人口多见,平均年龄26.78岁,多数患者未接种麻疹疫苗或麻疹疫苗史不详。成人麻疹患者临床症状重,皮疹典型,为充血性斑丘疹,麻疹黏膜斑(Koplik’s spots)明显,且持续时间长,可合并肝脏和心肌损伤,但并发症以肺炎和支气管炎为主。结论:有必要加强成人的免疫接种,尤其是外来的务工人员,强化医务人员对麻疹的认识,避免麻疹的流行。