Medical studies have found that tumor mutation burden (TMB) is positively correlated with the efficacy of immunotherapy for non-small cell lung cancer (NSCLC), and TMB value can be used to predict the efficacy of targeted therapy and chemotherapy. However, the calculation of TMB value mainly depends on the whole exon sequencing (WES) technology, which usually costs too much time and expenses. To deal with above problem, this paper studies the correlation between TMB and slice images by taking advantage of digital pathological slices commonly used in clinic and then predicts the patient TMB level accordingly. This paper proposes a deep learning model (RCA-MSAG) based on residual coordinate attention (RCA) structure and combined with multi-scale attention guidance (MSAG) module. The model takes ResNet-50 as the basic model and integrates coordinate attention (CA) into bottleneck module to capture the direction-aware and position-sensitive information, which makes the model able to locate and identify the interesting positions more accurately. And then, MSAG module is embedded into the network, which makes the model able to extract the deep features of lung cancer pathological sections and the interactive information between channels. The cancer genome map (TCGA) open dataset is adopted in the experiment, which consists of 200 pathological sections of lung adenocarcinoma, including 80 data samples with high TMB value, 77 data samples with medium TMB value and 43 data samples with low TMB value. Experimental results demonstrate that the accuracy, precision, recall and F1 score of the proposed model are 96.2%, 96.4%, 96.2% and 96.3%, respectively, which are superior to the existing mainstream deep learning models. The model proposed in this paper can promote clinical auxiliary diagnosis and has certain theoretical guiding significance for TMB prediction.
Objective To scientifically construct a self-management behavior scale for postoperative patients with osteoporotic fractures, in order to assess the self-management behavior level of this patient population. Methods Between November 2022 and February 2023, a scale item pool was constructed using literature analysis and expert panel discussions. A preliminary version of the scale was formed based on feedback from 30 experts and 15 patients. From March 2023 to March 2024, a convenience sampling method was used to survey 230 patients post-osteoporotic fracture surgery from a tertiary hospital in Guangzhou. Cronbach’s α coefficient, split-half reliability, and test-retest reliability were used to assess the reliability of the scale, while content validity and exploratory factor analysis were used to evaluate its validity. Results The developed scale consisted of 5 dimensions and 27 items. The content validity index for each item ranged from 0.933 to 1.000. Exploratory factor analysis extracted 5 common factors, explaining 65.964% of the cumulative variance. The overall Cronbach’s α coefficient, split-half reliability, and test-retest reliability were 0.934, 0.780, and 0.958, respectively. The Cronbach’s α coefficient, split-half reliability, and test-retest reliability for each dimension ranged from 0.849 to 0.897, 0.816 to 0.904, and 0.826 to 0.894, respectively. Conclusions The self-management behavior scale for post-osteoporotic fracture surgery patients demonstrates good reliability and validity. It is a highly authoritative and scientific tool that can be used effectively to assess self-management behaviors in these patients and provide a basis for developing personalized self-management interventions.
Objective To explore the present situation of the efficiency about public tertiary general hospitals in Shandong province, measure and compare the efficiency and the state of returns to scale of hospitals under different bed scales. Methods Based on the input and output data of 137 public tertiary general hospitals in Shandong province in 2017, two input indicators (the number of employees and the number of actual beds) and two output indicators (the total number of outpatients and emergent patients, and the number of discharges) were selected. The technical efficiency, pure technical efficiency and scale efficiency of sample hospitals were calculated by using data envelopment analysis, and a comparative analysis was carried out under different bed scales. Results Of the 137 public tertiary general hospitals, the mean of technical efficiency value was 0.666, the medians of pure technical efficiency value and scale efficiency value in 2017 were 0.817 and 0.919, respectively. In the 137 sample hospitals, there were 132 hospitals (96.4%) in ineffective status; there were 90 hospitals (65.7%) exhibiting increasing returns to scale, 11 hospitals (8.0%) exhibiting constant returns to scale, and 36 hospitals (26.3%) exhibiting decreasing returns to scale. There were significant differences in hospital efficiency and returns to scale under different bed sizes (P<0.001), and the scale efficiency was the highest when the bed size was 1001-2000. Conclusions The overall operating efficiency of the public tertiary general hospitals in the province was not high yet. Most hospitals were in ineffective status and most of them were in the state of increasing returns to scale. The optimal scale of actual beds is between 1001 and 2000 beds from the perspective of scale efficiency.
During long-term electrocardiogram (ECG) monitoring, various types of noise inevitably become mixed with the signal, potentially hindering doctors' ability to accurately assess and interpret patient data. Therefore, evaluating the quality of ECG signals before conducting analysis and diagnosis is crucial. This paper addresses the limitations of existing ECG signal quality assessment methods, particularly their insufficient focus on the 12-lead multi-scale correlation. We propose a novel ECG signal quality assessment method that integrates a convolutional neural network (CNN) with a squeeze and excitation residual network (SE-ResNet). This approach not only captures both local and global features of ECG time series but also emphasizes the spatial correlation among ECG signals. Testing on a public dataset demonstrated that our method achieved an accuracy of 99.5%, sensitivity of 98.5%, and specificity of 99.6%. Compared with other methods, our technique significantly enhances the accuracy of ECG signal quality assessment by leveraging inter-lead correlation information, which is expected to advance the development of intelligent ECG monitoring and diagnostic technology.
[Abstract]Automatic and accurate segmentation of lung parenchyma is essential for assisted diagnosis of lung cancer. In recent years, researchers in the field of deep learning have proposed a number of improved lung parenchyma segmentation methods based on U-Net. However, the existing segmentation methods ignore the complementary fusion of semantic information in the feature map between different layers and fail to distinguish the importance of different spaces and channels in the feature map. To solve this problem, this paper proposes the double scale parallel attention (DSPA) network (DSPA-Net) architecture, and introduces the DSPA module and the atrous spatial pyramid pooling (ASPP) module in the “encoder-decoder” structure. Among them, the DSPA module aggregates the semantic information of feature maps of different levels while obtaining accurate space and channel information of feature map with the help of cooperative attention (CA). The ASPP module uses multiple parallel convolution kernels with different void rates to obtain feature maps containing multi-scale information under different receptive fields. The two modules address multi-scale information processing in feature maps of different levels and in feature maps of the same level, respectively. We conducted experimental verification on the Kaggle competition dataset. The experimental results prove that the network architecture has obvious advantages compared with the current mainstream segmentation network. The values of dice similarity coefficient (DSC) and intersection on union (IoU) reached 0.972 ± 0.002 and 0.945 ± 0.004, respectively. This paper achieves automatic and accurate segmentation of lung parenchyma and provides a reference for the application of attentional mechanisms and multi-scale information in the field of lung parenchyma segmentation.
ObjectiveTo measure the operational efficiency and explore the phenomenon of the economy of scale in secondary public general hospitals of China for improving the health service efficiency.MethodsFrom February to August 2019, the data set of two input indicators (the number of employees and actual open beds) and two output indicators (the numbers of outpatients and discharges) in 511 secondary general hospitals of Shandong, Anhui, Shanxi, Hubei and Hainan provinces in 2018 were collected for data envelopment analysis. The analysis processes were three folds: First, the technical efficiency, pure technical efficiency, scale efficiency and scale compensation status of the sample hospitals were calculated respectively. Second, the comparative analysis of efficiency value and scale compensation status was carried out in 5 groups according to the bed scale. Finally, the input and output projection analysis was carried out on the ineffective decision making units.ResultsThe medians of technical efficiencies, pure technical efficiencies, and scale efficiencies of the 511 secondary general hospitals were 0.472, 0.531, and 0.909, respectively. In the 511 hospitals, 493 hospitals (96.5%) were in ineffective state, of which 321 hospitals (62.8%) were in the state of decreasing return to scale. The staff redundancy of the group with beds >100 and ≤300 was 23.86%, and its service quantity could be increased by 39.37%.ConclusionsThe overall operating efficiencies are inefficiency in secondary general hospitals of China and the optimal scale of actual open beds is between 300 and 500 beds from the perspective of scale efficiency.
The study on complexity of glucose fluctuation not only helps us understand the regulation of the glucose homeostasis system but also brings us a new insight of the research methodology on glucose regulation. In the experiments, we analyzed the complexity of the temporal structure of the 72 hours continuous glucose time series from a group of 93 subjects with type Ⅱ diabetes mellitus using the multi-scale entropy method. We adapted the most recently improved refined composite multi-scale entropy (RCMSE) algorithm which could overcome the shortcomings on the 72 hours short time series analysis. We then quantified and compared the complexity of continuous glucose time series between groups with type Ⅱ diabetes mellitus with different mean absolute glycemic excursion (MAGE) and glycated hemoglobin (HbA1c). The results implied that the complexity of glucose time series decreased on lower MAGE group compared to high MAGE group, and the entropy on scale 1 to 6 which corresponded to 5 to 30 min had significant differences between these two groups; the complexity of glucose time series decreased with the increasing HbA1c level but the entropy had no statistical difference among groups at different scales. Therefore, RCMSE provided us with a new prospect to analyze the glucose time series and it was proved that less complexity of glucose dynamics could indicate the impaired gluco-regulation function from the MAGE point of view or HbA1c for patients, and the glucose complexity had the potential to become a new biomarker to reflect the fluctuation of the glucose time series.
ObjectiveTo investigate the feasibility and effect of early pulmonary rehabilitation (PR) in patients after acute exacerbation of chronic obstructive pulmonary disease (COPD) in a district hospital. MethodsA single-centre prospective study was conducted. The COPD patients after an episode of acute exacerbation and referred to the outpatient department were recruited from January 2013 to December 2014. They were randomized to a group with PR (PR group) and a group without PR (wPR group). The following data were recorded and evaluated including age, gender, forced vital capacity (FVC), forced expiratory volume in one second (FEV1), and FEV1 as a percentage of the predicted value (FEV1% pred).The baseline and the post-PR medical research council scale (MRC), St. George's respiratory questionnaire (SGRQ), and six-minute walk distance (6MWD) were also compared. ResultsA total of 91 cases were enrolled with 46 cases in the PR group and 45 cases in the wPR group. The age, gender, the severity of COPD were similar in two groups (P > 0.05). The MRC score and SGRQ score of the PR group were significantly improved 3 months later compare with the baseline (P < 0.05), and did not changed significantly in the wPR group (P > 0.05). There were 26 patients whose SGRQ scores decreased > 4 in the PR group (26/46, 56.5%), which was significantly higher than the wPR group (7/45, 15.6%) (P < 0.05). The 6MWD of the PR group was significantly increased 3 months later compare with the baseline (P < 0.05), and did not changed significantly in the wPR group (P > 0.05). There were 22 patients whose 6MWD increased > 54 meters in the PR group (22/46, 47.8%), which was significantly higher than the wPR group (9/45, 20.0%) (P < 0.05). ConclusionsIt is feasible and safety to perform early PR in patients after acute exacerbation of COPD in the district hospital. The early PR can improve the MRC score, SGQR score, and 6MWD in COPD patients.
ObjectiveTo investigate the quality of life (QoL) of patients with differentiated thyroid cancer (DTC) after surgery and analyze its relevant influencing factors. MethodsThe patients with DTC who underwent surgical resection in the First Affiliated Hospital of Zhengzhou University from December 1, 2021 to October 1, 2023 were investigated through the postoperative follow-up platform and follow-up management group. The postoperative QoL of DTC patients were evaluate using the Chinese version of the Thyroid Cancer Specific Quality of Life Questionnaire (THYCA-QoL) specific scale and the Chinese version of the European Organization for Research and Treatment of Cancer (EORTC) developed a quality of life questionnaire consisting of 30 items (QLQ-C30). The higher overall average score of THYCA-QoL scale, the more clinical symptoms of patients, namely the negative QoL. The higher the EORTC QLQ-C30 overall health status score, the better QoL. In addition, multiple linear regression was used to explore the risk factors affecting the postoperative specific QoL score of DTC patients. ResultsA total of 1 076 patients’ questionnaires were collected. The EORTC QLQ-C30 overall health status score of 1 076 patients was 67±22 and the THYCA-QoL overall score was 22±13. The results of multivariate linear regression analysis showed that the early postoperative period (<6 months), male, age, without postoperative lifetime medication and without postoperative iodine-131 radiotherapy had negative effects on the overall score of THYCA-QoL scale (P<0.05), meanwhile the early postoperative period (<6 months) or later (≥12 months), without postoperative lifetime medication and without postoperative iodine-131 radiotherapy had positive effects on the overall health status score of EORTC QLQ-C30 (P<0.05). ConclusionsEORTC QLQ-C30 combined with THYCA-QoL can evaluate not only the common symptoms of cancer, but also the specific symptoms of thyroid cancer after surgery. And understanding the factors affecting the QoL of patients with thyroid cancer after surgery could provide targeted and supportive treatment and nursing for discharged patients to improve the QoL of patients with thyroid cancer after surgery.
Atrial fibrillation (AF) is a life-threatening heart condition, and its early detection and treatment have garnered significant attention from physicians in recent years. Traditional methods of detecting AF heavily rely on doctor’s diagnosis based on electrocardiograms (ECGs), but prolonged analysis of ECG signals is very time-consuming. This paper designs an AF detection model based on the Inception module, constructing multi-branch detection channels to process raw ECG signals, gradient signals, and frequency signals during AF. The model efficiently extracted QRS complex and RR interval features using gradient signals, extracted P-wave and f-wave features using frequency signals, and used raw signals to supplement missing information. The multi-scale convolutional kernels in the Inception module provided various receptive fields and performed comprehensive analysis of the multi-branch results, enabling early AF detection. Compared to current machine learning algorithms that use only RR interval and heart rate variability features, the proposed algorithm additionally employed frequency features, making fuller use of the information within the signals. For deep learning methods using raw and frequency signals, this paper introduced an enhanced method for the QRS complex, allowing the network to extract features more effectively. By using a multi-branch input mode, the model comprehensively considered irregular RR intervals and P-wave and f-wave features in AF. Testing on the MIT-BIH AF database showed that the inter-patient detection accuracy was 96.89%, sensitivity was 97.72%, and specificity was 95.88%. The proposed model demonstrates excellent performance and can achieve automatic AF detection.