Chronic obstructive pulmonary disease (COPD) is a serious chronic respiratory disease. Improving the ability to identify patients with COPD in primary medical institutions is important to prevent and treat the disease. With the continuous development of medical digitization, the application of big data informatization in the medical and health fields has become possible. Recently, applying innovative technologies such as big data analysis, machine learning, and artificial intelligence-assisted decision-making in the medical field has become an interdisciplinary research hotspot. Based on the identification and diagnosis of COPD in the high-risk population, this study proposes a convenient and effective clinical decision support system to help identify patients with COPD in primary health institutions. The results of the preliminary experiments show that the proposed method is convenient and effective compared with the existing methods.

Background At present, chronic respiratory diseases are a major burden in terms of morbidity and mortality and are of increasing public health concern in China. Meanwhile, the prevalence of diabetes has increased by more than 10 times over the last 40 years. While a few studies have investigated the association between chronic respiratory diseases and diabetes mellitus, the association is not clear. This study aimed to explore this association and provide evidence. Methods In this single-center study, we enrolled participants aged ≥ 20 years undergoing at least two regular health check-ups from 2009 to 2019 at MJ Healthcare Center in Beijing. Each health check-up included physical examination, biochemical tests, a pulmonary function test, a questionnaire. A total of 11,107 adults were included, and cross-sectional and longitudinal analyses were performed. Results We found that both prediabetic and diabetic adults had lower lung function than the normal population at baseline, indicating that lung function decline may start from prediabetic status. Quantitatively, with 1-mmol/L increase in fasting plasma glucose level, the forced vital capacity (FVC), forced expiratory volume in 1 s (FEV 1 ), FVC% and FEV 1 % lowered by 25 ml, 13 ml, 0.71-1.03%, and 0.46-0.72%, respectively. However, no significant difference was found in the rates for the lung function decline among different baseline diabetes statuses. Conclusion People with higher blood glucose level had more severe lung function decline, with decline starting from prediabetic status, but no significant difference was noted in the rate of lung function decline based on different baseline diabetic statuses.

Bronchiectasis is defined as a permanent dilation of the bronchi that can cause pulmonary ventilation dysfunction. CT examination is an important means of diagnosing bronchiectasis. It can also be used in severity scoring. Current studies on bronchiectasis have focused on high-resolution CT (HRCT), ignoring the more common low-dose CT (LDCT). Methodologically, existing studies have not adopted an authoritative standard to classify the severity of bronchiectasis. In effect, the accuracy of detection and classification needs to be improved for practical application. In this paper, the ACER image enhancement method, RDU-Net lung lobe segmentation method and HDC Mask R-CNN model were proposed to detect and classify bronchiectasis. Moreover, a Python-based system was developed: after inputing an LDCT image of a patient’s lung, it can automatically perform a series of processing, then call on the trained deep learning model for detection and classification, and automatically obtain the patient’s bronchiectasis final score according to the Reiff and BRICS scoring criteria. In this paper, the mapping relationship between original lung CT image data and bronchiectasis scoring system was established. The accuracy of the method proposed in this paper was 91.4%; the IOU, sensitivity and specificity were 88.8%, 88.6% and 85.4%, respectively; and the recognition speed of one picture was about 1 s. Compared to a human doctor, the system can process large amounts of data simultaneously, quickly and efficiently, with the same judgment accuracy as a human doctor. Doctors only need to judge the uncertain cases, which significantly reduces the burden of doctors and provides a useful reference for doctors to diagnose the disease.

Bronchiectasis can cause pulmonary ventilation dysfunction, which will bring huge social and economic burden. Deep learning methods are rarely used in the detection and classification of bronchiectasis. Current studies on bronchiectasis mainly focus on high resolution CT (HRCT), ignoring the more common low-dose CT (LDCT). Methodologically, existing studies do not use an authoritative standard to classify the severity of bronchiectasis. In effect, the accuracy of detection and classification needs to be improved for practical application. According to the above problems, we adopt LDCT data, contrast two deep learning models for the detection and classification of bronchiectasis effect, then we use dilated convolution to promote deep learning model for detection and classification of bronchiectasis. Finally, we developed an automatic detection and scoring system for bronchiectasis combining with authoritative scoring standards. According to the experiments that the detection rate of bronchiectasis in LDCT images by our developed bronchiectasis detection and scoring system can reach 91.0

目的 探讨胸膜恶性病变内科胸腔镜下结节表现与胸水生化及肿瘤标志物指标水平的关系.方法 选取2011年2月-2022年1月于山东省立医院东院呼吸与危重症医学科住院的110例胸膜恶性病变患者为研究对象,其中肺癌90例,恶性胸膜间皮瘤18例,弥漫大B细胞淋巴瘤1例,卵巢浆液性癌1例.根据内科胸腔镜视野内胸膜结节的数量逐次分为6层:无结节组,有结节组(胸膜有大小不一的结节分布);结节组进一步分为结节散在组(胸腔镜下所有视野内有胸膜结节且总数≤10个),结节弥漫组(胸腔镜下所有视野内胸膜结节总数＞10个);结节弥漫组进一步分为结节弥漫较多组(胸腔镜下胸膜结节总数＞10个,单个镜下视野内结节总数≤10个),结节弥漫成片组(胸腔镜下胸膜结节总数＞10个,单个镜下视野内结节总数＞10个).测定胸水生化4 项,胸水乳酸脱氢酶(lactate dehydrogenase,LDH)、腺苷脱氨酶(adenosine deaminase,ADA)、葡萄糖(glucose,GLU)、蛋白定量(protein quantification,TP)水平,胸水癌胚抗原(carcinoembryonic antigen,CEA)、糖类抗原125(carbohydrate antigen-125,CA125)水平,以及血清 CEA、血清细胞角蛋白 19 片段(cytokeratin 19 fragment,CYFRA21-1)水平,分别比较无结节组和结节组、结节散在组和结节弥漫组、结节弥漫较多组和结节弥漫成片组组间各指标水平差异.结果 结节组胸水LDH水平显著高于无结节组(P＜0.01),结节弥漫组胸水LDH水平高于结节散在组(P＜0.05).与结节弥漫较多组相比,结节弥漫成片组胸水LDH和ADA水平明显升高(P＜0.01),GLU水平明显降低(P＜0.05).配对组间病程长短、吸烟指数、胸水TP、胸水CEA、胸水CA125、血清CEA、血清CYFRA21-1指标水平比较,差异均无统计学意义.结论 胸膜恶性病变内科胸腔镜下不同结节表现患者的胸水LDH、ADA、GLU表达水平存在差异,结节越多,尤其是结节弥漫成片者,其胸水LDH、ADA水平越高,胸水GLU水平越低.

Abstract Background Nowadays chronic respiratory diseases are a major burden in terms of morbidity and mortality and of increasing public health concern in China. Meanwhile, prevalence of diabetes has increased more than 10 times over forty years. A few studies investigating the association between chronic respiratory diseases and diabetes mellitus have been done these years. However, the association was not clear, and we aimed to answer this question with solid proof. Methods Our study is a single-center study performed in MJ Healthcare Center in Beijing. We enrolled subjects aged ≥ 20 years undergoing at least two regular health check-ups between 2009 and 2019 in MJ Healthcare Center in Beijing. Each health check-up included regular tests, biochemical tests, a pulmonary function test and a questionnaire. 11,107 adults were included and cross-sectional and longitudinal analysis were performed. Results We found that both pre-diabetic and diabetic adults had lower lung function compared to normal population at baseline, indicating that lung function decrement may start from prediabetic status. Quantitatively, with 1 mmol/L increase of FPG (fasting plasma glucose), FVC (forced vital capacity), FEV1 (forced expiratory volume), FVC% and FEV1% lowered 25ml, 13ml, 0.71%-1.03% and 0.46%-0.72% respectively. However, no statistical significance was found regarding the rates for the lung function decline between different baseline diabetes status. Conclusion People with higher blood glucose had more severe lung function decline and lung function decrement started from pre-diabetic status, but there was no difference in the rate of lung function decrease based on different baseline diabetic status.

ObjectivesTo identify factors associated with length of stay (LOS) in chronic obstructive pulmonary disease (COPD) hospitalised patients, which may help shorten LOS and reduce economic burden accrued over hospital stay.DesignA retrospective cohort study.SettingThis study was performed in a tertiary hospital in China.ParticipantsPatients with COPD who were aged ≥40 years and newly admitted between 2016 and 2017.Primary and secondary outcome measuresLOS at initial admission was the primary outcome and health expenditures were the secondary outcome. To identify factors associated with LOS, we collected information at index hospitalisation and constructed a conceptual model using directed acyclic graph. Potential factors were classified into five groups: demographic information, disease severity, comorbidities, hospital admission and environmental factors. Negative binomial regression model was fitted for each block of factors and a parsimonious analysis was performed.ResultsIn total, we analysed 565 patients with COPD. The mean age was 69±11 years old and 69.4% were men. The median LOS was 10 (interquartile range 8–14) days. LOS was significantly longer in patients with venous thromboembolism (VTE) (16 vs 10 days, p=0.0002) or with osteoporosis (15 vs 10 days, p=0.0228). VTE ((rate ratio) RR 1.38, 95% CI 1.07 to 1.76), hypoxic–hypercarbic encephalopathy (RR 1.53, 95% CI 1.06 to 2.20), respiratory infection (RR 1.12, 95% CI 1.01 to 1.24), osteoporosis (RR 1.45, 95% CI 1.07 to 1.96) and emergence admission (RR 1.08, 95% CI 1.01 to 1.16) were associated with longer LOS. In parsimonious analysis, all these factors remained significant except emergency admission, highlighting the important role of concomitant morbidities in patients’ hospital stay. Total hospitalisation cost and patients’ out-of-pocket cost increased monotonically with LOS (both ptrend <0.0001).ConclusionPatients’ concomitant morbidities predicted excessive LOS in patients with COPD. Healthcare cost increased over the LOS. Quality improvement initiatives may need to identify patients at high risk for lengthy stay and implement early interventions to reduce COPD economic burden.

支气管扩张症是一种常见的慢性呼吸道疾病,严重影响患者的生活质量,带来了沉重的社会经济负担.随着人工智能的发展,可利用计算机视觉领域的目标检测技术辅助诊断这类疾病.报告了支气管扩张症人工智能诊断系统的研究现状,介绍了支气管扩张症的临床诊断方式,并基于此提出了计算机辅助诊断该类疾病的诊断技术路线,总结了CT影像噪声抑制、肺实质提取、肺叶分割的传统和深度学习方法,针对支气管扩张金标准数据集匮乏的问题,从两个方面综述了目标检测应用于计算机辅助诊断的问题及挑战,详细比较了不同算法的特点和适用场景.最后讨论了未来可能的发展趋势.

Medical thoracoscopy is considered an overall safe procedure, whereas numbers of studies focus on complications of diagnostic thoracoscopy and talc poudrage pleurodesis. We conduct this study to evaluate the safety of medical thoracoscopy in the management of pleural diseases and to compare complications in different therapeutic thoracoscopic procedures. A retrospective study was performed in 1926 patients, 662 of whom underwent medical thoracoscopy for diagnosis and 1264 of whom for therapeutic interventions of pleural diseases. Data on complications were obtained from the patients, notes on computer system, laboratory and radiographic findings. Chi-square test was performed to compare categorical variables and Fisher’s exact test was used for small samples. The mean age was 51 ± 8.4 (range 21–86) years and 1117 (58%) were males. Diagnostic procedure was taken in 662 (34.4%) patients, whereas therapeutic procedure was taken in 1264 (65.6%) patients. Malignant histology was reported in 860 (44.6%) and 986 (51.2%) revealed benign pleural diseases. Eighty patients (4.2%) were not definitely diagnosed and they were considered as unidentified pleural effusion. One patient died during the creation of artificial pneumothorax, and the causes of death were supposed as air embolism or an inhibition of phrenic motoneurons and circulatory system. Complication of lung laceration was found in six patients (0.3%) and reexpansion pulmonary edema was observed in two patients (0.1%). Higher incidence of prolonged air leak was observed in bulla electrocoagulation group, in comparison with pleurodesis group. Moreover, pain and fever were the most frequently complications in pleurodesis group and cutaneous infection in entry site was the most frequently reported complication in pleural decortication of empyema group. Medical thoracoscopy is generally a safe and effective method, not only in the diagnosis of undiagnosed pleural effusions, but also in the management of pleural diseases. Mastering medical thoracoscopy well, improving patient management after the procedure and attempts to reduce the occurrence of post-procedural complications are the targets that physicians are supposed to achieve in the future.

BackgroundRefractory (recurrent or persistent) spontaneous pneumothorax with high recurrence rates required treatment either by continuous chest drainage or interventional approaches. Pleurodesis by sclerosing agents has become a significant therapy in the treatment of refractory spontaneous pneumothorax (RSP) on account of its high efficiency and safety. However, the efficacy, safety and appropriate mode of administration of intrapleural erythromycin for pleurodesis have not yet been realized in the treatment of RSP.MethodsThe trial was performed to compare thoracoscopic erythromycin poudrage with erythromycin slurry via a chest tube for patients with documented RSP. Fifty-seven patients with RSP were enrolled in this study with 30 patients for erythromycin poudrage and 27 patients for erythromycin slurry. Response to pleurodesis, complications and recurrences were recorded. Continuous variables were compared with t-test. Chi-square test was performed to compare categorical variables and Fisher's exact test was used for small samples.ResultsTwenty-four patients in the erythromycin poudrage group (80%) and sixteen in the erythromycin slurry (ES) group (59.26%) had an immediately successful pleurodesis within 5 days (P=0.087). Patients in erythromycin poudrage had shorter duration of postprocedural chest tube drainage (6.23±3.04 days) than patients in ES (10.67±9.81 days) (P=0.032). During the follow-up, there was no significant statistical difference in recurrence rates between the two groups. Common adverse reactions included fever and chest pain with no significant difference between the two groups.ConclusionsErythromycin is an effective and safe sclerosing agent for pleurodesis in management of RSP. Both methods are safe but erythromycin poudrage is more effective than ES.

支气管扩张是一种常见疾病，可引起肺通气功能障碍且病程长，会造成巨大的社会经济负担。使用深度学习的方法对支气管扩张进行检测与分类，使其在判断准确率与人类医生相当的情况下，快速高效地对大量数据同时进行处理，不仅能够减轻医生负担，还能为医生诊断支气管扩张提供有用的参考，具有很高的价值和意义。图像预处理的好坏是影响深度学习效果的一个重要因素。肺叶分割则是处理肺部CT图像的一个难点与重点。本研究使用基于U-Net的肺叶分割方法处理低剂量CT(LDCT)数据，然后使用深度学习模型Mask R-CNN对支气管扩张进行检测与分类。实验表明，使用肺叶分割的预处理方法可以有效提升深度学习模型对支气管扩张的检测与分类效果。本实验最后训练好的模型对使用了肺叶分割后的LDCT图像中支气管扩张的检测准确率可以达到89.8%，平均分类准确率为91.0%，识别一张图片的速度约为1.5s。