Construction and validation of a risk-prediction model for anastomotic leakage after radical gastrectomy: A cohort study in China

Objectives:Anastomotic leakage(AL)stands out as a prevalent and severe complication following gastric cancer surgery.It frequently precipitates additional serious complications,significantly influencing the overall survival time of patients.This study aims to enhance the risk-assessment strategy for AL following gastrectomy for gastric cancer.Methods:This study included a derivation cohort and validation cohort.The derivation cohort included patients who underwent radical gastrectomy at Sir Run Run Shaw Hospital,Zhejiang University School of Medicine,from January 1,2015 to December 31,2020.An evidence-based predictor questionnaire was crafted through extensive literature review and panel discussions.Based on the questionnaire,inpatient data were collected to form a model-derivation cohort.This cohort underwent both univariate and multivariate analyses to identify factors associated with AL events,and a logistic regression model with stepwise regression was developed.A 5-fold cross-validation ensured model reliability.The validation cohort included patients from August 1,2021 to December 31,2021 at the same hospital.Using the same imputation method,we organized the validation-queue data.We then employed the risk-prediction model constructed in the earlier phase of the study to predict the risk of AL in the subjects included in the validation queue.We compared the predictions with the actual occurrence,and evaluated the external validation performance of the model using model-evaluation indicators such as the area under the receiver operating characteristic curve(AUROC),Brier score,and calibration curve.Results:The derivation cohort included 1377 patients,and the validation cohort included 131 patients.The independent predictors of AL after radical gastrectomy included age65 y,preoperative albumin<35 g/L,resection extent,operative time240 min,and intraoperative blood loss90 mL.The predictive model exhibited a solid AUROC of 0.750(95%CI:0.694e0.806;p<0.001)with a Brier score of 0.049.The 5-fold cross-validation confirmed these findings with a calibrated C-index of 0.749 and an average Brier score of 0.052.External validation showed an AUROC of 0.723(95%CI:0.564e0.882;p?0.006)and a Brier score of 0.055,confirming reliability in different clinical settings.Conclusions:We successfully developed a risk-prediction model for AL following radical gastrectomy.This tool will aid healthcare professionals in anticipating AL,potentially reducing unnecessary interventions.

Endoscopic ultrasound-guided tissue sampling induced pancreatic duct leak resolved by the placement of a pancreatic stent:A case report

BACKGROUND Pancreatic ductal leaks complicated by endoscopic ultrasonography-guided tissue sampling(EUS-TS)can manifest as acute pancreatitis.CASE SUMMARY A 63-year-old man presented with persistent abdominal pain and weight loss.Diagnosis:Laboratory findings revealed elevated carbohydrate antigen 19-9(5920 U/mL)and carcinoembryonic antigen(23.7 ng/mL)levels.Magnetic resonance imaging of the pancreas revealed an approximately 3 cm ill-defined space-occupying lesion in the inferior aspect of the head,with severe encasement of the superior mesenteric artery.Pancreatic ductal adenocarcinoma was confirmed after pathological examination of specimens obtained by EUS-TS using the fanning method.Interventions and outcomes:The following day,the patient experienced severe abdominal pain with high amylase(265 U/L)and lipase(1173 U/L)levels.Computed tomography of the abdomen revealed edematous wall thickening of the second portion of the duodenum with adjacent fluid collections and a suspicious leak from either the distal common bile duct or the main pancreatic duct in the head.Endoscopic retrograde cholangiopancreatography revealed dye leakage in the head of the main pancreatic duct.Therefore,a 5F 7 cm linear plastic stent was deployed into the pancreatic duct to divert the pancreatic juice.The patient’s abdominal pain improved immediately after pancreatic stent insertion,and amylase and lipase levels normalized within a week.Neoadjuvant chemotherapy was then initiated.CONCLUSION Using the fanning method in EUS-TS can inadvertently cause damage to the pancreatic duct and may lead to clinically significant pancreatitis.Placing a pancreatic stent may immediately resolve acute pancreatitis and shorten the waiting time for curative therapy.When using the fanning method during EUSTS,ductal structures should be excluded to prevent pancreatic ductal leakage.

Impact of open hepatectomy on postoperative bile leakage in patients with biliary tract cancer

BACKGROUND Bile leakage is a common and serious complication of open hepatectomy for the treatment of biliary tract cancer.AIM To evaluate the incidence,risk factors,and management of bile leakage after open hepatectomy in patients with biliary tract cancer.METHODS We retrospectively analyzed 120 patients who underwent open hepatectomy for biliary tract cancer from February 2018 to February 2023.Bile leak was defined as bile drainage from the surgical site or drain or the presence of a biloma on imaging.The incidence,severity,timing,location,and treatment of the bile leaks were recorded.The risk factors for bile leakage were analyzed using univariate and multivariate logistic regression analyses.RESULTS The incidence of bile leak was 16.7%(20/120),and most cases were grade A(75%,15/20)according to the International Study Group of Liver Surgery classification.The median time of onset was 5 d(range,1-14 d),and the median duration was 7 d(range,2-28 d).The most common location of bile leakage was the cut surface of the liver(70%,14/20),followed by the anastomosis site(25%,5/20)and the cystic duct stump(5%,1/20).Most bile leaks were treated conservatively with drainage,antibiotics,and nutritional support(85%,17/20),whereas some required endoscopic retrograde cholangiopancreatography with stenting(10%,2/20)or percutaneous transhepatic cholangiography with drainage(5%,1/20).Risk factors for bile leakage include male sex,hepatocellular carcinoma,major hepatectomy,blood loss,and blood transfusion.CONCLUSION Bile leakage is a frequent complication of open hepatectomy for biliary tract cancer.However,most cases are mild and can be conservatively managed.Male sex,hepatocellular carcinoma,major hepatectomy,blood loss,and blood transfusion were associated with an increased risk of bile leak.

Preoperative neutrophil-to-lymphocyte ratio predicts symptomatic anastomotic leakage in elderly colon cancer patients: Multicenter propensity score-matched analysis

BACKGROUND The neutrophil-to-lymphocyte ratio(NLR),a composite inflammatory biomarker,is associated with the prognosis in patients with colorectal tumors.However,whether the NLR can be used as a predictor of symptomatic postoperative ana-stomotic leakage(AL)in elderly patients with colon cancer is unclear.AIM To assess the role of the NLR in predicting the occurrence of symptomatic AL after surgery in elderly patients with colon cancer.METHODS Data from elderly colon cancer patients who underwent elective radical colectomy with anastomosis at three centers between 2018 and 2022 were retrospectively analyzed.Receiver operating characteristic curve analysis was performed to determine the best predictive cutoff value for the NLR.Twenty-two covariates were matched using a 1:1 propensity score matching method,and univariate and multivariate logistic regression analyses were used to determine risk factors for the development of postoperative AL.RESULTS Of the 577 patients included,36(6.2%)had symptomatic AL.The optimal cutoff value of the NLR for predicting AL was 2.66.After propensity score matching,the incidence of AL was significantly greater in the≥2.66 NLR subgroup than in the<2.66 NLR subgroup(11.5%vs 2.5%;P=0.012).Univariate logistic regression analysis revealed statistically significant correlations between blood transfusion intraoperatively and within 2 d postoper-atively,preoperative albumin concentration,preoperative prognostic nutritional index,and preoperative NLR and AL occurrence(P<0.05);multivariate logistic regression analysis revealed that an NLR≥2.66[odds ratio(OR)=5.51;95%confidence interval(CI):1.50-20.26;P=0.010]and blood transfusion intraoperatively and within 2 d postoperatively(OR=2.52;95%CI:0.88-7.25;P=0.049)were risk factors for the occurrence of symptomatic AL.CONCLUSION A preoperative NLR≥2.66 and blood transfusion intraoperatively and within 2 d postoperatively are associated with a higher incidence of postoperative symptomatic AL in elderly patients with colon cancer.The preoperative NLR has predictive value for postoperative symptomatic AL after elective surgery in elderly patients with colon cancer.

How to preserve the native or reconstructed esophagus after perforations or postoperative leaks: A multidisciplinary 15-year experience

BACKGROUND Esophageal perforation or postoperative leak after esophageal surgery remain a life-threatening condition.The optimal management strategy is still unclear.AIM To determine clinical outcomes and complications of our 15-year experience in the multidisciplinary management of esophageal perforations and anastomotic leaks.METHODS A retrospective single-center observational study was performed on 60 patients admitted at our department for esophageal perforations or treated for an anastomotic leak developed after esophageal surgery from January 2008 to December 2023.Clinical outcomes were analyzed,and complications were evaluated to investigate the efficacy and safety of our multidisciplinary management based on the preservation of the native or reconstructed esophagus,when feasible.RESULTS Among the whole series of 60 patients,an urgent surgery was required in 8 cases due to a septic state.Fifty-six patients were managed by endoscopic or hybrid treatments,obtaining the resolution of the esophageal leak/perforation without removal of the native or reconstructed esophagus.The mean time to resolution was 54.95±52.64 days,with a median of 35.5 days.No severe complications were recorded.Ten patients out of 56(17.9%)developed pneumonia that was treated by specific antibiotic therapy,and in 6 cases(10.7%)an atrial fibrillation was recorded.Seven patients(12.5%)developed a stricture within 12 months,requiring one or two endoscopic pneumatic dilations to solve the problem.Mortality was 1.7%.CONCLUSION A proper multidisciplinary approach with the choice of the most appropriate treatment can be the key for success in managing esophageal leaks or perforations and preserving the esophagus.

Surgeon Perspectives on Anastomotic Leaks and FluidAI’s StreamTM Platform: Integrating Qualitative Insights for Technological Innovation

Purpose: This article investigates the critical importance of integrating surgeons’ direct input into the development of innovative technologies that address gaps in surgical care, including those aimed at reducing anastomotic leaks (AL), a major complication in gastrointestinal surgery. While traditional quantitative research methods are prevalent, they often overlook the invaluable insights of the surgeons who manage these complications firsthand. Subjects and Methods: This study employs a qualitative approach, utilizing semi-structured interviews with 40 surgeons from various specialties, including general, bariatric, colorectal, trauma, hepato-biliary, and thoracic surgery. The interviews were designed to probe the needs of surgeons, challenges currently faced, and gaps in clinical practice, research, and technology for detection and/or management of AL. The data were analyzed using thematic analysis, which revealed significant gaps in current technologies for early detection and prevention of leaks. Results: Surgeons expressed strong interest in FluidAI’s Stream™ Platform, a non-invasive medical device designed to monitor postoperative drainage fluid in real-time, providing continuous data on AL risk. The ability of this platform to offer early prediction through pH and electrical conductivity analysis was particularly appealing to participants, who emphasized the importance of timely interventions in improving patient outcomes. The study’s findings highlight not only the clinical challenges but also the emotional toll that AL takes on surgeons, underlining the need for innovations that are both data-driven and humanistic. Conclusion: By centering surgeons’ perspectives, this research advocates for a human-centered approach to technological advancement, ensuring that new tools are both clinically effective and aligned with the real-world needs of surgical practitioners.

Surgical treatment of mixed cervical spondylosis with spontaneous cerebrospinal fluid leakage: A case report

BACKGROUND Spontaneous cerebrospinal fluid(CSF)leaks associated with cervical spondylosis are rare.To our knowledge,only a few cases have been reported in which treatment is challenging and varies from case to case.Here,we review the literature and describe the surgical treatment of a 70-year-old woman who presented with a CSF leak due to a cervical spine spur.CASE SUMMARY A 70-year-old female patient who was treated for a cerebral infarction,presented with complains of weakness in the right lower extremity and a feeling of stepping on cotton.The patient underwent regular neck massage and presented with neck and right shoulder pain radiating to the right upper extremity one-month ago.Magnetic resonance imaging showed a strip of leaking cerebrospinal fluid posterior to the C1-4 vertebrae,and computed tomography showed a“sickleshaped”disc prolapse with calcification in C4/5.We chose to perform an anterior cervical discectomy.When the prolapsed C4/5 disc was scraped,clear fluid leakage was observed,and exploration revealed a 1 mm diameter rupture in the anterior aspect of the dura mater,which was compressed continuously with cotton patties,with no significant cerebrospinal fluid leakage after 1 h.CONCLUSION Three months after surgery,the patient was asymptomatic and follow-up imaging demonstrated complete resolution.

Research on Leak Location Method of Water Supply Pipeline Based on MVMD

At present,the leakage rate of the water distribution network in China is still high,and the waste of water resources caused by water distribution network leakage is quite serious every year.Therefore,the location of pipeline leakage is of great significance for saving water resources and reducing economic losses.Acoustic emission technology is the most widely used pipeline leak location technology.The traditional non-stationary random signal de-noising method mainly relies on the estimation of noise parameters,ignoring periodic noise and components unrelated to pipeline leakage.Aiming at the above problems,this paper proposes a leak location method for water supply pipelines based on a multivariate variational mode decomposition algorithm.This method combines the two parameters of the energy loss coefficient and the correlation coefficient between adjacent modes,and adaptively determines the decomposition mode number K according to the characteristics of the signal itself.According to the correlation coefficient,the effective component is selected to reconstruct the signal and the cross-correlation time delay is estimated to determine the location of the pipeline leakage point.The experimental results show that this method has higher accuracy than the cross-correlation method based on VMD and the cross-correlation method based on EMD,and the average relative positioning error is less than 2.2%.

Choosing the best endoscopic approach for post-bariatric surgical leaks and fistulas:Basic principles and recommendations

Post-surgical leaks and fistulas are the most feared complication of bariatric surgery.They have become more common in clinical practice given the increasing number of these procedures and can be very difficult to treat.These two related conditions must be distinguished and characterized to guide the appropriate treatment.Leak is defined as a transmural defect with communication between the intra and extraluminal compartments,while fistula is defined as an abnormal communication between two epithelialized surfaces.Traditionally,surgical treatment was the preferred approach for leaks and fistulas and was associated with high morbidity with significant mortality rates.However,with the development of novel devices and techniques,endoscopic therapy plays an increasingly essential role in managing these conditions.Early diagnosis and endoscopic therapy initiation after clinical stabilization are crucial to success since clinical success rates are higher for acute leaks and fistulas when compared to late and chronic leaks and fistulas.Several endoscopic techniques are available with different mechanisms of action,including direct closure,covering/diverting or draining.The treatment should be individualized by considering the characteristics of both the patient and the defect.Although there is a lack of high-quality studies to provide standardized treatment algorithms,this narrative review aims to provide a summary of the current scientific evidence and,based on this data and our extensive experience,make recommendations to help choose the best endoscopic approach for the management of post-bariatric surgical leaks and fistulas.

A reliability-oriented genetic algorithm-levenberg marquardt model for leak risk assessment based on time-frequency features

Since leaks in high-pressure pipelines transporting crude oil can cause severe economic losses,a reliable leak risk assessment can assist in developing an effective pipeline maintenance plan and avoiding unexpected incidents.The fast and accurate leak detection methods are essential for maintaining pipeline safety in pipeline reliability engineering.Current oil pipeline leakage signals are insufficient for feature extraction,while the training time for traditional leakage prediction models is too long.A new leak detection method is proposed based on time-frequency features and the Genetic Algorithm-Levenberg Marquardt(GA-LM)classification model for predicting the leakage status of oil pipelines.The signal that has been processed is transformed to the time and frequency domain,allowing full expression of the original signal.The traditional Back Propagation(BP)neural network is optimized by the Genetic Algorithm(GA)and Levenberg Marquardt(LM)algorithms.The results show that the recognition effect of a combined feature parameter is superior to that of a single feature parameter.The Accuracy,Precision,Recall,and F1score of the GA-LM model is 95%,93.5%,96.7%,and 95.1%,respectively,which proves that the GA-LM model has a good predictive effect and excellent stability for positive and negative samples.The proposed GA-LM model can obviously reduce training time and improve recognition efficiency.In addition,considering that a large number of samples are required for model training,a wavelet threshold method is proposed to generate sample data with higher reliability.The research results can provide an effective theoretical and technical reference for the leakage risk assessment of the actual oil pipelines.

Negligible Warming Caused by Nord Stream Methane Leaks

Unanticipated sabotage of two underwater pipelines in the Baltic Sea(Nord Stream 1 and 2)happened on 26September 2022.Massive quantities of natural gas,primarily methane,were released into the atmosphere,which lasted for about one week.As a more powerful greenhouse gas than CO_(2),the potential climatic impact of methane is a global concern.Using multiple methods and datasets,a recent study reported a relatively accurate magnitude of the leaked methane at 0.22±0.03 million tons(Mt),which was lower than the initial estimate in the immediate aftermath of the event.Under an energy conservation framework used in IPCC AR6,we derived a negligible increase in global surface air temperature of 1.8×10^(-5)℃ in a 20-year time horizon caused by the methane leaks with an upper limit of 0.25 Mt.Although the resultant warming from this methane leak incident was minor,future carbon release from additional Earth system feedbacks,such as thawing permafrost,and its impact on the methane mitigation pathways of the Paris Agreement,warrants investigation.

A sutureless technique for securing leaking sclerotomies with viscoelastic substances in 23-gauge microincision vitrectomy surgery

AIM:To introduce and evaluate the clinical efficacy of a new technique,the use of viscoelastic substances(VS)to close leaking sclerotomy in 23G microincision vitrectomy,and to observe its effect on the visual acuity and intraocular pressure(IOP)of patients.METHODS:Patients who underwent 23G vitrectomy in Ningbo Eye Hospital before the use of VS technique(June 2019 to September 2020)and after the use of VS technique(October 2020 to December 2021)were selected as the subjects of this study.The above cases underwent operation by the same surgeon and were retrospectively analyzed.VS technique was used as the alternative to suturing,in which a small amount of VS was injected at the leaking sclerotomy and then gently massaged to confirm leaking sclerotomy closure.RESULTS:A total of 174 eyes were covered in the study,including 84 eyes in the control group(before the use of VS technique)and 90 eyes in the VS technique group.The number of eyes that needed to be sutured decreased considerably from 42.9%in the control group to 3.3%in the VS technique group,and the proportion of subconjunctival hemorrhage at 1-2d after surgery decreased remarkably from 35.7%in the control group to 2.2%in the VS technique group.No substantial differences in the incidence of mean IOP and low IOP were found between 1-2 and 3-20d after surgery in the VS technique group.No major complications associated with VS technique were identified during the study.CONCLUSION:In 23G microincision vitrectomy,VS technique is a safe,simple,and effective method to close leaking sclerotomy.

Progress in the study and treatment of peri-device leak after left atrial appendage closure

For patients with atrial fibrillation with an increased risk of stroke and contraindications to long-term anticoagulation,percutaneous left atrial appendage closure(LAAC)has become an important alternative to long-term oral anticoagulation.Incomplete closure of the LAAC during the procedure leads to faster blood flow in the interstitial space around the device,resulting in peri-device leak(PDL),which is not uncommon.Studies are still inconclusive in determining the incidence,long-term safety,and management of PDL.Therefore,this article reviewed the progress made in the research and treatment of PDL after LAAC.

基于压裂液自发吸入模型的页岩气压裂液滤失定量预测

非常规油气资源开发常使用水力压裂技术提高单井产量,然而压裂现场数据表明,大量压裂液会滞留在地层中导致压裂液的返排率较低,将对储层和地下水环境造成一定影响。为进一步研究压裂液滤失机理并准确预测压裂液滤失量,首先建立了由毛细管力作用引起的压裂液自发吸入模型,然后对压裂液滤失量进行定量计算,并在现场进行了验证。最后,引入无量纲吸入率参数分析了控制压裂液滤失的关键因素。研究结果表明:(1)页岩气水平井压裂施工中大约50%~95%的压裂液通过基质吸入,压裂液吸入量仅与吸入率参数、裂缝面积和吸收时间有关;(2)当润湿相黏度与非润湿相黏度之比超过阈值时,吸入率参数主要由岩石的孔径分布参数决定,流体黏度的影响非常有限;(3)当孔径分布参数介于0.5~0.7时,吸入率参数达到相对较高的值,即更多的压裂液被吸收到地层中;(4)当润湿相黏度与非润湿相黏度之比大于10,孔径分布参数小于0.8时,优化后的自吸模型具有较大的适用性;(5)由毛细管力机理引起的压裂液滤失量与实际储层观察到的滤失量相近,可认为页岩储层有足够的存储滤失液的能力,不会影响地下水层中的饮用水。结论认为,建立的压裂液自发吸入模型,能够准确预测页岩气水平井压裂液滤失量,为非常规油气的生产及环境保护提供了技术支撑。

从管段走向管网:管道泄漏诊断技术研究进展

管道泄漏诊断技术在保障管道系统安全运行中起着至关重要的作用。首先,介绍了管道泄漏诊断系统的结构,并指出由单一管段向复杂管网泄漏诊断的发展趋势。进一步从基于数据驱动的传统泄漏检测方法、管道泄漏信号源定位技术和基于深度学习的复杂管网泄漏检测方法3个方面进行综述,分析了不同方法的优势、局限性和适用范围。最后指出,随着管网系统的复杂度增加,传统方法的局限性逐渐显现,基于深度学习技术的复杂管网微弱泄漏诊断、多源信号融合和管网智能化的研究将成为未来的研究趋势。

炼化企业挥发性有机化合物减排的探索与实践

炼化企业加工过程有组织、无组织排放的挥发性有机化合物(VOCs)量较大,对大气环境中的颗粒物、臭氧浓度等产生重大影响。A公司自“十三五”以来对VOCs减排进行了探索与实践,通过采取油气回收、储罐浮盘高效密封改造、呼吸阀改型升级、无组织排放改为有组织回收、VOCs焚烧、常态化泄漏检测与修复工作等多种减排措施,VOCs排放量已从2015年的4230 t下降到2022年的2157 t,降低比例达到49%,取得了显著的成效。

断控型缝洞气藏酸压规模与无阻流量的关系研究

顺北二区发育典型的超深断控型缝洞储集体,由于钻井过程泥浆漏失量大,通常选择酸压或是酸洗完井作为解堵增产措施。为了研究酸液用量和酸压规模对无阻流量的影响,研究基于顺北二区地质特征,建立了钻遇裂缝(漏失井)和未钻遇裂缝两种情况的数值模型,利用裂缝扩展—气藏数值模拟方法,对两种情况井的酸压缝形态进行了模拟,进一步模拟了两种地质条件和不同酸压规模下的气井早期无阻流量,并用现场数据进行了反演验证。对比结果发现,当气井钻遇裂缝带时,酸压可以提高气井无阻流量,但幅度不大,酸压的规模不宜过大;当气井未钻遇裂缝带时,酸压则可以明确大幅度提高气井无阻流量和控制储量。

低颅压综合征合并颅内出血的诊断和治疗

目的探讨低颅压综合征合并颅内出血的病因、临床表现、影像学特点及救治方法。方法回顾性分析2015年1月—2022年12月苏州大学附属张家港医院神经外科收治的14例低颅压综合征合并颅内出血患者的临床资料,并进行定期随访,了解其预后及转归。结果14例低颅压综合征患者中,13例存在直立性头痛。4例自发性低颅压综合征合并双侧慢性硬脑膜下血肿患者,行头颅核磁共振成像(MRI)增强显示硬脑膜下出血或积液、硬脑膜强化、静脉结构充盈、垂体充血和脑组织下垂等影像学特征,钻颅引流手术治疗3例、保守治疗1例;10例创伤性低颅压综合征伴颅内出血患者保守治疗7例,钻颅引流手术治疗2例,开颅血肿清除手术治疗1例;治疗后相关症状明显好转或消失。结论对于低颅压综合征合并颅内出血的患者,临床上应根据患者的个体情况选择保守治疗或手术治疗;早期明确病因有助于临床治疗方案的优化,改善患者神经功能及预后。

基于迁移学习的气体泄漏红外图像去噪方法

非制冷型红外相机由于其成本低、寿命长、性能稳定等优势在气体泄漏检测领域有着广泛应用,而良好的图像去噪算法可以有效提升其检测灵敏度与准确性。结合深度学习和迁移学习技术,提出了一种基于深度迁移学习的气体泄漏红外图像去噪方法。首先使用静止场景数据集对卷积神经网络模型进行训练,然后固定部分模型参数,并通过仿真气体数据集对模型再次训练,最终获得适用于气体泄漏红外图像去噪的模型。实验结果表明,该方法可以对非制冷型红外相机拍摄的气体红外图像进行去噪,去噪后的图像具有明显的气体轮廓信息,同时可以分辨出泄漏源的位置。因此,该方法可以帮助非制冷型红外相机更好地完成气体泄漏检测任务。

基于交叉注意力的多源数据融合的气体泄漏检测

为解决单一传感器在管道气体泄漏检测时容易出现误报、漏报的问题,及时预警并反馈泄漏状况,提出一种基于交叉注意力的多源数据融合管道泄漏检测方法。首先,利用预训练的ShuffleNetV2模型提取热像仪数据的空间特征;然后,结合一维卷积神经网络(1DCNN)和双向门控循环单元(BiGRU),构建1DCNN-BiGRU模型,以提取气体传感器数据的时序特征;最后,运用交叉注意力捕获数据的时空关联性得到2个数据源的特征表示,通过残差方式进行特征连接后输入到分类层中,得到识别结果。结果表明:所构建的多源数据融合模型(SCGA)对气体识别准确率为99.22%,损失值在0~0.04内波动;与仅使用气体传感器数据的支持向量机(SVM)、1DCNN、BiGRU模型相比,准确率至少提升4.12%;与仅使用热图像传感器数据的MobileNetV3、ShuffleNetV2、ResNet18模型相比,准确率至少提升1.14%;与将时序特征和空间特征直接拼接的多源数据融合模型(SCG)相比,准确率提升1%。SCGA模型对气体识别具有较高精度。