Peritoneal fluid indocyanine green test for diagnosis of gut leakage in anastomotic leakage rats and colorectal surgery patients

BACKGROUND Application of indocyanine green(ICG)fluorescence has led to new developments in gastrointestinal surgery.However,little is known about the use of ICG for the diagnosis of postoperative gut leakage(GL).In addition,there is a lack of rapid and intuitive methods to definitively diagnose postoperative GL.AIM To investigate the effect of ICG in the diagnosis of anastomotic leakage in a surgical rat GL model and evaluate its diagnostic value in colorectal surgery patients.METHODS Sixteen rats were divided into two groups:GL group(n=8)and sham group(n=8).Approximately 0.5 mL of ICG(2.5 mg/mL)was intravenously injected postoperatively.The peritoneal fluid was collected for the fluorescence test at 24 and 48 h.Six patients with rectal cancer who had undergone laparoscopic rectal cancer resection plus enterostomies were injected with 10 mL of ICG(2.5 mg/mL)on postoperative day 1.Their ostomy fluids were collected 24 h after ICG injection to identify the possibility of the ICG excreting from the peripheral veins to the enterostomy stoma.Participants who had undergone colectomy or rectal cancer resection were enrolled in the diagnostic test.The peritoneal fluids from drainage were collected 24 h after ICG injection.The ICG fluorescence test was conducted using OptoMedic endoscopy along with a near-infrared fluorescent imaging system.RESULTS The peritoneal fluids from the GL group showed ICG-dependent green fluorescence in contrast to the sham group.Six samples of ostomy fluids showed green fluorescence,indicating the possibility of ICG excreting from the peripheral veins to the enterostomy stoma in patients.The peritoneal fluid ICG test exhibited a sensitivity of 100%and a specificity of 83.3%for the diagnosis of GL.The positive predictive value was 71.4%,while the negative predictive value was 100%.The likelihood ratios were 6.0 for a positive test result and 0 for a negative result.CONCLUSION The postoperative ICG test in a drainage tube is a valuable and simple technique for the diagnosis of GL.Hence,it should be employed in clinical settings in patients with suspected GL.

Effect of stress-dependent microannulus aperture on well leakage

Debonding at the cement-casing interface is recognized as a principal failure mechanism leading to CO_(2) leakage in wells.This detachment gives rise to a microannulus,which notably possesses greater permeability than undamaged cement,undermining its sealing efficacy.Conventionally,the permeability of the microannulus is regarded as a uniform value throughout the well.However,fundamentally,a microannulus is one type of fracture,and its gap or aperture size is affected by the effective stress.In this work,we developed a unique experimental apparatus.This equipment facilitates the curing of cement inside a steel casing,the formation of a microannulus between the casing and the cement,and the investigation of the fluid flow dynamics along the microannulus under laboratory-replicated in situ conditions.The microannulus was formed by injecting fluid from one end of the setup,and receiving similar amount of fluid on the other end signified the development of the leakage channel.Additionally,strain gauges affixed to the casing’s external surface yielded key information on the microannulus’s opening and closure.We observed a noticeable decline in microannulus hydraulic aperture(or permeability)in relation to effective stress and an exponential equation fits their relationship.Our findings also indicate a distinct behavior when comparing liquid CO_(2) with water.Specifically,it is easier for liquid CO_(2) to create the microannulus.However,the hydraulic aperture range for this microannulus(0.7-6 mm)is considerably smaller than that created by water flow(2-17 mm).Finally,we integrated the stressdependent microannulus aperture size into the combined analysis of well mechanical integrity and well leakage.The outcomes consistently demonstrated that when factoring in the stress-dependent aperture sizes,the leakage rates are 3e5 times compared to a fixed aperture model.The traditional assumption of a constant aperture significantly underestimates fluid leakage risks.

Enhanced ferroelectric and improved leakage of BFO-based thin films through increasing entropy strategy

BiFeO_(3)(BFO)has received considerable attention as a lead-free ferroelectric film due to its large theoretical remnant polariza-tion.However,BFO suffers from a large leakage current,resulting in poor ferroelectric properties.Herein,the sol-gel method was used to deposit a series of BFO-based thin films on fluorine-doped tin oxide substrates,and the effects of the substitution of the elements Co,Cu,Mn(B-site)and Sm,Eu,La(A-site)on the crystal structure,ferroelectricity,and leakage current of the BFO-based thin films were invest-igated.Results confirmed that lattice distortion by X-ray diffraction can be attributed to the substitution of individual elements in the BFO-based films.Sm and Eu substitutions contribute to the lattice distortion in a pseudo-cubic structure,while La is biased toward pseudo-tet-ragonal.Piezoelectric force microscopy confirmed that reversible switching of ferroelectric domains by nearly 180°can be realized through the prepared films.The ferroelectric hysteresis loops showed that the order for the polarization contribution is as follows:Cu>Co>Mn(B-site),Sm>La>Eu(A-site).The current density voltage curves indicated that the order for leakage contribution is as follows:Mn<Cu<Co(B-site),La<Eu<Sm(A-site).Scanning electron microscopy showed that the introduction of Cu elements facilitates the formation of dense grains,and the grain size distribution statistics proved that La element promotes the reduction of grain size,leading to the increase of grain boundaries and the reduction of leakage.Finally,a Bi_(0.985)Sm_(0.045)La_(0.03)Fe_(0.96)Co_(0.02)Cu_(0.02)O_(3)(SmLa-CoCu)thin film with a qualitative leap in the remnant polarization from 25.5(Bi_(0.985)Sm_(0.075)FeO_(3))to 98.8µC/cm^(2)(SmLa-CoCu)was prepared through the syner-gistic action of Sm,La,Co,and Cu elements.The leakage current is also drastically reduced from 160 to 8.4 mA/cm^(2)at a field strength of 150 kV/cm.Thus,based on the increasing entropy strategy of chemical engineering,this study focuses on enhancing ferroelectricity and decreasing leakage current,providing a promising path for the advancement of ferroelectric devices.

Securing offshore resources development:A mathematical investigation into gas leakage in long-distance flexible pipes

Gas flexible pipes are critical multi-layered equipment for offshore oil and gas development.Under high pressure conditions,small molecular components of natural gas dissolve into the polymer inner liner of the flexible pipes and further diffuse into the annular space,incurring annular pressure build-up and/or production of acidic environment,which poses serious challenges to the structure and integrity of the flexible pipes.Gas permeation in pipes is a complex phenomenon governed by various factors such as internal pressure and temperature,annular structure,external temperature.In a long-distance gas flexible pipe,moreover,gas permeation exhibits non-uniform features,and the gas permeated into the annular space flows along the metal gap.To assess the complex gas transport behavior in long-distance gas flexible pipes,a mathematical model is established in this paper considering the multiphase flow phenomena inside the flexible pipes,the diffusion of gas in the inner liner,and the gas seepage in the annular space under varying permeable properties of the annulus.In addition,the effect of a variable temperature is accounted.A numerical calculation method is accordingly constructed to solve the coupling mathematical equations.The annular permeability was shown to significantly influence the distribution of annular pressure.As permeability increases,the annular pressure tends to become more uniform,and the annular pressure at the wellhead rises more rapidly.After annular pressure relief followed by shut-in,the pressure increase follows a convex function.By simulating the pressure recovery pattern after pressure relief and comparing it with test results,we deduce that the annular permeability lies between 123 and 512 m D.The results help shed light upon assessing the annular pressure in long distance gas flexible pipes and thus ensure the security of gas transport in the emerging development of offshore resources.

Underwater Gas Leakage Flow Detection and Classification Based on Multibeam Forward-Looking Sonar

The risk of gas leakage due to geological flaws in offshore carbon capture, utilization, and storage, as well as leakage from underwater oil or gas pipelines, highlights the need for underwater gas leakage monitoring technology. Remotely operated vehicles(ROVs) and autonomous underwater vehicles(AUVs) are equipped with high-resolution imaging sonar systems that have broad application potential in underwater gas and target detection tasks. However, some bubble clusters are relatively weak scatterers, so detecting and distinguishing them against the seabed reverberation in forward-looking sonar images are challenging. This study uses the dual-tree complex wavelet transform to extract the image features of multibeam forward-looking sonar. Underwater gas leakages with different flows are classified by combining deep learning theory. A pool experiment is designed to simulate gas leakage, where sonar images are obtained for further processing. Results demonstrate that this method can detect and classify underwater gas leakage streams with high classification accuracy. This performance indicates that the method can detect gas leakage from multibeam forward-looking sonar images and has the potential to predict gas leakage flow.

Side-Channel Leakage Analysis of Inner Product Masking

The Inner Product Masking(IPM)scheme has been shown to provide higher theoretical security guarantees than the BooleanMasking(BM).This scheme aims to increase the algebraic complexity of the coding to achieve a higher level of security.Some previous work unfolds when certain(adversarial and implementation)conditions are met,and we seek to complement these investigations by understanding what happens when these conditions deviate from their expected behaviour.In this paper,we investigate the security characteristics of IPM under different conditions.In adversarial condition,the security properties of first-order IPMs obtained through parametric characterization are preserved in the face of univariate and bivariate attacks.In implementation condition,we construct two new polynomial leakage functions to observe the nonlinear leakage of the IPM and connect the security order amplification to the nonlinear function.We observe that the security of IPMis affected by the degree and the linear component in the leakage function.In addition,the comparison experiments from the coefficients,signal-to-noise ratio(SNR)and the public parameter show that the security properties of the IPM are highly implementation-dependent.

Study of leakage current degradation based on stacking faults expansion in irradiated SiC junction barrier Schottky diodes

A comprehensive investigation was conducted to explore the degradation mechanism of leakage current in SiC junction barrier Schottky(JBS)diodes under heavy ion irradiation.We propose and verify that the generation of stacking faults(SFs)induced by the recombination of massive electron-hole pairs during irradiation is the cause of reverse leakage current degradation based on experiments results.The irradiation experiment was carried out based on Ta ions with high linear energy transfer(LET)of 90.5 MeV/(mg/cm^(2)).It is observed that the leakage current of the diode undergoes the permanent increase during irradiation when biased at 20%of the rated reverse voltage.Micro-PL spectroscopy and PL micro-imaging were utilized to detect the presence of SFs in the irradiated SiC JBS diodes.We combined the degraded performance of irradiated samples with SFs introduced by heavy ion irradiation.Finally,three-dimensional(3D)TCAD simulation was employed to evaluate the excessive electron-hole pairs(EHPs)concentration excited by heavy ion irradiation.It was observed that the excessive hole concentration under irradiation exceeded significantly the threshold hole concentration necessary for the expansion of SFs in the substrate.The proposed mechanism suggests that the process and material characteristics of the silicon carbide should be considered in order to reinforcing against the single event effect of SiC power devices.

Thoracic spinal cord injury and paraplegia caused by intradural cement leakage after percutaneous kyphoplasty: A case report

BACKGROUND Percutaneous kyphoplasty(PKP)is a pivotal intervention for osteoporotic fractures,pathological vertebral compression fractures,and vertebral bone tumors.Despite its efficacy,the procedure presents challenges,notably complications arising from intradural cement leakage.Timely and accurate diagnosis,coupled with emergent intervention is imperative to improve patient prognosis.This case report illuminates the intricacies and potential complications associated with PKP,emphasizing the critical need for vigilant monitoring,prompt diagnosis,and immediate intervention to mitigate adverse outcomes.CASE SUMMARY A 58-year-old male patient,experiencing a T7 osteoporosis-related pathological compression fracture,underwent PKP at a local hospital.Two weeks postprocedure,the patient developed paraplegic and dysuric symptoms,necessitating emergency decompression surgery.Gradual improvement was achieved,marked by the restoration of muscle strength,sensation,and mobility.CONCLUSION PKP Intradural cement leakage following PKP is unusual and potentially fatal.Prompt imaging examinations,urgent evaluation,and the decompression surgery are essential,which help alleviate symptoms associated with spinal damage,markedly improving the overall prognosis.

Serum nutritional predictive biomarkers and risk assessment for anastomotic leakage after laparoscopic surgery in rectal cancer patients

BACKGROUND Anastomotic leakage(AL)is one of the severest complications after laparoscopic surgery for middle/low rectal cancer,significantly impacting patient outcomes.Identifying reliable predictive factors for AL remains a clinical challenge.Serum nutritional biomarkers have been implicated in surgical outcomes but are un-derexplored as predictive tools for AL in this setting.Our study hypothesizes that preoperative serum levels of prealbumin(PA),albumin(ALB),and transferrin(TRF),along with surgical factors,can accurately predict AL risk.AIM To determine the predictive value of preoperative serum nutritional biomarkers for rectal cancer AL following laparoscopic surgery.METHODS In the retrospective cohort study carried out at a tertiary cancer center,we examined 560 individuals who underwent laparoscopic procedures for rectal cancer from 2018 to 2022.Preoperative serum levels of PA,ALB,and TRF were measured.We employed multivariate logistic regression to determine the independent risk factors for AL,and a predictive model was constructed and evaluated using receiver operating characteristic curve analysis.RESULTS AL occurred in 11.96%of cases,affecting 67 out of 560 patients.Multivariate analysis identified PA,ALB,and TRF as the independent risk factor,each with an odds ratio of 2.621[95%confidence interval(CI):1.582-3.812,P=0.012],3.982(95%CI:1.927-4.887,P=0.024),and 2.109(95%CI:1.162-2.981,P=0.031),respectively.Tumor location(<7 cm from anal verge)and intraoperative bleeding≥300 mL also increased AL risk.The predictive model demonstrated an excellent accuracy,achieving an area under the receiver operating characteristic curve of 0.942,a sensitivity of 0.844,and a specificity of 0.922,demonstrating an excellent ability to discriminate.CONCLUSION Preoperative serum nutritional biomarkers,combined with surgical factors,reliably predict anastomotic leakage risk after rectal cancer surgery,highlighting their importance in preoperative assessment.

Suppressing Leakage Currents and Improving Performance of Indoor Organic Photovoltaic Devices

Organic photovoltaic(OPV) devices hold great promise for indoor light harvesting,offering a theoretical upper limit of power conversion efficiency that surpasses that of other photovoltaic technologies.However,the presence of high leakage currents in OPV devices commonly constrains their effective performance under indoor conditions.In this study,we identified that the origin of the high leakage currents in OPV devices lay in pinhole defects present within the active layer(AL).By integrating an automated spin-coating strategy with sequential deposition processes,we achieved the compactness of the AL and minimized the occurrence of pinhole defects therein.Experimental findings demonstrated that with an increase in the number of deposition cycles,the density of pinhole defects in the AL underwent a marked reduction.Consequently,the leakage current experienced a substantial decrease by several orders of magnitude which achieved through well-calibrated AL deposition procedures.This enabled a twofold enhancement in the power conversion efficiency(PCE) of the OPV devices under conditions of indoor illumination.

Endoscopic clipping of gastrojejunostomy leakage following Whipple procedure: A case report

BACKGROUND Currently,perioperative complications of classic Whipple surgery occur at a rate of approximately 40%.Common complications include delayed gastric emptying,pancreatic fistula,and bile leakage,whereas gastrojejunostomy(GJ)leakage is rare.CASE SUMMARY This case report will assess the management of a GJ leak in a 71-year-old male patient following the Whipple procedure.After surgery,the patient was trans-ferred to the clinic after four days of intensive care,where vacuum therapy was used to handle a developing subcutaneous collection.The patient,who had bile in the drains and incision during follow-up,underwent endoscopic examination on the 21st day after the operation.An opening of approximately 4 mm was observed in the GJ anastomosis during endoscopy.Five titanium clips were used to close the openings.The drainage of bile decreased to less than 50 mL on the first day after the procedure,and the patient's oral intake was opened.CONCLUSION Current literature reports a GJ leakage rate of 0.54%following Whipple surgery,with clinical findings lasting on average between 4-34 days.Surgery was the main form of therapy for this case,with a success rate of 84%,and percutaneous drai-nage was also utilized as a treatment option.This case report is the first to docu-ment endoscopic treatment of GJ leaks following the classic Whipple procedure.

Characteristics of gut microbiota in anastomotic leakage patients in cold zones post-colorectal cancer surgery: A high-throughput sequencing and propensity-score matching study

Objective:The study aimed to explore the association between gut microbiota and anastomotic leakage(AL)after surgery in colorectal cancer(CRC)patients from a frigid zone,based on high-throughput sequencing.Methods:A total of 98 CRC patients admitted to the Second Affiliated Hospital of Harbin Medical University from July 2018 to February 2019,who met the inclusion criteria,were included.Among these,10 patients were diagnosed as AL.After propensity-score matching of baseline characteristics,10 patients from the anastomotic leakage group(AG)and 10 patients from the normal group(NG)were finally included in this study.Fecal samples were collected,and total DNA was extracted for high-throughput sequencing and bioinformatic analysis.Results:Alpha diversity analysis showed no significant difference between the two groups,while beta diversity analysis revealed significant differences in principal components.Differential microbiota were classified as Proteobacteria at the phylum level(P=0.021).At the genus level,the abundances of Streptococcus(P=0.045),Citrobacter(P=0.008)and Klebsiella(P=0.002)were significantly different between the two groups.LEfSe analysis indicated that these genera contributed most to the differences between the groups.Conclusion:The characteristics of the gut microbiota in the AG and NG were significantly different,and these differences might be associated with AL in CRC patients from frigid zones.

Evaluating Privacy Leakage and Memorization Attacks on Large Language Models (LLMs) in Generative AI Applications

The recent interest in the deployment of Generative AI applications that use large language models (LLMs) has brought to the forefront significant privacy concerns, notably the leakage of Personally Identifiable Information (PII) and other confidential or protected information that may have been memorized during training, specifically during a fine-tuning or customization process. We describe different black-box attacks from potential adversaries and study their impact on the amount and type of information that may be recovered from commonly used and deployed LLMs. Our research investigates the relationship between PII leakage, memorization, and factors such as model size, architecture, and the nature of attacks employed. The study utilizes two broad categories of attacks: PII leakage-focused attacks (auto-completion and extraction attacks) and memorization-focused attacks (various membership inference attacks). The findings from these investigations are quantified using an array of evaluative metrics, providing a detailed understanding of LLM vulnerabilities and the effectiveness of different attacks.

A Case Report and Literature Review: A Case of Delayed Bile Leakage Following Laparoscopic Cholecystectomy

Background: Delayed bile leakage after laparoscopic cholecystectomy, defined as occurring more than 72 hours after surgery, is a rare and serious complication of laparoscopic cholecystectomy, with an incidence rate of 0.060%. Case Declaration: This case report details a patient diagnosed with delayed bile leakage 43 days after laparoscopic cholecystectomy. The patient was discharged from our hospital after undergoing CT-guided puncture treatment, with no obvious complications identified. The patient was monitored for one year following the procedure, during which time no significant discomfort was reported. Objective: This case report is to analyse and review the clinical manifestations, diagnosis, treatment and prevention of delayed bile leakage after cholecystectomy, with reference to the relevant literature. Results: Delayed bile leakage after laparoscopic cholecystectomy can be prevented, although not eliminated. It is recommended that the operator treat the operation with caution, avoid taking risks, and adhere to careful procedures and strict separation according to the requirements. This approach is key to preventing late bile leakage in the postoperative period.

Evaluation of the Air Leakage Flowrate in Sintering Processes

Iron ore sintering is a pre-treatment technology by which orefines are converted into porous and permeable sin-ters,which are the used in blast furnaces.This process can be adversely affected by air leakage phenomena of various types.As experimental measurements are relatively difficult and often scarcely reliable,here a theoretical model based on typicalfluid-dynamic concepts and relationships is elaborated.Through the analysis of two extreme cases,namely,those in which leakage is due to a small hole or a full rupture,a generalized hole-bed mod-el is introduced,which for thefirst time also includes a complete bed permeability equation and can deal with different leakage position conditions.The results show that the model can evaluate the influence of leakage on the system at one time and be used to calculate theflowrate and pressure drop.Notably,the obtained results are within a 15%deviation with respect to available experiment values,used for comparison.

Modeling of Hydrogen Blending on the Leakage and Diffusion of Urban Buried Hydrogen-Enriched Natural Gas Pipeline

With the introduction of various carbon reduction policies around the world,hydrogen energy,as a kind of clean energy with zero carbon emission,has attracted much attention.The safe and economical transportation of hydrogen is of great significance to the development of hydrogen energy industries.Utilizing natural gas pipelines to transport hydrogen is considered to be an efficient and economical way.However,hydrogen has a higher risk of leakage due to its strong diffusion capacity and lower explosive limit than conventional natural gas.Therefore,it is of great significance to study the leakage and diffusion law of hydrogen-enriched natural gas(HENG)pipelines for the safe transportation of hydrogen energy.In this study,the leakage and diffusion characteristics of urban buried HENG pipelines are investigated numerically,and the dangerous degree of leakage is analyzed based on the time and area when the gas concentration reaches the lower explosive limit.The influences of hydrogen blending ratio(HBR),operating pressure,leakage hole size and direction,as well as soil type on the leakage and diffusion law of HENG are analyzed.Results show that the hydrogen mixing is not the key factor in increasing the degree of risk after gas leakage for urban buried HENG pipelines.When the HBR is 5%,10%,15% and 20%,the corresponding first dangerous time is 1053,1041,1019 and 998 s,respectively.Thiswork is expected to provide a valuable reference for the safe operation and risk prevention of HENG pipelines in the future.

A Novel Parameter-Optimized Recurrent Attention Network for Pipeline Leakage Detection

Accurate detection of pipeline leakage is essential to maintain the safety of pipeline transportation.Recently,deep learning(DL)has emerged as a promising tool for pipeline leakage detection(PLD).However,most existing DL methods have difficulty in achieving good performance in identifying leakage types due to the complex time dynamics of pipeline data.On the other hand,the initial parameter selection in the detection model is generally random,which may lead to unstable recognition performance.For this reason,a hybrid DL framework referred to as parameter-optimized recurrent attention network(PRAN)is presented in this paper to improve the accuracy of PLD.First,a parameter-optimized long short-term memory(LSTM)network is introduced to extract effective and robust features,which exploits a particle swarm optimization(PSO)algorithm with cross-entropy fitness function to search for globally optimal parameters.With this framework,the learning representation capability of the model is improved and the convergence rate is accelerated.Moreover,an anomaly-attention mechanism(AM)is proposed to discover class discriminative information by weighting the hidden states,which contributes to amplifying the normalabnormal distinguishable discrepancy,further improving the accuracy of PLD.After that,the proposed PRAN not only implements the adaptive optimization of network parameters,but also enlarges the contribution of normal-abnormal discrepancy,thereby overcoming the drawbacks of instability and poor generalization.Finally,the experimental results demonstrate the effectiveness and superiority of the proposed PRAN for PLD.

Harmonics in the Squirrel Cage Induction Motor Analytic Calculation-Part Ⅰ: Differential Leakage, Attenuation, Asynchronous Parasitic Torques

The magnetic field generated in the air gap of the cage asynchronous machine and the harmonics of the magnetomotive forces creating that magnetic field, as well as the related differential leakage, attenuation, asynchronous parasitic torques have been discussed in great detail in the literature, but always separately, for a long time. However, systematization of the phenomenon still awaits. Therefore, it is worth summarizing the completeness of the phenomena in a single study – with a new approach at the same time-in order to reveal the relationships between them. The role of rotor slot number is emphasized much more than before. An existing, commonly used, but still impractical basic figure has been modified to more clearly demonstrate the response of the rotor for the harmonics of the stator. The need to treat differential leakage, asynchronous parasitic torques and attenuation together will be demonstrated: new formula for asynchronous parasitic torque is derived;the long-used characteristic curves for differential leakage and attenuation used separately so far was merged into one, correct curve in order to provide a correct design guide for the engineers.

Establishment and application of three predictive models of anastomotic leakage after rectal cancer sphincter-preserving surgery

BACKGROUND Anastomotic leakage(AL)occurs frequently after sphincter-preserving surgery for rectal cancer and has a significant mortality rate.There are many factors that influence the incidence of AL,and each patient’s unique circumstances add to this diversity.The early identification and prediction of AL after sphincter-preserving surgery are of great significance for the application of clinically targeted preventive measures.Developing an AL predictive model coincides with the aim of personalised healthcare,enhances clinical management techniques,and advances the medical industry along a more precise and intelligent path.AIM To develop nomogram,decision tree,and random forest prediction models for AL following sphincter-preserving surgery for rectal cancer and to evaluate the predictive efficacy of the three models.METHODS The clinical information of 497 patients with rectal cancer who underwent sphincter-preserving surgery at Jincheng People’s Hospital of Shanxi Province between January 2017 and September 2022 was analyzed in this study.Patients were divided into two groups:AL and no AL.Using univariate and multivariate analyses,we identified factors influencing postoperative AL.These factors were used to establish nomogram,decision tree,and random forest models.The sensitivity,specificity,recall,accuracy,and area under the receiver operating characteristic curve(AUC)were compared between the three models.RESULTS AL occurred in 10.26%of the 497 patients with rectal cancer.The nomogram model had an AUC of 0.922,sensitivity of 0.745,specificity of 0.966,accuracy of 0.936,recall of 0.987,and accuracy of 0.946.The above indices in the decision tree model were 0.919,0.833,0.862,0.951,0.994,and 0.955,respectively and in the random forest model were 1.000,1.000,1.000,0.951,0.994,and 0.955,respectively.The DeLong test revealed that the AUC value of the decision-tree model was lower than that of the random forest model(P<0.05).CONCLUSION The random forest model may be used to identify patients at high risk of AL after sphincter-preserving surgery for rectal cancer owing to its strong predictive effect and stability.

Detecting the backfill pipeline blockage and leakage through an LSTM-based deep learning model

Detecting a pipeline's abnormal status,which is typically a blockage and leakage accident,is important for the continuity and safety of mine backfill.The pipeline system for gravity-transport high-density backfill(GHB)is complex.Specifically designed,efficient,and accurate abnormal pipeline detection methods for GHB are rare.This work presents a long short-term memory-based deep learning(LSTM-DL)model for GHB pipeline blockage and leakage diagnosis.First,an industrial pipeline monitoring system was introduced using pressure and flow sensors.Second,blockage and leakage field experiments were designed to solve the problem of negative sample deficiency.The pipeline's statistical characteristics with different working statuses were analyzed to show their complexity.Third,the architecture of the LSTM-DL model was elaborated on and evaluated.Finally,the LSTM-DL model was compared with state-of-the-art(SOTA)learning algorithms.The results show that the backfilling cycle comprises multiple working phases and is intermittent.Although pressure and flow signals fluctuate stably in a normal cycle,their values are diverse in different cycles.Plugging causes a sudden change in interval signal features;leakage results in long variation duration and a wide fluctuation range.Among the SOTA models,the LSTM-DL model has the highest detection accuracy of98.31%for all states and the lowest misjudgment or false positive rate of 3.21%for blockage and leakage states.The proposed model can accurately recognize various pipeline statuses of complex GHB systems.