分析化学综合实验:基于纳米酶和智能手机的维生素C比色检测

将中国科学家首创的纳米酶和常用的智能手机结合设计了一个比色分析实验。该实验设计思路是将科学前沿、课程思政与本科实验结合,使得学生在掌握知识技能同时,了解科学前沿领域,增强文化自信,培养科学严谨、敢于创新的优秀品质,助力实验教学全面育人。该实验不依赖大型贵重仪器,可操作性强,灵活度高,适宜作为高年级分析化学综合实验或化学综合实验。

Earthquake relocation using a 3D velocity model and implications on seismogenic faults in the Beijing-Tianjin-Hebei region

To enhance the understanding of the geometry and characteristics of seismogenic faults in the Beijing-Tianjin-Hebei region,we relocated 14805 out of 16063 earthquakes(113°E-120°E,36°N-43°N)that occurred between January 2008 and December 2020 using the double-difference tomography method.Based on the spatial variation in seismicity after relocation,the Beijing-Tianjin-Hebei region can be divided into three seismic zones:Xingtai-Wen'an,Zhangbei-Ninghexi,and Tangshan.(1)The Xingtai-Wen'an Seismic Zone has a northeastsouthwest strike.The depth profile of earthquakes perpendicular to the strike reveals three northeast-striking,southeast-dipping,high-angle deep faults(>10 km depth),including one below the shallow(<10 km depth)listric,northwest-dipping Xinghe fault in the Xingtai region.Two additional deep faults in the Wen'an region are suggested to be associated with the 2006 M 5.1 Wen'an Earthquake and the 1967 M 6.3 Dacheng earthquake;(2)The Zhangbei-Ninghexi Seismic Zone is oriented north-northwest.Multiple northeast-striking faults(10-20 km depth),inferred from the earthquake-intensive zones,exist beneath the shallow(<10 km depth)Xiandian Fault,Xiaotangshan Fault,Huailai-Zhuolu Basin North Fault,Yangyuan Basin Fault and Yanggao Basin North Fault;(3)In the Tangshan Seismic Zone,earthquakes are mainly concentrated near the northeast-striking Tangshan-Guye Fault,Lulong Fault,and northwest-striking Luanxian-Laoting Fault.An inferred north-south-oriented blind fault is present to the north of the Tangshan-Guye Fault.The 1976 M 7.8 Tangshan earthquake occurred at the junction of a shallow northwest-dipping fault and a deep southeast-dipping fault.This study emphasizes that earthquakes in the region are primarily associated with deep blind faults.Some deep blind faults have different geometries compared to shallow faults,suggesting a complex fault system in the region.Overall,this research provides valuable insights into the seismogenic faults in the Beijing–Tianjin–Hebei region.Further studies and monitoring of these faults are essential for earthquake mitigation efforts in this region.

Genomic prediction of yield performance among single-cross maize hybrids using a partial diallel cross design

Genomic prediction(GP)in plant breeding has the potential to predict and identify the best-performing hybrids based on the genotypes of their parental lines.In a GP experiment,34 elite inbred lines were selected to make 285 single-cross hybrids in a partial-diallel cross design.These lines represented a mini-core collection of Chinese maize germplasm and comprised 18 inbred lines from the Stiff Stalk heterotic group and 16 inbred lines from the Non-Stiff Stalk heterotic group.The parents were genotyped by sequencing and the 285 hybrids were phenotyped for nine yield and yield-related traits at two locations in the summer sowing area(SUS)and three locations in the spring sowing area(SPS)in the main maizeproducing regions of China.Multiple GP models were employed to assess the accuracy of trait prediction in the hybrids.By ten-fold cross-validation,the prediction accuracies of yield performance of the hybrids estimated by the genomic best linear unbiased prediction(GBLUP)model in SUS and SPS were 0.51 and 0.46,respectively.The prediction accuracies of the remaining yield-related traits estimated with GBLUP ranged from 0.49 to 0.86 and from 0.53 to 0.89 in SUS and SPS,respectively.When additive,dominance,epistasis effects,genotype-by-environment interaction,and multi-trait effects were incorporated into the prediction model,the prediction accuracy of hybrid yield performance was improved.The ratio of training to testing population and size of training population optimal for yield prediction were determined.Multiple prediction models can improve prediction accuracy in hybrid breeding.

基于血浆代谢组学和网络药理学探讨芎芷地龙汤治疗偏头痛的作用机制

目的:基于网络药理学和血浆代谢组学探讨芎芷地龙汤(Xiongzhi Dilong decoction,XZDLD)对降钙素基因相关肽(calcitonin gene-related peptide,CGRP)诱导的偏头痛的作用机制。方法:采用超高效液相色谱-线性离子阱-静电场轨道阱高分辨质谱法(ultra-high-performance liquid chromatography-linear trap quadrupole orbitrap mass spectrometry,UPLC-LTQ-Orbitrap-MS)对XZDLD的化学成分进行鉴定。经硬脑膜套管注射CGRP建立偏头痛大鼠模型,通过观察大鼠偏头痛样行为、测定机械痛阈和温度痛阈评估XZDLD治疗偏头痛的疗效。基于网络药理学和血浆代谢组学的联合分析识别其治疗偏头痛的关键靶点,并应用蛋白免疫印迹法和免疫组织化学对相关蛋白进行验证。结果:应用UPLC-LTQ-Orbitrap-MS共识别出方中38个化合物。与模型大鼠相比,XZDLD各组在前30分钟显著改善了偏头痛样行为(均P<0.05),并在第19‒22天提高了机械痛阈(均P<0.05),在第20‒22天提高了温度痛阈(均P<0.05)。基于网络药理学识别出128个XZDLD治疗偏头痛的潜在靶点。基于血浆代谢组学识别出在对照组、模型组和XZDLD组中有17种不同的内源性代谢产物,主要与色氨酸和酪氨酸代谢途径相关。将二者联合分析后确定了6个关键靶点进行验证:MAOA、MAOB、CYP1A1、CYP1A2、CYP1B1和ADH1C。与模型组相比,XZDLD显著降低了MAOA、MAOB和CYP1B1蛋白的表达(P=0.024;P=0.004;P=0.039),并升高了CYP1A1、CYP1A2和ADH1C的表达(P=0.033;P=0.045;P=0.027)。结论:芎芷地龙汤可以改善大鼠偏头痛样行为,提高痛阈,其作用机制可能与调节色氨酸和酪氨酸代谢途径有关,为其临床应用提供依据,同时为偏头痛研究提供思路。

Application of next-generation sequencing technology to precision medicine in cancer: joint consensus of the Tumor Biomarker Committee of the Chinese Society of Clinical Oncology

Next-generation sequencing(NGS) technology is capable of sequencing millions or billions of DNA molecules simultaneously.Therefore, it represents a promising tool for the analysis of molecular targets for the initial diagnosis of disease, monitoring of disease progression, and identifying the mechanism of drug resistance. On behalf of the Tumor Biomarker Committee of the Chinese Society of Clinical Oncology(CSCO) and the China Actionable Genome Consortium(CAGC), the present expert group hereby proposes advisory guidelines on clinical applications of NGS technology for the analysis of cancer driver genes for precision cancer therapy. This group comprises an assembly of laboratory cancer geneticists, clinical oncologists, bioinformaticians,pathologists, and other professionals. After multiple rounds of discussions and revisions, the expert group has reached a preliminary consensus on the need of NGS in clinical diagnosis, its regulation, and compliance standards in clinical sample collection. Moreover, it has prepared NGS criteria, the sequencing standard operation procedure(SOP), data analysis, report, and NGS platform certification and validation.

Coordinated silencing of the Sp1-mediated long noncoding RNA MEG3 by EZH2 and HDAC3 as a prognostic factor in pancreatic ductal adenocarcinoma

Objective:Pancreatic ductal adenocarcinoma(PDAC)is a disease with high mortality.Many so-called"junk"noncoding RNAs need to be discovered in PDAC.The purpose of this study was therefore to investigate the function and regulatory mechanism of the long noncoding RNA MEG3 in PDAC.Methods:The Gene Expression Omnibus database(GEO database)was used to determine the differential expression of long noncoding RNAs in PDAC,and MEG3 was selected for subsequent verification.Tissue and cell samples were used to verify MEG3 expression,followed by functional detection in vitro and in vivo.Microarrays were used to characterize long noncoding RNA and mRNA expression profiles.Competing endogenous RNA analyses were used to detect differential MEG3 and relational miRNA expression in PDAC.Finally,promoter analyses were conducted to explain the downregulation of MEG3 PDAC.Results:We generated a catalogue of PDAC-associated long noncoding RNAs in the GEO database.The ectopic expression of MEG3 inhibited PDAC growth and metastasis in vitro and in vivo,which was statistically significant(P<0.05).Microarray analysis showed that multiple microRNAs interacted with MEG3.We also showed that MEG3,as a competing endogenous RNA,directly sponged miR-374a-5p to regulate PTEN expression.The transcription factor,Sp1,recruited EZH2 and HDAC3 to the promoter and transcriptionally repressed MEG3 expression.Finally,clinical data showed that MEG3 and miR-374a-5p expressions were correlated with clinicopathological features.Statistically,Sp1,EZH2,HDAC3,and miR-374 a-5p were negatively correlated with MEG3(P<0.05).Conclusions:Reduced MEG3 levels played a crucial role in the PDAC malignant phenotype,which provided insight into novel and effective molecular targets of MEG3 for pancreatic cancer treatment.

Mapping QTL for flowering time-related traits under three plant densities in maize

Flowering time is an indicator of adaptation in maize and a key trait for selection in breeding.The genetic basis of flowering time in maize,especially in response to plant density,remains unclear.The objective of this study was to identify maize quantitative trait loci(QTL)associated with flowering time-related traits that are stably expressed under several plant densities and show additive effects that vary with plant density.Three hundred recombinant inbred lines(RIL)derived from a cross between Ye 478 and Qi 319,together with their parents,were planted at three plant densities(90,000,120,000,and 150,000 plants ha^(-1))in four environments.The five traits investigated were days to tasseling(DTT),days to silking(DTS),days to pollen shed(DTP),interval between anthesis and silking(ASI),and interval between tasseling and anthesis(TAI).A high-resolution bin map was used for QTL mapping.In the RIL population,the DTT,DTS,and DTP values increased with plant density,whereas the ASI and TAI values showed negligible response to plant density.A total of 72 QTL were identified for flowering time-related traits,including 15 stably expressed across environments.Maize flowering time under different densities seems to be regulated by complex pathways rather than by several major genes or an independent pathway.The effects of some stable QTL,especially qDTT8-1 and qDTT10-4,varied with plant density.Fine mapping and cloning of these QTL will shed light on the mechanism of flowering time and assist in breeding earlymaturing maize inbred lines and hybrids.

Duchesnea Phenolic Fraction Inhibits Tumor Growth through Restoring the Th1/Th2 Balance in U14 Cervical Cancer Bearing Mice

Duchesnea indica (Andr.) Focke has been traditionally used to treat cancer in Asian countries for centuries. In the present study, transplanted U14 cervical cancer mouse model was used to evaluate the antitumor and immunomodulatory activity of Duchesnea phenolic fraction (DPF). ELISA and RIA assay were employed to measured the serum concentration of Th1/Th2 cytokines (IL-2, IL-4, IFN-γ and TNF-α). Administration with 0.25 g/kg, 0.5 g/kg and 1 g/kg DPF significantly reduced the tumor weight by 34.37%, 43.89% and 56.28%, respectively, as compared to the tumor control group. Furthermore, the serum level of IL-2, IFN-γ and TNF-α increased and IL-4 level decreased in a dose-dependent manner during DPF treatment, indicating that the antitumor activity of DPF may be associated with the decrease of TNF-α level and restoration of the balance of Th1/Th2 cell responses. These data suggested that DPF, a mixture of plant polyphenols, had potent anticancer activity which was in part accomplished by its immunomodulatory ability.

IN THIS ISSUE

Shanghai Archives of Psychiatry is a comprehensive journal of psychiatry, including reviews, original articles, case reports, forums, and 'biostatistics in psychiatry' as our main columns. For more information, please refer to the official website of our journal (www.shanghaiarchivesofpsychiatry.org). Starting from the present issue, our journal plans to periodically publish special issues focusing on a particular topic. In this issue we turn a special focus to the topic of schizophrenia.

Surface coal mining impacts on land use change and ecological service value:a case study in Shengli coalfield,Inner Mongolia

Coal plays a crucial role in global economic development and remains the most common and widely distributed fossil fuel worldwide.As the world's largest developing country,China's mining and utilization of coal resources have contributed signifcantly to the country’s rapid economic growth.Inner Mongolia is an ecologically fragile arid and semi-arid area of China.The exploitation of opencast mining has seriously hindered the sustainable use of regional land and the residents'well-being.Using ENVI-based remote sensing images from 2000,2005,2010,2015,and 2020,this study employed a random forest algorithm to divide land utilization types into construction land,vegetation,cultivated land,bare land,and water areas and analyzed the characteristics of land use and ecosystem service value changes over the past 20 years.The results were as follows:(1)Construction land in the mining area changed minimally from 2000 to 2020;vegetation and water bodies showed a decreasing trend,whereas bare and cultivated lands showed an increasing trend.Bare land exhibited the largest change in area proportion and water bodies the smallest.(2)The total ecosystem service value of the mining area declined from 10.939 to 9.527 billion Yuan.Vegetation ecosystem service value was the highest,followed by cultivated land and water,with the bare land ecosystem service value the lowest.(3)On a spatial scale,the total ecosystem service value of the Shengli mining area decreased year by year,indicating that land use changes in the mining area do have an impact on ecosystem service value.

Deep learning model improves radiologists'performance in detection and classification of breast lesions

Objective:Computer-aided diagnosis using deep learning algorithms has been initially applied in the field of mammography,but there is no large-scale clinical application.Methods:This study proposed to develop and verify an artificial intelligence model based on mammography.Firstly,mammograms retrospectively collected from six centers were randomized to a training dataset and a validation dataset for establishing the model.Secondly,the model was tested by comparing 12 radiologists’performance with and without it.Finally,prospectively enrolled women with mammograms from six centers were diagnosed by radiologists with the model.The detection and diagnostic capabilities were evaluated using the freeresponse receiver operating characteristic(FROC)curve and ROC curve.Results:The sensitivity of model for detecting lesions after matching was 0.908 for false positive rate of 0.25 in unilateral images.The area under ROC curve(AUC)to distinguish the benign lesions from malignant lesions was0.855[95%confidence interval(95%CI):0.830,0.880].The performance of 12 radiologists with the model was higher than that of radiologists alone(AUC:0.852 vs.0.805,P=0.005).The mean reading time of with the model was shorter than that of reading alone(80.18 s vs.62.28 s,P=0.032).In prospective application,the sensitivity of detection reached 0.887 at false positive rate of 0.25;the AUC of radiologists with the model was 0.983(95%CI:0.978,0.988),with sensitivity,specificity,positive predictive value(PPV),and negative predictive value(NPV)of94.36%,98.07%,87.76%,and 99.09%,respectively.Conclusions:The artificial intelligence model exhibits high accuracy for detecting and diagnosing breast lesions,improves diagnostic accuracy and saves time.

PKD3 promotes metastasis and growth of oral squamous cell carcinoma through positive feedback regulation with PD-L1 and activation of ERK-STAT1/3-EMT signalling

Oral squamous cell carcinoma(OSCC)has a high incidence of metastasis.Tumour immunotherapy targeting PD-L1 or PD-1 has been revolutionary;however,only a few patients with OSCC respond to this treatment.Therefore,it is essential to gain insights into the molecular mechanisms underlying the growth and metastasis of OSCC.In this study,we analysed the expression levels of protein kinase D3(PKD3)and PD-L1 and their correlation with the expression of mesenchymal and epithelial markers.We found that the expression of PKD3 and PD-L1 in OSCC cells and tissues was significantly increased,which correlated positively with that of mesenchymal markers but negatively with that of epithelial markers.Silencing PKD3 significantly inhibited the growth,metastasis and invasion of OSCC cells,while its overexpression promoted these processes.Our further analyses revealed that there was positive feedback regulation between PKD3 and PD-L1,which could drive EMT of OSCC cells via the ERK/STAT1/3 pathway,thereby promoting tumour growth and metastasis.Furthermore,silencing PKD3 significantly inhibited the expression of PD-L1,and lymph node metastasis of OSCC was investigated with a mouse footpad xenograft model.Thus,our findings provide a theoretical basis for targeting PKD3 as an alternative method to block EMT for regulating PD-L1 expression and inhibiting OSCC growth and metastasis.

Effect of Working Experience on Air Traffic Controller Eye Movement

Eye movement is an important indicator of information-seeking behavior and provides insight into cognitive strategies which are vital for decision-making.Various measures based on eye movements have been proposed to capture humans’ability to process information in a complex environment.The effectiveness of these measures has not yet been fully explored in the field of air traffic management.This paper presents a comparative study on eye-movement measures in air traffic controllers with different levels of working experience.Two commonly investigated oculomotor behaviors,fixation and saccades,together with gaze entropy,are examined.By comparing the statistical properties of the relevant metrics,it is shown that working experience has a notable effect on eye-movement patterns.Both fixation and saccades differ between qualified and novice controllers,with the former type of controller employing more efficient searching strategies.These findings are useful in enhancing the quality of controller training and contributing to an understanding of the information-seeking mechanisms humans use when executing complex tasks.

Measurement of serum cystatin C,creatinine clearance and urea micro-albumin as renal function evaluation indicators in cancer patients during chemotherapy with platinum

Objective:Chemotherapy drugs such as platinum may cause damage to the renal function,creatinine clearance(Ccr),as a "golden standard" indicator in clinical evaluation of renal function,was limited in application due to complicated detection steps.By detecting the expression of serum Cystatin C(Cys C),Ccr and urinary micro-albumin(UMA),this study was designed to analyze and discuss their roles and status in renal function evaluation for cancer patients before and after chemotherapy with platinum.Methods:We retrospectively reviewed 110 patients who receiving platinum-containing protocols or non-platinum-containing ones,and got the expression of Cys C,Ccr(was calculated by Cockcroft-Gault equation) and UMA,then analyzed whether there were differences for Cys C,Ccr and UMA in those patients;for patients with mildly impaired renal function(Ccr between 50-75 mL/min),whether there were differences for Cys C and UMA before and after chemotherapy with platinum.Results:There was statistical significance for Ccr,Cys C and UMA in patients who receiving platinum-containing protocols(85.01 ± 28.40) vs(76.79 ± 26.63) mL/min,(1.49 ± 0.50) vs(1.80 ± 0.84) mg/L and(14.30 ± 9.15) vs(16.90 ± 10.95) mg/L,P = 0.00,0.00 and 0.01),and no statistical significance for those receiving non-platinum-containing ones(89.45 ± 29.69) vs(86.78 ± 27.96) mL/min,(1.51 ± 0.78) vs(1.63 ± 0.73)mg/L and(17.31 ± 10.46) vs(16.59 ± 8.33) mg/L,P = 0.45,0.07 and 0.57);and there were also significant differences for Cys C for patients with mildly impaired renal function before and after chemotherapy(1.68 ± 0.55) vs(2.04 ± 0.68) mg/L,P = 0.03),while no statistical significance for UMA for the same ones(21.11 ± 10.06) vs(21.22 ± 8.81) mg/L,P = 0.93).There were statistical significance both for Cys C and UMA before and after chemotherapy in platinum-containing group,but the AUC for Ccr and Cys C is greater than that for UMA(P < 0.02).Conclusion:Cys C and UMA can both access renal dysfunction early after chemotherapy,but Cys C is more sensitive than UMA in reflecting early renal dysfunction,so Cys C can replace Ccr and become a reliable indicator in the assessment of renal function for cancer patients before and after chemotherapy especially with platinum.

Using Helmholtz resonator arrays to improve dipole transmission efficiency in waveguide

It is well known that the radiation efficiency of an acoustic dipole is very low, increasing the radiation efficiency of an acoustic dipole is a difficult task, especially in an ordinary waveguide.In addition, current acoustic superlenses all utilize in-phase sources to do the super-resolution imaging, it is almost impossible to realize super-resolution imaging of an acoustic dipole.In this paper, after using the Helmholtz resonator arrays(HRAs) which are placed at the upper and lower surfaces of the waveguide, we observe a large dipole radiation efficiency at the certain frequency, which gives a method to observe an acoustic dipole in the far field and offers a novel model which is promising to realize the superlens with a source of an acoustic dipole.We discuss how the arrangement of HRAs affects the transmission of the acoustic dipole.

The Island Rule with lateral and bottom friction

The Island Rule, derived from the Sverdrup theory, is widely used to estimate and analyze water transport through a strait. Previous studies presented single-or multi-island rules with either lateral or bottom friction. In this paper,an analytical model of wind-driven circulation is assumed based on linear dynamics. Considering both lateral and bottom friction, the analytic solutions of the transport streamfunction around the islands are derived and the volume transport through the channel is presented. The results are similar to those of Wajsowicz, but the frictional constants represent different values. The analytic solution shows that the relationship between the lateral frictional and bottom frictional dissipation is complex in terms of the frictional constants. To understand the interaction between the two friction types, lateral and bottom friction values were randomly chosen on a barotropic beta plane. The result shows an approximately linear relationship between the lateral and bottom friction in consisting of the combined frictional constants. We studied the effect of the channel width on the transport through the channel. The results show that the friction enhances the flow under some widths, which is similar to the flow behavior when only the lateral friction is considered. We also compared the transport through the channel at different depths and founded that the deeper the water, the smaller the transport reduction ratio when the horizontal eddy viscosity coefficient and the bottom drag coefficient remained constants. To further present the combined role of lateral frictional and bottom frictional dissipation, we compared our model with the model of Wajsowicz for two islands, where only the lateral or bottom friction were considered, with different channel widths. The results showed that the effect of the lateral friction is greater than the bottom friction when the channel is narrow, especially in the Munk boundary layer thickness. When the channel is much wider than the Munk boundary layer thickness, the role of the bottom friction is greater than that of the lateral friction. The model was applied to the Indonesian throughflow and yielded a reduction of approximately 20% in the transport.

IN THIS ISSUE

We are delighted to announce that Shanghai Archives of Psychiatry will be published by BMJ Publishing Group as of mid 2018. BMJ is an international publisher of medical publications. This change will work as an important step for the journal to become a truly international platform for eastern and western mental health professionals to exchange new research findings and service developments.

Preparation of porous α-Fe_2O_3-supported Pt and its sensing performance to volatile organic compounds

Porous α-Fe2O3 was synthesized by a simple hydrothermal treatment of FeC13 aqueous solution followed by a calcination process. In the synthesis of porous α-Fe2O3, no templates or pore-directing agents were used. The as-prepared porous α-Fe2O3 was further employed as a support for loading Pt nanoparticles. The gas sensing performance of the obtained porous α-Fe2O3-supported Pt to VOCs was investigated. The sensor presented a high response and fast response-recovery characteristic to several VOCs including acetone, ether, methanol, ethanol, butanol and hexanol. Meanwhile, it exhibited a much higher response than the pure α-Fe2O3 at the operating temperature of 260 ℃. The enhanced sensing properties may be related to the unique porous structure of the α-Fe2O3 support and the promoting effect of active Pt nanoparticles for the sensing reactions.

Decision Aid Model for Private-owned Electric Vehicles Participating in Frequency Regulation Ancillary Service Market

To reduce the difficulty and enhance the enthusiasm of private-owned electric vehicles(EVs) in participating in frequency regulation ancillary service market(FRASM), a decision aid model(DAM) is proposed. This paper presents three options for EV participating in FRASM, i. e., the base mode(BM), unidirectional charging mode(UCM), and bidirectional charging/discharging mode(BCDM), based on a reasonable simplification of users' participating willingness. In BM, individual EVs will not be involved in FRASM, and DAM will assist users to set the optimal charging schemes based on travel plans under the time-of-use(TOU) price. UCM and BCDM are two modes in which EVs can take part in FRASM. DAM can assist EV users to create their quotation plan, which includes hourly upper and lower reserve capabilities and regulation market mileage prices. In UCM and BCDM, the difference is that only the charging rate can be adjusted in the UCM, and the EVs in BCDM can not only charge but also discharge if necessary. DAM can estimate the expected revenue of all three modes, and EV users can make the final decision based on their preferences. Simulation results indicate that all the three modes of DAM can reduce the cost, while BCDM can get the maximum expected revenue.

Deep Learning in Predicting Preterm Birth:A Comparative Study of Machine Learning Algorithms

Objective:To determine whether deep learning algorithms are suitable for predicting preterm birth.Methods:A retrospective study was conducted at Peking University Third Hospital from January 2018 to June 2023.Birth data were divided into two parts based on the date of delivery:the first part was used for model training and validation,while real world viability was evaluated using the second part.Four machine learning algorithms(logistic regression,random forest,support vector machine,and transformer)were employed to predict preterm birth.Receiver operating characteristic curves were plotted,and the area under the curve(AUC),sensitivity,specificity,positive predictive value(PPV),negative predictive value(NPV),and accuracy were calculated.Results:This research included data on 30,965 births,where 24,770 comprised the first part,and included 3164(12.77%)in the preterm birth group,with 6195 in the second part,including 795(12.83%)in the preterm birth group.Significant differences in various factors were observed between the preterm and full-term birth groups.The transformer model(AUC=79.20%,sensitivity=73.67%,specificity=72.48%,PPV=28.21%,NPV=94.95%,and accuracy=72.61%in the test dataset)demonstrated superior performance relative to logistic regression(AUC=77.96%in the test dataset),support vectormachine(AUC=71.70%in the test dataset),and random forest(AUC=75.09%in the test dataset)approaches.Conclusion:This study highlights the promise of deep learning algorithms,specifically the transformer algorithm,for predicting pretermbirth.