Clinical efficacy and safety of erlotinib combined with chemotherapy in the treatment of advanced pancreatic cancer: A meta-analysis.

BACKGROUND: Advanced pancreatic cancer is resistant to chemotherapeutic drugs, resulting in limited treatment efficacy and poor prognosis. Combined administration of the chemotherapeutic gemcitabine and erlotinib is considered a potential first-line treatment for advanced pancreatic cancer. However, their comparative benefits and potential risks remain unclear. AIM: To assess the clinical efficacy and safety of erlotinib combined with other chemotherapy regimens for the treatment of advanced pancreatic cancer. METHODS: Literature on the clinical efficacy and safety of erlotinib combined with chemotherapy for advanced pancreatic cancer was retrieved through an online search. The retrieved literature was subjected to a methodological qualitative assessment and was analyzed using the RevMan 5.3 software. Ten randomized controlled trials involving 2444 patients with advanced pancreatic cancer were included in the meta-analysis. RESULTS: Compared with chemotherapeutic treatment, erlotinib combined with chemotherapy significantly prolonged the progression-free survival time of pancreatic cancer patients [hazard ratio (HR) = 0.78, 95%CI: 0.66-0.92, P = 0.003]. Meanwhile, the overall survival (HR= 0.99, 95%CI: 0.72-1.37, and P = 0.95) and disease control rate (OR = 0.93, 95%CI: 0.45-0.91, P = 0.84) were not significantly favorable. In terms of safety, the erlotinib and chemotherapy combination was associated with a significantly higher risk of diarrhea (OR = 3.59, 95%CI: 1.63-7.90, P < 0.05) and rash (OR = 3.63, 95%CI: 1.64-8.01, P < 0.05) compared with single-agent chemotherapy. Moreover, the risk of vomiting (OR = 1.27, 95%CI: 0.62-2.59, P = 0.51), regurgitation/anorexia (OR = 1.61, 95%CI: 0.25-10.31, P = 0.62), and infection (OR = 0.72, 95%CI: 0.28-1.87, P = 0.50) were not significant in either group. CONCLUSION: Compared with a single chemotherapeutic modality, erlotinib combined with gemcitabine can prolong progression-free survival in pancreatic cancer, but does not improve survival benefit or disease control rate, and can increase the risk of diarrhea and rash.

The impact of environmental regulation on green investment efficiency of thermal power enterprises in China-based on a three-stage exogenous variable model.

Due to the increased frequency of extreme weather events and the implementation of the China's dual-carbon target, thermal power companies have been under pressure to construct green infrastructure and to actively pursue low-carbon transformation in response to stricter environmental regulations. This research thus selects 30 listed thermal power enterprises in China as study objects and assesses their green investment efficiency in the low-carbon transition process using three-stage DEA evaluation model with environmental regulation as an exogenous variable. Based on this, a benchmark regression model is used to corroborate the relationship between environmental regulation and green investment. Simultaneously, we carry out analysis to compare the correlation between thermal power firms' green investment efficiency and their focus on green investments. The results show in terms of total efficiency that environmental regulation significantly improves the total efficiency of 80% of thermal power enterprises compared to the absence of this exogenous variable. With the addition of environmental regulation, firms' total efficiency declines gradually in general from 2018 to 2022, with the mean value of efficiency falling by 0.068. In terms of stage-specific efficiency, the efficiency of the green investment stage of the majority of firms is between 0.3 and 0.6, which is much lower than that of the operational stage and the market performance stage. In terms of sub-indicator efficiency, both green investment efficiency and social donation efficiency among thermal power enterprises show obvious polarization, with 30% of them having an efficiency of 1 and 30% less than 0.1. In terms of green investment focus, thermal power unit renovation has a more obvious role in boosting the green investment efficiency of thermal power enterprises than do wind power and photovoltaic projects. Therefore, both governmental departments and thermal power enterprises need to take active measures in order to achieve green transformation from the perspective of green investment efficiency. Through the segmentation of important projects of green investment, this paper provides a reasonable investment direction reference for the sustainable transformation of China's thermal power industry. It also provides a rich and novel theoretical basis for the Chinese government to further improve the relevant environmental protection laws and regulations of thermal power industry.

Data-Independent Acquisition-Based Quantitative Proteomic Analysis Reveals Potential Salivary Biomarkers of Primary Sjögren's Syndrome.

Objective As primary Sj?gren's syndrome (pSS) primarily affects the salivary glands, saliva can serve as an indicator of the glands' pathophysiology and the disease's status. This study aims to illustrate the salivary proteomic profiles of pSS patients and identify potential candidate biomarkers for diagnosis.Methods The discovery set contained 49 samples (24 from pSS and 25 from age- and gender-matched healthy controls [HCs]) and the validation set included 25 samples (12 from pSS and 13 from HCs). Totally 36 pSS patients and 38 HCs were centrally randomized into the discovery set or to the validation set at a 2:1 ratio. Unstimulated whole saliva samples from pSS patients and HCs were analyzed using a data-independent acquisition (DIA) strategy on a 2D LC?HRMS/MS platform to reveal differential proteins. The crucial proteins were verified using DIA analysis and annotated using gene ontology (GO) and International Pharmaceutical Abstracts (IPA) analysis. A prediction model for SS was established using random forests.Results A total of 1,963 proteins were discovered, and 136 proteins exhibited differential representation in pSS patients. The bioinformatic research indicated that these proteins were primarily linked to immunological functions, metabolism, and inflammation. A panel of 19 protein biomarkers was identified by ranking order based on P-value and random forest algorichm, and was validated as the predictive biomarkers exhibiting good performance with area under the curve (AUC) of 0.817 for discovery set and 0.882 for validation set.Conclusions The candidate protein panel discovered may aid in pSS diagnosis. Salivary proteomic analysis is a promising non-invasive method for prognostic evaluation and early and precise treatments for pSS patients. DIA offers the best time efficiency and data dependability and may be a suitable option for future research on the salivary proteome.

Effect of Reduced INR in Early Pregnancy on the Occurrence of Preeclampsia: A Retrospective Cohort Study.

To investigate the effect of reduced early-pregnancy activated partial thrombin time (APTT), prothrombin time (PT), and international standardized ratio (INR) on the risk of preeclampsia. A total of 8549 pregnant women with singleton births were included. Early pregnancy APTT, PT, and INR levels, with age, birth, prepregnancy body mass index, fibrinogen (FBG), thrombin time (TT), D-dimer (DD2), antithrombin III (ATIII), fibrin degradation products (FDP) as confounders, generalized linear model of APTT, the relative risk of PT and INR when INR reduction. After adequate adjustment for confounders, the relative risk of preeclampsia was 0.703 for every 1 s increase in plasma PT results in early pregnancy, and for every 0.1 increase in plasma INR results, the relative risk of preeclampsia was 0.767. With a PT less than the P25 quantile (<11 s), the relative risk of preeclampsia was 1.328. The relative risk of preeclampsia at an INR less than the P25 quantile (<0.92) was 1.24. There was no statistical association between APTT on the risk of preeclampsia. The relative risk of preeclampsia is strongly associated with a decrease in PT and INR in early pregnancy. PT and INR in early pregnancy were a potential marker in the risk stratification of preeclampsia. Focusing on reduced PT and INR levels in early pregnancy can help to identify early pregnancies at risk for preeclampsia.

Theoretical Study of Efficient Photon-Phonon Resonance Absorption in the Tungsten-Related Vibrational Mode of Scheelite.

Tungsten (W) is an extremely rare and vital metal extensively used in metallurgy, the chemical industry, optoelectronic devices, and machinery manufacturing. In this work, an environmentally friendly and efficient physical method based on photon-phonon resonance absorption (PPRA) is proposed for separating W from scheelite. We calculated the vibrational spectrum of calcium tungstate (CaWO4) and assigned the infrared (IR) absorption and Raman scattering peaks through a dynamic analysis of the normal modes. We focused on the strong IR absorption peaks related to W and identified three high-intensity IR-active modes at around 830 cm-1, corresponding to the stretching of the W-O bonds. Therefore, we propose the use of high-power terahertz (∼25 THz) laser radiation to facilitate W extraction from compounds, leveraging the high efficiency of PPRA. Experimental testing is required to determine the precise absorption frequency under industrial production conditions.

Structurally Preserved Liquidambar Infructescences, Associated Pollen, and Leaves from the Late Oligocene of the Nanning Basin, South China.

Liquidambar L. is a significant constituent of the Cenozoic flora in the Northern Hemisphere. Currently, this genus exhibits a discontinuous distribution across Asia and North America, with the center of diversity being in southeastern Asia. This study presents the first occurrence of Liquidambar in the Oligocene of South China. Fossil sweetgum infructescences, associated pollen, and leaves have been found in the Nanning Basin, Guangxi. A new species, Liquidambar nanningensis sp. nov., is described based on the morphological and anatomical characteristics of three-dimensionally preserved infructescences. The Liquidambar fossils from the Nanning Basin show a combination of features indicative of the former genera of Altingiaceae, Altingia, Liquidambar s. str., and Semiliquidambar. The new occurrence expands the taxonomic and morphological diversity of the Paleogene Liquidambar species in South China.

Computational Assignment of Tantalum-related Strong Absorption Peaks in the Infrared Spectrum of Potassium Heptafluorotantalate.

Tantalum (Ta) is a valuable and rare metal that is extensively used in the production of implant materials and high-performance capacitors. However, a convenient and effective method for the separation of Ta from other compounds has yet to be developed. On the basis of first-principle density functional theory (DFT), we simulated the vibrational spectrum of potassium heptafluorotantalate (K2TaF7). By performing a dynamics analysis of vibrational modes, we assigned peaks in infrared (IR) absorption and Raman scattering spectra to their corresponding vibrations. We focused on the strong IR absorption peaks of Ta-related vibrational modes in K2TaF7 and concluded that three observed IR absorption peaks, at 285, 315, and 530 cm-1, are good candidates. Provided with high power radiation at these three frequencies (at about 8.55, 9.45, and 15.9 THz), the good efficiency of photon-phonon resonance absorption will facilitate Ta separation from a compound.

Combining immune-checkpoint inhibitors with tocilizumab to treat a lung adenocarcinoma patient with pre-existing polymyalgia rheumatica: A case report.

Immune-checkpoint inhibitors (ICIs) have changed the management of advanced cancers. However, patients with pre-existing autoimmune diseases (ADs) have usually been excluded from clinical trials of ICIs due to concerns about exacerbation of AD. Here, we combined ICIs with selective immunosuppressant treatment in a metastatic lung adenocarcinoma patient with active pre-existing polymyalgia rheumatica (PMR). Remarkably, the strategy led to durable response and no exacerbation of PMR. Thus, we provide the first clinical evidence of treating metastatic cancer with ICIs and concomitant use of tocilizumab and hydroxychloroquine for active pre-existing PMR.

Synergistic effects of BTN3A1, SHP2, CD274, and STAT3 gene polymorphisms on the risk of systemic lupus erythematosus: a multifactorial dimensional reduction analysis.

OBJECTIVE: Systemic lupus erythematosus is a complex autoimmune disorder, and evidence supports the significance of genetic polymorphisms in SLE genetic susceptibility. The aim of this study was to assess the effects of BTN3A1 (butyrophilin 3A1), SHP2 (Src homology-2 containing protein tyrosine phosphatase), CD274 (programmed cell death 1 ligand 1), and STAT3 (signal transducer-activator of transcription 3) gene interactions on SLE risk. MATERIALS AND METHODS: Two hundred and ninety patients diagnosed with SLE and 370 healthy controls were recruited. A multifactor dimensionality reduction (MDR) approach was used to determine the epistasis among single nucleotide polymorphisms (SNPs) on the BTN3A1 (rs742090), SHP2 (rs58116261), CD174 (rs702275), and STAT3 (rs8078731) genes. The best risk prediction model was identified in terms of precision and cross-validation consistency. RESULTS: Allele A and genotype AA were negatively related to genetic susceptibility of SLE for BTN3A1 rs742090 (OR = 0.788 (0.625-0.993), P = 0.044; OR = 0.604 (0.372-0.981), P = 0.040). For STAT3 rs8078731, allele A and genotype AA were positively related to the risk of SLE (OR = 1.307 (1.032-1.654), P = 0.026; OR = 1.752 (1.020-3.010), P = 0.041). MDR analysis revealed the most significant interaction between BTN3A1 rs742090 and SHP2 rs58116261. The best risk prediction model was a combination of BTN3A1 rs742090, SHP2 rs58116261, and STAT3 rs8078731 (accuracy = 0.5866, consistency = 10/10, OR = 1.9870 (1.5964-2.4731), P = 0.001). CONCLUSION: These data indicate that risk prediction models formed by gene interactions (BTN3A1, SHP2, STAT3) can identify susceptible populations of SLE. Key Points • BTN3A1 rs742090 polymorphism was a protective factor for systemic lupus erythematosus, while STAT3 rs8078731 polymorphism was a risk factor. • There was a strong synergistic effect of BTN3A1 rs742090 and SHP2 rs58116261, and interaction among BTN3A1 rs742090, SHP2 rs58116261, and STAT3 rs8078731 constructed the best model to show association with SLE risk.

Multiscale Synergetic Bandgap/Structure Engineering in Semiconductor Nanofibrous Aerogels for Enhanced Solar Evaporation.

Solar-driven interface evaporation has been identified as a sustainable seawater desalination and water purification technology. Nonetheless, the evaporation performance is still restricted by salt deposition and heat loss owing to weak solar spectrum absorption, tortuous channels, and limited plane area of conventional photothermal material. Herein, the semiconductor nanofibrous aerogels with a narrow bandgap, vertically aligned channels, and a conical architecture are constructed by the multiscale synergetic engineering strategy, encompassing bandgap engineering at the atomic scale and structure engineering at the nano-micro scale. As a proof-of-concept demonstration, a Co-doped MoS2 nanofibrous aerogel is synthesized, which exhibits the entire solar absorption, superhydrophilic, and excellent thermal insulation, achieving a net evaporation rate of 1.62 kg m-2 h-1 under 1 sun irradiation, as well as a synergistically efficient dye ion adsorption function. This work opens up new possibilities for the development of solar evaporators for practical applications in clean water production.

Optoelectronic Evolution in Halogen-Doped Organic-Inorganic Halide Perovskites: A First-Principles Analysis.

Cl, Br, and I are elements in the halogen family, and are often used as dopants in semiconductors. When employed as dopants, these halogens can significantly modify the optoelectronic properties of materials. From the perspective of halogen doping, we have successfully achieved the stabilization of crystal structures in CH3NH3PbX3, CH3NH3PbI3-xClx, CH3NH3PbI3-xBrx, and CH3NH3PbBr3-xClx, which are organic-inorganic hybrid perovskites. Utilizing first-principles density functional theory calculations with the CASTEP module, we investigated the optoelectronic properties of these structures by simulations. According to the calculations, a smaller difference in electronegativity between different halogens in doped structures can result in smoother energy bands, especially in CH3NH3PbI3-xBrx and CH3NH3PbBr3-xClx. The PDOS of the Cl-3p orbitals undergoes a shift along the energy axis as a result of variances in electronegativity levels. The optoelectronic performance, carrier mobility, and structural stability of the CH3NH3PbBr3-xClx system are superior to other systems like CH3NH3PbX3. Among many materials considered, CH3NH3PbBr2Cl exhibits higher carrier mobility and a relatively narrower bandgap, making it a more suitable material for the absorption layer in solar cells. This study provides valuable insights into the methodology employed for the selection of specific types, quantities, and positions of halogens for further research on halogen doping.

High-Performance Waterproof, Breathable, and Radiative Cooling Membranes Based on Nanoarchitectured Fiber/Meshworks.

Smart membranes with protection and thermal-wet comfort are highly demanded in various fields. Nevertheless, the existing membranes suffer from a tradeoff dilemma of liquid resistance and moisture permeability, as well as poor thermoregulating ability. Herein, a novel strategy, based on the synchronous occurrence of humidity-induced electrospinning and electromeshing, is developed to synthesize a dual-network structured nanofiber/mesh for personal comfort management. Manipulating the ejection, deformation, and phase separation of spinning jets and charged droplets enables the creation of nanofibrous membranes composed of radiative cooling nanofibers and 2D nanostructured meshworks. With a combination of a true-nanoscale fiber (∼70 nm) in 2D meshworks, a small pore size (0.84 µm), and a superhydrophobic surface (151.9°), the smart membranes present high liquid repellency (95.6 kPa), improved breathability (4.05 kg m-2 d-1), and remarkable cooling performance (7.9 °C cooler than commercial cotton fabrics). This strategy opens up a pathway to the design of advanced smart textiles for personal protection.

A Theoretical Analysis of the Differential Chemical Reaction Results Caused by Chirality Induction.

The theory of electron spin has been proposed for a century, but the study of quantum effects in biological molecules is still in its infancy. Chirality-induced spin selectivity (CISS) is a very modern theory that can explain many biochemical phenomena. In this paper, we propose a new theoretical model based on CISS theory and quantum chemistry theory, which can well explain the theoretical explanation of the chiral selectivity of chiral proteins. Moreover, this theory can predict the spin state of corresponding chiral molecules. Taking the L-DOPA and AADC enzymes as examples, this theoretical model elucidates the AADC enzyme's chiral catalysis selectivity and successfully predicts the spin state of L-DOPA and D-DOPA's valence electrons.

Association of STAT3 gene polymorphisms with systemic lupus erythematosus in a Chinese Han population.

OBJECTIVE: Evidence supports the important role of STAT3 in SLE; however, association between STAT3 gene polymorphisms and SLE risk needs discussion. METHODS: Three hundred SLE patients and 380 healthy controls from Chinese Han population were included. DNA is extracted from peripheral blood mononuclear cells and the clinical characteristics of patients are collected. STAT3 gene polymorphisms (rs6503695, rs744166, rs9912773, and rs12601982) were genotyped by the Kompetitive Allele-Specific PCR (KASP) method. SPSS 26.0 was utilized to analyze the genetic susceptibility of SLE and STAT3 gene polymorphisms. RESULTS: Frequencies of genotypes CT, TT, and TT+CT were significantly lower in SLE patients compared with those in healthy controls with respect to rs6503695 (p = .007, p < .001, p = .001). Frequencies of rs744166 genotypes AG, AA, and AA+AG were decreased in SLE patients as compared to those in healthy controls (p = .034, p = .006, p = .009). The recessive models (CC vs GG+GC) for rs9912773 and (AA vs GG+GA) for rs12601982 were significantly related to SLE patients (p = .014, p = .035). Moreover, allele C of rs6503695 was related to optic nerve damage in SLE patients (p = .036). rs744166 allele G was correlated with positive rash and albuminuria in SLE patients (p = .006, p = .014). For rs9912773, SLE patients carrying genotype GG had higher serum C3 and C4 levels compared to genotype GC+CC (p = .029, p = .028). The rs12601982 allele G was strongly associated with positive hypocomplementemia in SLE patients (p = .034). SLE patients carrying genotypes GG, GC, and CC had different SLEDAI score for rs12601982 (GG vs GC vs CC, p = .003). CONCLUSION: STAT3 gene polymorphisms associated with SLE susceptibility.

Systemic lupus erythematosus with high disease activity identification based on machine learning.

OBJECTIVE: Clinical evaluation of systemic lupus erythematosus (SLE) disease activity is limited and inconsistent, and high disease activity significantly, seriously impacts on SLE patients. This study aims to generate a machine learning model to identify SLE patients with high disease activity. METHOD: A total of 1014 SLE patients with low disease activity and 453 SLE patients with high disease activity were included. A total of 94 clinical, laboratory data and 17 meteorological indicators were collected. After data preprocessing, we use mutual information and multisurf to evaluate and select the importance of features. The selected features are used for machine learning modeling. Performance of the model is evaluated and verified by a series of binary classification indicators. RESULTS: We screened out hematuria, proteinuria, pyuria, low complement, precipitation, sunlight and other features for model construction by integrated feature selection. After hyperparameter optimization, the LGB has the best performance (ROC: AUC = 0.930; PRC: AUC = 0.911, APS = 0.913; balance accuracy: 0.856), and the worst is the naive bayes (ROC: AUC = 0.849; PRC: AUC = 0.719, APS = 0.714; balance accuracy: 0.705). Finally, the selection of features has good consistency in the composite feature importance bar plot. CONCLUSION: We identify SLE patients with high disease activity by a simple machine learning pipeline, especially the LGB model based on the characteristics of proteinuria, hematuria, pyuria and other feathers screened out by collective feature selection.

Late Oligocene fossil acorns and nuts of Quercus section Cyclobalanopsis from the Nanning Basin, Guangxi, South China.

Quercus is the largest genus within the Fagaceae and has a rich fossil record. Most of the fossil material is attributed to the subgenus Quercus based on leaves, pollen or rarely acorns and nuts. Fossil records of Q. section Cyclobalanopsis characterized by ring-cupped acorns are relatively few and especially those described based on nuts are scant. In this study, we described four new species of Quercus section Cyclobalanopsis based on mummified acorns and nuts: Q. paleodisciformis X.Y. Liu et J.H. Jin sp. nov., Q. paleohui X.Y. Liu et J.H. Jin sp. nov., Q. nanningensis X.Y. Liu et J.H. Jin sp. nov. and Q. yongningensis X.Y. Liu et J.H. Jin sp. nov. These species closely resemble the extant species Q. disciformis, Q. hui, Q. kerrii, and Q. dinghuensis. The occurrence of Q. section Cyclobalanopsis in the Oligocene stratum of Guangxi, South China, suggests that the section has diversified within its extant distribution center since the Oligocene. By combining records from other areas, we propose that the section first appeared in the middle Eocene of East Asia (Sino-Japan), has diversified in situ with a few elements scattering into West Asia and southern Europe since the Oligocene and Pliocene, respectively, and finally became restricted in East Asia since the Pleistocene. This indicates that the section originated and diversified in East Asia, before spreading into West Asia no later than the Oligocene and into southern Europe by the Pliocene. Subsequently it disappeared from South Europe and West Asia due to the appearance of the (summer dry) Mediterranean climate and widespread cooling during the Pleistocene.

Exploring machine learning methods for predicting systemic lupus erythematosus with herpes.

OBJECTIVES: To investigate whether machine learning, which is widely used in disease prediction and diagnosis based on demographic data and serological markers, can predict herpes occurrence in patients with systemic lupus erythematosus (SLE). METHODS: A total of 286 SLE patients were included in this study, including 200 SLE patients without herpes and 86 SLE patients with herpes. SLE patients were randomly divided into a training group and a test group, and 18 demographic characteristics and serological indicators were compared between the two groups. RESULTS: We selected basophil, monocyte, white blood cell, age, immunoglobulin E, SLE Disease Activity Index, complement 4, neutrophil, and immunoglobulin G as the basic features of modeling. A random forest model had the best performance, but logistic and decision tree analyses had better clinical decision-making benefits. Random forest had a good consistency between feature importance judgment and feature selection. The 10-fold cross-validation showed the optimization of five model parameters. CONCLUSION: The random forest model may be an excellently performing model, which may help clinicians to identify SLE patients whose disease is complicated by herpes early.

Investigation of the relationship between changes in maternal coagulation profile in the first trimester and the risk of developing preeclampsia.

Normal pregnancy is a hypercoagulable state with an increase in coagulation factor levels and a decrease in natural anticoagulation. However, a higher hypercoagulable state with prolonged activated partial thromboplastin time (APTT), prothrombin time (PT), increased D-dimer, and mean platelet volume is seen in women with preeclampsia at the time of onset. In addition, endothelial dysfunction occurs before the clinical symptoms of preeclampsia. Therefore, we undertook this study to investigate the coagulation profile in the first trimester in women who developed preeclampsia later. A total of 853 pregnant women with singleton births at the Obstetrics and Gynecology Hospital of Fudan University between January 2021 and December 2021 were included in this case-control study. In the comparison with the controls (n = 531), the mean value of D-dimer, APTT, thrombin time (TT), antithrombin (AT)), and fibrin degradation products (FDP) was significantly lower in preeclamptic women at the time of diagnosis (n = 322). The changes in the coagulation profile were not associated with the severity or the time of onset. The reduced values of D-dimer, AT, and FDP, and increased values of TT were also observed in the first trimester in women who developed preeclampsia later and were not associated with the severity, or the time of onset of preeclampsia. After adjusting for maternal age and BMI, the values of D-dimer and AT in the first trimester were correlated to the risk of developing preeclampsia. Our findings suggest that there is an abnormal maternal response to the hemostatic system in early gestational age in women who developed preeclampsia later and measuring the coagulation profile could be an additional predictive marker of preeclampsia.

Lupus nephritis or not? A simple and clinically friendly machine learning pipeline to help diagnosis of lupus nephritis.

OBJECTIVE: Diagnosis of lupus nephritis (LN) is a complex process, which usually requires renal biopsy. We aim to establish a machine learning pipeline to help diagnosis of LN. METHODS: A cohort of 681 systemic lupus erythematosus (SLE) patients without LN and 786 SLE patients with LN was established, and a total of 95 clinical, laboratory data and 17 meteorological indicators were collected. After tenfold cross-validation, the patients were divided into training set and test set. The features selected by collective feature selection method of mutual information (MI) and multisurf were used to construct the models of logistic regression, decision tree, random forest, naive Bayes, support vector machine (SVM), light gradient boosting (LGB), extreme gradient boosting (XGB), and artificial neural network (ANN), the models were compared and verified in post-analysis. RESULTS: Collective feature selection method screens out antistreptolysin (ASO), retinol binding protein (RBP), lupus anticoagulant 1 (LA1), LA2, proteinuria and other features, and the hyperparameter optimized XGB (ROC: AUC = 0.995; PRC: AUC = 1.000, APS = 1.000; balance accuracy: 0.990) has the best performance, followed by LGB (ROC: AUC = 0.992; PRC: AUC = 0.997, APS = 0.977; balance accuracy: 0.957). The worst performance is naive Bayes model (ROC: AUC = 0.799; PRC: AUC = 0.822, APS = 0.823; balance accuracy: 0.693). In the composite feature importance bar plots, ASO, RF, Up/Ucr, and other features play important roles in LN. CONCLUSION: We developed and validated a new and simple machine learning pathway for diagnosis of LN, especially the XGB model based on ASO, LA1, LA2, proteinuria, and other features screened out by collective feature selection.