ObjectiveTo evaluate the effect of Ningying Formula （宁瘿方） combined with low-dose antithyroid drugs （ATDs） on the relapse risk for patients with Graves' hyperthyroidism （GH） during the remission phase， and to analyze the related factors between GH relapse and thyrotropin receptor antibody （TRAb） negativity， so as to provide evidence for the standardized management of GH in remission stage. MethodsA single-center retrospective cohort study was conducted， including 269 GH patients in the remission stage. After propensity score matching （PSM）， 102 matched pairs （204 patients） were established. The control group received low-dose ATDs as maintenance therapy， while the exposure group received the core Ningying Formula in addition to low-dose ATDs. The primary outcome was the GH recurrence rate； the secondary outcome was the thyrotropin receptor antibody （TRAb） negativity rate （TRAb＜1.75 IU/L）. Safety outcomes included treatment-related adverse events. Differences between groups were assessed using Cox regression models and Kaplan-Meier curves， with sensitivity analysis performed using inverse probability of treatment weighting （IPTW）. ResultsThe median follow-up in the matched cohort was 28.07 months. Regarding the GH recurrence outcome， the recurrence rate in the exposure group （18/102， 17.6%） was significantly lower than that in the control group （31/102， 30.4%； χ²=4.539， P=0.033）； regarding the TRAb negativity outcome， the TRAb negativity rate in the exposure group （50/102， 49.0%） was significantly higher than that in the control group （23/102， 22.5%； χ²=15.551， P＜0.001）. Multivariate Cox regression analysis for recurrence showed that Ningying Formula treatment reduced the risk of recurrence ［HR=0.324， 95%CI（0.170， 0.617）， P＜0.001］. Male ［HR=2.209， 95%CI（1.079， 4.520）， P=0.030］， higher initial TRAb level ［per 1 IU/L increase： HR=1.033， 95%CI（1.003， 1.064）， P=0.032］， and larger thyroid volume ［per 1 ml increase： HR=1.045， 95%CI（1.003， 1.088）， P=0.035］ were identified as independent risk factors for recurrence； multivariate Cox regression analysis for TRAb negativity indicated that Ningying Formula treatment promoted TRAb negativity ［HR=1.826， 95%CI（1.091， 3.056）， P=0.022］， while a higher initial TRAb level was associated with a lower probability of negativity ［HR=0.974， 95%CI（0.950， 0.998）， P=0.032］. Survival analysis showed significant differences in relapse rate between groups （Log-Rank P=0.003） and in TRAb outcomes （Log-Rank P=0.034）. The incidence of treatment-related adverse events was similar between groups （P=0.757）. The IPTW sensitivity analysis was consistent with the primary analysis， indicating robust results. ConclusionThe Ningying Formula combined with low-dose ATDs can significantly reduce the risk of recurrence and can improve the TRAb negativity rate in GH patients during the remission stage， without increasing common adverse events， making it an optional strategy for reducing relapse risk during remission. Male gender， higher baseline TRAb level， and larger thyroid volume indicate a higher risk of recurrence， warranting focused follow-up and stratified management.

Objective To explore a method for rapid and differential diagnosis of rejection after kidney transplantation through urine hyperspectral imaging technology. Methods Hyperspectral data information from urine samples of 118 recipients after kidney transplantation was collected, and a deep learning model was constructed to diagnose and classify the types of rejection. Results A deep learning diagnostic model based on the 34-layer residual network (ResNet-34) was constructed, and 118 patients were included and divided into the training set and the test set. Based on the pathological results of the transplanted kidney puncture, the urine samples of the patients were classified into five groups: the non-rejection group, the T-cell-mediated rejection group, the antibody-mediated rejection group, the mixed rejection group and the nephropathy recurrence group. The results showed that the diagnostic sensitivities of the model for the above five groups were 0.960, 0.980, 0.930, 0.940 and 0.943 respectively, and the diagnostic specificities were 0.983, 0.993, 0.997, 0.989 and 0.989 respectively. The overall diagnostic accuracy rate reached 95.7%. Conclusions The study provides a non-invasive, rapid and accurate auxiliary diagnostic method for the differential diagnosis of rejection after kidney transplantation.

OBJECTIVE To investigate the effects and mechanisms of Lycium ruthenicum Murr. in improving sleep. METHODS Network pharmacology was employed to identify the active components of L. ruthenicum and their associated disease targets， followed by enrichment analysis. A caffeine‑induced zebrafish model of sleep deprivation was established ， and the zebrafish were treated with L. ruthenicum Murr. extract （LRME） at concentrations of 0.1， 0.2 and 0.4 mg/mL， respectively； 24 h later， behavioral changes of zebrafish and pathological alterations in brain neurons were subsequently observed. The levels of inflammatory factors [interleukin-6 （IL-6）， IL-1β， IL-10， tumor necrosis factor-α （TNF-α）]， oxidative stress markers [superoxide dismutase （SOD）， malondialdehyde （MDA）， glutathione peroxidase （GSH-Px）， catalase （CAT）]， and neurotransmitters [5- hydroxytryptamine （5-HT）， γ-aminobutyric acid （GABA）， glutamic acid （Glu）， dopamine （DA）， and norepinephrine （NE）] were measured. The protein expression levels of protein kinase B1 （AKT1）， phosphorylated AKT1 （p-AKT1）， epidermal growth factor receptor （EGFR）， B-cell lymphoma 2 （Bcl-2）， sarcoma proto-oncogene，non-receptor tyrosine kinase （SRC）， and heat shock protein 90α family class A member 1 （HSP90AA1） in the zebrafish were also determined. RESULTS A total of 12 active components and 176 intersecting disease targets were identified through network pharmacology analysis. Among these， apigenin， naringenin and others were recognized as core active compounds， while AKT1， EGFR and others served as key targets； EGFR tyrosine kinase inhibitor resistance signaling pathway was identified as the critical pathway. The sleep improvement rates in zebrafish of LRME low-， medium-， and high-dose groups were 54.60%， 69.03% and 77.97%， 开发。E-mail：hjp_yft@163.com respectively， while the inhibition ratios of locomotor distance were 0.57， 0.83 and 0.95， respectively. Compared with the model group， the number of resting counts， resting time and resting distance were significantly increased/extended in LRME medium- and high-dose groups （P＜0.05）. Neuronal damage in the brain was alleviated. Additionally， the levels of IL-6， IL-1β， TNF-α， MDA， Glu， DA and NE， as well as the protein expression levels of AKT1， p-AKT1， EGFR， SRC and HSP90AA1， were markedly reduced （P＜0.05）， while the levels of IL-10， SOD， GSH-Px， CAT， 5-HT and GABA， as well as Bcl-2 protein expression， were significantly elevated （P＜0.05）. CONCLUSIONS L. ruthenicum Murr. demonstrates sleep-improving effects， and its specific mechanism may be related to the regulation of inflammatory responses， oxidative stress， neurotransmitter balance， and the EGFR tyrosine kinase inhibitor resistance signaling pathway.

Objective To systematically evaluate the risk prediction model of anastomotic fistula after radical resection of esophageal cancer, and to provide objective basis for selecting a suitable model. Methods A comprehensive search was conducted on Chinese and English databases including CNKI, Wanfang, VIP, CBM, PubMed, EMbase, Web of Science, The Cochrane Library for relevant studies on the risk prediction model of anastomotic fistula after radical resection of esophageal cancer from inception to April 30, 2023. Two researchers independently screened literatures and extracted data information. PROBAST tool was used to assess the risk of bias and applicability of included literatures. Meta-analysis was performed on the predictive value of common predictors in the model with RevMan 5.3 software. Results A total of 18 studies were included, including 11 Chinese literatures and 7 English literatures. The area under the curve (AUC) of the prediction models ranged from 0.68 to 0.954, and the AUC of 10 models was >0.8, indicating that the prediction performance was good, but the risk of bias in the included studies was high, mainly in the field of research design and data analysis. The results of the meta-analysis on common predictors showed that age, history of hypertension, history of diabetes, C-reactive protein, history of preoperative chemotherapy, hypoproteinemia, peripheral vascular disease, pulmonary infection, and calcification of gastric omental vascular branches are effective predictors for the occurrence of anastomotic leakage after radical surgery for esophageal cancer (P<0.05). Conclusion The study on the risk prediction model of anastomotic fistula after radical resection of esophageal cancer is still in the development stage. Future studies can refer to the common predictors summarized by this study, and select appropriate methods to develop and verify the anastomotic fistula prediction model in combination with clinical practice, so as to provide targeted preventive measures for patients with high-risk anastomotic fistula as soon as possible.

In order to explore the possible role and molecular mechanism of the combined action of leech and bear bile in liver and gallbladder diseases, this study first used network pharmacology methods to screen the components and targets of leech and bear bile, as well as the related target genes of liver and gallbladder diseases. The selected key genes were subjected to interaction network and GO/KEGG enrichment analysis. Then, using sodium oleate induced HepG2 cell lipid deposition model and DL-ethionine induced mouse fatty liver model, the activity of leech and bear bile alone and in combination in reducing liver fat was evaluated in vitro and in vivo, and the expression of key pathway related proteins suggested by network pharmacology was detected by Western blot. The results of network pharmacology analysis showed that the active ingredients of leech and bear bile have 295 intersecting targets with liver and gallbladder related diseases, involving more than 200 signaling pathways, including the PI3K/Akt signaling pathway and phospholipase D signaling pathway closely related to glucose and lipid metabolism. The results of in vitro validation experiments showed that both leech and bear bile, alone and in combination, can significantly inhibit the lipid deposition induced by sodium oleate in human liver cells, reduce the triacylglycerol level in cell culture supernatant, and inhibit the lipid content in liver cells. The observation results of Nile red staining confocal microscopy showed that the combination of leech and bear bile had better activity in reducing lipid deposition in liver cells compared to using them alone. In a mouse fatty liver model, the combination of leech and bear bile can better reduce elevated organ indices, blood lipids, and liver lipid levels, as well as lower the levels of serum liver injury biomarkers. The animals used in this experiment and related disposal meet the requirements of animal welfare. Before the experiment, it was reviewed and approved by IACUC, Institute of Materia Medica, Chinese Academy of Medical Sciences. The Western blot experiment results showed that the combination of leech and bear bile can significantly upregulate the expression levels of p-PI3K and p-Akt proteins, and increase the p-PI3K/PI3K and p-Akt/Akt ratios, which is consistent with the predicted results of network pharmacology. The combination of leech and bear bile has great potential for treating fatty liver disease, and activating the PI3K/Akt pathway may be one of the important mechanisms for reducing lipid deposition in liver cells.

ObjectiveTo understand the epidemiological distribution and gene evolutionary variation of influenza A (H3N2) viruses in Fengxian District, Shanghai, in the surveillance year of 2023, and to provide a reference basis for influenza prevention and control. MethodsThe prevalence of influenza virus in Fengxian District in the 2023 influenza surveillance year (April 2023‒March 2024) was analyzed. The hemagglutinin (HA) gene, neuraminidase (NA) gene, and amino acid sequences of 75 strains of H3N2 influenza viruses were compared with the vaccine reference strain for similarity matching and phylogenetic evolutionary analysis, in addition to an analysis of gene characterization and variation. ResultsIn Fengxian District, there was a mixed epidemic of H3N2 and H1N1 in the spring of 2023, with H3N2 being the predominant subtype in the second half of the year, and Victoria B becoming the predominant subtype in the spring of 2024. A total of 75 influenza strains of H3N2 with HA and NA genes were distributed in the 3C.2a1b.2a.2a.2a.3a.1 and B.4 branches, with overall similarity to the reference strain of the 2024 vaccine higher than that of the reference strain of the 2022 and 2023 vaccine. Compared with the 2023 vaccine reference strain, three antigenic sites and one receptor binding site were changed in HA, with three glycosylation sites reduced and two glycosylation sites added; where as in NA seven antigenic sites and the 222nd resistance site changed with two glycosylation sites reduced. ConclusionThe risk of antigenic variation and drug resistance of H3N2 in this region is high, and it is necessary to strengthen the publicity and education on the 2024 influenza vaccine and long-term monitoring of influenza virus prevalence and variation levels.

ObjectiveTo investigate the effect and potential mechanism of caffeic acid （CA） on severe acute pancreatitis （SAP） induced by caerulein combined with lipopolysaccharide （LPS）， and to provide a basis for the research on novel drugs for the treatment of SAP. MethodsC57BL/6J mice， aged 6 weeks， were divided into control group， model group， CA group， and octreotide acetate （OA） group， with 6 mice in each group. The mice in the control group were given injection of normal saline， and those in the other groups were given intraperitoneal injection of caerulein combined with LPS to establish a mouse model of SAP. At 1 hour after the first injection of caerulein， the mice in the CA group and the OA group were given intraperitoneal injection of CA or subcutaneous injection of OA at an interval of 8 hours. The general status of the mice was observed after 24 hours of modeling， and serum， pancreas， lung， and colon samples were collected. HE staining was used to observe the histopathological changes of the pancreas and lungs， and the serum levels of α-amylase， lipase， tumor necrosis factor-α （TNF-α）， interleukin-6 （IL-6）， alanine aminotransferase， aspartate aminotransferase， and creatinine were measured. RT-PCR was used to measure the expression of proinflammatory factors in the pancreas and lungs； myeloperoxidase （MPO） immunohistochemistry was used to observe the degree of neutrophil infiltration； Western blot was used to measure the activation of nuclear factor-kappa B （NF-κB） and the level of citrullinated histone H3 （CitH3）， a marker for the formation of neutrophil extracellular traps （NETs）， in the pancreas and lungs， as well as the expression level of ZO-1 in colon tissue. A one-way analysis of variance was used for comparison of continuous data between multiple groups， and the Dunnett’s t-test was used for further comparison between two groups. ResultsCompared with the control group， the model group had severe injury in the pancreas and lungs and significant increases in the activity of serum α- amylase and lipase and the levels of the proinflammatory cytokines IL-6， interleukin-1β （IL-1β）， and TNF-α in serum and lung tissue （all P<0.05）， as well as significant increases in NF-κB activation， neutrophil infiltration， and the formation of NETs in the pancreas and lungs （all P<0.05）. Compared with the model group， the CA group had alleviated pathological injury of the pancreas and lungs and significant reductions in the activity of serum α-amylase and the levels of the proinflammatory cytokines IL-6， IL-1β， and TNF-α in serum and lung tissue （all P<0.05）， as well as significant reductions in NF-κB activation， neutrophil infiltration， and the formation of NETs in the pancreas and lungs （all P<0.05）. ConclusionCA can alleviate SAP induced by caerulein combined with LPS in mice， possibly by inhibiting neutrophil recruitment and the formation of NETs.

ObjectiveTo explore the effects of compatibility of Ephedrae Herba，Asari Radix et Rhizoma， and Aconiti Lateralis Radix Praeparata on the expression of type 2 innate lymphoid cells（ILC2s）-related factors in the lung of allergic rhinitis（AR）mice. MethodsAccording to the random number table method，fifty-four C57BL/6J mice were randomly divided into the following groups： Blank group，model group，Mahuang Fuzi Xixintang group，Asari Radix et Rhizoma and Aconiti Lateralis Radix Praeparata group，Ephedrae Herba and Asari Radix et Rhizoma group，Ephedrae Herba and Aconiti Lateralis Radix Praeparata group，Ephedrae Herba group，Aconiti Lateralis Radix Praeparata group， and Asari Radix et Rhizoma group （6 mice in each group）. Except the blank group，the other groups were subjected to intraperitoneal injection of ovalbumin（OVA）and intranasal challenge to induce AR. After the AR model was established，the mice in the blank group and the model group were given 0.2 mL·d^-1 normal saline by gavage，while those in the Mahuang Fuzi Xixintang group（2.31 g·kg^-1），Asari Radix et Rhizoma and Aconiti Lateralis Radix Praeparata group（1.54 g·kg^-1）， Ephedrae Herba and Asari Radix et Rhizoma group（1.16 g·kg^-1）， Ephedrae Herba and Aconiti Lateralis Radix Praeparata group（1.93 g·kg^-1），Ephedrae Herba group（0.77 g·kg^-1），Aconiti Lateralis Radix Praeparata group（1.16 g·kg^-1），and Asari Radix et Rhizoma group（0.39 g·kg^-1）were given corresponding medicine by gavage，with the treatment lasting for 14 consecutive days. The survival state of mice in each group was observed， and the levels of serum immunoglobulins E（IgE）after intranasal challenge were measured by enzyme-linked immunosorbent assay（ELISA）. The pathological changes of nasal and lung tissues were observed by hematoxylin-eosin（HE）staining. The expression of ILC2s in lung tissue of mice was detected by immunofluorescence（IF）. The mRNA expression of GATA binding protein 3（GATA3），retinoic acid receptor-related orphan receptor-α（RORα）， and inhibitor of DNA binding 2（ID2）in the lung tissue of mice was detected by quantitative real-time polymerase chain reaction（real-time PCR）. The levels of IgE，interleukin（IL）-4，IL-5， and IL-13 in serum were detected by ELISA. ResultsCompared with the blank group，the model group had poor survival state of mice and significantly increased serum IgE level after intranasal challenge（p<0.01）. Additionally，the mice in the model group showed a large amount of neutrophil infiltration in the mucosa of the posterior turbinate， obvious nasal mucosal bleeding and purulent secretion，shed epithelium， thickened bronchial wall，obvious intravascular hyperemia and edema，diffusion and infiltration of a large number of inflammatory cells，seriously damaged alveolar structure，and local lung consolidation. The model group also exhibited significantly increased expression of ILC2s in the lung tissue（P<0.01），increased mRNA expression of GATA3 and RORα，decreased mRNA expression of ID2（P<0.05，P<0.01），and increased levels of serum IgE， IL-4，IL-5，and IL-13（P<0.05，P<0.01）. Compared with the model group，the Mahuang Fuzi Xixintang group and the other medicine treatment groups showed improved survival state of mice， significantly reduced inflammatory cell infiltration in the nasal and lung tissues，a small amount of nasal mucosal bleeding，trachea wall thinning，and no hyperemia，edema， and nasal secretions. Furthermore， the expression of ILC2s in lung tissue was significantly decreased（P<0.01）. The mRNA expression level of GATA3 was decreased（P<0.05），especially in the Aconiti Lateralis Radix Praeparata group（P<0.01）. The expression mRNA levels of RORα were decreased only in the Ephedrae Herba and Aconiti Lateralis Radix Praeparata group and the Ephedrae Herba group（P<0.05）. The levels of serum IgE were decreased（P<0.05）， and IL-5 levels were significantly decreased（P<0.01）. IL-4 levels were significantly decreased in the groups except the Aconiti Lateralis Radix Praeparata group（P<0.01），and the level of IL-13 in the Mahuang Fuzi Xixintang group was decreased（P<0.05）. The levels of IL-13 in were significantly decreased in the Ephedrae Herba and Aconiti Lateralis Radix Praeparata group， Ephedrae Herba group， Aconiti Lateralis Radix Praeparata group， and Asari Radix et Rhizoma group（P<0.01）. ConclusionDifferent compatibility of Ephedrae Herba，Asari Radix et Rhizoma， and Aconiti Lateralis Radix Praeparata can reduce the inflammation of OVA-induced AR mice and has more advantages in reducing the secretion of IgE and IL-5. The compatibility of Ephedrae Herba and Aconiti Lateralis Radix Praeparata has the most advantage in reducing the mRNA expression of GATA3 and RORα to inhibit the expression of ILC2s and thus exert the anti-allergic effect，while the other compatibility has the extensive advantage in inhibiting the mRNA expression of GATA3.

ObjectiveTo explore the effects of compatibility of Ephedrae Herba，Asari Radix et Rhizoma， and Aconiti Lateralis Radix Praeparata on the expression of type 2 innate lymphoid cells（ILC2s）-related factors in the lung of allergic rhinitis（AR）mice. MethodsAccording to the random number table method，fifty-four C57BL/6J mice were randomly divided into the following groups： Blank group，model group，Mahuang Fuzi Xixintang group，Asari Radix et Rhizoma and Aconiti Lateralis Radix Praeparata group，Ephedrae Herba and Asari Radix et Rhizoma group，Ephedrae Herba and Aconiti Lateralis Radix Praeparata group，Ephedrae Herba group，Aconiti Lateralis Radix Praeparata group， and Asari Radix et Rhizoma group （6 mice in each group）. Except the blank group，the other groups were subjected to intraperitoneal injection of ovalbumin（OVA）and intranasal challenge to induce AR. After the AR model was established，the mice in the blank group and the model group were given 0.2 mL·d^-1 normal saline by gavage，while those in the Mahuang Fuzi Xixintang group（2.31 g·kg^-1），Asari Radix et Rhizoma and Aconiti Lateralis Radix Praeparata group（1.54 g·kg^-1）， Ephedrae Herba and Asari Radix et Rhizoma group（1.16 g·kg^-1）， Ephedrae Herba and Aconiti Lateralis Radix Praeparata group（1.93 g·kg^-1），Ephedrae Herba group（0.77 g·kg^-1），Aconiti Lateralis Radix Praeparata group（1.16 g·kg^-1），and Asari Radix et Rhizoma group（0.39 g·kg^-1）were given corresponding medicine by gavage，with the treatment lasting for 14 consecutive days. The survival state of mice in each group was observed， and the levels of serum immunoglobulins E（IgE）after intranasal challenge were measured by enzyme-linked immunosorbent assay（ELISA）. The pathological changes of nasal and lung tissues were observed by hematoxylin-eosin（HE）staining. The expression of ILC2s in lung tissue of mice was detected by immunofluorescence（IF）. The mRNA expression of GATA binding protein 3（GATA3），retinoic acid receptor-related orphan receptor-α（RORα）， and inhibitor of DNA binding 2（ID2）in the lung tissue of mice was detected by quantitative real-time polymerase chain reaction（real-time PCR）. The levels of IgE，interleukin（IL）-4，IL-5， and IL-13 in serum were detected by ELISA. ResultsCompared with the blank group，the model group had poor survival state of mice and significantly increased serum IgE level after intranasal challenge（p<0.01）. Additionally，the mice in the model group showed a large amount of neutrophil infiltration in the mucosa of the posterior turbinate， obvious nasal mucosal bleeding and purulent secretion，shed epithelium， thickened bronchial wall，obvious intravascular hyperemia and edema，diffusion and infiltration of a large number of inflammatory cells，seriously damaged alveolar structure，and local lung consolidation. The model group also exhibited significantly increased expression of ILC2s in the lung tissue（P<0.01），increased mRNA expression of GATA3 and RORα，decreased mRNA expression of ID2（P<0.05，P<0.01），and increased levels of serum IgE， IL-4，IL-5，and IL-13（P<0.05，P<0.01）. Compared with the model group，the Mahuang Fuzi Xixintang group and the other medicine treatment groups showed improved survival state of mice， significantly reduced inflammatory cell infiltration in the nasal and lung tissues，a small amount of nasal mucosal bleeding，trachea wall thinning，and no hyperemia，edema， and nasal secretions. Furthermore， the expression of ILC2s in lung tissue was significantly decreased（P<0.01）. The mRNA expression level of GATA3 was decreased（P<0.05），especially in the Aconiti Lateralis Radix Praeparata group（P<0.01）. The expression mRNA levels of RORα were decreased only in the Ephedrae Herba and Aconiti Lateralis Radix Praeparata group and the Ephedrae Herba group（P<0.05）. The levels of serum IgE were decreased（P<0.05）， and IL-5 levels were significantly decreased（P<0.01）. IL-4 levels were significantly decreased in the groups except the Aconiti Lateralis Radix Praeparata group（P<0.01），and the level of IL-13 in the Mahuang Fuzi Xixintang group was decreased（P<0.05）. The levels of IL-13 in were significantly decreased in the Ephedrae Herba and Aconiti Lateralis Radix Praeparata group， Ephedrae Herba group， Aconiti Lateralis Radix Praeparata group， and Asari Radix et Rhizoma group（P<0.01）. ConclusionDifferent compatibility of Ephedrae Herba，Asari Radix et Rhizoma， and Aconiti Lateralis Radix Praeparata can reduce the inflammation of OVA-induced AR mice and has more advantages in reducing the secretion of IgE and IL-5. The compatibility of Ephedrae Herba and Aconiti Lateralis Radix Praeparata has the most advantage in reducing the mRNA expression of GATA3 and RORα to inhibit the expression of ILC2s and thus exert the anti-allergic effect，while the other compatibility has the extensive advantage in inhibiting the mRNA expression of GATA3.

ObjectiveThe rapid advancement of bioanalytical technologies has heightened the demand for high-throughput, label-free, and real-time cellular analysis. Electrochemical impedance spectroscopy (EIS) operating in the GHz frequency range (GHz-EIS) has emerged as a promising tool for characterizing cell suspensions due to its ability to rapidly and non-invasively capture the dielectric properties of cells and their microenvironment. Although GHz-EIS enables rapid and label-free detection of cell suspensions, significant challenges remain in interpreting GHz impedance data for complex samples, limiting the broader application of this technique in cellular research. To address these challenges, this study presents a novel method that integrates GHz-EIS with deep learning algorithms, aiming to improve the precision of cell suspension concentration identification and quantification. This method provides a more efficient and accurate solution for the analysis of GHz impedance data. MethodsThe proposed method comprises two key components: dielectric property dataset construction and backpropagation (BP) neural network modeling. Yeast cell suspensions at varying concentrations were prepared and separately introduced into a coaxial sensor for impedance measurement. The dielectric properties of these suspensions were extracted using a GHz-EIS dielectric property extraction method applied to the measured impedance data. A dielectric properties dataset incorporating concentration labels was subsequently established and divided into training and testing subsets. A BP neural network model employing specific activation functions (ReLU and Leaky ReLU) was then designed. The model was trained and tested using the constructed dataset, and optimal model parameters were obtained through this process. This BP neural network enables automated extraction and analytical processing of dielectric properties, facilitating precise recognition of cell suspension concentrations through data-driven training. ResultsThrough comparative analysis with conventional centrifugal methods, the recognized concentration values of cell suspensions showed high consistency, with relative errors consistently below 5%. Notably, high-concentration samples exhibited even smaller deviations, further validating the precision and reliability of the proposed methodology. To benchmark the recognition performance against different algorithms, two typical approaches—support vector machines (SVM) and K-nearest neighbor (KNN)—were selected for comparison. The proposed method demonstrated superior performance in quantifying cell concentrations. Specifically, the BP neural network achieved a mean absolute percentage error (MAPE) of 2.06% and an R² value of 0.997 across the entire concentration range, demonstrating both high predictive accuracy and excellent model fit. ConclusionThis study demonstrates that the proposed method enables accurate and rapid determination of unknown sample concentrations. By combining GHz-EIS with BP neural network algorithms, efficient identification of cell concentrations is achieved, laying the foundation for the development of a convenient online cell analysis platform and showing significant application prospects. Compared to typical recognition approaches, the proposed method exhibits superior capabilities in recognizing cell suspension concentrations. Furthermore, this methodology not only accelerates research in cell biology and precision medicine but also paves the way for future EIS biosensors capable of intelligent, adaptive analysis in dynamic biological research.