1.Programmed death-ligand 1 tumor proportion score in predicting the safety and efficacy of PD-1/PD-L1 antibody-based therapy in patients with advanced non-small cell lung cancer: A retrospective, multicenter, observational study.
Yuequan SHI ; Xiaoyan LIU ; Anwen LIU ; Jian FANG ; Qingwei MENG ; Cuimin DING ; Bin AI ; Yangchun GU ; Cuiying ZHANG ; Chengzhi ZHOU ; Yan WANG ; Yongjie SHUI ; Siyuan YU ; Dongming ZHANG ; Jia LIU ; Haoran ZHANG ; Qing ZHOU ; Xiaoxing GAO ; Minjiang CHEN ; Jing ZHAO ; Wei ZHONG ; Yan XU ; Mengzhao WANG
Chinese Medical Journal 2025;138(14):1730-1740
BACKGROUND:
This study aimed to investigate programmed death-ligand 1 tumor proportion score in predicting the safety and efficacy of PD-1/PD-L1 antibody-based therapy in treating patients with advanced non-small cell lung cancer (NSCLC) in a real-world setting.
METHODS:
This retrospective, multicenter, observational study enrolled adult patients who received PD-1/PD-L1 antibody-based therapy in China and met the following criteria: (1) had pathologically confirmed, unresectable stage III-IV NSCLC; (2) had a baseline PD-L1 tumor proportion score (TPS); and (3) had confirmed efficacy evaluation results after PD-1/PD-L1 treatment. Logistic regression, Kaplan-Meier analysis, and Cox regression were used to assess the progression-free survival (PFS), overall survival (OS), and immune-related adverse events (irAEs) as appropriate.
RESULTS:
A total of 409 patients, 65.0% ( n = 266) with a positive PD-L1 TPS (≥1%) and 32.8% ( n = 134) with PD-L1 TPS ≥50%, were included in this study. Cox regression confirmed that patients with a PD-L1 TPS ≥1% had significantly improved PFS (hazard ratio [HR] 0.747, 95% confidence interval [CI] 0.573-0.975, P = 0.032). A total of 160 (39.1%) patients experienced 206 irAEs, and 27 (6.6%) patients experienced 31 grade 3-5 irAEs. The organs most frequently associated with irAEs were the skin (52/409, 12.7%), thyroid (40/409, 9.8%), and lung (34/409, 8.3%). Multivariate logistic regression revealed that a PD-L1 TPS ≥1% (odds ratio [OR] 1.713, 95% CI 1.054-2.784, P = 0.030) was an independent risk factor for irAEs. Other risk factors for irAEs included pretreatment absolute lymphocyte count >2.5 × 10 9 /L (OR 3.772, 95% CI 1.377-10.329, P = 0.010) and pretreatment absolute eosinophil count >0.2 × 10 9 /L (OR 2.006, 95% CI 1.219-3.302, P = 0.006). Moreover, patients who developed irAEs demonstrated improved PFS (13.7 months vs. 8.4 months, P <0.001) and OS (28.0 months vs. 18.0 months, P = 0.007) compared with patients without irAEs.
CONCLUSIONS
A positive PD-L1 TPS (≥1%) was associated with improved PFS and an increased risk of irAEs in a real-world setting. The onset of irAEs was associated with improved PFS and OS in patients with advanced NSCLC receiving PD-1/PD-L1-based therapy.
Humans
;
Carcinoma, Non-Small-Cell Lung/metabolism*
;
Male
;
Female
;
Retrospective Studies
;
Middle Aged
;
Lung Neoplasms/metabolism*
;
Aged
;
B7-H1 Antigen/metabolism*
;
Programmed Cell Death 1 Receptor/metabolism*
;
Adult
;
Aged, 80 and over
;
Immune Checkpoint Inhibitors/therapeutic use*
2.Identification of blood-entering components of Anshen Dropping Pills based on UPLC-Q-TOF-MS/MS combined with network pharmacology and evaluation of their anti-insomnia effects and mechanisms.
Xia-Xia REN ; Jin-Na YANG ; Xue-Jun LUO ; Hui-Ping LI ; Miao QIAO ; Wen-Jia WANG ; Yi HE ; Shui-Ping ZHOU ; Yun-Hui HU ; Rui-Ming LI
China Journal of Chinese Materia Medica 2025;50(7):1928-1937
This study identified blood-entering components of Anshen Dropping Pills and explored their anti-insomnia effects and mechanisms. The main blood-entering components of Anshen Dropping Pills were detected and identified by UPLC-Q-TOF-MS/MS. The rationality of the formula was assessed by using enrichment analysis based on the relationship between drugs and symptoms, and core targets of its active components were selected as the the potential anti-insomnia targets of Anshen Dropping Pills through network pharmacology analysis. Furthermore, protein-protein interaction(PPI) network, Gene Ontology(GO) enrichment analysis, and Kyoto Encyclopedia of Genes and Genomes(KEGG) pathway analysis were performed on the core targets. An active component-core target network for Anshen Dropping Pills was constructed. Finally, the effects of low-, medium-, and high-dose groups of Anshen Dropping Pills on sleep episodes, sleep duration, and sleep latency in mice were measured by supraliminal and subliminal pentobarbital sodium experiments. Moreover, total scores of the Pittsburgh sleep quality index(PSQI) scale was used to evaluate the changes before and after the treatment with Anshen Dropping Pills in a clinical study. The enrichment analysis based on the relationship between drugs and symptoms verified the rationality of the Anshen Dropping Pills formula, and nine blood-entering components of Anshen Dropping Pills were identified by UPLC-Q-TOF-MS/MS. The network proximity revealed a significant correlation between eight components and insomnia, including magnoflorine, liquiritin, spinosin, quercitrin, jujuboside A, ginsenoside Rb_3, glycyrrhizic acid, and glycyrrhetinic acid. Network pharmacology analysis indicated that the major anti-insomnia pathways of Anshen Dropping Pills involved substance and energy metabolism, neuroprotection, immune system regulation, and endocrine regulation. Seven core genes related to insomnia were identified: APOE, ALB, BDNF, PPARG, INS, TP53, and TNF. In summary, Anshen Dropping Pills could increase sleep episodes, prolong sleep duration, and reduce sleep latency in mice. Clinical study results demonstrated that Anshen Dropping Pills could decrease total scores of PSQI scale. This study reveals the pharmacodynamic basis and potential multi-component, multi-target, and multi-pathway effects of Anshen Dropping Pills, suggesting that its anti-insomnia mechanisms may be associated with the regulation of insomnia-related signaling pathways. These findings offer a theoretical foundation for the clinical application of Anshen Dropping Pills.
Animals
;
Drugs, Chinese Herbal/administration & dosage*
;
Tandem Mass Spectrometry/methods*
;
Sleep Initiation and Maintenance Disorders/metabolism*
;
Mice
;
Network Pharmacology
;
Male
;
Chromatography, High Pressure Liquid
;
Humans
;
Protein Interaction Maps/drug effects*
;
Sleep/drug effects*
;
Female
;
Adult
3.Short-term effectiveness of minimally invasive treatment for posterolateral depressed tibial plateau fractures assisted by robots and arthroscopy.
Zhongyao CHEN ; Xing DU ; Gang LUO ; Dagang TANG ; Xinyi WANG ; Yiyang LI ; Kangwen SUN ; Yi DUAN ; Wei SHUI
Chinese Journal of Reparative and Reconstructive Surgery 2025;39(7):801-806
OBJECTIVE:
To investigate short-term effectiveness of robot-assisted fracture reduction and fixation combined with arthroscopic exploration for posterolateral depressed tibial plateau fractures.
METHODS:
Between January 2022 and January 2024, 8 patients with posterolateral depressed tibial plateau fractures (Schatzker type Ⅲ) were treated using robot-assisted fracture reduction and fixation combined with arthroscopic exploration, with simultaneous treatment of concomitant ligament or meniscus tears. There were 3 males and 5 females with an average age of 54.1 years (range, 42-68 years). Injury mechanisms included traffic accidents (3 cases) and falls (5 cases). The time from injury to operation ranged from 2 to 4 days (mean, 3.1 days). Operation time, intraoperative blood loss, hospital stay duration, visual analogue scale (VAS) score for pain, and complications were recorded. Fracture healing and knee Rasmussen scores were assessed radiographically, while knee function was evaluated using range of motion and Hospital for Special Surgery (HSS) scores.
RESULTS:
All operations were successfully completed. The operation time was 108-129 minutes (mean, 120.1 minutes). The intraoperative blood loss was 10-100 mL (mean, 41.3 mL). The hospital stay duration was 4-7 days (mean, 5.6 days). All incisions healed by first intention without complication such as peroneal nerve injury, vascular damage, or infection. All patients were followed up 32-48 weeks (mean, 40 weeks). Radiographic follow-up confirmed that the knee Rasmussen scores rated as excellent in 8 patients and all fractures healed with the healing time of 12-16 weeks (mean, 13.5 weeks). The VAS score for pain was 2-4 (mean, 2.8) at discharge and improved to 0 at 1 month after operation. The knee range of motion was 80°-110° (mean, 96.1°) at discharge and increased to 135°-140° (mean, 137.9°) at 1 month after operation. At 3 months after operation, the HSS score was 91-94 (mean, 92.8), all graded as excellent. No severe complication, including implant failure, occurred during follow-up.
CONCLUSION
For posterolateral depressed tibial plateau fractures, the minimally invasive approach combining robot-assisted fracture reduction and fixation with arthroscopic exploration demonstrates multiple advantages, including shorter operation time, reduced intraoperative blood loss, excellent wound healing, fewer complications, and rapid recovery of knee function. This technique achieves satisfactory short-term effectiveness, while its long-term effectiveness requires further evaluation.
Humans
;
Male
;
Tibial Fractures/surgery*
;
Female
;
Middle Aged
;
Adult
;
Arthroscopy/methods*
;
Minimally Invasive Surgical Procedures/methods*
;
Fracture Fixation, Internal/methods*
;
Aged
;
Treatment Outcome
;
Robotic Surgical Procedures/methods*
;
Operative Time
;
Range of Motion, Articular
;
Fracture Healing
;
Length of Stay
;
Tibial Plateau Fractures
4.Astragaloside IV delayed the epithelial-mesenchymal transition in peritoneal fibrosis by inhibiting the activation of EGFR and PI3K-AKT pathways.
Ying HUANG ; Chen-Ling CHU ; Wen-Hui QIU ; Jia-Yi CHEN ; Lu-Xi CAO ; Shui-Yu JI ; Bin ZHU ; Guo-Kun WANG ; Quan-Quan SHEN
Journal of Integrative Medicine 2025;23(6):694-705
OBJECTIVE:
Peritoneal fibrosis (PF) is an adverse event that occurs during long-term peritoneal dialysis, significantly impairing treatment efficiency and adversely affecting patient outcomes. Astragaloside IV (AS-IV), a principal active component derived from Astragalus membranaceus (Fisch.) Bunge, has exhibited anti-inflammatory and antifibrotic effects in various settings. This study aims to investigate the potential therapeutic efficacy and mechanism of AS-IV in the treatment of PF.
METHODS:
The PF mouse model was established by intraperitoneal injection of 4.25% peritoneal dialysis fluid (100 mL/kg). The epithelial-mesenchymal transition (EMT) of HMrSV5 cells was induced by the addition of 10 ng/mL transforming growth factor β (TGF-β). The differentially expressed genes in HMrSV5 cells treated with AS-IV were screened using transcriptome sequencing analysis. The potential targets of AS-IV were screened using network pharmacology and analyzed using molecular docking and molecular dynamics simulations.
RESULTS:
Administration of AS-IV at doses of 20, 40, or 80 mg/kg effectively mitigated the increase in peritoneal thickness and the development of fibrosis in mice with PF. The expression of the fibrosis marker α-smooth muscle actin in the peritoneum was significantly decreased in AS-IV-treated mice. The treatment of AS-IV (10, 20, and 40 μmol/L) significantly delayed the EMT of HMrSV5 cells induced by TGF-β, as demonstrated by the decreased number of 5-ethynyl-2'-deoxyuridine-positive cells, reduced migrated area, and decreased expression of fibrosis markers. A total of 460 differentially expressed genes were detected in AS-IV-treated HMrSV5 cells through transcriptome sequencing, with notable enrichment in the phosphatidylinositol-4,5-bisphosphate 3-kinase (PI3K)-AKT serine/threonine kinase 1 (AKT) signaling pathway. The reduced levels of phosphorylated PI3K (p-PI3K) and p-AKT were detected in HMrSV5 cells with AS-IV treatment. Epidermal growth factor receptor (EGFR) was predicted as a direct target of AS-IV, exhibiting strong hydrogen bond interactions. The activation of the PI3K-AKT pathway by the compound 740Y-P, and the activation of the EGFR pathway by NSC 228155 each partially counteracted the inhibitory effect of AS-IV on the EMT of HMrSV5 cells.
CONCLUSION
AS-IV delayed the EMT process in peritoneal mesothelial cells and slowed the progression of PF, potentially serving as a therapeutic agent for the early prevention and treatment of PF. Please cite this article as: Huang Y, Chu CL, Qiu WH, Chen JY, Cao LX, Ji SY, Zhu B, Wang GK, Shen QQ. Astragaloside IV delayed the epithelial-mesenchymal transition in peritoneal fibrosis by inhibiting the activation of EGFR and PI3K-AKT pathways. J Integr Med. 2025; 23(6):694-705.
Epithelial-Mesenchymal Transition/drug effects*
;
Animals
;
Saponins/pharmacology*
;
Triterpenes/pharmacology*
;
Mice
;
Peritoneal Fibrosis/pathology*
;
Proto-Oncogene Proteins c-akt/metabolism*
;
ErbB Receptors/metabolism*
;
Phosphatidylinositol 3-Kinases/metabolism*
;
Signal Transduction/drug effects*
;
Male
;
Humans
;
Molecular Docking Simulation
;
Cell Line
;
Mice, Inbred C57BL
5.Causal Associations between Particulate Matter 2.5 (PM 2.5), PM 2.5 Absorbance, and Inflammatory Bowel Disease Risk: Evidence from a Two-Sample Mendelian Randomization Study.
Xu ZHANG ; Zhi Meng WU ; Lu ZHANG ; Bing Long XIN ; Xiang Rui WANG ; Xin Lan LU ; Gui Fang LU ; Mu Dan REN ; Shui Xiang HE ; Ya Rui LI
Biomedical and Environmental Sciences 2025;38(2):167-177
OBJECTIVE:
Several epidemiological observational studies have related particulate matter (PM) exposure to Inflammatory bowel disease (IBD), but many confounding factors make it difficult to draw causal links from observational studies. The objective of this study was to explore the causal association between PM 2.5 exposure, its absorbance, and IBD.
METHODS:
We assessed the association of PM 2.5 and PM 2.5 absorbance with the two primary forms of IBD (Crohn's disease [CD] and ulcerative colitis [UC]) using Mendelian randomization (MR) to explore the causal relationship. We conducted two-sample MR analyses with aggregated data from the UK Biobank genome-wide association study. Single-nucleotide polymorphisms linked with PM 2.5 concentrations or their absorbance were used as instrumental variables (IVs). We used inverse variance weighting (IVW) as the primary analytical approach and four other standard methods as supplementary analyses for quality control.
RESULTS:
The results of MR demonstrated that PM 2.5 had an adverse influence on UC risk (odds ratio [ OR] = 1.010; 95% confidence interval [ CI] = 1.001-1.019, P = 0.020). Meanwhile, the results of IVW showed that PM 2.5 absorbance was also causally associated with UC ( OR = 1.012; 95% CI = 1.004-1.019, P = 0.002). We observed no causal relationship between PM 2.5, PM 2.5 absorbance, and CD. The results of sensitivity analysis indicated the absence of heterogeneity or pleiotropy, ensuring the reliability of MR results.
CONCLUSION
Based on two-sample MR analyses, there are potential positive causal relationships between PM 2.5, PM 2.5 absorbance, and UC.
Humans
;
Mendelian Randomization Analysis
;
Particulate Matter/analysis*
;
Polymorphism, Single Nucleotide
;
Inflammatory Bowel Diseases/genetics*
;
Air Pollutants/analysis*
;
Crohn Disease/genetics*
;
Colitis, Ulcerative/genetics*
;
Genome-Wide Association Study
;
Risk Factors
;
Environmental Exposure
6.Shenlian Extract Protects against Ultrafine Particulate Matter-Aggravated Myocardial Ischemic Injury by Inhibiting Inflammation and Cell Apoptosis.
Shui Qing QU ; Yan LIANG ; Shuo Qiu DENG ; Yu LI ; Yue DAI ; Cheng Cheng LIU ; Tuo LIU ; Lu Qi WANG ; Li Na CHEN ; Yu Jie LI
Biomedical and Environmental Sciences 2025;38(2):206-218
OBJECTIVE:
Emerging evidence suggests that exposure to ultrafine particulate matter (UPM, aerodynamic diameter < 0.1 µm) is associated with adverse cardiovascular events. Previous studies have found that Shenlian (SL) extract possesses anti-inflammatory and antiapoptotic properties and has a promising protective effect at all stages of the atherosclerotic disease process. In this study, we aimed to investigated whether SL improves UPM-aggravated myocardial ischemic injury by inhibiting inflammation and cell apoptosis.
METHODS:
We established a mouse model of MI+UPM. Echocardiographic measurement, measurement of myocardialinfarct size, biochemical analysis, enzyme-linked immunosorbent assay (ELISA), histopathological analysis, Transferase dUTP Nick End Labeling (TUNEL), Western blotting (WB), Polymerase Chain Reaction (PCR) and so on were used to explore the anti-inflammatory and anti-apoptotic effects of SL in vivo and in vitro.
RESULTS:
SL treatment can attenuate UPM-induced cardiac dysfunction by improving left ventricular ejection fraction, fractional shortening, and decreasing cardiac infarction area. SL significantly reduced the levels of myocardial enzymes and attenuated UPM-induced morphological alterations. Moreover, SL significantly reduced expression levels of the inflammatory cytokines IL-6, TNF-α, and MCP-1. UPM further increased the infiltration of macrophages in myocardial tissue, whereas SL intervention reversed this phenomenon. UPM also triggered myocardial apoptosis, which was markedly attenuated by SL treatment. The results of in vitro experiments revealed that SL prevented cell damage caused by exposure to UPM combined with hypoxia by reducing the expression of the inflammatory factor NF-κB and inhibiting apoptosis in H9c2 cells.
CONCLUSION
Overall, both in vivo and in vitro experiments demonstrated that SL attenuated UPM-aggravated myocardial ischemic injury by inhibiting inflammation and cell apoptosis. The mechanisms were related to the downregulation of macrophages infiltrating heart tissues.
Animals
;
Apoptosis/drug effects*
;
Particulate Matter/adverse effects*
;
Mice
;
Male
;
Inflammation/drug therapy*
;
Drugs, Chinese Herbal/therapeutic use*
;
Mice, Inbred C57BL
;
Myocardial Ischemia/drug therapy*
;
Cell Line
7.(Meta)transcriptomic Insights into the Role of Ticks in Poxvirus Evolution and Transmission: A Multicontinental Analysis.
Yu Xi WANG ; Jing Jing HU ; Jing Jing HOU ; Xiao Jie YUAN ; Wei Jie CHEN ; Yan Jiao LI ; Qi le GAO ; Yue PAN ; Shui Ping LU ; Qi CHEN ; Si Ru HU ; Zhong Jun SHAO ; Cheng Long XIONG
Biomedical and Environmental Sciences 2025;38(9):1058-1070
OBJECTIVE:
Poxviruses are zoonotic pathogens that infect humans, mammals, vertebrates, and arthropods. However, the specific role of ticks in transmission and evolution of these viruses remains unclear.
METHODS:
Transcriptomic and metatranscriptomic raw data from 329 sampling pools of seven tick species across five continents were mined to assess the diversity and abundance of poxviruses. Chordopoxviral sequences were assembled and subjected to phylogenetic analysis to trace the origins of the unblasted fragments within these sequences.
RESULTS:
Fifty-eight poxvirus species, representing two subfamilies and 20 genera, were identified, with 212 poxviral sequences assembled. A substantial proportion of AT-rich fragments were detected in the assembled poxviral genomes. These genomic sequences contained fragments originating from rodents, archaea, and arthropods.
CONCLUSION
Our findings indicate that ticks play a significant role in the transmission and evolution of poxviruses. These viruses demonstrate the capacity to modulate virulence and adaptability through horizontal gene transfer, gene recombination, and gene mutations, thereby promoting co-existence and co-evolution with their hosts. This study advances understanding of the ecological dynamics of poxvirus transmission and evolution and highlights the potential role of ticks as vectors and vessels in these processes.
Animals
;
Poxviridae/physiology*
;
Ticks/virology*
;
Phylogeny
;
Transcriptome
;
Evolution, Molecular
;
Poxviridae Infections/virology*
;
Genome, Viral
8.Study on micro wave ablation of lung tumor based on real anatomical model
Ju LIU ; Hong-Jian GAO ; Qi WANG ; Yu-Bo ZHANG ; Hui-Jing HE ; Wei-Wei WU ; Shui-Cai WU
Chinese Medical Equipment Journal 2024;45(9):27-34
Objective To plan microwave antenna puncture direction effectively and realize personalized preoperative simulation by exploring microwave ablation(MWV)outcomes of lung cancer based on real anatomical model.Methods Firstly,a personalized MWA simulation model consisting of the lung tissue,tumor and vascular system was constructed based on the lung CT data of real patients.Secondly,the MWA effect was simulated by coupling 2 physical fields including an electromagnetic field and a biological heat transfer field,so as to determine the volume of the ablation thermocoagulation zone and the temperature distribution of the lung tissue.Finally,the effects of the vascularized network on the ablation results were quantitatively evaluated in terms of conductivity and blood perfusion,and the ablation results were analyzed with different distances between the large vessels and the antennae(5 and 10 mm from the antennae tips)and puncture angles(large vessels parallelling or intersecting with the antennae tips).Results The vascularized network reduced the volume of the thermocoagulation zone by 0.5%to 3.7%,and blood perfusion made the ablation temperature and the volume of the thermocoagulation zone decreased significantly.The cooling effect gradually diminished with the increase of the distance between the large vessels and the antenna.With the same treatment parameters,the thermocoagulation zone formed when the large vessels paralleled with the antenna was obviously larger than that when the vessles intersected with the antenna.Conclusion Personalized MWA simulation analysis based on real CT data contributes to clarifying the temperature distribution and damage estimation close to the actual situation,which provides guidance and reference for precise treatment of the lung tumor and determination of microwave antenna puncture direction.[Chinese Medical Equipment Journal,2024,45(9):27-34]
9.Network Meta-analysis of the effects of different interactive modes of intervention on the rehabilitation of stroke patients
Shui LIU ; Fengling WANG ; Tiantian JIA ; Yunfen SUN
Chinese Journal of Practical Nursing 2024;40(31):2413-2421
Objective:To evaluate the effects of different interaction modes on the rehabilitation outcomes of stroke patients, and to provide reference for caregivers to choose the best interaction mode according to the rehabilitation goals.Methods:Computerized search of Web of Science, PubMed, Cochrane Library, EMbase, CNKI, Wanfang Database, VIP Database, and China Biomedical Literature Database for randomized controlled trials (RCTs) of interaction modes to improve rehabilitation outcomes of stroke patients was performed from the year of database construction to January 8, 2024. Two researchers independently screened the literature according to inclusion and exclusion criteria, evaluated the risk of bias in the included studies, and extracted data from them. Stata16.0 was used for a network meta-analysis.Results:A total of 22 articles were included that met the inclusion and exclusion criteria, involving 2 404 patients and 5 interaction modes, namely Cox health behavior interaction mode, doctor-patient interaction mode, King interaction compliance mode, dual track interaction mode, and online interaction mode. The results of the network Meta-analysis showed that in terms of improving self-care ability, the King interaction model [ SMD(95% CI)=0.25(0.05-0.45)], the network interaction model [ SMD(95% CI)=0.27(0.07-0.48)], and the Cox health behavior interaction model [ SMD(95% CI)=0.37(0.07-0.67)] were all superior to conventional nursing (all P<0.05). In terms of improving motor function, except for the dual track interactive mode, all other modes were superior to conventional nursing ( SMD values were -0.52--0.30, all P<0.05). There was no statistically significant difference in the application effects of different modes in improving the quality of life (all P>0.05). The ranking results of the area under the cumulative ranking probability curve (SUCRA) for improving self-care ability, motor fuction and quality of life were Cox health behavior interaction mode (SUCRA=83.7%), doctor-patient interaction mode (SUCRA=89.5%) and King interaction standard mode (SUCRA=78.2%). Conclusions:The Cox health behavior interaction model can improve the self-care ability of stroke patients, the doctor-patient interaction model can improve the motor function of stroke patients, and the King interaction standard model may have more advantages in improving the quality of life of stroke patients. It is suggested to combine the advantages of the three to maximize the rehabilitation effect of stroke patients.
10.Multicomponent Quantitative Analysis Model of Near Infrared Spectroscopy Based on Convolution Neural Network
Shui YU ; Ke-Wei HUAN ; Lei WANG ; Xiao-Xi LIU ; Xue-Yan HAN
Chinese Journal of Analytical Chemistry 2024;52(5):695-705
Near infrared spectroscopy(NIRS)has emerged as an indispensable analytical technology for quality monitoring in industrial and agricultural production.It is widely used in quantitative analysis in areas such as food,agriculture and medicine.To meet the requirements of industrial and agricultural production,it is particularly important to develop a NIRS quantitative analysis model that can predict the multicomponent of different samples.In this study,the multicomponent quantitative analysis model of NIRS based on convolution neural network(MulCoSpecNet)was proposed.MulCoSpecNet was composed of an encoding and decoding module,an expert module,a gate module,a multicomponent quantitative prediction module,and a hyperparameter optimizer.The spectral noise and random errors were mitigated,and the signal-to-noise ratio was enhanced through up-sampling and down-sampling in the encoding and decoding module.Diverse weightings were employed by the expert module and gate module to construct distinct sub-spectra.The model prediction accuracy and generalization ability were enhanced by the multicomponent quantitative prediction module,which employed convolutional and pooling operations.The hyperparameters in the hyperparameter space were synchronously optimized by the hyperparameter optimizer.By taking public NIRS datasets of grain and corn as examples,the prediction results of MulCoSpecNet were compared with partial least squares(PLS),extreme learning machine(ELM),support vector regression(SVM)and back propagation neural network(BP).The results showed that compared to PLS,the prediction accuracy of MulCoSpecNet to grain and corn were increased by 25.5%?45.2%and 10.0%?35.7%,respectively.Compared to ELM,the prediction accuracy of MulCoSpecNet were increased by 17.8%?38.6%and 18.2%?37.2%,respectively.Compared to SVM,the prediction accuracy of MulCoSpecNet were increased by 33.6%?47.0%and 31.3%?50.7%,respectively.Compared to BP,the prediction accuracy of MulCoSpecNet were increased by 2.0%?58.5%and 29.6%?48.6%,respectively.The issues of low prediction accuracy and poor generalization ability were effectively solved by the MulCoSpecNet,which was a NIRS multicomponent prediction model based on convolutional neural network.It provided a theoretical foundation for establishing non-destructive and high-precision NIRS multicomponent quantitative analysis model.

Result Analysis
Print
Save
E-mail