1.Skeleton Binding Protein 1 of Plasmodium berghei Influences Deformability and Cytoskeletal Ultrastructure of Infected Erythrocyte
Xin-Yue GUO ; Huan-Qi ZHAO ; Yan-Xuan ZHONG ; Ru-Meng JIANG ; Yao-Xian LI ; Lei-Ting PAN ; Qian WANG ; Xiao-Yu SHI
Progress in Biochemistry and Biophysics 2026;53(4):1015-1027
ObjectiveThe malaria parasites remodel the host erythrocyte structure by exporting parasite proteins that interact with the membrane skeleton proteins of red blood cells (RBCs), facilitating their intracellular survival and pathogenicity. Skeleton-binding protein 1 (SBP1) is a conserved exported protein across Plasmodium species. In Plasmodium falciparum, SBP1 has been reported to interact with erythrocyte membrane skeleton proteins 4.1R and spectrin, while its contribution to erythrocyte remodeling and parasite virulence in Plasmodium berghei (Pb) remains unclear. This study aims to determine whether PbSBP1 associates with the host cytoskeletal protein 4.1R and to investigate its role in the remodeling of host RBCs and the pathogenicity of Plasmodium berghei. MethodsIn Plasmodium berghei, the relationship between PbSBP1 and the erythrocyte cytoskeletal protein 4.1R was examined using co-immunoprecipitation. A Pbsbp1 gene knockout mutant of Plasmodium berghei (Pbsbp1∆) was generated based on the principle of double crossover homologous recombination. The deformability of erythrocytes infected with Pbsbp1∆ parasites was assessed using microfluidic methods. Microchannels with an array of cylindrical pillars were used to detect modifications in infected RBC deformability. The infected RBCs were squashed between the rows and recovered between the columns and the transit velocity (μm/s) of infected RBCs travelling through the microchannel was recorded. The component of the erythrocyte membrane skeleton junctional complex, tropomodulin (TMOD), was fluorescently labeled, and the cytoskeletal network of infected erythrocytes was imaged using super-resolution stochastic optical reconstruction microscopy (STORM) to analyze ultrastructural changes in the cytoskeleton of wild-type (WT) and Pbsbp1∆-infected erythrocytes. Actin-based junctional complexes were displayed as individual clusters by the labeled TMOD in the STORM images, and the cluster densities and distances between adjacent clusters of infected RBCs were calculated. Additionally, rodent malaria models (BALB/c mice) and experimental cerebral malaria models (C57BL/6 mice) were employed to monitor the growth of Pbsbp1∆ and WT parasites during the intraerythrocytic stage and their capacity to induce cerebral malaria in mice. ResultsPbSBP1 may participate in the remodeling of infected erythrocytes through direct or indirect interaction with the erythrocyte cytoskeletal protein 4.1R. Microfluidic assays revealed that the deformability of erythrocytes infected with Pbsbp1∆ parasites was significantly enhanced compared to those infected with WT parasites. STORM imaging further demonstrated that the ultrastructure of the erythrocyte cytoskeleton in Pbsbp1∆-infected cells was altered relative to that in WT-infected erythrocytes. The distances between nearest neighbors of clusters had a tendency to increase while the cluster densities were decreased in Pbsbp1∆-infected RBCs compared to WT-infected RBCs. Subsequent phenotypic analysis indicated that the growth rate of Pbsbp1∆ parasites during the intraerythrocytic stage was significantly slower than that of WT parasites, and their ability to induce cerebral malaria in mice was also attenuated. These findings suggest that PbSBP1 is involved in the remodeling of the erythrocyte membrane skeleton, likely through its direct or indirect interaction with protein 4.1R, thereby regulating the deformability of infected erythrocytes and influencing the pathogenicity of the blood-stage parasites. ConclusionThis study establishes a role for PbSBP1 in host erythrocyte remodeling and parasite virulence, providing new research strategies for the prevention and treatment of malaria.
2.Clinical application of KASP-based RHCE genotyping in RhD-positive patients
Xiaoyu LIAN ; Mengdan LI ; Xiaoyu GUAN ; Li TIAN ; Chenying WANG ; Di WU ; Tianqiong LUO ; Xiaolin DU ; Xin JI ; Haixia XU ; Jue WANG ; Ling LI ; Zhong LIU
Chinese Journal of Blood Transfusion 2026;39(5):596-602
Objective: To develop a RHCE genotyping assay based on kompetitive allele-specific PCR (KASP) and assess its clinical accuracy for RhCE blood group determination. Methods: KASP primers were designed to interrogate three RHCE loci: the 109 bp insertion/deletion in intron 2, c. 307T>C, and c. 676C>G. A total of 1 194 RhD-positive inpatients from Chengdu were typed by both KASP genotyping and manual tube serology. Discordant samples (n=10) were retested by both methods and further resolved by Sanger sequencing. An additional 377 cases were tested for the c. 48C>G locus to evaluate the predictive accuracy of individual loci and combined locus testing for RhC antigen. Results: Genotyping concordance with serology was 100.0% for both the c. 676C>G locus (RhE/Rhe) and the c. 307T>C locus (Rhc). For RhC prediction using the 109 bp insertion, overall accuracy was 99.7% (1 191/1 194); the 3 discordant cases were confirmed by Sanger sequencing to be false negatives attributable to 109 bp deletion in intron 2. Testing the c. 48C>G allele for RhC prediction yielded 7 false positives, with an accuracy of 98.1% (370/377). RhC antigen status was determined by combining the 109 bp insertion and the c. 48C allele. After excluding 10 samples with inconsistent results between the two loci, the accuracy reached 100% in the remaining 367 samples. When both loci were applied in combination, accuracy reached 100% in the 367 cases with concordant results. Among the 1 194 patients, CCee (45.8%) and CcEe (31.7%) were the most common RhCE phenotypes. The e antigen had the highest positivity rate (92.2%), and the Ce haplotype was the most frequent (66.9%). Conclusion: The KASP-based RHCE genotyping method achieves high accuracy for clinical RhCE typing. Combining the 109 bp insertion/deletion with the c. 48C allele significantly improves RhC antigen prediction compared with either locus alone. This method was applied to RhCE genotyping of 1 194 RhD-positive inpatients in Chengdu, providing local RhCE phenotype and haplotype distribution data to support RhCE-matched transfusion practice.
3.Immunodynamic changes in a mouse model of malignant pleural effusion
Xiao-Lei WEI ; Xu GUO ; Chuang-Xin ZHANG ; Qi WANG ; Xiao-Fan LIU ; Ming-Ming SHAO ; Huan-Zhong SHI ; Kan ZHAI
Laboratory Animal Research 2026;42(1):59-67
Background:
Malignant pleural effusion (MPE), a common complication of advanced cancers, is associated with poor prognosis and reduced quality of life. Although host–tumor interactions are known to drive MPE development, the associated immune dynamics during disease progression remain unclear. Using a Lewis lung carcinoma-induced MPE model in C57BL/6JNidfc mice, we systematically evaluated general parameters and immune cell changes at two-day intervals throughout disease progression.
Results:
The day of Lewis lung carcinoma cell injection into the pleural space was designated as day 0. By day 10 post-injection (p.i.), MPE-bearing mice exhibited ~ 10% body weight loss, marking the experimental endpoint. Pleural tumor mass and pleural effusion volume were minimal up to day 4 p.i. but increased sharply from day 6 onward.CD45⁺ immune cell counts rose over time, and days 6, 8, and 10 p.i. marked key stages of MPE progression. On day 6, B cells, T cells, and natural killer cells, but not macrophages and neutrophils, increased significantly compared to earlier timepoints. By day 8, all immune cell subsets except T cells exceeded day 6 levels, and at day 10, natural killer cell numbers declined while others continued to increase. Besides, the numbers of CD8⁺ T cells, Th1 cells, regulatory T cells, and M2 macrophages progressively increased from day 6 to 10. Based on these data, days 6 and 10 were defined as early and advanced MPE stages, respectively, with distinct immune phenotypes. In advanced MPE, CD8⁺ T cells displayed reduced IFN-γ, TNF-α, Granzyme B, Perforin, FasL, and Ki-67, but upregulated PD-1 and CTLA-4 relative to early stage. Similarly, Th1 cells showed decreased IFN-γ, TNF-α, and IL-2 production along with reduced Ki-67 expression. Advanced-stage M2 macrophages exhibited lower MHC-II levels and impaired phagocytosis, but higher PD-L1 and IL-10 production, while neutrophils showed reduced TNF-α release and phagocytic activity.
Conclusions
Our findings characterize the temporal immune dynamics associated with MPE progression in a mouse model, revealing a transition from an early immunostimulatory state to a late immunosuppressive state. This study enhances our understanding of MPE immunopathogenesis and provides a foundation for developing precise, stagespecific therapeutic strategies.
4.Guidelines for the perioperative diagnosis and treatment of oncogene-driven non-small cell lung cancer (2026)
Weidong WANG ; Yongbin LIN ; Hui TIAN ; Gaofeng LI ; Shun XU ; Yongde LIAO ; Haitao MA ; Junfeng LIU ; Chundong GU ; Xiaolong YAN ; Shumin WANG ; Daqiang SUN ; Jianyang LIU ; Tao XUE ; Shaohua MA ; Zhigang LI ; Shuanghu YUAN ; Gen LIN ; Ling CAI ; Jianping ZHOU ; Wenzhao ZHONG ; Naixin LIANG ; Yi HAN ; Junfeng WANG ; Weidong ZHANG ; Xin WANG ; Lianjuan CHEN ; Lunxu LIU ; Xiuyi ZHI ; Lanjun ZHANG
Chinese Journal of Clinical Thoracic and Cardiovascular Surgery 2026;33(09):1337-1353
Lung cancer constitutes the most prevalent and lethal malignant tumor in China. Approximately 85% of lung cancer diagnoses correspond to the non-small cell histological subtype [non-small cell lung cancer (NSCLC)]. Despite surgery being the mainstay for early-stage disease, postoperative recurrence remains high and adjuvant chemotherapy offers limited benefit. In recent years, targeted therapy has demonstrated substantial advantages in driver mutation-positive NSCLC. To this end, the Lung Cancer Medical Education Committee of the Chinese Medical Education Association developed guidelines based on a systematic review of evidence through November 2025, using the Grading of Recommendations, Assessment, Development and Evaluations (GRADE) approach and a modified Delphi method. Focusing on epidermal growth factor receptor (EGFR) and anaplastic lymphoma kinase (ALK), and addressing ROS proto-oncogene 1 (ROS1), B-Raf proto-oncogene serine/threonine kinase (BRAF) V600E mutation, and mesenchymal-epithelial transition factor (MET) exon 14 (METex14) skipping, the guideline covers molecular testing, neoadjuvant/adjuvant therapy, perioperative strategies, minimal residual disease monitoring, and postoperative surveillance. It defines testing requirements, specifies stage-directed and subtype-specific treatments, and standardizes minimal residual disease monitoring. These recommendations emphasize precision and feasibility to improve survival and quality of life.
5.Process Optimization and Health Risk Assessment of Calcined Haematitum Based on QbD Concept
Yue YANG ; Jingwei ZHOU ; Jialiang ZOU ; Guorong MEI ; Yifan SHI ; Lei ZHONG ; Jiaojiao WANG ; Xuelian GAN ; Dewen ZENG ; Xin CHEN ; Lin CHEN ; Hongping CHEN ; Shilin CHEN ; Yuan HU ; Youping LIU
Chinese Journal of Experimental Traditional Medical Formulae 2025;31(13):187-196
ObjectiveTo investigate the processing technology of calcined Haematitum based on the concept of quality by design(QbD) and to assess its health risk. MethodsTaking whole iron content, Fe2+ dissolution content and looseness as critical quality attributes(CQAs), and calcination temperature, calcination time, spreading thickness and particle size as critical process parameters(CPPs) determined by the failure mode and effect analysis(FMEA), the processing technology of calcined Haematitum was optimized by orthogonal test combined with analytic hierarchy process-criteria importance through intercriteria correlation(AHP-CRITIC) hybrid weighting method. The contents of heavy metals and harmful elements were determined by inductively coupled plasma mass spectrometry, and the health risk assessment was carried out by daily exposure(EXP), target hazard quotient(THQ) and lifetime cancer risk(LCR), and the theoretical value of the maximum limit was deduced. ResultsThe optimal processing technology for calcined Haematitum was calcination at 650 ℃, calcination time of 1 h, particle size of 0.2-0.5 cm, spreading thickness of 1 cm, and vinegar quenching for 1 time[Haematitum-vinegar(10:3)]. The contents of 5 heavy metals and harmful elements in 13 batches of calcined Haematitum were all decreased with reductions of up to 5-fold. The cumulative THQ of 2 batches of samples was>1, while the cumulative THQ of all batches of Haematitum was>1. The LCR of As in 1 batches of Haematitum was 1×10-6-1×10-4, and the LCR of the rest was<1×10-6, and the LCRs of calcined Haematitum were all<1×10-6, indicating that the carcinogenic risk of calcined Haematitum was low, but special attention should still be paid to Haematitum medicinal materials. Preliminary theoretical values of the maximum limits of Cu, As, Cd, Pb and Hg were formulated as 1 014, 25, 17, 27, 7 mg·kg-1. ConclusionThe optimized processing technology of calcined Haematitum is stable and feasible, and the contents of heavy metals and harmful elements are reduced after processing. Preliminary theoretical values of the maximum limits of Cu, As, Cd, Pb and Hg are formulated to provide a scientific basis for the formulation of standards for the limits of harmful elements in Haematitum.
6.Process Optimization and Health Risk Assessment of Calcined Haematitum Based on QbD Concept
Yue YANG ; Jingwei ZHOU ; Jialiang ZOU ; Guorong MEI ; Yifan SHI ; Lei ZHONG ; Jiaojiao WANG ; Xuelian GAN ; Dewen ZENG ; Xin CHEN ; Lin CHEN ; Hongping CHEN ; Shilin CHEN ; Yuan HU ; Youping LIU
Chinese Journal of Experimental Traditional Medical Formulae 2025;31(13):187-196
ObjectiveTo investigate the processing technology of calcined Haematitum based on the concept of quality by design(QbD) and to assess its health risk. MethodsTaking whole iron content, Fe2+ dissolution content and looseness as critical quality attributes(CQAs), and calcination temperature, calcination time, spreading thickness and particle size as critical process parameters(CPPs) determined by the failure mode and effect analysis(FMEA), the processing technology of calcined Haematitum was optimized by orthogonal test combined with analytic hierarchy process-criteria importance through intercriteria correlation(AHP-CRITIC) hybrid weighting method. The contents of heavy metals and harmful elements were determined by inductively coupled plasma mass spectrometry, and the health risk assessment was carried out by daily exposure(EXP), target hazard quotient(THQ) and lifetime cancer risk(LCR), and the theoretical value of the maximum limit was deduced. ResultsThe optimal processing technology for calcined Haematitum was calcination at 650 ℃, calcination time of 1 h, particle size of 0.2-0.5 cm, spreading thickness of 1 cm, and vinegar quenching for 1 time[Haematitum-vinegar(10:3)]. The contents of 5 heavy metals and harmful elements in 13 batches of calcined Haematitum were all decreased with reductions of up to 5-fold. The cumulative THQ of 2 batches of samples was>1, while the cumulative THQ of all batches of Haematitum was>1. The LCR of As in 1 batches of Haematitum was 1×10-6-1×10-4, and the LCR of the rest was<1×10-6, and the LCRs of calcined Haematitum were all<1×10-6, indicating that the carcinogenic risk of calcined Haematitum was low, but special attention should still be paid to Haematitum medicinal materials. Preliminary theoretical values of the maximum limits of Cu, As, Cd, Pb and Hg were formulated as 1 014, 25, 17, 27, 7 mg·kg-1. ConclusionThe optimized processing technology of calcined Haematitum is stable and feasible, and the contents of heavy metals and harmful elements are reduced after processing. Preliminary theoretical values of the maximum limits of Cu, As, Cd, Pb and Hg are formulated to provide a scientific basis for the formulation of standards for the limits of harmful elements in Haematitum.
7.Analysis of red blood cell transfusion reactions in China from 2018 to 2023
Bo PAN ; Xiaoyu GUAN ; Jue WANG ; Yunlong PAN ; Liu HE ; Haixia XU ; Xin JI ; Li TIAN ; Ling LI ; Zhong LIU
Chinese Journal of Blood Transfusion 2025;38(5):704-710
Objective: To analyze the demographic characteristics of patients with red blood cell transfusion reactions, the usage of red blood cell preparations, and the differences in the composition ratio of adverse reactions based on multi-center data from the Haemovigilance Network, in order to reveal the clinical characteristics of red blood cell transfusion and its underlying issues. Methods: Clinical data of patients who experienced transfusion reactions after red blood cell transfusion in the Haemovigilance Network from 2018 to 2023 were collected. The demographic characteristics of patients who experienced transfusion reactions with different types of red blood cell preparations, the utilization of these preparations, and the differences of the composition ratios of transfusion reactions were analyzed. Count data were expressed as numbers (n) or percentages (%), and comparisons between groups were performed using the Chi-square test. Results: Red blood cell transfusion reactions were more common in females (53.56%), with the majority of patients aged 50-69 years (35.54%). The Han polulation accounted for the vast majority of patients (92.77%), and patients in the hematology and obstetrics/gynecology departments had a relatively high proportion of transfusion reactions (13.26% and 14.26%, respectively). Leukocyte-reduced red blood cells and suspended red blood cells were the most common types of transfusion reactions reported among red blood cell preparations. Allergic reactions and non-hemolytic febrile reactions were the most common transfusion reactions, and there were significant differences in the composition ratios of allergic reactions (χ
=869.89, P<0.05) and non-hemolytic febrile reactions (χ
=812.75, P<0.05) across various types of red blood cell preparations. Conclusion: There are differences in the demographic characteristics and composition ratio of transfusion reactions among different red blood cell preparations. The management of red blood cell transfusion reactions should be tailored to patient characteristics and conditions, and the selection and use of blood products should be optimized to reduce or avoid the occurrence of transfusion reactions, such as considering the use of washed red blood cells for patients with a history of transfusion allergies or those prone to allergies.
8.Research of injury mapping relationship of lumbar spine in reclined occupants between anthropomorphic test devices and human body model.
Yu LIU ; Jing FEI ; Xin-Ming WAN ; Pei-Feng WANG ; Zhen LI ; Xiao-Ting YANG ; Lin-Wei ZHANG ; Zhong-Hao BAI
Chinese Journal of Traumatology 2025;28(2):130-137
PURPOSE:
To judge the injury mode and injury severity of the real human body through the measured values of anthropomorphic test devices (ATD) injury indices, the mapping relationship of lumbar injury between ATD and human body model (HBM) was explored.
METHODS:
Through the ATD model and HBM simulation, the mapping relationship of lumbar injury between the 2 subjects was explored. The sled environment consisted of a semi-rigid seat with an adjustable seatback angle and a 3-point seat belt system with a seatback-mounted D-ring. Three seatback recline states of 25°, 45°, and 65° were designed, and the seat pan angle was maintained at 15°. A 23 g, 47 km/h pulse was used. The validity of the finite element model of the sled was verified by the comparison of ATD simulation and test results. ATD model was the test device for human occupant restraint for autonomous vehicles (THOR-AV) dummy model and HBM was the total human model for safety (THUMS) v6.1. The posture of the 2 models was adjusted to adapt to the 3 seat states. The lumbar response of THOR-AV and the mechanical and biomechanical data on L1 - L5 vertebrae of THUMS were output, and the response relationship between THOR-AV and THUMS was descriptive statistically analyzed.
RESULTS:
Both THOR-AV and THUMS were submarined in the 65° seatback angle case. With the change of seatback angle, the lumbar spine axial compression force (Fz) of THOR-AV and THUMS changed in the similar trend. The maximum Fz ratio of THOR-AV to THUMS at 25° and 45° seatback angle cases were 1.6 and 1.7. The flexion moment (My) and the time when the maximum My occurred in the 2 subjects were very different. In particular, the form of moment experienced by the L1 - L5 vertebrae of THUMS also changed. The changing trend of My measured by THOR-AV over time can reflect the changing trend of maximum stress of L1 and L2 of THUMS.
CONCLUSION
The Fz of ATD and HBM presents a certain proportional relationship, and there is a mapping relationship between the 2 subjects on Fz. The mapping function can be further clarified by applying more pulses and adopting more seatback angles. It is difficult to map My directly because they are very different in ATD and HBM. The My of ATD and stress of HBM lumbar showed a similar change trend over time, and there may be a hidden mapping relationship.
Humans
;
Lumbar Vertebrae/injuries*
;
Finite Element Analysis
;
Biomechanical Phenomena
;
Manikins
;
Spinal Injuries/physiopathology*
9.Prediction of Pharmacoresistance in Drug-Naïve Temporal Lobe Epilepsy Using Ictal EEGs Based on Convolutional Neural Network.
Yiwei GONG ; Zheng ZHANG ; Yuanzhi YANG ; Shuo ZHANG ; Ruifeng ZHENG ; Xin LI ; Xiaoyun QIU ; Yang ZHENG ; Shuang WANG ; Wenyu LIU ; Fan FEI ; Heming CHENG ; Yi WANG ; Dong ZHOU ; Kejie HUANG ; Zhong CHEN ; Cenglin XU
Neuroscience Bulletin 2025;41(5):790-804
Approximately 30%-40% of epilepsy patients do not respond well to adequate anti-seizure medications (ASMs), a condition known as pharmacoresistant epilepsy. The management of pharmacoresistant epilepsy remains an intractable issue in the clinic. Its early prediction is important for prevention and diagnosis. However, it still lacks effective predictors and approaches. Here, a classical model of pharmacoresistant temporal lobe epilepsy (TLE) was established to screen pharmacoresistant and pharmaco-responsive individuals by applying phenytoin to amygdaloid-kindled rats. Ictal electroencephalograms (EEGs) recorded before phenytoin treatment were analyzed. Based on ictal EEGs from pharmacoresistant and pharmaco-responsive rats, a convolutional neural network predictive model was constructed to predict pharmacoresistance, and achieved 78% prediction accuracy. We further found the ictal EEGs from pharmacoresistant rats have a lower gamma-band power, which was verified in seizure EEGs from pharmacoresistant TLE patients. Prospectively, therapies targeting the subiculum in those predicted as "pharmacoresistant" individual rats significantly reduced the subsequent occurrence of pharmacoresistance. These results demonstrate a new methodology to predict whether TLE individuals become resistant to ASMs in a classic pharmacoresistant TLE model. This may be of translational importance for the precise management of pharmacoresistant TLE.
Epilepsy, Temporal Lobe/diagnosis*
;
Animals
;
Drug Resistant Epilepsy/drug therapy*
;
Electroencephalography/methods*
;
Rats
;
Anticonvulsants/pharmacology*
;
Neural Networks, Computer
;
Male
;
Humans
;
Phenytoin/pharmacology*
;
Adult
;
Disease Models, Animal
;
Female
;
Rats, Sprague-Dawley
;
Young Adult
;
Convolutional Neural Networks
10.Risk prediction of Reduning Injection batches by near-infrared spectroscopy combined with multiple machine learning algorithms.
Wen-Yu JIA ; Feng TONG ; Heng-Xu LIU ; Shu-Qin JIN ; Yong-Chao ZHANG ; Chen-Feng ZHANG ; Zhen-Zhong WANG ; Xin ZHANG ; Wei XIAO
China Journal of Chinese Materia Medica 2025;50(2):430-438
In this paper, near-infrared spectroscopy(NIRS) was employed to analyze 129 batches of commercial products of Reduning Injection. The batch reporting rate was estimated according to the report of Reduning Injection in the direct adverse drug reaction(ADR) reporting system of the drug marketing authorization holder of the Center for Drug Reevaluation of the National Medical Products Administration(National Center for ADR Monitoring) from August 2021 to August 2022. According to the batch reporting rate, the samples of Reduning Injection were classified into those with potential risks and those being safe. No processing, random oversampling(ROS), random undersampling(RUS), and synthetic minority over-sampling technique(SMOTE) were then employed to balance the unbalanced data. After the samples were classified according to appropriate sampling methods, competitive adaptive reweighted sampling(CARS), successive projections algorithm(SPA), uninformative variables elimination(UVE), and genetic algorithm(GA) were respectively adopted to screen the features of spectral data. Then, support vector machine(SVM), logistic regression(LR), k-nearest neighbors(KNN), naive bayes(NB), random forest(RF), and artificial neural network(ANN) were adopted to establish the risk prediction models. The effects of the four feature extraction methods on the accuracy of the models were compared. The optimal method was selected, and bayesian optimization was performned to optimize the model parameters to improve the accuracy and robustness of model prediction. To explore the correlations between potential risks of clinical use and quality test data, TreeNet was employed to identify potential quality parameters affecting the clinical safety of Reduning Injection. The results showed that the models established with the SVM, LR, KNN, NB, RF, and ANN algorithms had the F1 scores of 0.85, 0.85, 0.86, 0.80, 0.88, and 0.85 and the accuracy of 88%, 88%, 88%, 85%, 91%, and 88%, respectively, and the prediction time was less than 5 s. The results indicated that the established models were accurate and efficient. Therefore, near infrared spectroscopy combined with machine learning algorithms can quickly predict the potential risks of clinical use of Reduning Injection in batches. Three key quality parameters that may affect clinical safety were identified by TreeNet, which provided a scientific basis for improving the safety standards of Reduning Injection.
Spectroscopy, Near-Infrared/methods*
;
Drugs, Chinese Herbal/administration & dosage*
;
Machine Learning
;
Algorithms
;
Humans
;
Quality Control

Result Analysis
Print
Save
E-mail