OBJECTIVE: Rheumatoid arthritis (RA) is a systemic autoimmune disease that affects the small joints of the whole body and degrades the patients' quality of life. Zhengqing Fengtongning (ZF) is a traditional Chinese medicine preparation used to treat RA. ZF may cause liver injury. In this study, we aimed to develop a prediction model for abnormal liver function caused by ZF. METHODS: This retrospective study collected data from multiple centers from January 2018 to April 2023. Abnormal liver function was set as the target variable according to the alanine transaminase (ALT) level. Features were screened through univariate analysis and sequential forward selection for modeling. Ten machine learning and deep learning models were compared to find the model that most effectively predicted liver function from the available data. RESULTS: This study included 1,913 eligible patients. The LightGBM model exhibited the best performance (accuracy = 0.96) out of the 10 learning models. The predictive metrics of the LightGBM model were as follows: precision = 0.99, recall rate = 0.97, F1_score = 0.98, area under the curve (AUC) = 0.98, sensitivity = 0.97 and specificity = 0.85 for predicting ALT < 40 U/L; precision = 0.60, recall rate = 0.83, F1_score = 0.70, AUC = 0.98, sensitivity = 0.83 and specificity = 0.97 for predicting 40 ≤ ALT < 80 U/L; and precision = 0.83, recall rate = 0.63, F1_score = 0.71, AUC = 0.97, sensitivity = 0.63 and specificity = 1.00 for predicting ALT ≥ 80 U/L. ZF-induced abnormal liver function was found to be associated with high total cholesterol and triglyceride levels, the combination of TNF-α inhibitors, JAK inhibitors, methotrexate + nonsteroidal anti-inflammatory drugs, leflunomide, smoking, older age, and females in middle-age (45-65 years old). CONCLUSION This study developed a model for predicting ZF-induced abnormal liver function, which may help improve the safety of integrated administration of ZF and Western medicine. Please cite this article as: Yu Z, Kou F, Gao Y, Lyu CM, Gao F, Wei H. A machine learning model for predicting abnormal liver function induced by a Chinese herbal medicine preparation (Zhengqing Fengtongning) in patients with rheumatoid arthritis based on real-world study. J Integr Med. 2025; 23(1): 25-35.
Humans ; Arthritis, Rheumatoid/drug therapy* ; Drugs, Chinese Herbal/therapeutic use* ; Female ; Middle Aged ; Male ; Retrospective Studies ; Machine Learning ; Adult ; Aged ; Liver/physiopathology* ; Alanine Transaminase/blood*

The influence of material properties on fingerprint development effects were systematically studied.Firstly,carbon dots/NaYF4 and Cu nanoclusters/starch nanocomposites respectively possessing different fluorescent intensities and dual fluorescent colors,as well as NaYF4 micro-/nano-materials exhibiting different morphologies,sizes,and surface properties were chemically synthesized and further used for latent fingerprint development.Then,the developing effects were comprehensively evaluated by visual analysis combining with spectral characterization and Python-based calculation.Finally,the influences of material properties on latent fingerprint development were quantitatively evaluated from three dimensions including contrast,sensitivity,and selectivity.The fluorescence properties of developing materials and substrates could significantly affect the developing contrast,namely,the stronger the developing signal,the higher the contrast;the weaker the background noise,the higher the contrast.The sizes and morphologies of the developing materials could respectively influence the quantity and quality of developed minutiae,and significantly affect the developing sensitivity,namely,the smaller the particle size of developing materials,the more the quantity of developed minutiae and the higher the sensitivity;the smaller the surface area of developing materials,the higher the quality of developed minutiae and the higher the sensitivity.The surface properties together with the sizes and morphologies of developing materials could influence their adsorption performances,and significantly affect the developing selectivity,namely,the stronger the specific adsorption of developing materials with fingerprint substance,and the weaker the non-specific adsorption of developing materials with substrate,the higher the selectivity.Moreover,the fingerprint development using the materials with suitable surface area and appropriate mass would have a high selectivity.

Objective To evaluate the forensic application value of used dental floss as a source of bio-logical evidence for individual identification by analyzing the effects of dental floss sample collection methods,DNA extraction methods,preservation conditions,and sampling sites on the success rate of STR typing.Methods Dental floss samples were collected using three techniques:direct cutting,cotton swab wiping,and flocked swab wiping,respectively.DNA was extracted respectively by the Chelex,spin column-based and magnetic bead-based methods.DNA quantification and STR typing were per-formed using the Qubit kit and FGI HumDNA Typing kit(Platinum),respectively.Storage environ-ments(temperature and humidity,ultraviolet radiation)and sampling locations(the floss part,the handle part)on DNA quantity and STR typing were evaluated.Results Through conducting a statisti-cal analysis of three key indicators of average DNA mass concentration,STR locus detection rate,and typing accuracy rate,the direct cutting method demonstrated the highest efficacy,followed by cotton swab wiping mothed,and the flocked swab wiping method had the lowest efficacy.Direct cutting yielded an average DNA mass concentration greater than(4.94±1.87)ng/μL,with STR locus detection and accuracy rates of 100%.Bead-based DNA extraction method produced superior DNA concentration and quality compared to spin column-based and Chelex methods,regardless of whether the sampling technique used.Preservation conditions had a significant impact on the DNA analysis of samples.Par-ticularly,the STR typing accuracy of samples preserved at 55℃/50%RH for 35 days dropped to(81.82±12.31)%,and that of samples exposed to ultraviolet radiation for 12 h dropped to(55.46±34.31)%.DNA concentration from the handle part of dental floss was extremely low,with an STR typing accuracy of only(30.91±27.35)%.Conclusion Using cotton swabs to wipe or directly cutting the thread of dental floss samples,and combining this approach with the magnetic bead method for DNA extraction,can best guarantee the concentration and quality of DNA.In addition,samples should be stored in low-temperature,low-humidity environment,protected from light and ultraviolet radiation.

Objective To propose a high-precision deep learning-based image assessment method of osteosarcoma chemotherapy efficacy for clinical treatment,as existing methos have low accuracy of osteosarcoma assessment.Methods The low incidence of osteosarcoma led to the small scale of its imaging data and the problem of imbalance in data categories.This study combined deep learning with clinical medical information,combined the bone sarcoma generation module of BoneGAN and the scale lesion information capture module,and proposed OMLA-Net,a deep learning assessment network for chemotherapy effect of bone sarcoma based on multi-scale lesion attention network,which achieved computer-aided bone tumor assessment with integrated data augmentation and focused lesion information through pre-training and generalized loss training.Results In this study,40 cases of osteosarcoma MRI data were used as the basis for the comparison test on the generated dataset,and the OMLA-Net assessment outperformed the SOTA method Conv-LSTM-GAN in terms of the assessment effects such as accuracy and F1 scores,and the difference was statistically significant(Bootstrap statistical method P＜0.05);the subsequent K-fold cross-validation ablation experiments further demonstrated the effectiveness of each module proposed by OMLA-Net.Conclusion OMLA-Net can effectively perform the impact assessment of chemotherapy effect on osteosarcoma,which provides a new idea for subsequent clinical application.

The objective of this study was to analyze the effects on cell viability, apoptosis, and cell cycle of non-small cell lung cancer (NSCLC) A549 cells after intervention with Agrimonia pilosa (AP) and investigate Agrimonia pilosa anti-tumor activity in vitro. Meanwhile, liquid chromatography mass spectrometry (LC-MS) metabolomics technology was used to analyze the changes of cellular metabolites and metabolic pathways. The results of this study will provide a theoretical and experimental basis for investigating the mechanism of the effect of Agrimonia pilosa on non-small cell lung cancer A549 cells. The results showed that the cell nucleus of A549 cells crumpled and apoptosis occurred with the increase of drug concentration. The survival rate of the cells decreased, and the inhibition rate reached 21.5% and 91.74% under the low and high dose conditions, respectively. Lactate dehydrogenase (LDH) content increased (P < 0.05). Metabolomics results showed significant differences in metabolism between groups, thirty-three distinct metabolites including LysoPC(24:0/0:0), LysoPC(17:0/0:0) and PC(O-40:5) were deduced. The pathway enrichment showed that the Agrimonia pilosa plays an anti-tumor role mainly by regulating the metabolism of glycerophosphate and purine in A549 cells, in which the effect on glycerophosphate metabolism pathway was most significant. The results of combined pharmacodynamics suggested that Agrimonia pilosa might induce apoptosis and inhibit the growth of A549 cells by regulating LysoPC(24:0/0:0), LysoPC(17:0/0:0) and PC(O-40:5) metabolites in A549 cells.

Objective To explore the relevant factors of new-onset conduction disturbance(NOCD)after transcatheter aortic valve replacement(TAVR),such as anatomical structure,device type,surgical strategies,etc.,discover relevant predictive factors,and establish a predictive model to assess the risk of conduction blockages.Methods From January 2016 to March 2022,clinical data of symptomatic patients with severe aortic valve stenosis or severe regurgitation who underwent TAVR at Xiangya Second Hospital of Central South University were collected through the hospital information system and imaging database.ECG,echocardiography,CTA,surgical materials,etc.,were extracted and analyzed by specialists.SPSS software was used for statistical analysis,and a multi-factor regression prediction model for NOCDwas built.Results A total of 184 patients were included,the occurrence rate of NOCD after TAVR was 31.0%,pure regurgitation patients'NOCD occurrence rate was 63.6%(7/11).The NOCD group had a larger aortic angles[(57.7±10.3)°vs.(52.0±9.0)°,P＜0.001],larger Oversizing[(129±28)%vs.(120±21)%,P=0.018],deeper implantation depth[(7.2±5.1)mm vs.(4.8±4.2)mm,P=0.001],and higher pure regurgitation patients'proportion[12.3%vs.3.1%,P=0.037]than the non-NOCD group.Multifactorial Logistic regression analysis indicated that an aorta angle＞54.5°(OR 3.78,95%CI 1.86-7.63,P＜0.001)or implantation depth＞5.7 mm(OR 3.39,95%CI 1.68-6.85,P＜0.001)are independent risk factors for new onset conduction disturbances after TAVR,and a predictive model was established with aortic angle,implantation depth,and Oversizing ratio as variables.The receiver operating characteristics curve showed area under ROC curve 0.709,95%CI 0.623-0.795,predicting NOCD after TAVR.Conclusions A retrospective analysis carried out at a single center discovered that the aortic angle in the NOCD group was larger than that in the non-NOCD group,the Oversizing ratio was higher,the implantation location was deeper,and there was a higher proportion of patients with pure regurgitation lesions.An aortic angle greater than 54.5°or an implantation depth more than 5.7 mm were identified as independent risk factors for NOCD after TAVR.

Objective:The main purpose of this study is to analyse the current situation and inequity status of children's medical security in China from the vision of children first.Methods:Using data from the China Family Panel Studies 2020 and based on the framework of universal health coverage cube,multivariate regression is used to analyse the differences in medical security between children and adults and among groups of children.Results:The participation rate of children in China is 80.96%,out-of-pocket ratios are 64.71%and 90.09%for inpatient and outpatient groups respectively.In terms of participation rate,insured children are less than that of adults(OR=0.434,P＜0.01);within children's groups,attending school(OR=2.075,P＜0.01)significantly increases children's participation rate,while left-behind by parent(s)(OR=0.791,P＜0.05)significantly decrease children's participation rate.With respect to service and cost coverage,children have higher out-of-pocket ratios compared to adults(β=0.066,P＜0.01);within children's groups,children eged 6 years and older have lower out-of-pocket medical expenses(β＜-0.316,P＜0.01),children with higher family income(β＜-0.022,P＜0.05),participated(β=-0.033,P＜0.01),and hospitalized(β=-0.270,P＜0.01)have lower out-of-pocket ratios.Conclusion:Double in equality exists in children's medical security in China.The level of children's health security in China is significantly lower than that of adults;within children's groups,children aged 0～5 years,not in school,left-behind by parent(s),and from lower-income families are more vulnerable.It is proposed to focus on increasing the participation rate of children through measures such as optimizing the contribution for children and launching family joint insurance.Policy design should also consider the needs of children and raise the level of children's benefits.Meanwhile,the focus should be on helping vulnerable groups in children,so as to ultimately achieve"children first"in health security.

Objective:To investigate the factors influencing fall risk scores in elderly individuals.Methods:A total of 4 419 individuals were randomly selected using the cluster sampling method from Beijing, Nanning(Guangxi), and Yinchuan(Ningxia).Data on demographic characteristics and fall-related incidents were gathered and analyzed for their correlation with fall risk scores.Results:The fall risk score showed significant associations with various factors, such as the history of falls within one year( β=-3.607, 95% CI: -3.881 to -3.332), care methods( β=2.442, 95% CI: 2.226 to 2.658), exercise( β=0.714, 95% CI: 0.443 to 0.986), retirement( β=-0.585, 95% CI: -0.819 to -0.351), age( β=0.173, 95% CI: 0.159 to 0.187), and use of walking aids( β=-3.737, 95% CI: -4.054 to -3.421). Conclusions:Fall risk scores in older adults are influenced by a variety of factors.Factors such as no history of falls within the past year, living independently, engaging in physical activity, and being employed may contribute to lower fall risk scores in older adults.

Transmission electron microscopy(TEM)is considered as an important characterization tool for revealing morphology of materials and an indispensable strategy for studying the mechanisms of charge-discharge process in battery.TEM samples needs be less than 0.1 μm thick,which means electrodeposited materials must undergo pre-treatment processes such as focusing ion beam etching,ultra-thin slicing,or ultrasonic dispersion before they can be observed via TEM.However,such treatments cause structure changes,and what real formed in electrodes is hard to estimate.In this work,a self-interlacing film layer composed of carbon nanotubes(CNTs)was fabricated on a copper grid through blade coating.A novel TEM grid was produced by optimizing the interlacing film's thickness and covering area through adjusting the interlacing state of various concentrations of CNTs.Utilizing the novel TEM grid as the battery's positive electrode,electrode deposits were acquired and subjected to TEM analysis to generate high-definition microstructure images of the electrode surface.This process provided new insights into sample preparation for investigating the deposition/stripping mechanism in high-energy-density metal anodes.

Obesity-associated protein (FTO) is an important m6A demethylase that regulates RNA methylation modification and can promote the proliferation of acute myeloid leukemia(AML) cells. FTO regulates the methylation level of AML through multiple cellular signaling pathways such as FTO/RARA/ASB2, FTO/m6A/CEBPA, and PDGFRB/ERK, and participates in the occurrence, development, treatment and prognosis of AML. At present, studies have found that a variety of inhibitors targeting FTO have shown good anti-leukemia effects, and the study of FTO will provide new ideas for the treatment of AML. This review focus on the mechanism of action of FTO in AML and the research progress of FTO inhibitors in AML.
Humans ; Methylation ; Leukemia, Myeloid, Acute/genetics* ; Prognosis ; Alpha-Ketoglutarate-Dependent Dioxygenase FTO/metabolism*