OBJECTIVE:Based on different algorithms of machine learning,the prediction model of lumbar disc herniation has become a trend and hot spot in the development of precision medicine.However,there is limited evidence on the reporting quality and methodological quality of prediction models of lumbar disc herniation outcomes using machine learning.This article is aimed to explore the performance of machine learning algorithms in predicting the prognosis of lumbar disc herniation by comprehensively analyzing the report quality and risk of bias of previous studies that developed and validated prognosis prediction models based on machine learning through a comprehensive literature search,in order to explore the performance of machine learning algorithms in predicting the prognosis of lumbar disc herniation.METHODS:The databases of CNKI,WanFang,VIP,SinOMED,PubMed,Web of Science,Embase,and The Cochrane Library were searched by computer.Studies on the use of machine learning to develop(and/or validate)prognostic prediction models for lumbar disc herniation were collected from the inception of the database to December 31,2023.Two researchers independently screened the literature,extracted data,and assessed the risk of bias of the included studies.The reporting quality and risk of bias of the included studies were assessed by the Multivariable Transparent Reporting of Predictive Models(TRIPOD)statement and the Predictive Model Risk of Bias Assessment Tool(PROBAST).The results of the evaluation were analyzed using descriptive statistics and visual charts.RESULTS:(1)A total of 23 articles were included,and the TRIPOD compliance of each study ranged from 11％to 87％,with a median compliance of 54％.The quality of reporting of titles,detailed descriptions of treatment measures,blinding of predictors,handling of missing data,details of risk stratification,specific procedures for enrollment,model interpretation,and model performance was mostly poor,with TRIPOD adherence rates ranging from 4％to 35％.(2)Of all included studies,61％had a high risk of bias and 39％had an unclear overall risk of bias.The area under the curve,accuracy,sensitivity and specificity were used to evaluate the performance of the model.The areas under the curve of 20 models were reported,ranging from 0.561 to 0.999.Three models reported the accuracy of the model,ranging from 82.07％to 89.65％.(3)Among all included studies,the statistical analysis domain was most often assessed as having a high risk of bias,mainly due to the small number of valid samples,the selection of predictors based on univariate analysis and the lack of calibration and discrimination assessment of the model in the study.CONCLUSION:These results indicate that machine learning can achieve good predictive ability in the development and validation of prognostic models for lumbar disc herniation.The commonly used algorithms include regression algorithm,support vector machine,decision tree,random forest,artificial neural network,naive Bayes and other algorithms.Reasonable algorithms combined with clinical practice can improve the accuracy of prognosis prediction of lumbar disc herniation.However,the reporting and methodological quality of prognosis prediction models based on machine learning are poor,the prediction performance of different models varies greatly,and the generalization and extrapolation of research models are unclear.There is an urgent need to improve the design,implementation and reporting of such studies.To promote the application of machine learning in the clinical practice of lumbar disc herniation prediction models,it is necessary to comprehensively consider various predictors related to the prognosis of the disease before modeling,and strictly follow the relevant standards of PROBAST tool during modeling.

OBJECTIVE:Based on different algorithms of machine learning,the prediction model of lumbar disc herniation has become a trend and hot spot in the development of precision medicine.However,there is limited evidence on the reporting quality and methodological quality of prediction models of lumbar disc herniation outcomes using machine learning.This article is aimed to explore the performance of machine learning algorithms in predicting the prognosis of lumbar disc herniation by comprehensively analyzing the report quality and risk of bias of previous studies that developed and validated prognosis prediction models based on machine learning through a comprehensive literature search,in order to explore the performance of machine learning algorithms in predicting the prognosis of lumbar disc herniation.METHODS:The databases of CNKI,WanFang,VIP,SinOMED,PubMed,Web of Science,Embase,and The Cochrane Library were searched by computer.Studies on the use of machine learning to develop(and/or validate)prognostic prediction models for lumbar disc herniation were collected from the inception of the database to December 31,2023.Two researchers independently screened the literature,extracted data,and assessed the risk of bias of the included studies.The reporting quality and risk of bias of the included studies were assessed by the Multivariable Transparent Reporting of Predictive Models(TRIPOD)statement and the Predictive Model Risk of Bias Assessment Tool(PROBAST).The results of the evaluation were analyzed using descriptive statistics and visual charts.RESULTS:(1)A total of 23 articles were included,and the TRIPOD compliance of each study ranged from 11％to 87％,with a median compliance of 54％.The quality of reporting of titles,detailed descriptions of treatment measures,blinding of predictors,handling of missing data,details of risk stratification,specific procedures for enrollment,model interpretation,and model performance was mostly poor,with TRIPOD adherence rates ranging from 4％to 35％.(2)Of all included studies,61％had a high risk of bias and 39％had an unclear overall risk of bias.The area under the curve,accuracy,sensitivity and specificity were used to evaluate the performance of the model.The areas under the curve of 20 models were reported,ranging from 0.561 to 0.999.Three models reported the accuracy of the model,ranging from 82.07％to 89.65％.(3)Among all included studies,the statistical analysis domain was most often assessed as having a high risk of bias,mainly due to the small number of valid samples,the selection of predictors based on univariate analysis and the lack of calibration and discrimination assessment of the model in the study.CONCLUSION:These results indicate that machine learning can achieve good predictive ability in the development and validation of prognostic models for lumbar disc herniation.The commonly used algorithms include regression algorithm,support vector machine,decision tree,random forest,artificial neural network,naive Bayes and other algorithms.Reasonable algorithms combined with clinical practice can improve the accuracy of prognosis prediction of lumbar disc herniation.However,the reporting and methodological quality of prognosis prediction models based on machine learning are poor,the prediction performance of different models varies greatly,and the generalization and extrapolation of research models are unclear.There is an urgent need to improve the design,implementation and reporting of such studies.To promote the application of machine learning in the clinical practice of lumbar disc herniation prediction models,it is necessary to comprehensively consider various predictors related to the prognosis of the disease before modeling,and strictly follow the relevant standards of PROBAST tool during modeling.

ObjectiveTo collate and compare the characteristics and differences in the methods for constructing animal models of different subtypes of gastroesophageal reflux disease （GERD） based on literature， providing a reference for researchers in this field regarding animal model construction. MethodsExperimental studies related to GERD including reflux esophagitis （RE）， nonerosive reflux disease （NERD） and Barrett's esophagus （BE） model construction from January 1， 2014 to January 27， 2024， were retrieved from databases such as CNKI， Wanfang， VIP， Web of Science， and Pubmed. Information on animal strains， genders， modeling methods including disease-syndrome combination models， modeling cycles were extracted； for studies with model evaluation， the methods of model evaluation were also extracted； then analyzing all those information. ResultsA total of 182 articles were included. SD rats were most frequently selected when inducing animal models of RE （88/148， 59.46%） and NERD （9/14， 64.29%）. For BE， C57BL/6 mice were most commonly used （11/20， 55.00%）. Male animals （RE： 111/135， 82.22%； NERD： 11/14， 78.57%； BE： 10/12， 83.33%） were the most common gender among the three subtypes. The key to constructing RE animal models lies in structural damage to the esophageal mucosal layer， gastric content reflux， or mixed reflux， among which forestomach ligation + incomplete pylorus ligation （42/158， 26.58%） was the most common modeling method； the key to constructing NERD animal models lies in micro-inflammation of the esophageal mucosa， visceral hypersensitivity， and emotional problems， and intraperitoneal injection of a mixed suspension of ovalbumin and aluminum hydroxide combined with acid perfusion in the lower esophagus （8/14， 57.14%） was the most common modeling method； the key to constructing BE animal models lies in long-term inflammatory stimulation of the esophageal mucosa and bile acid reflux， and constructing interleukin 2-interleukin 1β transgenic mice （7/25， 28.00%） was the most common modeling method. Adverse psychological stress was the most common method for inducing liver depression. ConclusionsThe construction key principles and methodologies for RE， NERD， and BE animal models exhibit significant differences. Researchers should select appropriate models based on subtype characteristics （e.g.， RE focusing on structural damage， NERD emphasizing visceral hypersensitivity）. Current studies show insufficient exploration of traditional Chinese medicine disease-syndrome combination models. Future research needs to optimize syndrome modeling approaches （e.g.， composite etiology simulation） and establish integrated Chinese-Western medicine evaluation systems to better support mechanistic investigations of traditional Chinese medicine.

Neutralizing antibodies have been designed to specifically target and bind to the receptor binding domain (RBD) of spike (S) protein to block severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) virus from attaching to angiotensin converting enzyme 2 (ACE2). This study reports a distinctive nanobody, designated as VHH21, that directly catalyzes the S-trimer into an irreversible transition state through postfusion conformational changes. Derived from camels immunized with multiple antigens, a set of nanobodies with high affinity for the S1 protein displays abilities to neutralize pseudovirion infections with a broad resistance to variants of concern of SARS-CoV-2, including SARS-CoV and BatRaTG13. Importantly, a super-resolution screening and analysis platform based on visual fluorescence probes was designed and applied to monitor single proteins and protein subunits. A spontaneously occurring dimeric form of VHH21 was obtained to rapidly destroy the S-trimer. Structural analysis via cryogenic electron microscopy revealed that VHH21 targets specific conserved epitopes on the S protein, distinct from the ACE2 binding site on the RBD, which destabilizes the fusion process. This research highlights the potential of VHH21 as an abzyme-like nanobody (nanoabzyme) possessing broad-spectrum binding capabilities and highly effective anti-viral properties and offers a promising strategy for combating coronavirus outbreaks.
Single-Domain Antibodies/immunology* ; Spike Glycoprotein, Coronavirus/metabolism* ; SARS-CoV-2/immunology* ; Animals ; Humans ; Antibodies, Neutralizing/immunology* ; Camelus ; COVID-19/immunology* ; Antibodies, Viral/immunology* ; Angiotensin-Converting Enzyme 2

Objective To explore TCM syndrome distribution law in patients with overlapping non-erosive reflux disease(NERD)and epigastric pain syndrome(EPS)gastrointestinal symptoms.Methods A multi-center,cross-sectional study was conducted to investigate the general information of 800 patients with overlapping NERD and EPS gastrointestinal symptoms in four hospitals,such as gender,age,body mass index(BMI)and four diagnostic information of TCM.Descriptive frequency analysis,factor analysis and clustering analysis were used to summarize the TCM syndrome types and distribution characteristics.Results The average age of 800 patients with overlapping NERD and EPS gastrointestinal symptoms was(44.50±14.43)years old,the average BMI was(23.17±4.80)kg/m2,and the male to female ratio was 3:5.Frequency of 95 TCM symptoms/signs≥20%.18 common factor variables were obtained based on factor analysis,and the cumulative contribution rate was 67.11%.The first three syndrome elements of disease location were liver,stomach and spleen,and the disease nature syndrome elements were qi stagnation,qi deficiency and yin deficiency.Based on the clustering analysis of 18 common factor variables,combined with expert discussion,four main TCM syndrome types were obtained,which were liver-stomach stagnation heat syndrome(213 cases,26.63%),spleen-stomach damp heat syndrome(209 cases,26.13%),spleen-stomach deficiency and cold qi stagnation syndrome(190 cases,23.75%)and qi-phlegm stagnation syndrome(188 cases,23.50%).There was no significant difference in the distribution of TCM syndrome types among patients with different genders,ages and BMI values(P>0.05).Patients with a course of disease≥2 years and those residing long-term north of the Qinling-Huaihe Line showed a significantly higher prevalence of spleen-stomach dampness-heat syndrome(P<0.05).Conclusion The syndrome elements of disease location of overlapping NERD and EPS gastrointestinal symptoms are mainly liver,stomach and spleen.The TCM syndrome types are liver-stomach stagnation heat syndrome,spleen-stomach damp heat syndrome,spleen-stomach deficiency cold qi stagnation syndrome and qi-phlegm stagnation syndrome.The course of disease and the regional differences between north and south may be the influencing factors of the distribution of syndrome types.

Objective To explore TCM syndrome distribution law in patients with overlapping non-erosive reflux disease(NERD)and epigastric pain syndrome(EPS)gastrointestinal symptoms.Methods A multi-center,cross-sectional study was conducted to investigate the general information of 800 patients with overlapping NERD and EPS gastrointestinal symptoms in four hospitals,such as gender,age,body mass index(BMI)and four diagnostic information of TCM.Descriptive frequency analysis,factor analysis and clustering analysis were used to summarize the TCM syndrome types and distribution characteristics.Results The average age of 800 patients with overlapping NERD and EPS gastrointestinal symptoms was(44.50±14.43)years old,the average BMI was(23.17±4.80)kg/m2,and the male to female ratio was 3:5.Frequency of 95 TCM symptoms/signs≥20%.18 common factor variables were obtained based on factor analysis,and the cumulative contribution rate was 67.11%.The first three syndrome elements of disease location were liver,stomach and spleen,and the disease nature syndrome elements were qi stagnation,qi deficiency and yin deficiency.Based on the clustering analysis of 18 common factor variables,combined with expert discussion,four main TCM syndrome types were obtained,which were liver-stomach stagnation heat syndrome(213 cases,26.63%),spleen-stomach damp heat syndrome(209 cases,26.13%),spleen-stomach deficiency and cold qi stagnation syndrome(190 cases,23.75%)and qi-phlegm stagnation syndrome(188 cases,23.50%).There was no significant difference in the distribution of TCM syndrome types among patients with different genders,ages and BMI values(P>0.05).Patients with a course of disease≥2 years and those residing long-term north of the Qinling-Huaihe Line showed a significantly higher prevalence of spleen-stomach dampness-heat syndrome(P<0.05).Conclusion The syndrome elements of disease location of overlapping NERD and EPS gastrointestinal symptoms are mainly liver,stomach and spleen.The TCM syndrome types are liver-stomach stagnation heat syndrome,spleen-stomach damp heat syndrome,spleen-stomach deficiency cold qi stagnation syndrome and qi-phlegm stagnation syndrome.The course of disease and the regional differences between north and south may be the influencing factors of the distribution of syndrome types.

Objective To investigate the distribution of TCM syndromes and syndrome elements of irritable bowel syndrome(IBS);To provide reference for clinical TCM syndrome differentiation and treatment.Methods The patients with IBS who filled in the questionnaire were collected from 18 tertiary Chinese medicine hospitals in China from November 2019 to December 2022,including Xiyuan Hospital,China Academy of Chinese Medical Sciences,Guangdong Provincial Hospital of Traditional Chinese Medicine,the First Affiliated Hospital of Henan University of Traditional Chinese Medicine.The contents of questionnaire included the patients'general condition,medical history(onset time,condition changes),Rome Ⅳ symptom diagnostic scale,somatic symptom cluster scale,quality of life scale,hospital anxiety and depression scale,TCM syndromes,etc.The methods of factor analysis and systematic clustering analysis were used,the factors of disease and syndrome were extracted,and the classification of TCM syndrome types was summarized.Results Totally 157 patients were included,87 were male and 70 were female.The age was from 18 to 74 years old.The longest course of disease was 30 years and the shortest was 3 months,with an average of(48.31±5.61)months.Anxiety score:was 3.66±0.30,depression score was 3.39±0.28.The most common TCM symptom was emotional distress(83.4%),followed by diarrhea(80.9%)and abdominal pain(72.6%).The results of factor analysis showed that rotation finally converged after 16 iterations,and 8 common factors and 33 variables were obtained,with a cumulative contribution rate of 60.016%.The sites of IBS were mainly distributed in liver,spleen,large intestine and stomach.The main syndrome factors were qi stagnation,phlegm,dampness,heat and yang deficiency.The results of clustering analysis of 8 common factors showed that the main TCM syndrome types were liver depression and qi stagnation syndrome,damp-heat internal accumulation syndrome,liver depression and spleen deficiency syndrome,and liver-stomach digression syndrome.The main TCM syndrome of diarrhea-predominant IBS was liver stagnation and spleen deficiency syndrome,and the main TCM syndrome of mixed type and constipation type was damp-heat accumulation syndrome.There were statistically significant differences in the distribution of TCM syndrome types in patients with different types(P<0.05).Conclusion The location of IBS is mainly in liver,spleen and large intestine,especially in liver.The TCM syndrome types are mainly liver depression and qi stagnation syndrome,damp-heat internal accumulation syndrome,liver depression and spleen deficiency syndrome.

The human gastrointestinal tract is the largest reservoir of bacteria in the body,inhabiting a very complex and active microbial community.Under normal circumstances,the interaction between the intestinal flora and the host maintains a dynamic balance.Spleen deficiency syndrome is a common classic syndrome type in TCM clinical practice.A large number of studies have shown that spleen deficiency syndrome is closely related to intestinal microorganisms,and the balance of intestinal flora is the basis for the normal functioning of the spleen's main transportation and transformation functions.Intestinal flora imbalance can lead to a series of manifestations of spleen deficiency.In addition,intestinal flora is an important medium for the metabolism of polysaccharide components and the effectiveness of traditional Chinese medicine for invigorating the spleen,and traditional Chinese medicine for invigorating the spleen can also play a therapeutic role by regulating the structure and quantity of intestinal flora.This article summarizes the relationship between intestinal flora and spleen deficiency syndrome in physiology,pathology,and the efficacy of traditional Chinese medicine for invigorating the spleen.Based on intestinal flora,the study of spleen deficiency syndrome aims to provide some thoughts and suggestions for revealing the connotation of spleen deficiency syndrome in traditional Chinese medicine.

Objective:To explore the noninvasive diagnosis model and its clinical significance of acute myocardial infarction(AMI) in emergency patients with high-risk chest pain established based on chest pain database.Methods:A total of 467 patients with acute high-risk chest pain admitted to the Affiliated Hospital of Jining Medical University from January 2020 to October 2022 were selected. The patients were divided into AMI group (317 cases) and non-AMI group (150 cases) according to the occurrence of AMI. The clinical data of the two groups were compared, and Lasso regression and Logistic regression were used to analyze the related risk factors of AMI. R language was used to establish a diagnostic model, and concordance index (C-index) was used to evaluate the predictive ability of the model. Calibration curve and decision analysis curve (DCA) were used to verify and evaluate the established model externally.Results:The results of the univariate analysis showed that the proportion of patients with coronary heart disease, respiratory rate, myoglobin, creatine kinase isoenzyme-MB (CK-MB), cardiac troponin I (cTnI), D-dimer, N-terminal pro-brain natriuretic peptide, C- reactive protein, fibrinogen, lactic acid, ST-segment elevation and abnormal ventricular wall movement in the AMI group were higher than those in the non-AMI group: 51.10 % (162/317) vs. 21.33%(32/150), (19.25 ± 2.44) times/min vs. (16.30 ± 2.15) times/min, (270.03 ± 26.59) μg/L vs. (71.44 ± 19.85) μg/L, (30.51 ± 8.22) μg/L vs. (3.22 ± 0.88) μg/L, (4.51 ± 1.38) μg/L vs. (0.04 ± 0.01) μg/L, (1.69 ± 0.51) mg/L vs. (0.32 ± 0.09) mg/L, (2 085.66 ± 561.24) ng/L vs. (964.39 ± 257.40) ng/L, (13.98 ± 4.52) mg/L vs. (7.11 ± 2.26) mg/L, (4.07 ± 0.83) g/L vs. (2.95 ± 0.78) g/L, (2.20 ± 0.49) mmol/L vs. (1.36 ± 0.35) mmol/L, 80.76%(256/317) vs. 16.67% (25/150), 95.27%(302/317) vs. 17.33% (26/150); the platelet count, activited partial thomboplastin time, prothombin time and left ventricular ejection fractionin in the AMI group were lower than those in the non-AMI group: (168.97 ± 29.66) × 10 9/L vs. (230.58 ± 30.57) × 10 9/L, (30.25 ± 4.59) s vs. (33.59 ± 4.16) s, (11.82 ± 0.74) s vs. (13.25 ± 1.02) s, (47.25 ± 5.33)% vs. (58.49 ± 5.07)%, there were statistical differences ( P<0.05). Using 17 variables with P<0.05 in univariate analysis as independent variables, Lasso regression analysis selected 7 predictive variables as coronary heart disease, myoglobin, CK-MB, cTnI, D-dimer, ST segment elevation and abnormal ventricular wall movement. Multivariate Logistic regression analysis showed that coronary heart disease, myoglobin, CK-MB, cTnI, D-dimer, ST-segment elevation and abnormal ventricular wall movement were the related risk factors of AMI ( P<0.05). Hosmer-Lemeshow goodness of fit test showed that the fit was good ( χ2 = 2.56, df = 9, P = 0.860); R language was used to draw the non-invasive diagnosis model of AMI, and the C-index was 0.945, indicated good predictive ability. Calibration curve analysis showed that the calibration degrees of the model establishment population and the external verification population were 0.918 and 0.924, respectively, indicated that the model was in good agreement with the actual observation results. The DCA curve showed that the column graph model for diagnosing AMI had significant positive net benefit and good clinical utility. Conclusions:Coronary heart disease, myoglobin, CK-MB, cTnI, D-dimer, ST-segment elevation and abnormal ventricular wall movement can be used as non-invasive diagnostic markers for AMI in patients with acute high-risk chest pain in emergency department. The prediction performance of the diagnostic model based on the above factors is good.

Objective:To develop and evaluate a nomogram prediction model for the 3-month mortality risk of patients with sepsis-associated acute kidney injury (S-AKI).Methods:Based on the American Medical Information Mart for Intensive Care-Ⅳ (MIMIC-Ⅳ), clinical data of S-AKI patients from 2008 to 2021 were collected.Initially, 58 relevant predictive factors were included, with all-cause mortality within 3 months as the outcome event. The data were divided into training and testing sets at a 7∶3 ratio. In the training set, univariate Logistic regression analysis was used for preliminary variable screening. Multicollinearity analysis, Lasso regression, and random forest algorithm were employed for variable selection, combined with the clinical application value of variables, to establish a multivariable Logistic regression model, visualized using a nomogram. In the testing set, the predictive value of the model was evaluated through internal validation. The receiver operator characteristic curve (ROC curve) was drawn, and the area under the curve (AUC) was calculated to evaluate the discrimination of nomogram model and Oxford acute severity of illness score (OASIS), sequential organ failure assessment (SOFA), and systemic inflammatory response syndrome score (SIRS). The calibration curve was used to evaluate the calibration, and decision curve analysis (DCA) was performed to assess the net benefit at different probability thresholds.Results:Based on the survival status at 3 months after diagnosis, patients were divided into 7?768 (68.54%) survivors and 3?566 (31.46%) death. In the training set, after multiple screenings, 7 variables were finally included in the nomogram model: Logistic organ dysfunction system (LODS), Charlson comorbidity index, urine output, international normalized ratio (INR), respiratory support mode, blood urea nitrogen, and age. Internal validation in the testing set showed that the AUC of nomogram model was 0.81 [95% confidence interval (95% CI) was 0.80-0.82], higher than the OASIS score's 0.70 (95% CI was 0.69-0.71) and significantly higher than the SOFA score's 0.57 (95% CI was 0.56-0.58) and SIRS score's 0.56 (95% CI was 0.55-0.57), indicating good discrimination. The calibration curve demonstrated that the nomogram model's calibration was better than the OASIS, SOFA, and SIRS scores. The DCA curve suggested that the nomogram model's clinical net benefit was better than the OASIS, SOFA, and SIRS scores at different probability thresholds. Conclusions:A nomogram prediction model for the 3-month mortality risk of S-AKI patients, based on clinical big data from MIMIC-Ⅳ and including seven variables, demonstrates good discriminative ability and calibration, providing an effective new tool for assessing the prognosis of S-AKI patients.