OBJECTIVE: As an age-related neurodegenerative disease, the prevalence of mild cognitive impairment (MCI) increases with age. Within the framework of traditional Chinese medicine, spleen-kidney deficiency syndrome (SKDS) is recognized as the most frequent MCI subtype. Due to the covert and gradual onset of MCI, in community settings it poses a significant challenge for patients and their families to discern between typical aging and pathological changes. There exists an urgent need to devise a preliminary diagnostic tool designed for community-residing older adults with MCI attributed to SKDS (MCI-SKDS). METHODS: This investigation enrolled 312 elderly individuals diagnosed with MCI, who were randomly distributed into training and test datasets at a 3:1 ratio. Five machine learning methods, including logistic regression (LR), decision tree (DT), naive Bayes (NB), support vector machine (SVM), and gradient boosting (GB), were used to build a diagnostic prediction model for MCI-SKDS. Accuracy, sensitivity, specificity, precision, F1 score, and area under the curve were used to evaluate model performance. Furthermore, the clinical applicability of the model was evaluated through decision curve analysis (DCA). RESULTS: The accuracy, precision, specificity and F1 score of the DT model performed best in the training set (test set), with scores of 0.904 (0.845), 0.875 (0.795), 0.973 (0.875) and 0.973 (0.875). The sensitivity of the training set (test set) of the SVM model performed best among the five models with a score of 0.865 (0.821). The area under the curve of all five models was greater than 0.9 for the training dataset and greater than 0.8 for the test dataset. The DCA of all models showed good clinical application value. The study identified ten indicators that were significant predictors of MCI-SKDS. CONCLUSION The risk prediction index derived from machine learning for the MCI-SKDS prediction model is simple and practical; the model demonstrates good predictive value and clinical applicability, and the DT model had the best performance. Please cite this article as: Ai YT, Zhou S, Wang M, Zheng TY, Hu H, Wang YC, Li YC, Wang XT, Zhou PJ. Development of a machine learning-based risk prediction model for mild cognitive impairment with spleen-kidney deficiency syndrome in the elderly. J Integr Med. 2025; 23(4): 390-397.
Humans ; Cognitive Dysfunction/diagnosis* ; Aged ; Male ; Female ; Machine Learning ; Spleen ; Aged, 80 and over ; Kidney ; Medicine, Chinese Traditional

OBJECTIVE: This study examines utilizes the advantages of machine learning algorithms to discern key determinants in prognosticate postoperative circulatory complications (PCCs) for older patients. METHODS: This secondary analysis of data from a randomized controlled trial involved 1,720 elderly participants in five tertiary hospitals in Beijing, China. Participants aged 60-90 years undergoing major non-cardiac surgery under general anesthesia. The primary outcome metric of the study was the occurrence of PCCs, according to the European Society of Cardiology and the European Society of Anaesthesiology diagnostic criteria. The analysis metrics contained 67 candidate variables, including baseline characteristics, laboratory tests, and scale assessments. RESULTS: Our feature selection process identified key variables that significantly impact patient outcomes, including the duration of ICU stay, surgery, and anesthesia; APACHE-II score; intraoperative average heart rate and blood loss; cumulative opioid use during surgery; patient age; VAS-Move-Median score on the 1st to 3rd day; Charlson comorbidity score; volumes of intraoperative plasma, crystalloid, and colloid fluids; cumulative red blood cell transfusion during surgery; and endotracheal intubation duration. Notably, our Random Forest model demonstrated exceptional performance with an accuracy of 0.9872. CONCLUSION We have developed and validated an algorithm for predicting PCCs in elderly patients by identifying key risk factors.
Aged ; Aged, 80 and over ; Female ; Humans ; Male ; Middle Aged ; Cardiovascular Diseases/etiology* ; Machine Learning ; Postoperative Complications/etiology* ; Risk Factors ; Randomized Controlled Trials as Topic ; Secondary Data Analysis

mRNA therapy involves delivering target molecules in the form of mRNA into cells to treat dis-eases.The highly variable nature of mRNA sequences offers potential solutions for high-throughput drug discovery and personalized treatment.This review begins with an overview of the development history of mRNA,tracing its journey from discovery to becoming a potential treatment.The review also discusses the applications of mRNA in protein replacement therapy,cancer treatment,in vivo gene editing,and in-fectious disease prevention based on the different categories of proteins delivered by mRNA.Additionally,optimizing mRNA formulations and their delivery vehicles is crucial for clinical application.This review further explains how to enhance the translation efficiency and stability of mRNA through nucleoside modi-fications and sequence optimization,and we systematically compare the pros and cons of novel circular mRNA versus traditional linear mRNA in vaccine development.Moreover,we summarize common deliv-ery methods,such as lipid nanoparticles,and discuss the latest advancements in targeted delivery sys-tems.For currently approved and in-development mRNA drugs,we systematically review the diseases treated,effector molecules delivered,and their clinical stages.Finally,we explore the challenges facing mRNA therapies and the potential diseases they could address,aiming to provide a theoretical foundation and reference for the development of mRNA therapies.

AIM To establish the quantitative models for gallic acid,mononucleoside,loganin,resveratrol,and rhein in Yishen Xiezhuo Mixture.METHODS HPLC was adopted in the content determination of various effective components,after which the near-infrared spectroscopy(NIRS)data were collected in 128 batches of samples and pretreatment was conducted,competitive adaptive reweighting sampling(CARS)algorithm was used for screening wavelength,partial least square method(PLS)regression analysis was performed.RESULTS There were no significant differences between the predicted values obtained by PLS models and measured values obtained by HPLC for various effective components(P＞0.05).CONCLUSION The quantitative models established by NIRS combined with chemometrics display good predictive performance,which can be used for the rapid determination of effective components in Yishen Xiezhuo Mixture,and provide a reference for the rapid monitoring of other traditional Chinese medicine preparations in production processes.

Objective To explore the ArcCHECK system-based methods for dose verification of ultra-long target for cervical cancer VMAT so as to assure the precision of cervical cancer radiotherapy.Methods A total of 33 patients with ultra-long target(target length≥26 cm)admitted to some hospital for cervical cancer VMAT from 2021 to 2023 were selected retrospectively,and radiotherapy plans were designed for the patients with VMAT technology and verified dosimetrically with different methods.Firstly,the dose distribution data were collected respectively at 5 and 8 cm away from the center of the ArcCHECK system along the bed exit direction,and enrolled into Group Test 1 and Test 2 respectively.Then the ArcCHECK system was flipped 180°,and the dose distribution data were acquired at 8 cm away from the center along the bed exit direction and included into Group Test 3.Dose merging between Group Test 2 and Test 3 with the Merge function was carried out to obtain the dose distribution data which were divided into Group Test 4.The monitor units of Group Test 1,2 and 4 were summarized,and difference analyses were performed on the length of the target area,detection point and irradiation time.Group Test 1,2 and 4 were compared in terms of γ pass rate,normalized dose deviation,confidence limit(CL)of pass rate and acceptance rate(γ pass rate≥95%and γ pass rate≥90%).Spearman's correlation coefficient was used to correlate the parameters such as maximum transverse diameter,length,volume and monitor unit of the target area and expected execution time of the plan.SPSS 19.0 software was used for statistical analysis.Results Group Test 1,2 and 4 had the monitor unit being(758.76±107.63)MU,and had statistically significant differences in length of the target area,detection point and irradiation time(P<0.01).In Group Test 4 γ pass rate under 2%/2 mm criterion did not reach 90%,and in Group Test 1 and 2 γ pass rates under 3%/3 mm and 3%/2 mm criteria both amounted to 95%.Group Test 1,2 and 4 had statistically significant differences in γ pass rate and normalized dose deviation(all P<0.05).In Group Test 1 there were more than 90%of the verification results where γ pass rate≥95%and more than 95%where γ pass rate≥90%under 3%/3 mm criterion.The monitor unit was positively correlated with the maximum transverse diameter,length and volume of the target area,respectively(0.337≤r≤0.568,P<0.05),and the expected execution time of the plan was positively correlated with the volume and monitor unit of the target area,respectively(0.457≤r≤0.517,P<0.01).Conclusion The dose verification method with the target at 5 cm away from the center along the bed exit direction can be applied clinically with high feasibility to the dose verification during the radiotherapy of the cervical cancer VMAT patients with ultra-long target,with the safety of the verification devices ensured effectively.

With the rapid development of generative artificial intelligence(GAI)technologies,their widespread application in academic research and writing is continuously expanding the boundaries of sci-entific inquiry.However,this trend has also raised a series of ethical and regulatory challenges,inclu-ding issues related to authorship,content authenticity,citation accuracy,and accountability.In light of the growing involvement of AI in generating academic content,establishing an open,controllable,and trustworthy ethical governance framework has become a key task for safeguarding research integrity and maintaining trust within the academic community.This expert consensus outlines ethical requirements across key stages of AI-assisted academic writing-including topic selection,data management,citation practices,and authorship attribution.It aims to clarify the boundaries and ethical obligations surrounding AI use in academic writing,ensuring that technological tools enhance efficiency without compromising in-tegrity.The goal is to provide guidance and institutional support for building a responsible and sustainable research ecosystem.

Objective To analyze the clinical distribution and antimicrobial susceptibility of Ralstonia mannitolilytica strains isolated from clinical specimens at a tertiary hospital in Shanghai.The results could inform better clinical treatment of R.mannitolilytica.Methods A total of 47 R.mannitolilytica isolated from January 2022 to August 2024 were collected.The clinical data of patients from whom these strains were isolated were reviewed and analyzed.Results The 47 strains of R.mannitolilytica were mainly isolated from hematology department(85.1％,40/47)and intensive care unit(4.3％,2/47).In the 47 patients with R.mannitolilytica isolate,83.0％had hematological disease and 85.1％stayed in hospital for at least 28 days.Overall,63.8％of the 47 patients used antibiotics for at least 3 weeks and 76.6％of the patients used at least three types of antibiotics during hospital stay.All of the 47 R.mannitolilytica strains were resistant to aztreonam,while 84.6％,83.3％,70.4％,and 69.6％of the strains were resistant to meropenem,ticarcillin-clavulanate acid,ceftazidime,and piperacillin-tazobactam,respectively,58.7％,55.8％,52.2％,and 42.2％of the strains were resistant to amikacin,tobramycin,cefepime,and imipenem,respectively.In contrast,88.1％,83.3％,82.9％,67.4％and 60.5％of the strains were susceptible to minocycline,doxycycline,cotrimoxazole,ciprofloxacin,and levofloxacin,respectively.Conclusions Most of the R.mannitolilytica strains were multi-drug resistant.The bacteria is more prevalent in patients with hematological disorders and long-term treatment with multiple broad-spectrum antimicrobial agents.

AIM To establish the quantitative models for gallic acid,mononucleoside,loganin,resveratrol,and rhein in Yishen Xiezhuo Mixture.METHODS HPLC was adopted in the content determination of various effective components,after which the near-infrared spectroscopy(NIRS)data were collected in 128 batches of samples and pretreatment was conducted,competitive adaptive reweighting sampling(CARS)algorithm was used for screening wavelength,partial least square method(PLS)regression analysis was performed.RESULTS There were no significant differences between the predicted values obtained by PLS models and measured values obtained by HPLC for various effective components(P＞0.05).CONCLUSION The quantitative models established by NIRS combined with chemometrics display good predictive performance,which can be used for the rapid determination of effective components in Yishen Xiezhuo Mixture,and provide a reference for the rapid monitoring of other traditional Chinese medicine preparations in production processes.

Objective To study the risk factors and strain resistance of Escherichia coli with extended-spectrum β-lactamases(ESBL)-producing bloodstream infection,so as to provide clinical basis for rational use of antibiotics and effective prevention and control of bloodstream infection.Methods The clinical data of patients with bloodstream infections caused by Escherichia coli in a tertiary hospital in Chongqing from January 2018 to December 2022 were retrospectively collected.The clinical characteristics and drug resistance of bloodstream infections caused by Escherichia coli were statistically analysed.According to the ESBL confirmation test of Escherichia coli strains,the patients were divided into the ESBL-producing group and the non-ESBL-producing group.The chi-square test was used to compare the differences in influencing factors between the two groups,and then the independent influencing factors of ESBL production were analyzed through multivariate Logistic regression.Results A total of 408 patients were included.The detection rate of ESBL-producing strains was 60.3％(246/408),and the detection rates in the nephrology department and the intensive care unit were relatively high(both＞76.0％).Diabetes[OR=1.98,95％CI(1.24,3.17)]and urinary tract intubation[OR=1.60,95％CI(1.02,2.51)]were independent influencing factors for bloodstream infection with ESBL-producing Escherichia coli.The resistance rate of ESBL-producing Escherichia coli to levofloxacin and ceftriaxone was＞90.0％.Moreover,the resistance rates of the second-generation cephalosporins(except ceftazidime),compound sulfamethoxazole,ciprofloxacin and amtronam were significantly higher than those in the non-ESBL-producing group(P＜0.05).Both groups of strains showed high sensitivity to amikacin and carbapenem drugs.Conclusion The severe current situation of bloodstream infections caused by ESBL-producing Escherichia coli in this region showing a high prevalence of drug resistance characteristics.Diabetes and urinary tract intubation,as independent risk factors,suggest that key monitoring should be implemented for such high-risk populations in clinical practice.Given that ESBL-producing strains remain sensitive to carbapenems and amikacin,it can be recommended as the first empirical medication.It is of great public health significance to achieve the effect of curbing the spread of such multi-drug resistant bacteria by establishing an early warning system based on risk factor assessment and standardized management of invasive operations.

Objective To study the risk factors and strain resistance of Escherichia coli with extended-spectrum β-lactamases(ESBL)-producing bloodstream infection,so as to provide clinical basis for rational use of antibiotics and effective prevention and control of bloodstream infection.Methods The clinical data of patients with bloodstream infections caused by Escherichia coli in a tertiary hospital in Chongqing from January 2018 to December 2022 were retrospectively collected.The clinical characteristics and drug resistance of bloodstream infections caused by Escherichia coli were statistically analysed.According to the ESBL confirmation test of Escherichia coli strains,the patients were divided into the ESBL-producing group and the non-ESBL-producing group.The chi-square test was used to compare the differences in influencing factors between the two groups,and then the independent influencing factors of ESBL production were analyzed through multivariate Logistic regression.Results A total of 408 patients were included.The detection rate of ESBL-producing strains was 60.3％(246/408),and the detection rates in the nephrology department and the intensive care unit were relatively high(both＞76.0％).Diabetes[OR=1.98,95％CI(1.24,3.17)]and urinary tract intubation[OR=1.60,95％CI(1.02,2.51)]were independent influencing factors for bloodstream infection with ESBL-producing Escherichia coli.The resistance rate of ESBL-producing Escherichia coli to levofloxacin and ceftriaxone was＞90.0％.Moreover,the resistance rates of the second-generation cephalosporins(except ceftazidime),compound sulfamethoxazole,ciprofloxacin and amtronam were significantly higher than those in the non-ESBL-producing group(P＜0.05).Both groups of strains showed high sensitivity to amikacin and carbapenem drugs.Conclusion The severe current situation of bloodstream infections caused by ESBL-producing Escherichia coli in this region showing a high prevalence of drug resistance characteristics.Diabetes and urinary tract intubation,as independent risk factors,suggest that key monitoring should be implemented for such high-risk populations in clinical practice.Given that ESBL-producing strains remain sensitive to carbapenems and amikacin,it can be recommended as the first empirical medication.It is of great public health significance to achieve the effect of curbing the spread of such multi-drug resistant bacteria by establishing an early warning system based on risk factor assessment and standardized management of invasive operations.