Intelligent prescription recommendation has become an important research direction in traditional Chinese medicine (TCM), offering new opportunities to support clinical decision-making and promote the modernization of TCM practice. With the rapid development of artificial intelligence (AI), a variety of computational approaches have been proposed to learn prescription patterns from clinical data and generate personalized treatment recommendations. However, despite increasing research activity, systematic and comprehensive reviews of AI-driven methods for TCM prescription recommendation remain limited. In this study, we present a comprehensive review of computational approaches for herbal prescription recommendation (HPR) in TCM. Existing methods are systematically categorized into several major paradigms, including traditional machine learning methods, topic model methods, sequential generative methods, deep learning and graph-based methods, and large language model–based frameworks. In addition to summarizing methodological developments, we also review commonly used public datasets and evaluation metrics in this field. Furthermore, representative models with publicly available implementations are experimentally evaluated on multiple benchmark datasets to provide a comparative analysis of their performance on the HPR task. Finally, we discuss the key challenges that hinder the practical deployment of intelligent prescription recommendation systems, including data heterogeneity, limited interpretability, and insufficient integration of TCM domain knowledge. Future research directions are outlined to facilitate the development of more reliable, interpretable, and clinically applicable AI-assisted HPR systems for TCM.

Objective To construct a clinical-radiological nomo-gram model for severe mycoplasma pneumoniae pneumonia coinfec-tion with other pathogens(Co-SMPP)in children.Methods The clinical and radiological data of children with severe mycoplasma pneumoniae pneumonia(SMPP)who underwent nucleic acid testing or bronchoalveolar lavage(BAL)were analyzed retrospectively.The data analysis were performed by using SPSS 27.0 software.The group comparison between simple SMPP and Co-SMPP children was conducted by using t-tests,Mann-Whitney U tests,or chi-square tests.Nomogram analysis was performed by using R software and rms packages.The predictive performance of the model was evaluated by using the receiver operating characteristic(ROC)curve.Results A total of 194 SMPP children were included in the study,including 136 cases(70.1％)with simple SMPP,58 cases(29.9％)with Co-SMPP.The fibrinogen and albumin levels were lower in Co-SMPP children[(3.53±0.85)g/L,41.00(39.03,43.68)g/L]than in simple SMPP children[(3.79±0.80)g/L,42.80(41.00,44.40)g/L],with P values of 0.047 and 0.036,respec-tively.The probability of bronchial stenosis and grid shadow were higher in Co-SMPP children than in simple SMPP children,and there were significant differences between the two groups(P＜0.001,P=0.010).The odds ratio of bronchial stenosis in predicting Co-SMPP children was 14.085.The clinical-radiological nomogram model had an area under the curve(AUC)of 0.840,with sensi-tivity and specificity of 0.756 and 0.848,respectively.Conclusion The nomogram model based on clinical-radiological features can effectively predict Co-SMPP.

Objective To construct a clinical-radiological nomo-gram model for severe mycoplasma pneumoniae pneumonia coinfec-tion with other pathogens(Co-SMPP)in children.Methods The clinical and radiological data of children with severe mycoplasma pneumoniae pneumonia(SMPP)who underwent nucleic acid testing or bronchoalveolar lavage(BAL)were analyzed retrospectively.The data analysis were performed by using SPSS 27.0 software.The group comparison between simple SMPP and Co-SMPP children was conducted by using t-tests,Mann-Whitney U tests,or chi-square tests.Nomogram analysis was performed by using R software and rms packages.The predictive performance of the model was evaluated by using the receiver operating characteristic(ROC)curve.Results A total of 194 SMPP children were included in the study,including 136 cases(70.1％)with simple SMPP,58 cases(29.9％)with Co-SMPP.The fibrinogen and albumin levels were lower in Co-SMPP children[(3.53±0.85)g/L,41.00(39.03,43.68)g/L]than in simple SMPP children[(3.79±0.80)g/L,42.80(41.00,44.40)g/L],with P values of 0.047 and 0.036,respec-tively.The probability of bronchial stenosis and grid shadow were higher in Co-SMPP children than in simple SMPP children,and there were significant differences between the two groups(P＜0.001,P=0.010).The odds ratio of bronchial stenosis in predicting Co-SMPP children was 14.085.The clinical-radiological nomogram model had an area under the curve(AUC)of 0.840,with sensi-tivity and specificity of 0.756 and 0.848,respectively.Conclusion The nomogram model based on clinical-radiological features can effectively predict Co-SMPP.

Objective:To understand the status and influencing factors of social isolation in elderly individuals with chronic diseases.Methods:A multi-stage sampling method was used to select elderly individuals from eight communities or villages in Hefei from July to September 2022. The study employed a general information survey, the Lubben Social Network Scale (LSNS-6) , the Geriatric Depression Scale (GDS-15) , the Social Support Rating Scale (SSRS) , and the Personal Social Capital Scale 16 (PSCS-16) . Binary Logistic regression analysis was used to explore the factors influencing social isolation in elderly individuals with chronic diseases.Results:A total of 1 133 elderly individuals were surveyed, among which 538 had chronic diseases. Among the 538 elderly individuals with chronic diseases, 209 were socially isolated, resulting in a social isolation rate of 38.8%. Binary Logistic regression analysis revealed that living area, fear of falling, depression, social capital, and social support were significant factors influencing social isolation ( P<0.05) . Conclusions:The social isolation rate among elderly individuals with chronic diseases is high. Special attention should be given to elderly individuals living in rural areas, those who fear falling, and those experiencing depression. Additionally, improving social capital and social support can help alleviate social isolation in these elderly individuals.

Objective:To explore the potential categories and influencing factors of attitudes to aging among the elderly in nursing homes.Methods:Convenience sampling was used to select elderly from 15 nursing homes in Anhui Province from March to July 2024 for the study. The survey was conducted using the General Information Questionnaire, Attitudes to Ageing Questionnaire, Belongingness Scale for Older Adults in Nursing Facilities, and the Lubben Social Network Scale. Mplus 8.3 was used to conduct a latent profile analysis, and multivariate Logistic regression was employed to explore the factors influencing the latent categories of attitudes toward aging among the elderly in nursing facilities.Results:A total of 370 questionnaires were distributed, and 366 valid questionnaires were recovered, with an effective recovery rate of 98.9%. The attitudes to aging of 366 elderly of nursing facilities were expressed in three potential categories, namely, negative-perceived type (48.6%), moderate-low psychosocial loss type (35.0%), and positive and optimistic-comprehensive type (16.4%). Multicategorical Logistic regression analysis showed that the number of children, location of the nursing home, educational level, self-rating health, belongingness to the nursing home, and social network were the influencing factors of the potential categories of attitudes to aging among the elderly in the nursing home, and the difference was statistically significant ( P<0.05) . Conclusions:There is group heterogeneity in the attitudes to aging among the elderly in nursing homes. Healthcare professionals should focus on negative-perceived elderly and provide targeted interventions based on the potential categories of factors influencing their attitudes to aging.

Objective:To understand the status and influencing factors of social isolation in elderly individuals with chronic diseases.Methods:A multi-stage sampling method was used to select elderly individuals from eight communities or villages in Hefei from July to September 2022. The study employed a general information survey, the Lubben Social Network Scale (LSNS-6) , the Geriatric Depression Scale (GDS-15) , the Social Support Rating Scale (SSRS) , and the Personal Social Capital Scale 16 (PSCS-16) . Binary Logistic regression analysis was used to explore the factors influencing social isolation in elderly individuals with chronic diseases.Results:A total of 1 133 elderly individuals were surveyed, among which 538 had chronic diseases. Among the 538 elderly individuals with chronic diseases, 209 were socially isolated, resulting in a social isolation rate of 38.8%. Binary Logistic regression analysis revealed that living area, fear of falling, depression, social capital, and social support were significant factors influencing social isolation ( P<0.05) . Conclusions:The social isolation rate among elderly individuals with chronic diseases is high. Special attention should be given to elderly individuals living in rural areas, those who fear falling, and those experiencing depression. Additionally, improving social capital and social support can help alleviate social isolation in these elderly individuals.

Objective:To explore the potential categories and influencing factors of attitudes to aging among the elderly in nursing homes.Methods:Convenience sampling was used to select elderly from 15 nursing homes in Anhui Province from March to July 2024 for the study. The survey was conducted using the General Information Questionnaire, Attitudes to Ageing Questionnaire, Belongingness Scale for Older Adults in Nursing Facilities, and the Lubben Social Network Scale. Mplus 8.3 was used to conduct a latent profile analysis, and multivariate Logistic regression was employed to explore the factors influencing the latent categories of attitudes toward aging among the elderly in nursing facilities.Results:A total of 370 questionnaires were distributed, and 366 valid questionnaires were recovered, with an effective recovery rate of 98.9%. The attitudes to aging of 366 elderly of nursing facilities were expressed in three potential categories, namely, negative-perceived type (48.6%), moderate-low psychosocial loss type (35.0%), and positive and optimistic-comprehensive type (16.4%). Multicategorical Logistic regression analysis showed that the number of children, location of the nursing home, educational level, self-rating health, belongingness to the nursing home, and social network were the influencing factors of the potential categories of attitudes to aging among the elderly in the nursing home, and the difference was statistically significant ( P<0.05) . Conclusions:There is group heterogeneity in the attitudes to aging among the elderly in nursing homes. Healthcare professionals should focus on negative-perceived elderly and provide targeted interventions based on the potential categories of factors influencing their attitudes to aging.

Objective:To search and evaluate the literatures on the application of mechanical insufflation-exsufflation technique (MI-E) in patients with invasive mechanical ventilation in China and abroad, and to summarize the best evidence to provide evidence-based basis for clinical practice.Methods:The literatures related to the use of MI-E technique in invasive mechanical ventilation patients were searched from the establishment of the database to April 1, 2022 in BMJ Best Practice, UpToDate Clinical Advisor, Scottish Intercollegiate Guidelines Network (SIGN), Guidelines International Network (GIN), National Institute for Health and Care Excellence (NICE), National Guideline Clearinghouse (NGC), Registered Nurses' Association of Ontario (RNAO), medlive, Cochrane Library, Joana Briggs Instiute, Web of Science, PubMed, Embase, Cumulative Index to Nursing and Allied Health Literature (CINAHL), SinoMed, China National Knowledge Infrastructure (CNKI), Wanfang Database, China Science and Technology Journal Database, and Website of American Association for Respiratory Care, including guideline, expert consensus, clinical decision, evidence summary, systematic review and randomized controlled trial. The JBI Center for Evidence-Based Health Care Expert Consensus Evaluation Criteria (2016) was used to evaluate the quality of the included systematic reviews; the JBI Center for Evidence-Based Health Care Evaluation Criteria for Randomized Controlled Trials was used to evaluate the quality of the included randomized controlled trial. Two researchers independently evaluated the quality of literature, and extracted and summarized the evidence based on professional judgment.Results:A total of 7 literatures were enrolled, including 3 systematic reviews and 4 randomized controlled trials. After quality evaluation, 7 articles were all enrolled. Thirteen best evidences were formed from four aspects of indications, contraindications, parameter settings, and attention.Conclusions:The study summarizes the best evidence for the application of MI-E technique in invasive mechanical ventilation patients. It is recommended that medical staff undergo professional training, combined with their professional judgment as well as the patient's clinical specific conditions and willingness, and accurately apply MI-E technology to invasive mechanical ventilation patients.

Objective: To investigate the effects of ginsenoside Rg3 on the proliferation, apoptosis, migration and invasion of osteosarcoma 143B cells and its possible mechanisms. Methods: Osteosarcoma 143B cells were treated with gradient concentrations of Rg3 (40, 50, 60, 70 and 80 µmol/L) for 24, 48 and 72 h, respectively, comparing with a control group of 143B cells treated with DMSO. The effects of Rg3 on the viability and proliferation of 143B cells were measured by MTT assay and colony-forming assay, respectively. Then the value of half-maximal inhibitory concentration (IC50) were calculated in order to screen the optimal drug concentrations and its action time. The apoptosis of 143B cells was measured by Hoechst 33258 staining and its cell cycle distribution was detected by FCM method. The migration and invasion abilities of 143B cells were detected by scratch wound healing assay and Transwell assay, respectively. The expression level of proliferating cell nuclear antigen (PCNA) mRNA was detected by real-time fluorescent quantitative PCR. The Western blotting was used to detect the proliferation marker PCNA and apoptosis-related proteins Bcl-2, Bax, cleaved-Caspase 3, as well as the expression level of migration-and invasion-related proteins matrix metalloproteinase-2 (MMP-2), MMP-7. Finally, Luciferase Gene Reportor System was used to screen the signaling pathways regulated by Rg3. The expression levels of protein kinase B (PKB, also known as AKT), phospho-AKT (p-AKT), cAMP-response element binding protein (CREB), and p-CREB were measured by Western blotting. Results: Comparing with the control group, Rg3 in the concentration of 40, 50, 60, 70 and 80 µmol/L could cause the inhibition of the proliferation of 143B cells which had a positive relationship with the concentration and action time (P < 0.001), and the IC50 of Rg3 to 143B cells was (51.00±3.46µmol/L. Furthermore, Rg3 inhibited the expression of PCNA at mRNA and protein levels (P < 0.05). In addition, Rg3 could also promote the apoptosis of 143B and inhibit their migration and invasion abilities (all P < 0.05). The expression levels of apoptosis-related protein Bcl-2 in 143B cells treated with Rg3 was down-regulated, while the expression level of the proteins Bax and cleaved-Caspase3 were up-regulated remarkably (all P < 0.05). The expression level of migration-and invasion-related proteins MMP-2 and MMP-7 were also decreased (all P < 0.05). At the same time, the transcriptional activity of CREB was impaired, and the expression levels of p-AKT, p-CREB were decreased remarkably (both P < 0.05). Conclusion: Rg3 can inhibit the proliferative, imaginational and invasive of osteosarcoma 143B cells, and also induced its apoptosis, which may be related with the depression of the activation of CREB signaling pathway.

Objective To investigate the relationship between serum markers β amyloid (Aβ), tau and thyroid hormone levels and post-stroke cognitive impairment (PSCI) in the acute phase of cerebral infarction. Methods A total of 214 patients with acute cerebral infarction were enrolled. The baseline data and serological indicators were collected and the cognitive function of patients was evaluated. All patients were divided into cognitive impairment group and normal group based on follow-up results. The differences of Aβ1-42, tau protein and thyroxine levels between the two groups and their relationship with disease progression were analyzed. The Cox regression analysis and ROC curve were used to compare the above parameters to predict the development of PSCI. Results The total protein level of Tau (210.6 ±98.9 pg/mL) was higher and Aβ1-42 (426.1 ±123.5 pg/mL) and triiodothyronine (T3) (1.43 ±0.57 nmol/L), free thyroxine (FT4) (13.15±2.23 pmol/L) was significantly lower in the cognitive impairment group than in the normal group (P<0.05). Tau protein (r=-0.457), Aβ1-42 (r=0.348), T3 (r=0.211), and FT4 (r=0.306) were all associated with disease progression (P<0.05). Cox regression analysis showed that Aβ1-42 and T3 were important influencing factors in the occurrence of PSCI. The area under the curve of Aβ1-42 combined with T3 was 0.841. The specificity and the sensitivity were 74.8% and 85.3%, respectively, with a diagnostic cutoff value of 0.572. Conclusion Aβ1-42 and T3 levels in the acute phase of cerebral infarction may predict the progression of PSCI.