Objective To develop a personalized recommendation strategy for tranexamic acid administration during the perioperative period of orthopedic surgery based on machine learning,aiming to reduce perioperative bleeding and related complications and improving clinical outcomes.Methods A total of 11 727 patients undergoing orthopedic surgery from the INSPIRE database were subjected in this study.Missing data were handled using multiple imputation methods,and relevant feature variables were screened using Boruta analysis.We constructed various machine learning models,including Gradient Boosting Machine(GBM),Generalized Linear Model(GLM),eXtreme Gradient Boosting(XGBoost),K-Nearest Neighbors(KNN),Neural Network(NNET),Naive Bayes(NB),and Random Forest(RF),to evaluate their performance in predicting intraoperative bleeding and prolonged postoperative length of hospital stay.The optimal model was then selected and further integrated using a weighted ensemble,aiming to achieve the best prognosis by recommending usage strategies for tranexamic acid.The predictive performance of the constructed model was then verified against the testing set,and compared with the physician decision-making to complete the evaluation.Results In predicting intraoperative bleeding,the RF model achieved an area under the receiver operating characteristic curve(AUC)of 0.73,which was significantly better than other models.In predicting the prolonged postoperative length of hospital stay,the XGBoost model performed the best,with an AUC value of 0.84.Based on the above best-performing models,an ensemble strategy was implemented.The patients who followed the recommended strategy had reduced intraoperative bleeding and shorter postoperative length of hospital stay.Conclusion The use of tranexamic acid is associated with intraoperative bleeding and postoperative length of hospital stay.Personalized decision-making recommendation based on our constructed model can effectively improve the outcomes of the patients undergoing orthopedic surgery.

Objective:To evaluate the safety and efficacy of the probiotic Bifidobacterium longum subsp. longum BL21 (BL21) in preventing radiation-induced diarrhea (RID) in cervical cancer patients during radiotherapy (RT) and to investigate the intestinal microbiota in the patients. Methods:This study was a prospective, single-arm, phase Ⅱ clinical trial, involving cervical cancer patients treated with radical and adjuvant RT. From the first day of RT, participants took one pack of BL21 powder (containing 20 billion colony-forming unit(CFU) of Bifidobacterium longum subsp. longum BL21) orally every day until the end of RT. The occurrence of adverse events and RID during RT were assessed as per Common Terminology Criteria for Adverse Events ( CTCAE) v5.0. In this way, the safety and efficacy of BL21 in preventing RID were evaluated. Additionally, the intestinal microbiota in fecal samples collected from the patients before and after RT were analyzed using 16S rRNA sequencing. Results:A total of 35 cervical cancer patients were enrolled in this study, with 29 cases incorporated for the final analysis. No serious adverse event related to the administration of BL21 was observed. The patients exhibited slight RID, with the majority (22/29) developing no or grade 1 RID during RT. The microbiota in the fecal samples showed decreased alpha diversity after RT, as indicated by the Chao1 ( P = 0.002) and Shannon ( P = 0.005) indices. Furthermore, these samples exhibited a notably higher abundance of genus Clostridium (LDA score = 3.98). The fecal samples from patients with grade 1 RID or no RID post-RT exhibited higher alpha diversity than those from patients with grade 2 RID or above post-RT (Chao1: P = 0.07, Shannon: P = 0.28), as well as a high abundance of genera Gemmiger (LDA score = 4.48) and Dorea (LDA score = 3.83). Conclusions:The administration of BL21 to cervical cancer patients during RT is simple, convenient, safe, and effective in preventing RID, thus warranting further investigation.

The theory of the "Three Phases of moxibustion sensation", originating from ZHOU Meisheng's Moxibustion Cord, summarizes the clinical transmission process of moxibustion sensation into three phases: initial sensation, diffusion, and conduction. Inspired by this theory, the authors analyze factors affecting moxibustion sensation-including moxibustion temperature, location, dose, and technique-and summarize its guiding role in clinical practice. It is proposed that in clinical application, the generation pattern of the initial sensation phase can be used to judge the immediate efficacy of moxibustion and adjust treatment locations accordingly; the diffusion pattern of the diffusion phase can help assess individual moxibustion dose to ensure optimal therapeutic effects; and the conduction phase not only indicates the endpoint of moxibustion therapy but can also reveal hidden lesions and deeper pathological causes in patients. In addition, due to differences in patient constitution and disease state, the manifestation of moxibustion sensation may not always strictly follow the pattern of the "Three Phases", requiring careful clinical differentiation.
Moxibustion/methods* ; Humans ; Sensation ; Acupuncture Points

Objective To investigate the indications,therapeutic effects,and compatibility patterns of modified Sini San formulas.Methods Modified Sini San formulas recorded in the Selected Compilation of Encyclopedia of Chinese Medicinal Formulas were retrieved.Frequency analysis,cluster analysis,and association rule mining were performed on the herbs of Sini San modified formulas.Results A total of 34 modified Sini San formulas were included,involving 127 additional medicinals.Analysis of the properties,flavors,and meridian tropism of the top 30 high-frequency additional medicinals,including Chuanxiong Rhizoma,Angelicae Sinensis Radix,Scutellariae Radix,Cortex Magnoliae Officinalis,Rehmanniae Radix,Rhei Radix et Rhizoma,Poria,Ginseng Radix et Rhizoma,Cyperi Rhizoma,Pinelliae Rhizoma,Atractylodis Rhizoma,and Citri Reticulatae Pericarpium,revealed that the additional medicinals were predominantly warm in nature,bitter in flavor,and acted the spleen meridian.Cluster analysis yielded six categories of medicinal combinations.Association rule mining identified that Sini San was frequently prescribed by combining with single herbs of Chuanxiong Rhizoma,Angelicae Sinensis Radix,and Rehmanniae Radix,or with herbal groups of Chuanxiong Rhizoma-Angelicae Sinensis Radix,Angelicae Sinensis Radix-Rehmanniae Radix,Angelicae Sinensis Radix-Persicae Semen,Angelicae Sinensis Radix-Carthami Flos,Platycodonis Radix-Chuanxiong Rhizoma,and Carthami Flos-Persicae Semen-Angelicae Sinensis Radix.Conclusion Later physicians have expanded the application of Sini San after modification to treat externally contracted diseases with exterior syndrome,epidemic diseases,abdominal masses,eye disorders,and other conditions.Sini San is often used in combination with formulas such as Taohong Siwu Decoction and Yueju Pills.Commonly-paired additional medicinals fall into six primary categories corresponding to its expanded therapeutic applications,i.e.,stasis-resolving,blood-activating,exterior-releasing,qi-regulating,deficiency-supplementing,and purgative medicinals.The analytical results may provide new insights for modern clinical applications-pharmacological research on Sini San.

Objective:To evaluate the safety and efficacy of the probiotic Bifidobacterium longum subsp. longum BL21 (BL21) in preventing radiation-induced diarrhea (RID) in cervical cancer patients during radiotherapy (RT) and to investigate the intestinal microbiota in the patients. Methods:This study was a prospective, single-arm, phase Ⅱ clinical trial, involving cervical cancer patients treated with radical and adjuvant RT. From the first day of RT, participants took one pack of BL21 powder (containing 20 billion colony-forming unit(CFU) of Bifidobacterium longum subsp. longum BL21) orally every day until the end of RT. The occurrence of adverse events and RID during RT were assessed as per Common Terminology Criteria for Adverse Events ( CTCAE) v5.0. In this way, the safety and efficacy of BL21 in preventing RID were evaluated. Additionally, the intestinal microbiota in fecal samples collected from the patients before and after RT were analyzed using 16S rRNA sequencing. Results:A total of 35 cervical cancer patients were enrolled in this study, with 29 cases incorporated for the final analysis. No serious adverse event related to the administration of BL21 was observed. The patients exhibited slight RID, with the majority (22/29) developing no or grade 1 RID during RT. The microbiota in the fecal samples showed decreased alpha diversity after RT, as indicated by the Chao1 ( P = 0.002) and Shannon ( P = 0.005) indices. Furthermore, these samples exhibited a notably higher abundance of genus Clostridium (LDA score = 3.98). The fecal samples from patients with grade 1 RID or no RID post-RT exhibited higher alpha diversity than those from patients with grade 2 RID or above post-RT (Chao1: P = 0.07, Shannon: P = 0.28), as well as a high abundance of genera Gemmiger (LDA score = 4.48) and Dorea (LDA score = 3.83). Conclusions:The administration of BL21 to cervical cancer patients during RT is simple, convenient, safe, and effective in preventing RID, thus warranting further investigation.