Objective To compare the performance and efficacy of prognostic models constructed by different machine learning algorithms in predicting the survival period of lung transplantation (LTx) recipients. Methods Data from 483 recipients who underwent LTx were retrospectively collected. All recipients were divided into a training set and a validation set at a ratio of 7:3. The 24 collected variables were screened based on variable importance (VIMP). Prognostic models were constructed using random survival forest (RSF) and extreme gradient boosting tree (XGBoost). The performance of the models was evaluated using the integrated area under the curve (iAUC) and time-dependent area under the curve (tAUC). Results There were no significant statistical differences in the variables between the training set and the validation set. The top 15 variables ranked by VIMP were used for modeling and the length of stay in the intensive care unit (ICU) was determined as the most important factor. Compared with the XGBoost model, the RSF model demonstrated better performance in predicting the survival period of recipients (iAUC 0.773 vs. 0.723). The RSF model also showed better performance in predicting the 6-month survival period (tAUC _{6 months} 0.884 vs. 0.809, P = 0.009) and 1-year survival period (tAUC _{1 year} 0.896 vs. 0.825, P = 0.013) of recipients. Based on the prediction cut-off values of the two algorithms, LTx recipients were divided into high-risk and low-risk groups. The survival analysis results of both models showed that the survival rate of recipients in the high-risk group was significantly lower than that in the low-risk group (P<0.001). Conclusions Compared with XGBoost, the machine learning prognostic model developed based on the RSF algorithm may preferably predict the survival period of LTx recipients.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

This study aims to reveal the effect and mechanism of Gentianella turkestanorum total extract(GTI) in ameliorating non-alcoholic steatohepatitis(NASH). UPLC-Q-TOF-MS was employed to identify the chemical components in GTI. SwissTarget-Prediction, GeneCards, OMIM, and TTD were utilized to screen the targets of GTI components and NASH. The common targets shared by GTI components and NASH were filtered through the STRING database and Cytoscape 3.9.0 to identify core targets, followed by GO and KEGG enrichment analysis. AutoDock was used for molecular docking of key components with core targets. A mouse model of NASH was established with a methionine-choline-deficient high-fat diet. A 4-week drug intervention was conducted, during which mouse weight was monitored, and the liver-to-brain ratio was measured at the end. Hematoxylin-eosin staining, Sirius red staining, and oil red O staining were employed to observe the pathological changes in the liver tissue. The levels of various biomarkers, including aspartate aminotransferase(AST), alanine aminotransferase(ALT), hydroxyproline(HYP), total cholesterol(TC), triglycerides(TG), low-density lipoprotein cholesterol(LDL-C), high-density lipoprotein cholesterol(HDL-C), malondialdehyde(MDA), superoxide dismutase(SOD), and glutathione(GSH), in the serum and liver tissue were determined. RT-qPCR was conducted to measure the mRNA levels of interleukin 1β(IL-1β), interleukin 6(IL-6), tumor necrosis factor α(TNF-α), collagen type I α1 chain(COL1A1), and α-smooth muscle actin(α-SMA). Western blotting was conducted to determine the protein levels of IL-1β, IL-6, TNF-α, and potential drug targets identified through network pharmacology. UPLC-Q-TOF/MS identified 581 chemical components of GTI, and 534 targets of GTI and 1 157 targets of NASH were screened out. The topological analysis of the common targets shared by GTI and NASH identified core targets such as IL-1β, IL-6, protein kinase B(AKT), TNF, and peroxisome proliferator activated receptor gamma(PPARG). GO and KEGG analyses indicated that the ameliorating effect of GTI on NASH was related to inflammatory responses and the phosphoinositide 3-kinase(PI3K)/AKT pathway. The staining results demonstrated that GTI ameliorated hepatocyte vacuolation, swelling, ballooning, and lipid accumulation in NASH mice. Compared with the model group, high doses of GTI reduced the AST, ALT, HYP, TC, and TG levels(P<0.01) while increasing the HDL-C, SOD, and GSH levels(P<0.01). RT-qPCR results showed that GTI down-regulated the mRNA levels of IL-1β, IL-6, TNF-α, COL1A1, and α-SMA(P<0.01). Western blot results indicated that GTI down-regulated the protein levels of IL-1β, IL-6, TNF-α, phosphorylated PI3K(p-PI3K), phosphorylated AKT(p-AKT), phosphorylated inhibitor of nuclear factor kappa B alpha(p-IκBα), and nuclear factor kappa B(NF-κB)(P<0.01). In summary, GTI ameliorates inflammation, dyslipidemia, and oxidative stress associated with NASH by regulating the PI3K/AKT/NF-κB signaling pathway.
Animals ; Non-alcoholic Fatty Liver Disease/genetics* ; Mice ; Network Pharmacology ; Male ; Drugs, Chinese Herbal/administration & dosage* ; Chromatography, High Pressure Liquid ; Liver/metabolism* ; Mice, Inbred C57BL ; Humans ; Mass Spectrometry ; Tumor Necrosis Factor-alpha/metabolism* ; Disease Models, Animal ; Molecular Docking Simulation

OBJECTIVE: To explore the early clinical efficacy of a three-stage external treatment with traditional Chinese medicine (TCM) in the treatment of talar bone contusion caused by acute ankle sprain. METHODS: A retrospective analysis was performed on 360 patients with primary lateral ankle sprain admitted from September 2021 to July 2024. Patients with talar bone contusion were selected based on MRI examination, and 73 cases were finally included. According to different treatment methods, they were divided into the observation group and the control group. The observation group consisted of 35 cases, including 16 males and 19 females, aged 24 to 37 years old with an average of (30.34±2.68) years old, and received the three-stage external TCM treatment combined with the "POLICE" protocol. The control group included 38 cases, including 18 males and 20 females, aged 24 to 35 years old with an average of (29.87±2.57) years old, and was treated with the "POLICE" protocol alone. The volume of bone marrow edema (BME) area shown by MRI before treatment and 6 weeks after treatment was measured using 3D Slicer software, and the BME improvement rate was calculated. The "Figure of 8" measurement method was used to assess ankle swelling before treatment and at 1 and 3 weeks after treatment. The visual analogue scale (VAS) was used to evaluate ankle pain before treatment and at 1 and 6 weeks after treatment. At 6 weeks after treatment, the American Orthopaedic Foot and Ankle Society (AOFAS) ankle-hindfoot score and Karlsson ankle function score system were used to evaluate the improvement of ankle function. RESULTS: A total of 73 patients with talar bone contusion caused by ankle sprain completed the 6-week follow-up. At 6 weeks after treatment, the BME improvement rate in the observation group was (39.18±0.06)%, which was higher than (26.75±0.03)% in the control group, with a statistically significant difference (P<0.05). After 1 week of treatment, the VAS score in the observation group was (2.89±0.72) points, lower than (3.37±0.79) points in the control group, and the difference was statistically significant (P<0.05). The ankle swelling degree in the observation group was (50.20±3.19) cm, lower than (52.00±3.60) cm in the control group, with a statistically significant difference (P<0.05). After 3 weeks of treatment, there was no statistically significant difference in ankle swelling between the two groups. At 6 weeks after treatment, there was no statistically significant difference in VAS scores between the two groups. At 6 weeks after treatment, the AOFAS ankle-hindfoot score and Karlsson score in the observation group were (87.43±4.18) and (82.77±5.93) points, respectively, which were higher than (82.92±4.87) and (76.45±6.85) points in the control group, with statistically significant differences (P<0.05). According to the AOFAS ankle-hindfoot score, 8 cases were excellent and 27 cases were good in the observation group;2 cases were excellent, 33 cases were good, and 3 cases were fair in the control group. The difference between the two groups was statistically significant (χ²=7.089, P=0.029). CONCLUSION The three-stage external TCM treatment combined with the "POLICE" protocol has a significant early clinical efficacy. It can significantly reduce ankle pain and swelling in patients with bone contusion caused by acute lateral ankle sprain, promote the absorption of bone marrow edema, and accelerate the recovery of ankle function.
Ankle Injuries/drug therapy* ; Drugs, Chinese Herbal/administration & dosage* ; Talus/injuries* ; Retrospective Studies ; Administration, Cutaneous ; Magnetic Resonance Imaging ; Humans ; Male ; Female ; Young Adult ; Adult ; Contusions/etiology* ; Visual Analog Scale ; Musculoskeletal Pain/etiology* ; Recovery of Function/drug effects* ; Treatment Outcome ; Follow-Up Studies

OBJECTIVE: To explore the differences in clinical efficacy between enhanced workflows and express workflows in robotic-assisted total hip arthroplasty(THA). METHODS: A retrospective analysis was conducted on 46 patients who underwent robotic-assisted THA between November 2020 and May 2021. They were divided into the enhanced workflows group and the express workflows group based on the surgical methods. There were 20 patients in the enhanced workflows group, including 11 males and 9 females;aged from 51 to 78 years old with an average of (67.30±7.52) years old. The BMI ranged from 18.24 to 24.03 kg·m^-2 with an average of(23.80±3.01) kg·m^-2. There were 26 patients in the express workflows group, including 12 males and 14 females;aged from 57 to 84 years old with a mean age of (67.58±7.29) years old, and their BMI ranged from 19.72 to 30.08 kg·m^-2 with an average of (24.41 ±2.92) kg·m^-2. The operation time, hospital stay, and perioperative complications of the patients were recorded. The postoperative acetabular prosthesis anteversion angle, abduction angle, limb length, and offset distance data were measured. The Harris hip score at the latest follow-up was recorded. RESULTS: All patients completed the surgery as planned and were followed up, with the follow-up period ranging from 47 to 54 months with a mean of (49.78±1.85) months and the length of hospital stay ranging from 2 to 11 days with an average of (6.57±1.82 ) days. The operation time of enhanced workflows group was (93.41±16.41) minutes, which was longer than that of the express workflow groups (75.19±18.36) minutes, and the difference was statistically significant (P<0.05). In enhanced workflows group, the postoperative acetabular anteversion angle was (19.20±4.46)°, the limb length discrepancy was (-1.55±9.13) mm, and changes of the offset was (-5.15±6.77) mm. The corresponding values in express workflows group were (20.46±3.29)°, (2.19±4.39) mm, and (-2.39±4.34) mm, respectively. There was no statistically significant difference in these indicators between the two groups(P>0.05). One patient in the enhanced workflows group developed deep venous thrombosis after surgery. No cases of dislocation or periprosthetic infection. At the latest follow-up, all patients had well-positioned prostheses without loosening. Harris hip score was (90.50±1.67) points in enhanced workflows group and (90.73±2.36) points in the express workflows group, with no statistically significant difference between the two groups (P>0.05). CONCLUSION The clinical efficacy of robot assisted total hip arthroplasty technology is satisfactory. The enhanced workflows will increase the surgical time. For patients with normal anatomical hip joint disease, this study did not find significant advantages in joint stability and functional scoring for the enhanced workflows.
Humans ; Arthroplasty, Replacement, Hip/methods* ; Male ; Female ; Aged ; Middle Aged ; Robotic Surgical Procedures/methods* ; Retrospective Studies ; Aged, 80 and over ; Workflow ; Treatment Outcome

OBJECTIVE: To investigate the characteristics of gut microbiota changes in patients with acute myeloid leukemia (AML) undergoing induction chemotherapy and to explore the relationship between infectious complications and gut microbiota. METHODS: Fecal samples were collected from 37 newly diagnosed AML patients at four time points: before induction chemotherapy, during chemotherapy, during the neutropenic phase, and during the recovery phase. Metagenomic sequencing was used to analyze the dynamic changes in gut microbiota. Correlation analyses were conducted to assess the relationship between changes in gut microbiota and the occurrence of infectious complications. RESULTS: During chemotherapy, the gut microbiota α-diversity (Shannon index) of AML patients exhibited significant fluctuations. Specifically, the diversity decreased significantly during induction chemotherapy, further declined during the neutropenic phase (P < 0.05, compared to baseline), and gradually recovered during the recovery phase, though not fully returning to baseline levels.The abundances of beneficial bacteria, such as Firmicutes and Bacteroidetes, gradually decreased during chemotherapy, whereas the abundances of opportunistic pathogens, including Enterococcus, Klebsiella, and Escherichia coli, progressively increased.Analysis of the dynamic changes in gut microbiota of seven patients with bloodstream infections revealed that the bloodstream infection pathogens could be detected in the gut microbiota of the corresponding patients, with their abundance gradually increasing during the course of infection. This finding suggests that bloodstream infections may be associated with opportunistic pathogens originating from the gut microbiota.Compared to non-infected patients, the baseline samples of infected patients showed a significantly lower relative abundance of Bacteroidetes (P < 0.05). Regression analysis indicated that Bacteroidetes abundance is an independent predictive factor for infectious complications (P < 0.05, OR =13.143). CONCLUSION During induction chemotherapy in AML patients, gut microbiota α-diversity fluctuates significantly, and the abundance of opportunistic pathogens increase, which may be associated with bloodstream infections. Patients with lower baseline Bacteroidetes abundance are more prone to infections, and its abundance can serve as an independent predictor of infectious complications.
Humans ; Gastrointestinal Microbiome ; Leukemia, Myeloid, Acute/microbiology* ; Induction Chemotherapy ; Feces/microbiology* ; Male ; Female ; Middle Aged