E-eye and FT-NIR combined with multivariate algorithms to rapidly evaluate the dynamic changes in the quality of Gastrodia elata during steaming process.

Gastrodia elata (GE) is traditionally subjected to steaming, and steaming duration plays a crucially important role in determining GE quality. This study examined the variations in bioactive components during the steaming process and proposed the utilization of electronic eye and Fourier Transform near-infrared (FT-NIR) spectroscopy for quality assessment. The findings revealed that the levels of parishin E parishin B, parishin A, and gastrodin initially rose and subsequently declined, while 4-Hydroxybenzyl alcohol exhibited a rapid decrease followed by stabilization. With prolonged steaming, the brightness of GE decreased, while the red and yellow tones became more pronounced and the color saturation increased. FT-NIR divided the steaming process into three stages: 0 min (raw GE), 0-9 min (partially steamed GE), and 9-30 min (fully steamed GE), and the partial least squares regression models effectively predicted the levels of five components. Overall, this study provided valuable insights into quality control in food processing.

Rapid evaluation of Ziziphi Spinosae Semen and its adulterants based on the combination of FT-NIR and multivariate algorithms.

Ziziphi Spinosae Semen (ZSS) is a valued seed renowned for its sedative and sleep-enhancing properties. However, the price increase has been accompanied by adulteration. In this study, chromaticity analysis and Fourier transform near-infrared (FT-NIR) combined with multivariate algorithms were employed to identify the adulteration and quantitatively predict the adulteration ratio. The findings suggested that the utilization of chromaticity extractor was insufficient for identification of adulteration ratio. The raw spectrum of ZMS and HAS adulterants extracted by FT-NIR was processed by SNV + CARS and 1d + SG + ICO respectively, the average accuracy of machine learning classification model was improved from 77.06 % to 97.58 %. Furthermore, the R2 values of the calibration and prediction set of the two quantitative prediction regression models of adulteration ratio are greater than 0.99, demonstrating excellent linearity and predictive accuracy. Overall, this study demonstrated that FT-NIR combined with multivariate algorithms provided a significant approach to addressing the growing issue of ZSS adulteration.

[Discrimination of different processing degrees and quantitative study of processing end point of vinegar-processing Cyperi Rhizoma pieces based on electronic sensory technology].

In this study, CM-5 spectrophotometer and Heracles NEO ultra-fast gas-phase electronic nose were used to analyze the changes in color and odor of vinegar-processed Cyperi Rhizoma(VPCR) pieces. Various analysis methods such as DFA and partial least squares discriminant analysis(PLS-DA) were combined to identify different processing degrees and quantify the end point of processing. The results showed that with the increase in vinegar processing, the brightness parameter L~* of VPCR pieces decreased gradua-lly, while the red-green value a~* and yellow-blue value b~* initially increased and reached their maximum at 8 min of processing, followed by a gradual decrease. A discriminant model based on the color parameters L~*, a~*, and b~* was established(with a discrimination accuracy of 98.5%), which effectively differentiated different degrees of VPCR pieces. Using the electronic nose, 26 odor components were identified from VPCR samples at different degrees of vinegar processing. DFA and PLS-DA models were established for different degrees of VPCR pieces. The results showed that the 8-min processed samples were significantly distinct from other samples. Based on variable importance in projection(VIP) value greater than 1, 10 odor components, including 3-methylfuran, 2-methylbuty-raldehyde, 2-methylpropionic acid, furfural, and α-pinene, were selected as odor markers for differentiating the degrees of vinegar processing in VPCR. By combining the changes in color and the characteristic odor components, the optimal processing time for VPCR was determined to be 8 min. This study provided a scientific basis for the standardization of vinegar processing techniques for VPCR and the improvement of its quality standards and also offered new methods and ideas for the rapid identification and quality control of the end point of processing for other traditional Chinese medicine.

Effectiveness and safety of traditional Chinese medicine for diabetic retinopathy: A systematic review and network meta-analysis of randomized clinical trials.

BACKGROUND: Diabetic retinopathy (DR) is currently recognized as one of the most serious diabetic microangiopathies and a major cause of adult blindness. Commonly used clinical approaches include etiological control, microvascular improvement, and surgical intervention, but they are ineffective and have many side effects. Oral Chinese medicine (OCM) has been used for thousands of years to treat DR and is still widely used today, but it is unclear which OCM is more effective for DR. AIM: To estimate relative effectiveness and safety profiles for different classes of OCMs for DR, and provide rankings of the available OCMs. METHODS: The search time frame was from the creation of the database to January 2023. RevMan 5.3 and Stata 14.0 software were used to perform the systematic review and Network meta-analyses (NMA). RESULTS: A total of 107 studies and 9710 patients were included, including 4767 cases in the test group and 4973 cases in the control group. Based on previous studies and clinical reports, and combined with the recommendations of Chinese guidelines for the prevention and treatment of DR, 9 OCMs were finally included in this study, namely Compound Xueshuantong Capsules, Qiming Granules, Compound Danshen Dripping Pills, Hexue Mingmu Tablets (HXMM), Qiju Dihuang Pills (QJDH), Shuangdan Mingmu Capsules (SDMM), Danggui Buxue Decoction (DGBX), Xuefu Zhuyu Decoction and Buyang Huanwu Decoction. When these nine OCMs were analyzed in combination with conventional western medicine treatment (CT) compared with CT alone, the NMA results showed that HXMM + CT has better intervention effect on the overall efficacy of DR patients, HXMM + CT has better effect on improving patients' visual acuity, SDMM + CT has better effect on inhibiting vascular endothelial growth factor, DGBX + CT has better effect on reducing fundus hemorrhage area, HXMM + CT has better effect on reducing fasting blood glucose, and QJDH + CT has better effect on reducing glycated hemoglobin. When there are not enough clinical indicators for reference, SDMM + CT or HXMM + CT treatments can be chosen because they are effective for more indicators and demonstrate multidimensional efficacy. CONCLUSION: This study provides evidence that combining OCMs with CT leads to better outcomes in all aspects of DR compared to using CT alone. Based on the findings, we highly recommend the use of SDMM or HXMM for the treatment of DR. These two OCMs have demonstrated outstanding efficacy across multiple indicators.

Meta-analysis of outcomes from drug-eluting stent implantation in infrapopliteal arteries.

BACKGROUND: Percutaneous drug-eluting stent implantation (DESI) is an emerging and promising treatment modality for infrapopliteal artery diseases (IPADs). This systematic review and meta-analysis summarizes and quantitatively analyzes the outcomes of DESI in IPADs considering the hazard ratio (HR), which is a more accurate and appropriate outcome measure than the more commonly used relative risk and odds ratio. AIM: To explore the superiority of drug-eluting stents (DESs) vs traditional treatment modalities for IPADs. METHODS: The following postoperative indicators were the outcomes of interest: All-cause death (ACD)-free survival, major amputation (MA)-free survival, target lesion revascularization (TLR)-free survival, adverse event (AE)-free survival, and primary patency (PP) survival. The outcome measures were then compared according to their respective HRs with 95% confidence intervals (CIs). The participants were human IPAD patients who underwent treatments for infrapopliteal lesions. DESI was set as the intervention arm, and traditional percutaneous transluminal angioplasty (PTA) with or without bare metal stent implantation (BMSI) was set as the control arm. A systematic search in the Excerpta Medica Database (Embase), PubMed, Web of Science, and Cochrane Library was performed on November 29, 2022. All controlled studies published in English with sufficient data on outcomes of interest for extraction or conversion were included. When studies did not directly report the HRs but gave a corresponding survival curve, we utilized Engauge Digitizer software and standard formulas to convert the information and derive HRs. Then, meta-analyses were conducted using a random-effects model. RESULTS: Five randomized controlled trials and three cohort studies involving 2639 participants were included. The ACD-free and MA-free survival HR values for DESI were not statistically significant from those of the control treatment (P > 0.05); however, the HR values for TLR-free, AE-free, and PP-survival differed significantly [2.65 (95%CI: 1.56-4.50), 1.57 (95%CI: 1.23-2.01), and 5.67 (95%CI: 3.56-9.03), respectively]. CONCLUSION: Compared with traditional treatment modalities (i.e., PTA with or without BMSI), DESI for IPADs is superior in avoiding TLR and AEs and maintaining PP but shows no superiority or inferiority in avoiding ACD and MA.

Control status of ambulatory blood pressure and its relationship with arterial stiffness in the China nationwide registry of treated hypertensive patients: the REACTION-ABP study.

The control rate of ambulatory blood pressure (BP) is unclear in Chinese hypertensive patients, and whether it would be associated with the ambulatory arterial stiffness indices is also unknown. From June 2018 until December 2022, 4408 treated hypertensive patients (52.8% men, average age 58.2 years) from 77 hospitals in China were registered. Ambulatory BPs were measured with validated monitors and analyzed with a web-based standardized Shuoyun system ( www.shuoyun.com.cn ). The BP control rate was the highest in the office (65.7%), moderate in the daytime (45.0%), low in the morning (34.1%), and the lowest in the nighttime (27.6%, P < 0.001). Only 21.0% had their 24 h BP perfectly controlled. The stepwise regression analyses identified that the factors associated with an imperfect 24 h BP control included male sex, smoking and drinking habits, a higher body mass index, serum total cholesterol and triglycerides, and the use of several specific types of antihypertensive drugs. After adjustment for the above-mentioned factors, the 24 h pulse pressure (PP) and its components, the elastic and stiffening PPs, were all significantly associated with an uncontrolled office and ambulatory BP status with the standardized odds ratios ranging from 1.09 to 4.68 (P < 0.05). The ambulatory arterial stiffness index (AASI) was only associated with an uncontrolled nighttime and 24 h BP status. In conclusion, the control rates of 24 h ambulatory BP, especially that in the nighttime and morning time windows, were low in Chinese hypertensive patients, which might be associated with arterial stiffness in addition to other common risk factors.

Brachial and central hypertension in relation to coronary stenosis in patients with coronary angiography.

The clinical significance of central beyond brachial blood pressure (BP) remains unclear. In patients who underwent coronary angiography, the authors explored whether elevated central BP would be associated with coronary arterial disease (CAD) irrespective of the status of brachial hypertension. From March 2021 to April 2022, 335 patients (mean age 64.9 years, 69.9% men) hospitalized for suspected CAD or unstable angina were screened in an ongoing trial. CAD was defined if a coronary stenosis of ≥50%. According to the presence of brachial (non-invasive cuff systolic BP ≥140 mmHg or diastolic BP ≥90 mmHg) and central (invasive systolic BP ≥130 mmHg) hypertension, patients were cross-classified as isolated brachial hypertension (n = 23), isolated central hypertension (n = 93), and concordant normotension (n = 100) or hypertension (n = 119). In continuous analyses, both brachial and central systolic BPs were significantly related to CAD with similar standardized odds ratios (OR, 1.47 and 1.45, p < .05). While categorical analyses showed that patients with isolated central hypertension or concordant hypertension had a significantly higher prevalence of CAD and the Gensini score than those with concordant normotension. Multivariate-adjusted OR (95% confidence interval [CI]) for CAD was 2.24 (1.16 to 4.33, p = .009) for isolated central hypertension and 3.02 (1.58 to 5.78, p < .001) for concordant hypertension relative to concordant normotension. The corresponding OR (95% CI) of a high Gensini score was 2.40 (1.26-4.58) and 2.17 (1.19-3.96), respectively. In conclusion, regardless of the presence of brachial hypertension, elevated central BP was associated with the presence and severity of CAD, indicating that central hypertension is an important risk factor for coronary atherosclerosis.

E-eye, flash GC E-nose and HS-GC-MS combined with chemometrics to identify the adulterants and geographical origins of Ziziphi Spinosae Semen.

Ziziphi Spinosae Semen (ZSS), a valuable seed food, has faced increasing authenticity issues. In this study, the adulterants and geographical origins of ZSS were successfully identified by electronic eye, flash gas chromatography electronic nose (Flash GC e-nose) and headspace gas chromatography-mass spectrometry (HS-GC-MS). As a result, there were color differences between ZSS and adulterants, mainly represented by the a* value of ZSS was less than adulterants. In ZSS, 29 and 32 compounds were detected by Flash GC e-nose and HS-GC-MS. Spicy, sweety, fruity and herbal were the main flavor of ZSS. Five compounds were determined to be responsible for flavor differences between different geographical origins. In the HS-GC-MS analysis, the relative content of Hexanoic acid was the highest in ZSS from Hebei and Shandong, while 2,4-Decadien-1-ol was the highest in Shaanxi. Overall, this study provided a meaningful strategy for addressing authenticity problems of ZSS and other seed foods.

UPLC-Q-TOF/MS-Based Serum Metabolomics Reveals Potential Anti-tumor Mechanism of Banxia Xiexin Decoction in Colorectal Cancer Mice.

OBJECTIVE: To clarify the potential mechanism of Banxia Xiexin Decoction (BXD) on colorectal cancer (CRC) from the perspective of metabolomics. METHODS: Forty male C57BL/6 mice were randomly divided into normal control (NC), azoxymethane/dextran sulfate sodium (AOM/DSS) model, low-dose BXD (L-BXD), high-dose BXD (H-BXD) and mesalamine (MS) groups according to a random number table, 8 mice in each group. Colorectal cancer model was induced by AOM/DSS. BXD was administered daily at doses of 3.915 (L-BXD) and 15.66 g/kg (H-BXD) by gavage for consecutive 21 days, and 100 mg/kg MS was used as positive control. Following the entire modeling cycle, colon length of mice was measured and quantity of colorectal tumors were counted. The spleen and thymus index were determined by calculating the spleen/thymus weight to body weight. Inflammatory cytokine and changes of serum metabolites were analyzed by enzyme-linked immunosorbent assay kits and ultra performance liquid chromatography-quadrupole/time-of-flight mass spectrometry (UPLC-Q/TOF-MS), respectively. RESULTS: Notably, BXD supplementation protected against weight loss, mitigated tumor formation, and diminished histologic damage in mice treated with AOM/DSS (P<0.05 or P<0.01). Moreover, BXD suppressed expression of serum inflammatory enzymes, and improved the spleen and thymus index (P<0.05). Compared with the normal group, 102 kinds of differential metabolites were screened in the AOM/DSS group, including 48 potential biomarkers, involving 18 main metabolic pathways. Totally 18 potential biomarkers related to CRC were identified, and the anti-CRC mechanism of BXD was closely related to D-glutamine and D-glutamate metabolism, phenylalanine, tyrosine and tryptophan biosynthesis, arginine biosynthesis, nitrogen metabolism and so on. CONCLUSION: BXD exerts partial protective effects on AOM/DSS-induced CRC by reducing inflammation, protecting organism immunity ability, and regulating amino acid metabolism.

[Rapid identification and differential markers of Curcumae Radix decoction pieces of different sources based on Heracles Neo ultra-fast gas phase electronic nose].

Since Curcumae Radix decoction pieces have multiple sources, it is difficult to distinguish depending on traditional cha-racters, and the mixed use of multi-source Curcumae Radix will affect its clinical efficacy. Heracles Neo ultra-fast gas phase electronic nose was used in this study to quickly identify and analyze the odor components of 40 batches of Curcumae Radix samples from Sichuan, Zhejiang, and Guangxi. Based on the odor fingerprints established for Curcumae Radix decoction pieces of multiple sources, the odor components was identified and analyzed, and the chromatographic peaks were processed and analyzed to establish a rapid identification method. Principal component analysis(PCA), discriminant factor analysis(DFA), and soft independent modeling cluster analysis(SIMCA) were constructed for verification. At the same time, one-way analysis of variance(ANOVA) combined with variable importance in projection(VIP) was employed to screen out the odor components with P<0.05 and VIP>1, and 13 odor components such as ß-caryophyllene and limonene were hypothesized as the odor differential markers of Curcumae Radix decoction pieces of diffe-rent sources. The results showed that Heracles Neo ultra-fast gas phase electronic nose can well analyze the odor characteristics and rapidly and accurately discriminate Curcumae Radix decoction pieces of different sources. It can be applied to the quality control(e.g., online detection) in the production of Curcumae Radix decoction pieces. This study provides a new method and idea for the rapid identification and quality control of Curcumae Radix decoction pieces.

Seasonality in nighttime blood pressure and its associations with target organ damage.

There is some evidence that nighttime blood pressure varies between seasons. In the present analysis, we investigated the seasonal variation in ambulatory nighttime blood pressure and its associations with target organ damage. In 1054 untreated patients referred for ambulatory blood pressure monitoring, we performed measurements of urinary albumin-to-creatinine ratio (ACR, n = 1044), carotid-femoral pulse wave velocity (cfPWV, n = 1020) and left ventricular mass index (LVMI, n = 622). Patients referred in spring (n = 337, 32.0%), summer (n = 210, 19.9%), autumn (n = 196, 18.6%) and winter (n = 311, 29.5%) had similar 24-h ambulatory systolic/diastolic blood pressure (P ≥ 0.25). However, both before and after adjustment for confounding factors, nighttime systolic/diastolic blood pressure differed significantly between seasons (P < 0.001), being highest in summer and lowest in winter (adjusted mean values 117.0/75.3 mm Hg vs. 111.4/71.1 mm Hg). After adjustment for confounding factors, nighttime systolic/diastolic blood pressure were significantly and positively associated with ACR, cfPWV and LVMI (P < 0.006). In season-specific analyses, statistical significance was reached for all the associations of nighttime blood pressure with target organ damage in summer (P ≤ 0.02), and for some of the associations in spring, autumn and winter. The association between nighttime systolic blood pressure and ACR was significantly stronger in patients examined in summer than those in winter (standardized ß, 0.31 vs 0.11 mg/mmol, P for interaction = 0.03). In conclusion, there is indeed seasonality in nighttime blood pressure level, as well as in its association with renal injury in terms of urinary albumin excretion. Our study shows that there is indeed seasonal variability in nighttime blood pressure, highest in summer and lowest in winter, and its association with renal injury in terms of urinary albumin excretion varies between summer and winter as well.

Highly expressed carbohydrate sulfotransferase 11 correlates with unfavorable prognosis and immune evasion of hepatocellular carcinoma.

Despite great advance has been made in multi-modality treatments for HCC patients, the effectiveness is far from satisfactory with worse survival outcome, which may be partly explainable by the anti-tumor deficiency of the immune system. It is necessary to clarify the molecular mechanism of HCC immunodeficiency. Here, we demonstrated that carbohydrate sulfotransferase 11 (CHST11) was upregulated in HCC and related to advanced TNM stage. HCC patients with TP53 mutation showed higher CHST11 expression. Survival analysis revealed that CHST11 was an independent prognostic biomarker in HCC. Cellular functional experiments indicated that knockdown of CHST11 in HCC inhibited cell proliferation and metastasis. Gene functional enrichment analyses indicated that CHST11 modulated pathways related to tumor growth, metastasis and immune regulation. Continuative immune-related analyses revealed that CHST11 expression facilitated Tregs infiltration in HCC and promoted the expression of checkpoints PD-L1/PD-1, resulting in the immunosuppression of HCC. Targeting CHST11 may inhibit Tregs infiltration and enhance the antineoplastic effect of immune checkpoint inhibitors, which provides a novel insight into the combination immunotherapy with Treg-modulating agents and PD-L1/PD-1 inhibitors.

Preventive effect of one-day outpatient health management on adverse pregnancy outcomes in patients with gestational diabetes mellitus: a retrospective cohort study.

Background: One-day outpatient health management has been applied to treat gestational diabetes mellitus (GDM) and prevent further complications. However, the relationships between one-day outpatient health management and adverse pregnancy outcomes remain ambiguous, because of limited evidence. We analyzed the effects of one-day outpatient health management on premature birth, macrosomia and low-birth-weight infants in patients with GDM. Methods: We retrospectively enrolled pregnant women with GDM who delivered at Guiyang Maternal and Child Health Hospital between 2019 and 2021. Patients could voluntarily choose to participate in either the general outpatient health education or a one-day outpatient health management. Data on demographic and clinical characteristics were collected and pregnancy outcomes ascertained. Logistic regression analysis was used to detect the potential relationship between one-day outpatient health management and adverse pregnancy outcomes including preterm birth, macrosomia, and low-birth-weight infants. GDM, preterm birth, low birth weight and macrosomia was diagnosed according to the criteria established by Obstetrics and Gynecology (9th edition). Results: A total of 3,249 patients with GDM were included, and 798 (24.56%) patients participated in the one-day outpatient health management. Statistically significant differences were observed in the maternal age (P<0.05) and gravidity (P<0.001) between the study and control groups. The incidences of premature birth, low-birth-weight infant, and macrosomia in patients attending the one-day outpatient service were 9.6%, 8.1%, and 4.5%, while the incidences of those who did not attend the one-day outpatient service were 12.4%, 11.1%, and 7.5%. After adjusting for maternal age, ethnic groups, body mass index (BMI) before pregnancy, family history of diabetes, history of abnormal pregnancy, history of polycystic ovary syndrome, gravidity, hyperthyroidism and hypothyroidism, multivariate logistic regression analyses showed that this one-day outpatient health management was a protective factor for premature birth [odds ratio (OR) 0.751, 95% confidence interval (CI): 0.576-0.981], macrosomia (OR 0.567, 95% CI: 0.385-0.834) and low-birth-weight infants (OR 0.699, 95% CI: 0.522-0.937). Conclusions: The degree of acceptance of patients with GDM to a one-day outpatient health management is still low. This one-day outpatient health management may reduce the incidence of adverse pregnancy outcomes in women with GDM to a certain extent.

Using Machine Learning Methods to Predict Bone Metastases in Breast Infiltrating Ductal Carcinoma Patients.

Breast cancer (BC) was the most common malignant tumor in women, and breast infiltrating ductal carcinoma (IDC) accounted for about 80% of all BC cases. BC patients who had bone metastases (BM) were more likely to have poor prognosis and bad quality of life, and earlier attention to patients at a high risk of BM was important. This study aimed to develop a predictive model based on machine learning to predict risk of BM in patients with IDC. Six different machine learning algorithms, including Logistic regression (LR), Naive Bayes classifiers (NBC), Decision tree (DT), Random Forest (RF), Gradient Boosting Machine (GBM), and Extreme gradient boosting (XGB), were used to build prediction models. The XGB model offered the best predictive performance among these 6 models in internal and external validation sets (AUC: 0.888, accuracy: 0.803, sensitivity: 0.801, and specificity: 0.837). Finally, an XGB model-based web predictor was developed to predict risk of BM in IDC patients, which may help physicians make personalized clinical decisions and treatment plans for IDC patients.

Clinical Significance of Integrin Subunit Beta 4 in Head and Neck Squamous Cell Carcinoma.

Background: The expression level and clinical significance of integrin subunit beta 4 (ITGB4) in head and neck squamous cell carcinoma (HNSCC) remain unclear. Materials and Methods: Expression of ITGB4 in HNSCC tissues was evaluated by calculating standard mean differences (SMDs) based on gene chips, RNA-seq, and immunohistochemistry data (n = 2330) from multiple sources. Receiver operating characteristic (ROC) curves were used to detect the ability of ITGB4 to distinguish HNSCC from non-HNSCC samples. The relationship between the expression level of ITGB4 and clinical parameters was evaluated by calculating SMDs. Results: Identical results of mRNA and protein levels indicated remarkable up-expression of ITGB4 in HNSCC tissues. Further ROC curves showed that ITGB4 could distinguish HNSCC from non-HNSCC samples. Genetic alteration analysis of ITGB4 in HNSCC indicated that overexpression of ITGB4 in HNSCC was likely not owing to genetic alteration of ITGB4. Moreover, ITGB4 overexpression level may be correlated with clinical T stage. Conclusion: ITGB4 likely plays an essential role in HNSCC occurrence based on our study and its potential diagnostic value is worthy of further exploration in the future.

Application of Machine Learning Techniques to Predict Bone Metastasis in Patients with Prostate Cancer.

OBJECTIVE: This study aimed to develop and validate a machine learning model for predicting bone metastases (BM) in prostate cancer (PCa) patients. METHODS: Demographic and clinicopathologic variables of PCa patients in the Surveillance, Epidemiology and End Results (SEER) database from 2010 to 2017 were retrospectively analyzed. We used six different machine learning algorithms, including Decision tree (DT), Random forest (RF), Multilayer Perceptron (MLP), Logistic regression (LR), Naive Bayes classifiers (NBC), and eXtreme gradient boosting (XGB), to build prediction models. External validation using data from 644 PCa patients of the First Affiliated Hospital of Nanchang University from 2010 to 2016. The performance of the models was evaluated using the area under receiver operating characteristic curve (AUC), accuracy score, sensitivity (recall rate) and specificity. A web predictor was developed based on the best performance model. RESULTS: A total of 207,137 PCa patients from SEER were included in this study. Of whom, 6725 (3.25%) developed BM. Gleason score, Prostate-specific antigen (PSA) value, T, N stage and age were found to be the risk factors of BM. The XGB model offered the best predictive performance among these 6 models (AUC: 0.962, accuracy: 0.884, sensitivity (recall rate): 0.906, and specificity: 0.879). An XGB model-based web predictor was developed to predict BM in PCa patients. CONCLUSION: This study developed a machine learning model and a web predictor for predicting the risk of BM in PCa patients, which may help physicians make personalized clinical decisions and treatment strategy for patients.