Objective To identify and screen sensitive predictors associated with subscapularis (SSC) tendon tear and develop a web-based dynamic nomogram to assist clinicians in early identification and intervention of SSC tendon tear. Methods Between July 2016 and December 2021, 528 consecutive cases of patients who underwent shoulder arthroscopic surgery with completely MRI and clinical data were retrospectively analyzed. Patients admitted between July 2016 and July 2019 were included in the training cohort, and patients admitted between August 2019 and December 2021 were included in the validation cohort. According to the diagnosis of arthroscopy, the patients were divided into SSC tear group and non-SSC tear group. Univariate analysis, least absolute shrinkage and selection operator (LASSO) method, and 10-fold cross-validation method were used to screen for reliable predictors highly associated with SSC tendon tear in a training set cohort, and R language was used to build a nomogram model for internal and external validation. The prediction performance of the nomogram was evaluated by concordance index (C-index) and calibration curve with 1 000 Bootstrap. Receiver operating curves were drawn to evaluate the diagnostic performance (sensitivity, specificity, predictive value, likelihood ratio) of the predictive model and MRI (based on direct signs), respectively. Decision curve analysis (DCA) was used to evaluate the clinical implications of predictive models and MRI. Results The nomogram model showed good discrimination in predicting the risk of SSC tendon tear in patients [C-index=0.878; 95%CI (0.839, 0.918)], and the calibration curve showed that the predicted results were basically consistent with the actual results. The research identified 6 predictors highly associated with SSC tendon tears, including coracohumeral distance (oblique sagittal) reduction, effusion sign (Y-plane), subcoracoid effusion sign, biceps long head tendon displacement (dislocation/subluxation), multiple posterosuperior rotator cuff tears (≥2, supra/infraspinatus), and MRI suspected SSC tear (based on direct sign). Compared with MRI diagnosis based on direct signs of SSC tendon tear, the predictive model had superior sensitivity (80.2% vs. 57.0%), positive predictive value (53.9% vs. 53.3%), negative predictive value (92.7% vs. 86.3%), positive likelihood ratio (3.75 vs. 3.66), and negative likelihood ratio (0.25 vs. 0.51). DCA suggested that the predictive model could produce higher clinical benefit when the risk threshold probability was between 3% and 93%. ConclusionThe nomogram model can reliably predict the risk of SSC tendon tear and can be used as an important tool for auxiliary diagnosis.
With the increasing availability of clinical and biomedical big data, machine learning is being widely used in scientific research and academic papers. It integrates various types of information to predict individual health outcomes. However, deficiencies in reporting key information have gradually emerged. These include issues like data bias, model fairness across different groups, and problems with data quality and applicability. Maintaining predictive accuracy and interpretability in real-world clinical settings is also a challenge. This increases the complexity of safely and effectively applying predictive models to clinical practice. To address these problems, TRIPOD+AI (transparent reporting of a multivariable prediction model for individual prognosis or diagnosis+artificial intelligence) introduces a reporting standard for machine learning models. It is based on TRIPOD and aims to improve transparency, reproducibility, and health equity. These improvements enhance the quality of machine learning model applications. Currently, research on prediction models based on machine learning is rapidly increasing. To help domestic readers better understand and apply TRIPOD+AI, we provide examples and interpretations. We hope this will support researchers in improving the quality of their reports.
Inadvertent perioperative hypothermia (IPH) is one of the common complications of surgery, which can lead to a series of adverse consequences. In recent years, with the deepening development of precision medicine concepts, establishing predictive models to identify the risk of IPH early and implementing targeted interventions has become an important research direction for perioperative management. This article reviews the current research status of IPH predictive models in adults, focusing on the research design, modeling methods, selection of prediction factors, and prediction performance of different predictive models. It also explores the advantages and limitations of existing models, aiming to provide references for the selection, application, and optimization of relevant predictive models.
ObjectiveTo construct a predictive model for acute kidney injury (AKI) after coronary artery bypass grafting (CABG) based on uromodulin (UMOD) and tumor necrosis factor receptor-associated factor 6 (TRAF6). MethodsPatients undergoing CABG treatment at Tianjin Chest Hospital from 2022 to 2024 were prospectively enrolled. Based on whether they developed AKI post-surgery, patients were divided into the an AKI group and a non-AKI group. Differences in UMOD, TRAF6, blood urea nitrogen (BUN), serum creatinine (SCr), β-N-acetylglucosaminidase (NAG), and SCr clearance rate at different time points were compared between the two groups. Predictive models for AKI after CABG were constructed at various time points, and the predictive efficacy of the models for AKI was analyzed. ResultsA total of 70 patients were included, with 22 in the AKI group [13 males and 9 females, aged 55-72 (67.91±4.91) years] and 48 in the non-AKI group [32 males and 16 females, aged 56-72 (68.07±4.67) years]. The UMOD levels in the AKI group were lower than those in the non-AKI group at various time points including before surgery (t=34.283, P<0.001), postoperative 2 h (t=29.590, P<0.001), 4 h (t=30.705, P<0.001), 8 h (t=26.620, P<0.001), 12 h (t=29.671, P<0.001), and 24 h (t=31.397, P<0.001). The TRAF6 levels in the AKI group were higher than those in the non-AKI group at all these time points (P<0.001). Multivariate analysis showed that higher levels of TRAF6, BUN, SCr, NAG, and lower levels of UMOD and SCr clearance rate were risk factors for AKI after CABG (P<0.05). The receiver operating characteristic curve analysis showed that the area under the curve of the predictive model at postoperative 12 h was significantly higher than that of the remaining models. The risk of AKI after CABG was: log (Y)=12.333?1.582×UMOD+1.270×TRAF6+1.356×BUN+1.356×SCr+1.355×NAG?1.254×SCr clearance rate. ConclusionIn the occurrence process of AKI after CABG, TRAF6 exacerbates renal injury by activating inflammatory signals and promoting cell apoptosis, while UMOD alleviates renal injury by regulating renal tubular function and protecting renal tubular epithelial cells. Through the simulation analysis of the two biomarkers combined with renal injury indicators at postoperative 12 h, the occurrence of AKI after CABG can be effectively predicted.
ObjectiveTo investigate the prognosis and satisfaction of the R2 intervention procedure and develop related predictive models. Methods The clinical data of 64 patients with primary craniofacial hyperhidrosis who underwent R2 intervention surgery at the First Affiliated Hospital of Fujian Medical University from November 2018 to October 2022 were retrospectively analyzed. By statistically analyzing the risk factors for compensatory hyperhidrosis (CH) and satisfaction, and conducting feature screening, a relevant prediction model was established. ResultsFinally, 51 patients were collected, including 43 (84.3%) males and 8 (15.7%) females, with an average age of (30.27±7.22) years. Overall postoperative satisfaction was high, with only 5.9% of patients expressing regret about the surgery. However, 92.2% of patients experienced CH. The onset of postoperative CH was most prominent within the first 3 months postoperatively, with the incidence rate stabilizing thereafter. Preoperative heart rate and R2 sympathetic nerve clipping were identified as independent risk factors for severe CH. The preoperative body mass index, the degree of sweating in the chest and abdomen, are significantly correlated with postoperative satisfaction. Conclusion The R2 intervention surgery effectively alleviates the symptoms of primary craniofacial hyperhidrosis, and patient satisfaction is high.
ObjectiveTo explore the risk factors of lymph node metastasis in patients with colorectal cancer, and construct a risk prediction model to provide reference for clinical diagnosis and treatment.MethodsThe clinicopathological data of 416 patients with colorectal cancer who underwent radical resection of colorectal cancer in the Department of Gastrointestinal Surgery of the Second Affiliated Hospital of Nanchang University from May 2018 to December 2019 were retrospectively analyzed. The correlation between lymph node metastasis and preoperative inflammatory markers, clinicopathological factors and tumor markers were analyzed. Logistic regression was used to analyze the risk factors of lymph node metastasis, and R language was used to construct nomogram model for evaluating the risk of colorectal cancer lymph node metastasis before surgery, and drew a calibration curve and compared with actual observations. The Bootstrap method was used for internal verification, and the consistency index (C-index) was calculated to evaluate the accuracy of the model.ResultsThe results of univariate analysis showed that factors such as sex, age, tumor location, smoking history, hypertension and diabetes history were not significantly related to lymph node metastasis (all P>0.05). The factors related to lymph node metastasis were tumor size, T staging, tumor differentiation level, fibrinogen, neutrophil/lymphocyte ratio (NLR), platelet/lymphocyte ratio (PLR), fibrinogen/albumin ratio (FAR), fibrinogen/prealbumin ratio (FpAR), CEA, and CA199 (all P<0.05). The results of logistic regression analysis showed the FpAR [OR=3.630, 95%CI (2.208, 5.968), P<0.001], CA199 [OR=2.058, 95%CI (1.221, 3.470), P=0.007], CEA [OR=2.335, 95%CI (1.372, 3.975), P=0.002], NLR [OR=2.532, 95%CI (1.491, 4.301), P=0.001], and T staging were independent risk factors for lymph node metastasis. The above independent risk factors were enrolled to construct regression equation and nomogram model, the area under the ROC curve of this equation was 0.803, and the sensitivity and specificity were 75.2% and 73.5%, respectively. The consistency index (C-index) of the nomogram prediction model in this study was 0.803, and the calibration curve showed that the result of predicting lymph node metastasis was highly consistent with actual observations.ConclusionsFpAR>0.018, NLR>3.631, CEA>4.620 U/mL, CA199>21.720 U/mL and T staging are independent risk factors for lymph node metastasis. The nomogram can accurately predict the risk of lymph node metastasis in patients with colorectal cancer before surgery, and provide certain assistance in the formulation of clinical diagnosis and treatment plans.
ObjectiveTo identify the risk factors of bone metastasis in breast cancer and construct a predictive model. MethodsThe data of breast cancer patients met inclusion and exclusion criteria from 2010 to 2015 were obtained from the SEER*Stat database. Additionally, the data of breast cancer patients diagnosed with distant metastasis in the Affiliated Hospital of Southwest Medical University from 2021 to 2023 were collected. The patients from the SEER database were randomly divided into training (70%) and validation (30%) sets using R software, and the breast cancer patients from the Affiliated Hospital of Southwest Medical University were included in the validation set. The univariate and multivariate logistic regressions were used to identify risk factors of breast cancer bone metastasis. A nomogram predictive model was then constructed based on these factors. The predictive effect of the nomogram was evaluated using the area under the receiver operating characteristic curve (AUC), calibration curve, and decision curve analysis. ResultsThe study included 8 637 breast cancer patients, with 5 998 in the training set and 2 639 (including 68 patients in the Affiliated Hospital of Southwest Medical University) in the validation set. The statistical differences in the race and N stage were observed between the training and validation sets (P<0.05). The multivariate logistic regression analysis revealed that being of white race, having a low histological grade (Ⅰ–Ⅱ), positive estrogen and progesterone receptors status, negative human epidermal growth factor receptor 2 status, and non-undergoing surgery for the primary breast cancer site increased the risk of breast cancer bone metastasis (P<0.05). The nomogram based on these risk factors showed that the AUC (95% CI) of the training and validation sets was 0.676 (0.533, 0.744) and 0.690 (0.549, 0.739), respectively. The internal calibration using 1 000 Bootstrap samples demonstrated that the calibration curves for both sets closely approximated the ideal 45-degree reference line. The decision curve analysis indicated a stronger clinical utility within a certain probability threshold range. ConclusionsThis study constructs a nomogram predictive model based on factors related to the risk of breast cancer bone metastasis, which demonstrates a good consistency between actual and predicted outcomes in both training and validation sets. The nomogram shows a stronger clinical utility, but further analysis is needed to understand the reasons of the lower differentiation of nomogram in both sets.
ObjectiveTo investigate the relationship between the changes in preoperative serum creatinine (Cr), myoglobin (Mb), alanine aminotransferase (ALT) and postoperative fibrinogen (Fib), C- reactive protein (CRP) expression levels and postoperative hypoxemia in patients with aortic dissection aneurysm (ADA), and construct a predictive model. Additionally, the study explores the role of transpulmonary pressure-guided positive end expiratory pressure (PEEP) in improving postoperative hypoxemia. MethodsA retrospective analysis was conducted on the clinical data of ADA patients admitted to Tianjin Chest Hospital from April 2021 to August 2023. Patients were divided into a hypoxemia group [partial pressure of oxygen/fraction of inspiration oxygen (PaO2/FiO2) ≤200 mm Hg] and a non-hypoxemia group (PaO2/FiO2 >200 mm Hg) based on whether they developed postoperative hypoxemia. Univariate and multivariate regression analyses were used to identify risk factors for postoperative hypoxemia in ADA patients and to construct a predictive model for postoperative hypoxemia. The receiver operating characteristic (ROC) curve was plotted, and the Hosmer-Lemeshow goodness-of-fit test was used to evaluate the predictive value of the model. Furthermore, the impact of different ventilation modes on the improvement of postoperative hypoxemia was analyzed. From April 2021 to August 2023, 16 ADA patients with postoperative hypoxemia who received conventional mechanical ventilation were included in the control group. From September 2023 to December 2024, 28 ADA patients with postoperative hypoxemia who received transpulmonary pressure-guided PEEP were included in the experimental group. ICU stay duration, mechanical ventilation duration, hospital mortality rate, and respiratory and circulatory parameters were analyzed to evaluate the effect of transpulmonary pressure-guided PEEP on patients with postoperative hypoxemia after acute aortic dissection. ResultsA total of 98 ADA patients were included, of which 79 (80.61%) were males and 19 (19.39%) were females. Their ages ranged from 32 to 79 years, with an average age of (49.4±11.2) years. Sixteen (16.3%) patients developed postoperative hypoxemia. Body mass index (BMI), smoking history, cardiopulmonary bypass (CPB) duration, preoperative serum Cr, Mb, ALT, and postoperative Fib and CRP showed a certain correlation with postoperative hypoxemia in ADA patients (P<0.05). There was no statistical difference in other baseline data between the two groups (P>0.05). Logistic regression analysis results indicated that BMI [OR=1.613, 95%CI (1.260, 2.065)] and preoperative Mb [OR=2.344, 95%CI (1.048, 5.246)], ALT [OR=1.012, 95%CI (1.000, 1.024)], Cr [OR=1.752, 95%CI (1.045, 2.940)], postoperative Fib [OR=1.165, 95%CI (1.080, 1.258)] and intraoperative CPB time [OR=1.433, 95%CI (1.017, 2.020)] were influencing factors of postoperative hypoxemia in ADA patients (P<0.05). Based on this, a prediction model for postoperative hypoxemia in ADA patients was established. The area under the curve corresponding to the optimal critical point was 0.837 [95%CI (0.799, 0.875)], with a sensitivity of 87.5% and a specificity of 79.3%. The Hosmer-Lemeshow goodness of fit test showed P=0.536. Before treatment, there were no statistical differences in respiratory and circulatory parameters between the control group and the experimental group (P>0.05). After treatment, the levels of PEEP, PaO2/FiO2, end-expiratory esophageal pressure, and end-inspiratory transpulmonary pressure in the experimental group were higher than those in the control group (P<0.05). The duration of mechanical ventilation and ICU stay in the experimental group were shorter than those in the control group (P<0.05), while there was no statistical difference in mortality between the two groups (P=0.626). ConclusionThe hypoxia prediction model based on preoperative Cr, Mb, ALT and postoperative Fib levels, combined with transpulmonary pressure-guided PEEP optimization, provides a scientific basis for the precise management of postoperative hypoxemia in ADA. This approach not only improves the predictive ability of hypoxemia risk but also significantly improves the postoperative oxygenation status of patients through personalized mechanical ventilation strategies, providing new insights into the management of postoperative complications.
ObjectiveTo predict the risk factors affecting postoperative recurrence of granulomatous lobular mastitis (GLM) in the mass stage by machine learning algorithm, and to provide a reference for the early identification and prevention of postoperative recurrence of GLM in the mass stage. MethodsThe electronic medical records and follow-up data of patients with GLM in the Department of Breast Disease Unit, the First Affiliated Hospital of Henan University of Traditional Chinese Medicine from October 2020 to January 2023 were selected. A total of 340 patients with GLM in the mass stage who met the inclusion and exclusion criteria were selected as the research subjects. According to whether the patients relapsed after surgery, they were divided into recurrence group and non-recurrence group. The collected cases were randomly divided into training set and test set according to the ratio of 7:3. In the training set, the recurrence prediction model was constructed by using traditional logistic regression and three machine learning algorithms: artificial neural network, random forest and XGBoost (extrem gradient boosting). In the test set, the performance of the model was evaluated by sensitivity, specificity, accuracy,positive predictive value, negative predictive value, F1 value and area under the curve (AUC) value. The Shapley Additive exPlanation (SHAP) method was used to explore the important variables that affect the optimal model in identifying postoperative recurrence in the GLM mass phase. The optimal risk cutoff value of the prediction model was determined by the Youden index. Based on this, the postoperative patients in the GLM mass phase of the external test set were divided into high-risk and low-risk groups. ResultsA total of 392 patients who met the GLM mass stage were included, and 52 cases were excluded according to the exclusion criteria, and 340 cases were finally included, including 60 cases in the recurrence group and 280 cases in the non-recurrence group. Based on the results of univariate analysis, correlation analysis and clinically meaningful influencing factors, 12 non-zero coefficient characteristic variables were screened for the construction of the prediction model, and these 12 characteristic variables included other disease history, number of miscarriages, breastfeeding duration of the affected breast, history of milk stasis, lesion location, nipple indentation, fluctuation sensation, low-density lipoprotein, testosterone, previous antibiotic therapy, previous oral hormone medication, and perioperative traditional Chinese medicine treatment duration. The logistic regression prediction model, artificial neural network, random forest and XGBoost prediction models were constructed, and the results showed that the accuracy, positive predictive value and negative predictive value of the four prediction models were all >75%, among which the XGBoost model had the best performance, with accuracy, specificity, sensitivity, AUC, positive predictive value, negative predictive value and F1 values of 0.93, 0.99, 0.65, 0.87, 0.92, 0.93 and 0.76, respectively. SHAP method found that the duration of traditional Chinese medicine treatment during perioperative period, the duration of breast-feeding on the affected side, low density lipoprotein, testosterone and previous hormone drugs were the top five factors affecting XGBoost model to identify postoperative recurrence of GLM in mass stage. ConclusionsCompared with the traditional Logistic regression prediction model, the models based on machine learning for identifying postoperative recurrence in the GLM mass phase showed better performance, among which the XGBoost model performed best. Targeted preventive measures can be given based on the above risk factors to improve the postoperative prognosis of the GLM mass phase.
Objective To explore the independent risk factors for hospital infections in tertiary hospitals in Gansu Province, and establish and validate a prediction model. Methods A total of 690 patients hospitalized with hospital infections in Gansu Provincial Hospital between January and December 2021 were selected as the infection group; matched with admission department and age at a 1∶1 ratio, 690 patients who were hospitalized during the same period without hospital infections were selected as the control group. The information including underlying diseases, endoscopic operations, blood transfusion and immunosuppressant use of the two groups were compared, the factors influencing hospital infections in hospitalized patients were analyzed through multiple logistic regression, and the logistic prediction model was established. Eighty percent of the data from Gansu Provincial Hospital were used as the training set of the model, and the remaining 20% were used as the test set for internal validation. Case data from other three hospitals in Gansu Province were used for external validation. Sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve (AUC) were used to evaluate the model effectiveness. Results Multiple logistic regression analysis showed that endoscopic therapeutic manipulation [odds ratio (OR)=3.360, 95% confidence interval (CI) (2.496, 4.523)], indwelling catheter [OR=3.100, 95%CI (2.352, 4.085)], organ transplantation/artifact implantation [OR=3.133, 95%CI (1.780, 5.516)], blood or blood product transfusions [OR=3.412, 95%CI (2.626, 4.434)], glucocorticoids [OR=2.253, 95%CI (1.608, 3.157)], the number of underlying diseases [OR=1.197, 95%CI (1.068, 1.342)], and the number of surgical procedures performed during hospitalization [OR=1.221, 95%CI (1.096, 1.361)] were risk factors for hospital infections. The regression equation of the prediction model was: logit(P)=–2.208+1.212×endoscopic therapeutic operations+1.131×indwelling urinary catheters+1.142×organ transplantation/artifact implantation+1.227×transfusion of blood or blood products+0.812×glucocorticosteroids+0.180×number of underlying diseases+0.200×number of surgical procedures performed during the hospitalization. The internal validation set model had a sensitivity of 72.857%, a specificity of 77.206%, an accuracy of 76.692%, and an AUC value of 0.817. The external validation model had a sensitivity of 63.705%, a specificity of 70.934%, an accuracy of 68.669%, and an AUC value of 0.726. Conclusions Endoscopic treatment operation, indwelling catheter, organ transplantation/artifact implantation, blood or blood product transfusion, glucocorticoid, number of underlying diseases, and number of surgical cases during hospitalization are influencing factors of hospital infections. The model can effectively predict the occurrence of hospital infections and guide the clinic to take preventive measures to reduce the occurrence of hospital infections.