ObjectiveTo explore the risk factors which affect the severity of acute pancreatitis by using machine learning algorithms. MethodsA retrospective review was conducted of medical records from 262 patients hospitalized for acute pancreatitis at the Second Affiliated Hospital of Zhengzhou University between October 2022 and February 2024. Patients were classified according to the revised edition Atlanta Classification into mild cases (n=146) and non-mild cases (n=116). LASSO analysis was employed to identify predictors for non-mild acute pancreatitis. Six machine learning algorithms, including extreme gradient boosting, random forest, logistic regression, decision tree, support vector machine, and K-nearest neighbors were integrated to construct predictive models. Model performance was evaluated by comparing the following metrics: area under the curve (AUC), sensitivity, specificity, accuracy, F1 score, calibration curves, and decision curves. ResultsThrough LASSO regression analysis, six feature variables, including heart rate, white blood cell count, neutrophil count, C-reactive protein, albumin, and calcium ion were selected to train and test machine learning models. Results showed that extreme gradient boosting achieved the highest AUC value of 0.93 on the test set, making it the optimal model. The sensitivity, specificity, accuracy, Brier score, and F1 score of the extreme gradient boosting model were 0.97, 0.70, 0.85, 0.108, and 0.84. ConclusionThe prediction model developed using extreme gradient boosting has high clinical utility value, helps to predict the severity of acute pancreatitis at an early stage and is valuable in guiding clinical decision-making.
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.
ObjectiveTo analyze the prognostic factors of patients with bacterial bloodstream infection sepsis and to identify independent risk factors related to death, so as to potentially develop one predictive model for clinical practice. Method A non-intervention retrospective study was carried out. The relative data of adult sepsis patients with positive bacterial blood culture (including central venous catheter tip culture) within 48 hours after admission were collected from the electronic medical database of the First Affiliated Hospital of Dalian Medical University from January 1, 2018 to December 31, 2019, including demographic characters, vital signs, laboratory data, etc. The patients were divided into a survival group and a death group according to in-hospital outcome. The risk factors were analyzed and the prediction model was established by means of multi-factor logistics regression. The discriminatory ability of the model was shown by area under the receiver operating characteristic curve (AUC). The visualization of the predictive model was drawn by nomogram and the model was also verified by internal validation methods with R language. Results A total of 1189 patients were retrieved, and 563 qualified patients were included in the study, including 398 in the survival group and 165 in the death group. Except gender and pathogen type, other indicators yielded statistical differences in single factor comparison between the survival group and the death group. Independent risk factors included in the logistic regression prediction model were: age [P=0.000, 95% confidence interval (CI) 0.949 - 0.982], heart rate (P=0.000, 95%CI 0.966 - 0.987), platelet count (P=0.009, 95%CI 1.001 - 1.006), fibrinogen (P=0.036, 95%CI 1.010 - 1.325), serum potassium ion (P=0.005, 95%CI 0.426 - 0.861), serum chloride ion (P=0.054, 95%CI 0.939 - 1.001), aspartate aminotransferase (P=0.03, 95%CI 0.996 - 1.000), serum globulin (P=0.025, 95%CI 1.006 - 1.086), and mean arterial pressure (P=0.250, 95%CI 0.995 - 1.021). The AUC of the prediction model was 0.779 (95%CI 0.737 - 0.821). The prediction efficiency of the total score of the model's nomogram was good in the 210 - 320 interval, and mean absolute error was 0.011, mean squared error was 0.00018. Conclusions The basic vital signs within 48 h admitting into hospital, as well those homeostasis disordering index indicated by coagulation, liver and renal dysfunction are highly correlated with the prognosis of septic patients with bacterial bloodstream infection. Early warning should be set in order to achieve early detection and rescue patients’ lives.
ObjectiveTo explore the predictive value of a simple prediction model for patients with acute myocardial infarction.MethodsClinical data of 280 patients with acute ST-segment elevation myocardial infarction (STEMI) in the Department of Emergence Medicine, West China Hospital of Sichuan University from January 2019 to January 2020 were retrospectively analyzed. The patients were divided into a death group (n=34) and a survival group (n=246).ResultsAge, heart rate, body mass index (BMI), global registry of acute coronary events (GRACE), thrombolysis in myocardial infarction trial (TIMI) score, blood urea nitrogen, serum cystatin C and D-dimer in the survival group were less or lower than those in the death group (P<0.05). Left ventricle ejection fraction and the level of albumin, triglyceride, total cholesterol and low density lipoprotein cholesterol were higher and the incidence of Killip class≥Ⅲ was lower in the survival group compared to the death group (P<0.05). Multivariate logistic regression analysis showed that age, BMI, heart rate, diastolic blood pressure, and systolic blood pressure were independent risk factors for all-cause death in STEMI patients. Receiver operating characteristic (ROC) curve analysis showed that the area under the curve of simple prediction model for predicting death was 0.802, and similar to that of GRACE (0.816). The H-L test showed that the simple model had high accuracy in predicting death (χ2=3.77, P=0.877). Pearson correlation analysis showed that the simple prediction model was significantly correlated with the GRACE (r=0.651, P<0.001) and coronary artery stenosis score (r=0.210, P=0.001).ConclusionThe simple prediction model may be used to predict the hospitalization and long-term outcomes of STEMI patients, which is helpful to stratify high risk patients and to guide treatment.
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.
Objective To evaluate the clinical application value of four inflammatory indices [monocyte-to-lymphocyte ratio (MLR), platelet-to-lymphocyte ratio (PLR), systemic immune-inflammation index (SII), neutrophil-to-lymphocyte ratio (NLR)] in predicting postoperative mortality risk in patients with Siewert type Ⅱ esophagogastric junction adenocarcinoma, and to explore the predictive performance of four inflammatory indices. Methods This retrospective study collected clinical data from 310 patients with Siewert typeⅡ esophagogastric junction adenocarcinoma who were admitted to the Second Hospital of Lanzhou University between October 2016 and March 2023, and met the inclusion and exclusion criteria. Univariate analysis was used to initially screen variables related to postoperative mortality risk. The variance inflation factor (VIF) analysis was performed to assess multicollinearity issues, and multivariate regression analysis was used to further reveal the independent effects of key variables on postoperative mortality risk. The performance of the predictive models was evaluated using receive operatior characteristic curves and Kaplan-Meier survival analysis, and the effects of different inflammatory indices on patient survival were explored. Finally, machine learning methods such as Light GBM, random forest, support vector machine (SVM), and XGBoost were used to evaluate the predictive performance of the four inflammatory indices. Results The four inflammatory indices were significantly associated with postoperative mortality risk in patients with Siewert type Ⅱ esophagogastric junction adenocarcinoma (MLR: HR=2.6884, 95% CI 1.4559 to 4.9642, P=0.002; PLR: HR=1.0022, 95% CI1.0001 to 1.0043, P=0.041; SII: HR=1.0003, 95% CI1.0001 to 1.0006, P=0.002; NLR: HR=1.0697, 95% CI 1.0277 to 1.1134, P=0.001). Machine learning model results showed that NLR had the best performance in the random forest model, with an AUC of 0.863 in the training set and an AUC of 0.834 in the test set. Conclusion Preoperative clinical indicators, especially the NLR inflammatory factor, are of significant importance in predicting the postoperative mortality risk of patients with Siewert typeⅡ esophagogastric junction adenocarcinoma.
Objective The management of pulmonary nodules is a common clinical problem, and this study constructed a nomogram model based on FUT7 methylation combined with CT imaging features to predict the risk of adenocarcinoma in patients with pulmonary nodules. Methods The clinical data of 219 patients with pulmonary nodules diagnosed by histopathology at the First Affiliated Hospital of Zhengzhou University from 2021 to 2022 were retrospectively analyzed. The FUT7 methylation level in peripheral blood were detected, and the patients were randomly divided into training set (n=154) and validation set (n=65) according to proportion of 7:3. They were divided into a lung adenocarcinoma group and a benign nodule group according to pathological results. Single-factor analysis and multi-factor logistic regression analysis were used to construct a prediction model in the training set and verified in the validation set. The receiver operating characteristic (ROC) curve was used to evaluate the discrimination of the model, the calibration curve was used to evaluate the consistency of the model, and the clinical decision curve analysis (DCA) was used to evaluate the clinical application value of the model. The applicability of the model was further evaluated in the subgroup of high-risk CT signs (located in the upper lobe, vascular sign, and pleural sign). Results Multivariate logistic regression analysis showed that female, age, FUT7_CpG_4, FUT7_CpG_6, sub-solid nodules, lobular sign and burr sign were independent risk factors for lung adenocarcinoma (P<0.05). A column-line graph prediction model was constructed based on the results of the multifactorial analysis, and the area under the ROC curve was 0.925 (95%CI 0.877 - 0.972 ), and the maximum approximate entry index corresponded to a critical value of 0.562, at which time the sensitivity was 89.25%, the specificity was 86.89%, the positive predictive value was 91.21%, and the negative predictive value was 84.13%. The calibration plot predicted the risk of adenocarcinoma of pulmonary nodules was highly consistent with the risk of actual occurrence. The DCA curve showed a good clinical net benefit value when the threshold probability of the model was 0.02 - 0.80, which showed a good clinical net benefit value. In the upper lobe, vascular sign and pleural sign groups, the area under the ROC curve was 0.903 (95%CI 0.847 - 0.959), 0.897 (95%CI 0.848 - 0.945), and 0.894 (95%CI 0.831 - 0.956). Conclusions This study developed a nomogram model to predict the risk of lung adenocarcinoma in patients with pulmonary nodules. The nomogram has high predictive performance and clinical application value, and can provide a theoretical basis for the diagnosis and subsequent clinical management of pulmonary nodules.
ObjectiveTo develop and validate a Nomogram for predicting severe immune-related adverse events (irAEs) in patients with advanced non-small cell lung cancer (NSCLC) undergoing immunotherapy based on clinical features and inflammatory indicators. MethodsA total of 423 patients with advanced NSCLC treated with immunotherapy between January 2023 and January 2025 at Tianjin Fourth Center Hospital and Tianjin Cancer Hospital Airport Hospital were enrolled. Patients were divided into a severe irAEs group (≥grade 3, n=76) and a non-severe irAEs group (n=347), then randomly allocated into training and validation cohorts (7:3 ratio) . Clinical data, neutrophil-to-lymphocyte ratio (NLR), and interleukin-6/C-reactive protein (IL-6/CRP) levels were collected. Independent risk factors for severe irAEs during immunotherapy in advanced NSCLC were identified through logistic regression analysis, and a nomogram model was constructed accordingly. The discriminative ability, accuracy, and clinical utility of the model were evaluated using receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA). ResultsAmong the 423 included patients [274 males, 149 females, aged 44-78 (60.77±5.91) years], the overall incidence of irAEs was 57.92% (245/423), with severe irAEs occurring in 17.97% (76/423). Multivariate analysis revealed that Eastern Cooperative Oncology Group (ECOG) performance score ≥2, programmed death-ligand 1 (PD-L1) expression [tumor proportion score (TPS) ≥50%], combination therapy regimen, low NLR values, and high IL-6/CRP ratio were independent risk factors for severe irAEs during immunotherapy in advanced NSCLC (P<0.05). The area under the ROC curve (AUC) was 0.948 [95%CI (0.912, 0.985)] in the training cohort and 0.946 [95%CI (0.917, 0.976)] in the validation cohort. Calibration curves and DCA demonstrated good consistency and clinical net benefit of the model. ConclusionThe nomogram integrating clinical features and inflammatory markers effectively predicts the risk of severe irAEs in advanced NSCLC patients receiving immunotherapy, exhibiting excellent discrimination, calibration, and clinical practicality.
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.
