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 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.
ObjectiveTo establish and internally validate a predictive model for poorly differentiated adenocarcinoma based on CT imaging and tumor marker results. MethodsPatients with solid and partially solid lung nodules who underwent lung nodule surgery at the Department of Thoracic Surgery, the Affiliated Brain Hospital of Nanjing Medical University in 2023 were selected and randomly divided into a training set and a validation set at a ratio of 7:3. Patients' CT features, including average density value, maximum diameter, pleural indentation sign, and bronchial inflation sign, as well as patient tumor marker results, were collected. Based on postoperative pathological results, patients were divided into a poorly differentiated adenocarcinoma group and a non-poorly differentiated adenocarcinoma group. Univariate analysis and logistic regression analysis were performed on the training set to establish the predictive model. The receiver operating characteristic (ROC) curve was used to evaluate the model's discriminability, the calibration curve to assess the model's consistency, and the decision curve to evaluate the clinical value of the model, which was then validated in the validation set. ResultsA total of 299 patients were included, with 103 males and 196 females, with a median age of 57.00 (51.00, 67.25) years. There were 211 patients in the training set and 88 patients in the validation set. Multivariate analysis showed that carcinoembryonic antigen (CEA) value [OR=1.476, 95%CI (1.184, 1.983), P=0.002], cytokeratin 19 fragment antigen (CYFRA21-1) value [OR=1.388, 95%CI (1.084, 1.993), P=0.035], maximum tumor diameter [OR=6.233, 95%CI (1.069, 15.415), P=0.017], and average density [OR=1.083, 95%CI (1.020, 1.194), P=0.040] were independent risk factors for solid and partially solid lung nodules as poorly differentiated adenocarcinoma. Based on this, a predictive model was constructed with an area under the ROC curve of 0.896 [95%CI (0.810, 0.982)], a maximum Youden index corresponding cut-off value of 0.103, sensitivity of 0.750, and specificity of 0.936. Using the Bootstrap method for 1000 samplings, the calibration curve predicted probability was consistent with actual risk. Decision curve analysis indicated positive benefits across all prediction probabilities, demonstrating good clinical value. ConclusionFor patients with solid and partially solid lung nodules, preoperative use of CT to measure tumor average density value and maximum diameter, combined with tumor markers CEA and CYFRA21-1 values, can effectively predict whether it is poorly differentiated adenocarcinoma, allowing for early intervention.
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 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 summarize advances in the application of machine learning in the diagnosis and treatment of liver disease. Method The recent literatures on the progress of machine learning in the diagnosis, treatment and prognosis of liver diseases were reviewed. Results Machine learning could be used to diagnose and categorize substantial liver lesions, tumourous lesions and rare liver diseases at an early stage, which could facilitate clinicians to take timely and appropriate treatment measures. Machine learning was helpful in informing clinicians in choosing the best treatment decision, which was conducive to reducing medical risks. It could also help to determine the prognosis of patients in a comprehensive manner, and provide assistance in formulating early rehabilitation treatment plans, adjusting follow-up strategies and improving future prognosis. Conclusions Multiple types of machine learning algorithms have achieved positive results in the clinical application of liver diseases by constructing different prediction models, and have great potential and excellent prospects in multiple aspects such as diagnosis, treatment and prognosis of liver diseases.
Objective To identify independent risk factors for in-hospital all-cause mortality in patients with sepsis and to integrate them into the quick Sequential Organ Failure Assessment (qSOFA) score to construct modified models, thereby improving the ability of the original qSOFA to predict mortality risk. Methods This retrospective study included adult patients who met the Sepsis-3 criteria for sepsis and were admitted to the Intensive Care Unit or Emergency Intensive Care Unit of Zigong Fourth People’ s Hospital between January 2018 and December 2023. Demographic characteristics, vital signs, comorbidities, and laboratory parameters were collected, and the Sequential Organ Failure Assessment (SOFA) and qSOFA scores were calculated. Multivariable logistic regression analysis was used to identify independent predictors of in-hospital mortality. Independent predictors were dichotomized according to cut-off values derived from receiver operating characteristic (ROC) curves and combined with qSOFA to construct new models. The ROC analysis with bootstrap validation was used to assess predictive performance, and comparative performance was further evaluated using net reclassification improvement (NRI) and integrated discrimination improvement (IDI). Results A total of 218 patients were included. Multivariable logistic regression analysis identified blood urea nitrogen (BUN) [odds ratio (OR)=1.100, 95% confidence interval (CI) (1.040, 1.170)] and qSOFA [OR=2.610, 95%CI (1.450, 4.920)] as independent risk factors for in-hospital mortality, whereas high-density lipoprotein cholesterol (HDL-C) was an independent protective factor [OR=0.250, 95%CI (0.065, 0.841)]. After dichotomization by ROC-derived cut-off values, BUN and HDL-C were incorporated into qSOFA to generate B-qSOFA, H-qSOFA, and BH-qSOFA. Bootstrap ROC analysis showed that BH-qSOFA exhibited the highest discriminatory ability compared with all combined models as well as the conventional SOFA and qSOFA scores [area under the curve=0.803, 95%CI (0.735, 0.863)]. NRI and IDI analyses demonstrated that BH-qSOFA provided incremental prognostic improvement over qSOFA (NRI=0.969, IDI=0.165), B-qSOFA (NRI=0.644, IDI=0.054), and H-qSOFA (NRI=0.804, IDI=0.091) (all P<0.05). Conclusions Elevated BUN and qSOFA and decreased HDL-C are independent predictors of in-hospital mortality in sepsis. The BH-qSOFA model is simple and clinically practical, exhibits superior predictive performance over the original qSOFA. It may serve as a useful early instrument for prognostic risk stratification in patients with sepsis.
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 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 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.
