Objective To explore the correlation between the quantitative and qualitative features of CT images and the invasiveness of pulmonary ground-glass nodules, providing reference value for preoperative planning of patients with ground-glass nodules. MethodsThe patients with ground-glass nodules who underwent surgical treatment and were diagnosed with pulmonary adenocarcinoma from September 2020 to July 2022 at the Third Affiliated Hospital of Kunming Medical University were collected. Based on the pathological diagnosis results, they were divided into two groups: a non-invasive adenocarcinoma group with in situ and minimally invasive adenocarcinoma, and an invasive adenocarcinoma group. Imaging features were collected, and a univariate logistic regression analysis was conducted on the clinical and imaging data of the patients. Variables with statistical difference were selected for multivariate logistic regression analysis to establish a predictive model of invasive adenocarcinoma based on independent risk factors. Finally, the sensitivity and specificity were calculated based on the Youden index. Results A total of 555 patients were collected. The were 310 patients in the non-invasive adenocarcinoma group, including 235 females and 75 males, with a meadian age of 49 (43, 58) years, and 245 patients in the invasive adenocarcinoma group, including 163 females and 82 males, with a meadian age of 53 (46, 61) years. The binary logistic regression analysis showed that the maximum diameter (OR=4.707, 95%CI 2.060 to 10.758), consolidation/tumor ratio (CTR, OR=1.027, 95%CI 1.011 to 1.043), maximum CT value (OR=1.025, 95%CI 1.004 to 1.047), mean CT value (OR=1.035, 95%CI 1.008 to 1.063), spiculation sign (OR=2.055, 95%CI 1.148 to 3.679), and vascular convergence sign (OR=2.508, 95%CI 1.345 to 4.676) were independent risk factors for the occurrence of invasive adenocarcinoma (P<0.05). Based on the independent predictive factors, a predictive model of invasive adenocarcinoma was constructed. The formula for the model prediction was: Logit(P)=–1.293+1.549×maximum diameter of lesion+0.026×CTR+0.025×maximum CT value+0.034×mean CT value+0.72×spiculation sign+0.919×vascular convergence sign. The area under the receiver operating characteristic curve of the model was 0.910 (95%CI 0.885 to 0.934), indicating that the model had good discrimination ability. The calibration curve showed that the predictive model had good calibration, and the decision analysis curve showed that the model had good clinical utility. Conclusion The predictive model combining quantitative and qualitative features of CT has a good predictive ability for the invasiveness of ground-glass nodules. Its predictive performance is higher than any single indicator.
Objective To systematically evaluate risk prediction models for 30-day unplanned readmission in patients undergoing coronary artery bypass grafting (CABG). Methods We searched PubMed, EMbase, Cochrane Library, Web of Science, CINAHL, CNKI, CBM, WanFang, and VIP databases from inception to June 25, 2025. Two investigators independently screened literature, extracted data, and assessed bias risk/applicability using PROBAST criteria. Results Thirteen studies comprising 17 prediction models were included. Ten models reported the area under the receiver operating characteristic curve (AUC) for modeling (0.597-0.906), ten models reported the AUC for internal validation (0.57-0.92), and twelve models reported the AUC for external validation (0.537-0.865). Core predictors included age, female sex, diabetes, and heart failure. All studies had a high risk of bias. Conclusion The research on risk prediction models for 30-day unplanned readmission in patients undergoing CABG is still in its exploratory stages. Some models exhibit insufficient performance, and there is a need to enhance the processes of model validation and performance evaluation. It is expected that future efforts will focus on developing prediction models with excellent performance and high applicability, to assist healthcare providers in the early identification of high-risk patients for readmission.
ObjectiveTo review the recent research progress on prediction models for pancreatic fistula after pancreaticoduodenectomy and explore the potential application of prediction models in personalized treatment, aiming to provide useful reference information for clinical doctors to improve patient’s treatment outcomes and quality of life. MethodWe systematically searched and reviewed the literature on various prediction models for pancreatic fistula after pancreaticoduodenectomy in recent years domestically and internationally. ResultsSpecifically, the fistula risk score (FRS) and the alternative FRS (a-FRS), as widely used tools, possessed a certain degree of subjectivity due to the lack of an objective evaluation standard for pancreatic texture. The updated a-FRS (ua-FRS) had demonstrated superior predictive efficacy in minimally invasive surgery compared to the original FRS and a-FRS. The NCCH (National Cancer Center Hospital) prediction system, based on preoperative indicators, showed high predictive accuracy. Prediction models based on CT imaging informatics had improved the accuracy and reliability of predictions. Prediction models based on elastography had provided new perspectives for the assessment of pancreatic texture and the prediction of clinically relevant postoperative pancreatic fistula. The Stacking ensemble machine learning model contributed to the individualization and localization of prediction models. The existing pancreatic fistula prediction models showed satisfactory predictive efficacy, but there were still limitations in identifying high-risk patients for pancreatic fistula.ConclusionsAfter pancreaticoduodenectomy, pancreatic fistula remains a major complication that is difficult to overcome. The prevention of pancreatic fistula is crucial for improving postoperative recovery and reducing mortality rates. Future research should focus on the development and validation of pancreatic fistula prediction models, thereby enhancing their predictive power and increasing their predictive efficacy in different regional patients, providing a scientific basis for medical decision-making.
ObjectiveTo summarise the application research progress of clinical prediction models in postoperative complications of gastric cancer, in order to reduce the risk of complications after gastric cancer surgery. MethodThe literature on the study of postoperative complications of gastric cancer at home and abroad was read and reviewed. ResultsAt present, the main way of treating gastric cancer was still radical resection, and the occurrence of complications after surgical treatment seriously affected the recovery and survival quality of patients. With the deepening of research, the prediction models of postoperative complications in gastric cancer were constantly constructed, and these models provided strong evidence for the early judgement of postoperative complications in gastric cancer, and provided a scientific basis for the improvement of patients’ life quality. ConclusionClinical predictive models are expected to become risk screening tools for predicting the risk of postoperative complications of gastric cancer with clinical utility.
ObjectiveTo investigate the risk factors affecting severe postoperative complications (Clavien-Dindo classification Ⅲa or higher) in patients with end-stage hepatic alveolar echinococcosis (HAE) underwent ex vivo liver resection and autotransplantation (ELRA), and to develop a nomogram prediction model. MethodsThe clinical data of end-stage HAE patients who underwent ELRA at the West China Hospital of Sichuan University from January 2014 to June 2024 were retrospectively analyzed. The logistic regression was used to analyze the risk factors affecting severe postoperative complications. A nomogram prediction model was established basing on LASSO regression and its efficiency was evaluated using receiver operating characteristic (ROC) curve, calibration curve, and decision curve analysis. Simultaneously, a generalized linear model regression was used to explore the preoperative risk factors affecting the total surgery time. Test level was α=0.05. ResultsA total of 132 end-stage HAE patients who underwent ELRA were included. The severe postoperative complications occurred in 47 (35.6%) patients. The multivariate logistic analysis results showed that the patients with invasion of the main trunk of the portal vein or the first branch of the contralateral portal vein (type P2) had a higher risk of severe postoperative complications compared to those with invasion of the first branch of the ipsilateral portal vein (type P1) [odds ratio (OR) and 95% confidence interval (CI)=8.24 (1.53, 44.34), P=0.014], the patients with albumin bilirubin index (ALBI) grade 1 had a lower risk of severe postoperative complications compared to those with grade 2 or higher [OR(95%CI)=0.26(0.08, 0.83), P=0.023]. Additionally, an increased total surgery time or the autologous blood reinfusion was associated with an increased risk of severe postoperative complications [OR(95%CI)=1.01(1.00, 1.01), P=0.009; OR(95%CI)=1.00(1.00, 1.00), P=0.043]. The nomogram prediction model constructed with two risk factors, ALBI grade and total surgery time, selected by LASSO regression, showed a good discrimination for the occurrence of severe complications after ELRA [area under the ROC curve (95%CI) of 0.717 (0.625, 0.808)]. The generalized linear regression model analysis identified the invasion of the portal vein to extent type P2 and more distant contralateral second portal vein branch invasion (type P3), as well as the presence of distant metastasis, as risk factors affecting total surgery time [β (95%CI) for type P2/type P1=110.26 (52.94, 167.58), P<0.001; β (95%CI) for type P3/type P1=109.25 (50.99, 167.52), P<0.001; β (95%CI) for distant metastasis present/absent=61.22 (4.86, 117.58), P=0.035]. ConclusionsFrom the analysis results of this study, for the end-stage HAE patients with portal vein invasion degree type P2, ALBI grade 2 or above, longer total surgery time, and more autologous blood transfusion need to be closely monitored. Preoperative strict evaluation of the first hepatic portal invasion and distant metastasis is necessary to reduce the risk of severe complications after ELRA. The nomogram prediction model constructed based on ABLI grade and total surgery time in this study demonstrates a good predictive performance for severe postoperative complications, which can provide a reference for clinical intervention decision-making.
Objective To systematically evaluate the research quality and efficacy of prediction models for acute kidney injury (AKI) after heart valve surgery, screen key predictive factors, and provide evidence-based basis for clinical risk assessment. Methods Computer search was carried out in PubMed, Web of Science, EMBASE, Cochrane Library, Medline, China Biology Medicine Database, China National Knowledge Infrastructure, Wanfang Database, and VIP Database to collect studies on AKI prediction models after heart valve surgery published from January 2015 to July 2025. The PROBAST tool was used to evaluate the bias risk and applicability of the models, and the TRIPOD was used to assess the reporting quality. Meta-analysis was performed to integrate the effect sizes of high-frequency (≥3 times) predictive factors. Results A total of 24 studies (39 models) were included. Area under the curve (AUC) of the receiver operational characteristic curve was between 0.551 and 0.928, and the combined AUC was 0.77 (95%CI 0.72-0.82). The overall bias risk of the models was relatively high (100% of the studies had a high bias risk), only 2 studies conducted external validation, and the models in 10 studies were not validated. In terms of TRIPOD reporting quality, the overall reporting quality of 24 studies was low, with a compliance percentage (number of items) ranging from 36.36% to 77.27%. Meta-analysis showed that age (OR=1.041, P=0.006), diabetes (OR=1.64, P=0.001), hypertension (OR=2.529, P <0.001), blood transfusion (OR=1.49, P=0.001), cystatin C (OR=2.408, P=0.018), history of cardiac surgery (OR=2.585, P <0.001), atrial fibrillation (OR=1.33, P <0.001), and vascular complications (OR=1.22, P=0.008) were independent risk factors for postoperative AKI. Conclusion The clinical applicability of existing prediction models is limited, with high bias risk and low reporting quality, and the methodology needs to be optimized. Eight factors such as age and hypertension can be used as core indicators for postoperative AKI risk assessment. In the future, multicenter prospective studies should be carried out to develop more reliable prediction tools.
Cardiovascular diseases are the leading cause of death and their diagnosis and treatment rely heavily on the variety of clinical data. With the advent of the era of medical big data, artificial intelligence (AI) has been widely applied in many aspects such as imaging, diagnosis and prognosis prediction in cardiovascular medicine, providing a new method for accurate diagnosis and treatment. This paper reviews the application of AI in cardiovascular medicine.
ObjectiveTo systematically summarize the research progress in risk prediction models for postoperative anastomotic leakage in gastric cancer, and to explore the advantages and limitations of models constructed using traditional statistical methods and machine learning, thereby providing a theoretical basis for clinical precision prediction and early intervention. MethodBy analyzing domestic and international literature, the construction strategies of logistic regression, least absolute shrinkage and selection operator (LASSO) regression, and machine learning models (support vector machine, random forest, deep learning) were systematically reviewed, and their predictive performance and clinical applicability were compared. ResultsThe traditional logistic regression and LASSO regression models performed excellently in terms of interpretability and in small-sample scenarios but were limited by linear assumptions. The machine learning models significantly enhanced predictive capabilities for complex data through non-linear modeling and automatic feature extraction, but required larger data scales and had higher demands for interpretability. ConclusionsDifferent prediction models have their own advantages and limitations; in practical clinical applications, they should be flexibly selected or complementarily applied based on specific scenarios. Current anastomotic leakage prediction models are evolving from single factor analysis to multi-modal dynamic integration. Future efforts should combine artificial intelligence and multi-center prospective clinical studies to validate, so advancing the development of precise and individualized anastomotic leakage predictive tools for patients after gastric cancer resection.
ObjectiveProlonged mechanical ventilation (PMV) is a prognostic marker for short-term adverse outcomes in patients after lung transplantation.The risk of prolonged mechanical ventilation after lung transplantation is still not clear. The study to identify the risk factors of prolonged mechanical ventilation (PMV) after lung transplantation.Methods This retrospective observational study recruited patients who underwent lung transplantation in Wuxi People’s Hospital from January 2020 to December 2022. Relevant information was collected from patients and donors, including recipient data (gender, age, BMI, blood type, comorbidities), donor data (age, BMI, time of endotracheal intubation, oxygenation index, history of smoking, and any comorbidity with multidrug-resistant bacterial infections), and surgical data (surgical mode, incision type, operation time, cold ischemia time of the donor lung, intraoperative bleeding, and ECMO support), and postoperative data (multi-resistant bacterial lung infection, multi-resistant bacterial bloodstream infection, and mean arterial pressure on postoperative admission to the monitoring unit). Patients with a duration of mechanical ventilation ≤72 hours were allocated to the non-prolonged mechanical ventilation group, and patients with a duration of mechanical ventilation>72 hours were allocated to the prolonged mechanical ventilation group. LASSO regression analysis was applied to screen risk factors., and a clinical prediction model for the risk of prolonged mechanical ventilation after lung.ResultsPatients who met the inclusion criteria were divided into the training set and the validation set. There were 307 cases in the training set group and 138 cases in the validation set group. The basic characteristics of the training set and the validation set were compared. There were statistically significant differences in the recipient’s BMI, donor’s gender, CRKP of the donor lung swab, whether the recipient had pulmonary infection before the operation, the type of transplantation, the cold ischemia time of the donor lung, whether ECMO was used during the operation, the duration of ECMO assistance, CRKP of sputum, and the CRE index of the recipient's anal test (P<0.05). 2. The results of the multivariate logistic regression model showed that female recipients, preoperative mechanical ventilation in recipients, preoperative pulmonary infection in recipients, intraoperative application of ECMO, and the detection of multi-drug resistant Acinetobacter baumannii, multi-drug resistant Klebsiella pneumoniae and maltoclomonas aeruginosa in postoperative sputum were independent risk factors for prolonged mechanical ventilation after lung transplantation. The AUC of the clinical prediction model in the training set and the validation set was 0.838 and 0.828 respectively, suggesting that the prediction model has good discrimination. In the decision curves of the training set and the validation set, the threshold probabilities of the curves in the range of 0.05-0.98 and 0.02-0.85 were higher than the two extreme lines, indicating that the model has certain clinical validity.ConclusionsFemale patients, Preoperative pulmonary infection, preoperative mechanical ventilation,blood type B, blood type O, application of ECMO assistance, multi-resistant Acinetobacter baumannii infection, multi-resistant Klebsiella pneumoniae infection, and multi-resistant Stenotrophomonas maltophilia infection are independent risk factors for PMV (prolonged mechanical ventilation) after lung transplantation.
ObjectiveTo explore the risk factors affecting occurrence of arteriosclerosis obliterans (ASO) for patients with type 2 diabetes mellitus (T2DM) and to develop a nomogram predictive model using these risk factors. MethodsA case-control study was conducted. The patients with T2DM accompanied with ASO and those with T2DM alone, admitted to the First Affiliated Hospital of Xinjiang Medical University from January 2017 to December 2022, were retrospectively collected according to the inclusion and exclusion criteria. The basic characteristics, blood, thyroid hormones, and other relevant indicators of the paitents in two groups were compared. The multivariate logistic regression analysis was used to identify the risk factors for the occurrence of ASO in the patients with T2DM, and then a nomogram predictive model was developed. ResultsThere were 119 patients with T2DM alone and 114 patients with T2DM accompanied with lower extremity ASO in this study. The significant differences were observed between the two groups in terms of smoking history, white blood cell count, neutrophil count, lymphocyte count, platelet count, systemic immune-inflammation index, systemic inflammatory response index (SIRI), high-density lipoprotein cholesterol, apolipoprotein A1 (ApoA1), apolipoprotein α (Apoα), serum cystatin C, free-triiodothyronine (FT3), total triiodothyronine, FT3/total triiodothyronine ratio, fibrinogen (Fib), fibrinogen degradation products, and plasma D-dimer (P<0.05). Further the results of the multivariate logistic regression analysis revealed that the history of smoking, increased Fib level and SIRI value increased the probabilities of ASO occurrence in the patients with T2DM [OR (95%CI)=2.921 (1.023, 4.227), P=0.003; OR (95%CI)=2.641 (1.810, 4.327), P<0.001; OR (95%CI)=1.020 (1.004, 1.044), P=0.018], whereas higher levels of ApoA1 and FT3 were associated with reduced probabilities of ASO occurrence in the patients with T2DM [OR (95%CI)=0.231 (0.054, 0.782), P=0.021; OR (95%CI)=0.503 (0.352, 0.809), P=0.002]. The nomogram predictive model based on these factors demonstrated a good discrimination for predicting the ASO occurrence in the T2DM patients [area under the receiver operating characteristic curve (95%CI)=0.788 (0.730, 0.846)]. The predicted curve closely matched the ideal curve (Hosmer-Lemeshow goodness-of-fit test, χ2=5.952, P=0.653). The clinical decision analysis curve showed that the clinical net benefit of intervention based on the nomogram model was higher within a threshold probability range of 0.18 to 0.80 compared to no intervention or universal intervention. ConclusionsThe analysis results indicate that T2DM patients with a smoking history, elevated Fib level and SIRI value, as well as decreased ApoA1 and FT3 levels should be closely monitored for ASO risk. The nomogram predictive model based on these features has a good discriminatory power for ASO occurrence in T2DM patients, though its value warrants further investigation.