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.
Risk prediction models for postoperative pulmonary complications (PPCs) can assist healthcare professionals in assessing the likelihood of PPCs occurring after surgery, thereby supporting rapid decision-making. This study evaluated the merits, limitations, and challenges of these models, focusing on model types, construction methods, performance, and clinical applications. The findings indicate that current risk prediction models for PPCs following lung cancer surgery demonstrate a certain level of predictive effectiveness. However, there are notable deficiencies in study design, clinical implementation, and reporting transparency. Future research should prioritize large-scale, prospective, multi-center studies that utilize multiomics approaches to ensure robust data for accurate predictions, ultimately facilitating clinical translation, adoption, and promotion.
Objective To investigate the factors influencing the occurrence of postoperative pulmonary complications (PPCs) in liver transplant recipients and to construct Nomogram model to identify high-risk patients. Methods The clinical data of 189 recipients who underwent liver transplantation at the General Hospital of Eastern Theater Command from November 1, 2019 to November 1, 2022 were retrospective collected, and divided into PPCs group (n=61) and non-PPCs group (n=128) based on the occurrence of PPCs. Univariate and multivariate logistic regression analyses were used to determine the risk factors for PPCs, and the predictive effect of the Nomogram model was evaluated by receiver operator characteristic curve (ROC) and calibration curve. Results Sixty-one of 189 liver transplant patients developed PPCs, with an incidence of 32.28%. Univariate analysis results showed that PPCs were significantly associated with age, smoking, Child-Pugh score, combined chronic obstructive pulmonary disease (COPD), combined diabetes mellitus, prognostic nutritional index (PNI), time to surgery, amount of bleeding during surgery, and whether or not to diuretic intraoperatively (P<0.05). Multivariate logistic regression analysis showed that age [OR=1.092, 95%CI (1.034, 1.153), P=0.002], Child-Pugh score [OR=1.575, 95%CI (1.215, 2.041), P=0.001], combined COPD [OR=4.578, 95%CI (1.832, 11.442), P=0.001], combined diabetes mellitus [OR=2.548, 95%CI (1.024, 6.342), P=0.044], preoperative platelet count (PLT) [OR=1.076, 95%CI (1.017, 1.138), P=0.011], and operative time [OR=1.061, 95%CI (1.012, 1.113), P=0.014] were independent risk factors for PPCs. The prediction model for PPCs which constructed by using the above six independent risk factors in Nomogram had an area under the ROC curve of 0.806. Hosmer and Lemeshow goodness of fit test (P=0.129), calibration curve, and decision curve analysis showed good agreement with Nomogram model. Conclusion The Nomogram model constructed based on age, Child-Pugh score, combined COPD, combined diabetes mellitus, preoperative PLT, and time of surgery can better identify patients at high risk of developing PPCs after liver transplantation.
ObjectiveTo construct a prediction model for the postoperative recurrence risk of granulomatous lobular mastitis (GM) based on multiple systemic inflammatory indicators and clinicopathologic characteristics, with the aim of guiding clinical treatment. MethodsThe GM patients who underwent lesion resection at Sichuan Provincial Hospital for Women and Children from January 2017 to March 2024 were retrospectively collected. The univariate and multivariate logistic regression analyses were used to screen the risk factors for recurrence after GM lesion resection, and a nomogram prediction model was constructed based on the risk factors. The test level was set at α=0.05. ResultsA total of 533 patients with GM were included in this study, of whom 118 cases (22.1%) developed postoperative recurrence. The results of multivariate analysis showed that the not taking oral bromocriptine, having microabscess formation in postoperative pathological examination, systemic immune inflammation index (SII) >789.0×109/L, and immunoglobulin E (IgE) >64.4 U/mL were the independent risk factors for recurrence after GM lesion resection. Based on the risk factors, the nomogram predicting recurrence risk was constructed. The area under the receiver operating characteristic curve (95%CI) was 0.913 (0.895, 0.932), and its sensitivity and specificity were 90.5% and 88.9%, respectively. The calibration curve showed that the probability of recurrence after GM lesion resection predicted by using the nomogram was highly consistent with the actual recurrence probability. The decision curve analysis showed that the nomogram had a good clinical net benefit. ConclusionsThe findings of this study suggest that close postoperative monitoring for recurrence is warranted in patients who did not receive oral bromocriptine treatment, presented with microabscess formation on pathological examination, and exhibited elevated SII and IgE level. The postoperative GM recurrence prediction nomogram model constructed based on risk factors demonstrates a good predictive performance, providing a valuable reference for early treatment and management strategies of GM.
Breast cancer is the most common malignant tumor among Chinese females. We should focus on the research of risk assessment models of gene-environmental factors to guide primary and secondary prevention, and this public health strategy is expected to maximize the health benefits of the population. This paper introduces previous studies of risk factors and predictive models for Chinese breast cancer and provides three points for future research. Firstly, we should explore the specific risk factors related to breast cancer risk in Chinese population, such as overweight or reproductive control measures. Secondly, we should use evidence-based and machine learning methods to select environmental-genetic risk factors. Finally, we should set up an information collective platform for breast cancer risk factors to test the validity of prediction models based on a long-term follow-up cohort of Chinese females.
ObjectiveTo explore the risk factors of lymph node metastasis (LNM) in patients with early gastric cancer (EGC), and try to establish a risk prediction model for LNM of EGC.MethodsThe clinicopathologic data of EGC patients who underwent radical gastrectomy and lymph node dissection from January 1, 2015 to December 31, 2019 in this hospital were retrospectively analyzed. Univariate analysis and logistic regression analysis were used to determine the risk factors for LNM of EGC, and the risk prediction model for LNM of EGC was established based on the multivariate results.ResultsA total of 311 cases of EGC were included in this study, and 60 (19.3%) cases had LNM. Univariate and multivariate analysis showed that age (younger), depth of tumor invasion (submucosa), vascular invasion, and undifferentiated carcinoma were the risk factors for LNM of EGC (P<0.05). The optimal threshold for predicting LNM of EGC was 0.158 (area under the receiver operating characteristic curve was 0.864), the sensitivity was 80.0%, and the specificity was 79.3%.ConclusionsFrom results of this study, risk factors for LNM of EGC have age, depth of invasion, vascular invasion, and differentiation degree. Risk prediction model for LNM of EGC established on this results has high sensitivity and specificity, which could provide some references for treatment strategy of EGC.
Keloids are benign skin tumors resulting from the excessive proliferation of connective tissue in wound skin. Precise prediction of keloid risk in trauma patients and timely early diagnosis are of paramount importance for in-depth keloid management and control of its progression. This study analyzed four keloid datasets in the high-throughput gene expression omnibus (GEO) database, identified diagnostic markers for keloids, and established a nomogram prediction model. Initially, 37 core protein-encoding genes were selected through weighted gene co-expression network analysis (WGCNA), differential expression analysis, and the centrality algorithm of the protein-protein interaction network. Subsequently, two machine learning algorithms including the least absolute shrinkage and selection operator (LASSO) and the support vector machine-recursive feature elimination (SVM-RFE) were used to further screen out four diagnostic markers with the highest predictive power for keloids, which included hepatocyte growth factor (HGF), syndecan-4 (SDC4), ectonucleotide pyrophosphatase/phosphodiesterase 2 (ENPP2), and Rho family guanosine triphophatase 3 (RND3). Potential biological pathways involved were explored through gene set enrichment analysis (GSEA) of single-gene. Finally, univariate and multivariate logistic regression analyses of diagnostic markers were performed, and a nomogram prediction model was constructed. Internal and external validations revealed that the calibration curve of this model closely approximates the ideal curve, the decision curve is superior to other strategies, and the area under the receiver operating characteristic curve is higher than the control model (with optimal cutoff value of 0.588). This indicates that the model possesses high calibration, clinical benefit rate, and predictive power, and is promising to provide effective early means for clinical diagnosis.
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.
ObjectiveTo investigate factors influencing the results of bronchodilator reversibility tests (BDT) in mild to moderate asthma, and to develop a model predicting the result of BDT in this population. Methods A cross-sectional study was designed to recruit patients with forced expiratory volume in the first second (FEV1) ≥ 70% predicted from the Australasian Severe Asthma Network during 2014 to 2021, whose asthma diagnosis was confirmed by a positive bronchial challenge test. Structural questionnaires, BDT, fractional exhaled nitric oxide (FeNO), induced sputum and peripheral blood sampling were conducted. Patients were further divided into positive group and negative group according to their BDT result. Then the comparative analysis between two groups, correlation analysis, and multivariate logistical regression were performed. Logistic models for predicting BDT result were developed using variables screened through LASSO regression. Results A total of 334 patients were included. Compared with the BDT negative group (n=240), the BDT positive group (n=94) was found to have worse airway obstruction in lung function, asthma control and quality of life, higher eosinophil counts in both peripheral blood and induced sputum, and higher FeNO. According to the multivariate regression, the positive BDT results significantly correlated with Asthma Control Questionnaire score, Asthma Questionnaire of Life Quality score, FEV1%pred, MMEF%pred, FEV1/FVC, blood and sputum eosinophil counts and FeNO. A total of 326 patients were included in the training set, and FEV1%pred, MMEF%pred, FEV1/FVC, smoking pack years, blood and sputum eosinophil counts and FeNO were then screened out by LASSO regression as stable predictors. The areas under the receiver operating characteristic curve of the 3 prediction models (P<0.001) constructed using the variables above ranged from 0.810 to 0.834. Internal validation was performed, and both the discrimination (0.810, 0.834 and 0.812, respectively) and the calibration (0.135, 0.133 and 0.192, respectively) of the models were acceptable. Conclusion The BDT results of patients with mild to moderate asthma were associated with asthma control, lung function, systemic or airway eosinophilia and FeNO, and models including lung function, eosinophils, and FeNO, etc. could predict the BDT results well.
ObjectiveTo investigate the predictive value of volatile organic compounds (VOCs) on pulmonary nodules in people aged less than 50 years.MethodsThe 147 patients with pulmonary nodules and aged less than 50 years who were treated in the Department of Thoracic Surgery of Sichuan Cancer Hospital from August 1, 2019 to January 15, 2020 were divided into a lung cancer group and a lung benign disease group. The lung cancer group included 36 males and 68 females, with the age of 27-49 (43.54±5.73) years. The benign lung disease group included 23 males and 20 females, with the age of 22-49 (42.49±6.83) years. Clinical data and exhaled breath samples were collected prospectively from the two groups. Exhaled breath VOCs were analyzed by gas chromatography mass spectrometry. Binary logistic regression analysis was used to select variables and establish a prediction model. The sensitivity, specificity, and area under the receiver operating characteristic (ROC) curve of the prediction model were calculated.ResultsThere were statistically significant differences in sex (P=0.034), smoking history (P=0.047), cyclopentane (P=0.002), 3-methyl pentane (P=0.043) and ethylbenzene (P=0.009) between the two groups. The sensitivity, specificity and area under the ROC curve of the prediction model with gender, cyclopentane, 3-methyl pentane, ethylbenzene and N,N-dimethylformamide as variables were 80.8%, 60.5% and 0.781, respectively.ConclusionThe combination of VOCs and clinical characteristics has a certain predictive value for the benign and malignant pulmonary nodules in people aged less than 50 years.
