Early risk stratification of postoperative pneumonia after brain tumor surgery using routine perioperative variables: development and prospective multicenter validation of an interpretable prediction model
Aug 2026· Frontiers in Cellular and Infection Microbiology· Vol 16· 0 citations· 39 references
Medicine
TL;DR
This interpretable 11-variable model enables early POP risk stratification after brain tumor surgery and may support timely preventive intervention in neurosurgical care.
Abstract
Background Early postoperative pneumonia (POP) is a common and serious complication after brain tumor surgery, but early recognition is difficult because postoperative neurological dysfunction and respiratory symptoms are often non-specific. Existing models are mostly retrospective, not designed for neurosurgical patients, and rarely prospectively validated across centers. We aimed to develop an interpretable model for early POP risk stratification. Methods We used routine perioperative data from 1,856 patients undergoing brain tumor surgery at multiple centers in China between 2022 and 2025. Ten machine learning algorithms were compared. From 41 candidate variables, 11 predictors were selected using correlation analysis and LASSO. The final locked model was prospectively tested in one internal temporal cohort and three external cohorts. Performance was assessed by AUC, calibration, and decision curve analysis. Interpretability was evaluated using SHAP, a nomogram, and a web calculator. Results Logistic regression showed the best overall performance, with an AUC of 0.897 (95% CI, 0.842–0.952) in the internal cohort and a mean AUC of 0.876 ± 0.044 across the three external cohorts. Key predictors included chronic lung disease (CLD), diabetes mellitus (DM), body mass index (BMI), admission Karnofsky Performance Status (KPS), and preoperative albumin (Alb) and glucose (Glu). Conclusion This interpretable 11-variable model enables early POP risk stratification after brain tumor surgery and may support timely preventive intervention in neurosurgical care.
Background Elderly patients with colon cancer are at increased risk of major postoperative adverse events, but existing risk assessment tools often require detailed clinical or laboratory information. We developed and internally validated a rapid prediction nomogram using routinely available administrative variables. Methods This multicenter retrospective study included 4, 942 elderly patients with colon cancer from five hospitals. Major postoperative adverse events were identified using a predefined ICD-10 code-based algorithm adapted from the Healthgrades patient-safety framework. Given the low event rate, Firth penalized likelihood regression was used to develop the prediction model. Internal validation was performed using 1, 000 bootstrap resamples. Model performance was assessed by discrimination, calibration, Brier score, and decision curve analysis. Results Independent predictors included payment method (medical insurance: OR = 2.630), admission type (outpatient: OR = 0.501), surgical approach (minimally invasive: OR = 0.473), and comorbidity index (OR = 1.041). The full model showed moderate discrimination, with an apparent AUC of 0.724 and a bootstrap-corrected AUC of 0.709. The apparent and bootstrap-corrected Brier scores were 0.0244 and 0.0247, respectively. Decision curve analysis suggested potential net benefit across threshold probabilities of 1%–51%. Conclusion This nomogram may serve as a rapid, low-cost preliminary screening tool for estimating the risk of major postoperative adverse events in elderly patients with colon cancer. External validation and further refinement using more detailed clinical, nutritional, oncological, and functional variables are needed before broader clinical application.
Yixiang Huang, Xiaohui Yuan, Xiangbo Zhang et al.· Frontiers in Oncology· 0 citations
RF-based models can accurately and equitably predict perioperative complications in diverse spine surgery contexts, supporting personalized counseling, targeted monitoring, and optimized resource allocation.
Andrea Campagner, Francesco Langella, P. Bellosta-López et al.· European spine journal· 0 citations
An interpretable gradient-boosting model may support risk-stratified perioperative assessment for elderly patients undergoing abdominal surgery and Prospective multicenter validation is required before routine clinical implementation.
Qiang Zhong, Guiming Huang, Wen Zhou et al.· Frontiers in Surgery· 0 citations
BACKGROUND
Postoperative pulmonary infection (PPI) is a common and serious complication in older adults undergoing hip fracture surgery, leading to prolonged hospitalization, increased costs, and increased mortality. However, simple and reliable preoperative predictors remain limited. Therefore, this study aimed to develop and validate a hematology-based machine learning model for the early prediction of PPI in older hip fracture patients.
METHODS
A total of 3,944 patients aged ≥ 60 years who underwent hip fracture surgery were retrospectively enrolled from three cohorts: the discovery cohort (n = 1,745, Shanghai Xuhui Central Hospital, 2016-2020), the internal validation cohort (n = 1,306, 2021-2024), and the external validation cohort (n = 893, Shanghai Putuo People's Hospital, 2016-2024). Twenty-four preoperative hematologic variables were analyzed. Six supervised machine learning algorithms were compared via fivefold cross-validation. Model performance was evaluated by the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, F1 score, calibration, and decision curve analysis (DCA).
RESULTS
Patients who developed PPI were generally older and exhibited a neutrophil-dominant inflammatory profile, characterized by higher white blood cell counts, neutrophil, monocyte, platelet, and C-reactive protein levels, and lower lymphocyte, eosinophil, and basophil percentages (all p < 0.001). Among the evaluated algorithms, the extreme gradient boosting (XGBoost) model achieved the best overall performance, with AUCs of 1.00, 0.96, and 0.98 in the discovery, internal, and external cohorts, respectively. Calibration curves suggested good agreement between predicted and observed probabilities, and DCA indicated favorable clinical net benefit across threshold probabilities.
CONCLUSIONS
A hematology-based XGBoost model was developed to predict in-hospital PPI in older adults following hip fracture surgery. The model demonstrated good discriminative performance and interpretability in this study cohort, suggesting its potential utility as a supplementary tool for cost-effective perioperative risk stratification. However, further prospective validation in diverse populations and healthcare settings is required to confirm its generalizability and clinical applicability.
This LASSO-derived nomogram provides transparent, bedside-applicable risk stratification for postoperative composite complications in CRC surgery, identifying nutritional status as the dominant modifiable predictor and supporting targeted perioperative optimization.
Lu Wang, Shunshun Wang, Liqin Deng· Frontiers in Nutrition· 0 citations
Background Urinary dysfunction is a relatively common functional complication after laparoscopic radical surgery for rectal cancer and may affect postoperative recovery and quality of life. This study aimed to identify risk factors for urinary dysfunction after laparoscopic radical rectal cancer surgery and to develop a nomogram prediction model to facilitate early identification of high-risk patients. Methods A total of 392 patients who underwent laparoscopic radical surgery for rectal cancer between January 2021 and December 2025 were retrospectively included. Patients were grouped according to the occurrence of postoperative urinary dysfunction and randomly divided into a training cohort and a validation cohort at a ratio of 7:3. Demographic, tumor-related, and perioperative variables were collected. Univariable and multivariable logistic regression analyses were performed to identify independent predictors, and a nomogram model was constructed. Model performance was evaluated using receiver operating characteristic curves, calibration curves, the Hosmer-Lemeshow test, and decision curve analysis. Results Among the 392 patients, 84 developed postoperative urinary dysfunction, with an incidence of 21.4%. Multivariable logistic regression analysis showed that age ≥65 years, male sex, tumor distance from the anal verge ≤5 cm, intraoperative fluid rate ≥10 mL/kg/h, neoadjuvant chemoradiotherapy, documented incomplete pelvic autonomic nerve preservation, and postoperative urinary tract infection were independent factors associated with postoperative urinary dysfunction. A nomogram was constructed based on these predictors. The area under the curve was 0.864 (95% CI: 0.803–0.926) in the training cohort and 0.856 (95% CI: 0.774–0.938) in the validation cohort. Calibration curves and the Hosmer-Lemeshow test indicated good model fit, and decision curve analysis showed favorable clinical net benefit. Conclusion Age, sex, tumor distance from the anal verge, intraoperative fluid rate, neoadjuvant chemoradiotherapy, pelvic autonomic nerve preservation, and postoperative urinary tract infection were closely associated with urinary dysfunction after laparoscopic radical surgery for rectal cancer. The nomogram based on these factors showed good predictive performance and may help identify high-risk patients, guide urinary catheter management, and support postoperative follow-up.
