European journal of surgical oncology : the journal of the European Society of Surgical Oncology and the British Association of Surgical Oncology · 2025
Risk comparison and assessment model of deep vein thrombosis in patients with pituitary adenomas after Surgery:A retrospective cohort study.
СтатьяСравнительное исследованиеНазвание и аннотация: Перевод пока не подготовлен
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Wu Hongyu, Zhang Yu, Ma Xin, Mi Zenghua, Yang Zhijun
Аннотация
BACKGROUND: Deep vein thrombosis (DVT), a major component of venous thromboembolism (VTE), is a common postoperative complication. Its occurrence after pituitary adenoma surgery is influenced by multiple factors.
METHODS: This retrospective study analyzed 1440 pituitary adenoma cases treated at Beijing Tiantan Hospital (2018-2023). The incidence of postoperative DVT was recorded, and logistic regression was used to identify associated risk factors. Differences across pituitary adenoma subtypes were compared. Additionally, Regression and machine learning models were developed to predict DVT.
RESULTS: Among 397 patients who underwent postoperative lower limb ultrasound, 104 (7.2 %) developed DVT. Significant risk factors included advanced age, higher body mass index (BMI), intravenous cannulation, prolonged hospital stay, shorter preoperative activated partial thromboplastin time (APTT), longer thrombin time (TT), elevated platelet count, and higher postoperative D-dimer levels. Patients with Cushing's disease exhibited a significantly higher DVT incidence, potentially related to decreased pre- and postoperative APTT and PT/INR values. Conversely, patients with prolactin-secreting adenomas had a lower DVT incidence, possibly due to younger age and higher postoperative PT values. A support vector machine (SVM) model showed strong predictive performance (AUC: 0.82; accuracy: 86.08 %; specificity: 96.72 %).
CONCLUSION: DVT incidence varies by pituitary adenoma subtype. Machine learning enhances predictive models for postoperative DVT in pituitary adenoma patients.
METHODS: This retrospective study analyzed 1440 pituitary adenoma cases treated at Beijing Tiantan Hospital (2018-2023). The incidence of postoperative DVT was recorded, and logistic regression was used to identify associated risk factors. Differences across pituitary adenoma subtypes were compared. Additionally, Regression and machine learning models were developed to predict DVT.
RESULTS: Among 397 patients who underwent postoperative lower limb ultrasound, 104 (7.2 %) developed DVT. Significant risk factors included advanced age, higher body mass index (BMI), intravenous cannulation, prolonged hospital stay, shorter preoperative activated partial thromboplastin time (APTT), longer thrombin time (TT), elevated platelet count, and higher postoperative D-dimer levels. Patients with Cushing's disease exhibited a significantly higher DVT incidence, potentially related to decreased pre- and postoperative APTT and PT/INR values. Conversely, patients with prolactin-secreting adenomas had a lower DVT incidence, possibly due to younger age and higher postoperative PT values. A support vector machine (SVM) model showed strong predictive performance (AUC: 0.82; accuracy: 86.08 %; specificity: 96.72 %).
CONCLUSION: DVT incidence varies by pituitary adenoma subtype. Machine learning enhances predictive models for postoperative DVT in pituitary adenoma patients.