Prediction of intraoperative bleeding and blood transfusion in patients with recurrent retroperitoneal liposarcoma: a retrospective study

Liu, Wenqing; Zou, Boyuan; Tang, Maosheng; Li, Xiangji; Huang, Mei; Chen, Weida; Miao, Changxing

doi:10.21037/atm-22-4222

Cited by 3 publications

(1 citation statement)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The present study also indicated that the incidence of tumor recurrence was significantly lower in the well-differentiated group and the de-differentiated histological subtype was able to be used as an independent risk factor of LRFS for PRPLS cases. De-differentiated PRPLS frequently has an incomplete tumor capsule and irregular tumor shape, which makes the boundary between the tumor and normal tissue difficult to identify, thus prolonging the operation time, increasing intraoperative bleeding and hampering the completion of radical resection (10,19,23,24).…”

Section: Univariate Analysismentioning

confidence: 99%

Predictive factors and a novel nomogram for recurrence of primary retroperitoneal liposarcoma: Comprehensive analysis of 128 cases

Gao

Liu

et al. 2023

Oncol Lett

View full text Add to dashboard Cite

Since primary retroperitoneal liposarcoma (PRPLS) is rare in the clinic, related clinical studies are lacking. The present study was designed to investigate the predictive factors of short-term (≤1 year) recurrence (STR) and construct a novel nomogram of local recurrence-free survival (LRFS) for surgically resected PRPLS. A total of 128 PRPLS cases who underwent radical surgery were retrospectively analyzed. Based on the interval from the operation to tumor recurrence, the predictors of STR were screened using univariate and multivariate logistic regression analyses. Cox proportional hazard regression models were applied to identify the predictors of LRFS. Furthermore, the independent predictors acquired from multivariate analyses were used to construct a nomogram. Multivariate logistic regression analysis revealed that age ≥55 years [odds ratio (OR)=5.607, P=0.010], operative time ≥260 min (OR=9.716, P=0.005) and tumor necrosis (OR=3.781, P=0.037) were independent risk factors of STR for PRPLS. In the Cox regression analysis, clinical symptoms [hazard ratio (HR)=1.746, P=0.017], resection method (OR=0.370, P=0.021) and de-differentiated histological subtype (HR=1.975, P=0.048) were identified as independent predictors of LRFS. Subsequently, the independent predictors acquired from multivariate analyses were used to construct a nomogram for LRFS. Age, operative time, tumor necrosis, clinical symptoms, resection method and histological subtype were related to recurrence for surgically resected PRPLS and a novel nomogram was constructed based on the above predictors.

show abstract

Section: Univariate Analysismentioning

confidence: 99%

Predictive factors and a novel nomogram for recurrence of primary retroperitoneal liposarcoma: Comprehensive analysis of 128 cases

Gao

Liu

et al. 2023

Oncol Lett

View full text Add to dashboard Cite

show abstract

Perioperative Blood Transfusions and Cancer Progression: A Narrative Review

Abou Daher,

Heppell,

Lopez-Plaza

et al. 2024

Curr Oncol Rep

View full text Add to dashboard Cite

Machine learning algorithms to predict intraoperative hemorrhage in surgical patients: a modeling study of real-world data in Shanghai, China

Shi

Zhang

et al. 2023

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

Background Prediction tools for various intraoperative bleeding events remain scarce. We aim to develop machine learning-based models and identify the most important predictors by real-world data from electronic medical records (EMRs). Methods An established database of surgical inpatients in Shanghai was utilized for analysis. A total of 51,173 inpatients were assessed for eligibility. 48,543 inpatients were obtained in the dataset and patients were divided into haemorrhage (N = 9728) and without-haemorrhage (N = 38,815) groups according to their bleeding during the procedure. Candidate predictors were selected from 27 variables, including sex (N = 48,543), age (N = 48,543), BMI (N = 48,543), renal disease (N = 26), heart disease (N = 1309), hypertension (N = 9579), diabetes (N = 4165), coagulopathy (N = 47), and other features. The models were constructed by 7 machine learning algorithms, i.e., light gradient boosting (LGB), extreme gradient boosting (XGB), cathepsin B (CatB), Ada-boosting of decision tree (AdaB), logistic regression (LR), long short-term memory (LSTM), and multilayer perception (MLP). An area under the receiver operating characteristic curve (AUC) was used to evaluate the model performance. Results The mean age of the inpatients was 53 ± 17 years, and 57.5% were male. LGB showed the best predictive performance for intraoperative bleeding combining multiple indicators (AUC = 0.933, sensitivity = 0.87, specificity = 0.85, accuracy = 0.87) compared with XGB, CatB, AdaB, LR, MLP and LSTM. The three most important predictors identified by LGB were operative time, D-dimer (DD), and age. Conclusions We proposed LGB as the best Gradient Boosting Decision Tree (GBDT) algorithm for the evaluation of intraoperative bleeding. It is considered a simple and useful tool for predicting intraoperative bleeding in clinical settings. Operative time, DD, and age should receive attention.

show abstract

Prediction of intraoperative bleeding and blood transfusion in patients with recurrent retroperitoneal liposarcoma: a retrospective study

Cited by 3 publications

References 53 publications

Predictive factors and a novel nomogram for recurrence of primary retroperitoneal liposarcoma: Comprehensive analysis of 128 cases

Predictive factors and a novel nomogram for recurrence of primary retroperitoneal liposarcoma: Comprehensive analysis of 128 cases

Perioperative Blood Transfusions and Cancer Progression: A Narrative Review

Machine learning algorithms to predict intraoperative hemorrhage in surgical patients: a modeling study of real-world data in Shanghai, China

Contact Info

Product

Resources

About