Incidence, predictors and validation of risk scores to predict postoperative mortality after noncardiac vascular surgery, a prospective cohort study

Reis, Pedro; Lopes, Ana Isabel; Leite, Diana; Moreira, João; Mendes, Leonor; Ferraz, Sofia; Amaral, Tânia; Abelha, Fernando

doi:10.1016/j.ijsu.2019.12.010

Cited by 18 publications

(9 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The review further confirmed that random forests and gradient boosting were most frequently used and showed best model performance 8 . The results of our study were consistent with these results as, using XGBoost, we achieve an AUROC of 0.95 and an acceptable precision-recall trade-off 26 .…”

Section: Discussionsupporting

confidence: 90%

Enabling personalized perioperative risk prediction by using a machine-learning model based on preoperative data

Graeßner

Jungwirth

Frank

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Preoperative risk assessment is essential for shared decision-making and adequate perioperative care. Common scores provide limited predictive quality and lack personalized information. The aim of this study was to create an interpretable machine-learning-based model to assess the patient’s individual risk of postoperative mortality based on preoperative data to allow analysis of personal risk factors. After ethical approval, a model for prediction of postoperative in-hospital mortality based on preoperative data of 66,846 patients undergoing elective non-cardiac surgery between June 2014 and March 2020 was created with extreme gradient boosting. Model performance and the most relevant parameters were shown using receiver operating characteristic (ROC−) and precision-recall (PR-) curves and importance plots. Individual risks of index patients were presented in waterfall diagrams. The model included 201 features and showed good predictive abilities with an area under receiver operating characteristic (AUROC) curve of 0.95 and an area under precision-recall curve (AUPRC) of 0.109. The feature with the highest information gain was the preoperative order for red packed cell concentrates followed by age and c-reactive protein. Individual risk factors could be identified on patient level. We created a highly accurate and interpretable machine learning model to preoperatively predict the risk of postoperative in-hospital mortality. The algorithm can be used to identify factors susceptible to preoperative optimization measures and to identify risk factors influencing individual patient risk.

show abstract

Section: Discussionsupporting

confidence: 90%

Enabling personalized perioperative risk prediction by using a machine-learning model based on preoperative data

Graeßner

Jungwirth

Frank

et al. 2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Two studies reported a mean observed mortality rate (‘calibration-in-the-large’) lower than predicted by POSPOM which is in accordance with our results [ 9 , 12 ]. One study found an observed mortality similar to predicted [ 11 ]. Of all preceding validation studies, two studies examined calibration more closely via a calibration plot [ 8 , 14 ].…”

Section: Discussionsupporting

confidence: 66%

“…The performance of the POSPOM score has been evaluated mostly in specific surgical populations, including patients undergoing emergency abdominal surgery, [ 8 ] radical cystectomy, [ 9 ] vascular surgery, [ 10 , 11 ] and elderly patients with hip fractures [ 12 ]. Two studies have evaluated POSPOM in large heterogeneous surgical populations, using single center retrospective data [ 13 , 14 ].…”

Section: Introductionmentioning

confidence: 99%

Validation of the PreOperative Score to predict Post-Operative Mortality (POSPOM) in Dutch non-cardiac surgery patients

Stolze¹,

Garde

Posthuma

et al. 2022

BMC Anesthesiol

View full text Add to dashboard Cite

Background Standardized risk assessment tools can be used to identify patients at higher risk for postoperative complications and death. In this study, we validate the PreOperative Score to predict Post-Operative Mortality (POSPOM) for in-hospital mortality in a large cohort of non-cardiac surgery patients. In addition, the performance of POSPOM to predict postoperative complications was studied. Methods Data from the control cohort of the TRACE (routine posTsuRgical Anesthesia visit to improve patient outComE) study was analysed. POSPOM scores for each patient were calculated post-hoc. Observed in-hospital mortality was compared with predicted mortality according to POSPOM. Discrimination was assessed by receiver operating characteristic curves with C-statistics for in-hospital mortality and postoperative complications. To describe the performance of POSPOM sensitivity, specificity, negative predictive values, and positive predictive values were calculated. For in-hospital mortality, calibration was assessed by a calibration plot. Results In 2490 patients, the observed in-hospital mortality was 0.5%, compared to 1.3% as predicted by POSPOM. 27.1% of patients had at least one postoperative complication of which 22.4% had a major complication. For in-hospital mortality, POSPOM showed strong discrimination with a C-statistic of 0.86 (95% CI, 0.78–0.93). For the prediction of complications, the discrimination was poor to fair depending on the severity of the complication. The calibration plot showed poor calibration of POSPOM with an overestimation of in-hospital mortality. Conclusion Despite the strong discriminatory performance, POSPOM showed poor calibration with an overestimation of in-hospital mortality. Performance of POSPOM for the prediction of any postoperative complication was poor but improved according to severity.

show abstract

“…Numerous studies have examined predictors of adverse cardiovascular outcomes and mortality following Eur J Anaesthesiol 2022; 39:145-151 noncardiac surgery. [25][26][27][28][29][30][31][32][33][34][35][36][37][38][39] These studies differed in their selection of patients, types of surgery, proportions of emergency procedures and extent of postoperative morbidity. We aimed to identify the definition of intraoperative tachycardia that has the strongest association with adverse postoperative outcomes.…”

Section: Discussionmentioning

confidence: 99%

Associations between different measures of intra-operative tachycardia during noncardiac surgery and adverse postoperative outcomes

Shcherbakov

Bisharat

2021

European Journal of Anaesthesiology

View full text Add to dashboard Cite

BACKGROUND Intra-operative tachycardia during noncardiac surgery has been associated with adverse postoperative outcomes. However, harm thresholds for tachycardia have not been uniformly defined. The definition of intraoperative tachycardia that best correlates with adverse postoperative outcomes remains unclear.OBJECTIVE We aimed to identify the definition of intraoperative tachycardia during noncardiac surgery that is associated with the best predictive ability for adverse postoperative outcomes.DESIGN A single-centre retrospective cohort analysis.SETTING Secondary care hospital, Afula, Israel.PATIENTS AND METHODS Adults who underwent elective or nonelective noncardiac surgery during 2015 to 2019. Five intra-operative heart rate (HR) cut-off values and durations were applied with penalised logistic regression modelling for the outcome measures. MAIN OUTCOME MEASURESThe primary outcome was all-cause 30-day mortality; the secondary outcome was myocardial ischaemia or infarction (MI) within 30 days after noncardiac surgery. RESULTSThe derivation and validation datasets included 6490 and 4553 patients, respectively. Altogether, all-cause 30-day mortality and MI rates averaged 2.1% and 3.2%, respectively. Only two definitions of intra-operative tachycardia were significantly associated with the outcome measures: HR ! 100 bpm for ! 30 min and HR ! 120 bpm for ! 5 min. The C-statistics of the base models without tachycardia exposure for all-cause 30-day mortality and MI were 0.75 (95% confidence interval, CI, 0.74 to 0.78) and 0.73 (95% CI, 0.72 to 0.76), respectively. The addition of intra-operative tachycardia exposure to the base models significantly improved their predictive performance. The highest area under the curve (AUC) was achieved when tachycardia was defined as an intra-operative HR ! 100 bpm for at least 30 min: AUC 0.81 (95% CI, 0.80 to 0.84) and AUC 0.80 (95% CI, 0.79 to 0.82) for all-cause 30-day mortality and MI, respectively.CONCLUSION Intra-operative tachycardia, defined as an intra-operative HR ! 100 bpm for at least 30 min, was associated with the highest predictive power for adverse postoperative outcomes.

show abstract

Incidence, predictors and validation of risk scores to predict postoperative mortality after noncardiac vascular surgery, a prospective cohort study

Cited by 18 publications

References 35 publications

Enabling personalized perioperative risk prediction by using a machine-learning model based on preoperative data

Enabling personalized perioperative risk prediction by using a machine-learning model based on preoperative data

Validation of the PreOperative Score to predict Post-Operative Mortality (POSPOM) in Dutch non-cardiac surgery patients

Associations between different measures of intra-operative tachycardia during noncardiac surgery and adverse postoperative outcomes

Contact Info

Product

Resources

About