Prediction model for 30-day morbidity after gynecological malignancy surgery

Abstract

ObjectiveThe potential risk of postoperative morbidity is important for gynecologic cancer patients because it leads to delays in adjunctive therapy and additional costs. We aimed to develop a preoperative nomogram to predict 30-day morbidity after gynecological cancer surgery.MethodsBetween 2005 and 2015, 533 consecutive patients with elective gynecological cancer surgery in our center were reviewed. Of those patients, 373 and 160 patients were assigned to the model development or validation cohort, respectively. To investigate independent predictors of 30-day morbidity, a multivariate Cox regression model with backward stepwise elimination was utilized. A nomogram based on this Cox model was developed and externally validated. Its performance was assessed using the concordance index and a calibration curve.ResultsNinety-seven (18.2%) patients had at least one postoperative complication within 30 days after surgery. After bootstrap resampling, the final model indicated age, operating time, and serum albumin level as statistically significant predictors of postoperative morbidity. The bootstrap-corrected concordance index of the nomogram incorporating these three predictors was 0.656 (95% CI, 0.608–0.723). In the validation cohort, the nomogram showed fair discrimination [concordance index: 0.674 (95% CI = 0.619–0.732] and good calibration (P = 0.614; Hosmer-Lemeshow test).ConclusionThe 30-day morbidity after gynecologic cancer surgery could be predicted according to age, operation time, and serum albumin level. After further validation using an independent dataset, the constructed nomogram could be valuable for predicting operative risk in individual patients.

Simple radiologic assessment of visceral obesity and prediction of surgical morbidity in high-risk endometrial cancer: a reliability and accuracy pilot study

“…Previously published risk prediction models have performed worse than ours, having a diagnostic power insufficient for clinical use (< 0.70) 7,8 . Very few studies that evaluate surgical morbidity prediction have included the surgical approach in their models (i.e.…”

Gynecological Surgery and Machine Learning: Complications and Length of Stay Prediction

“…This study presents implementation of predictive models for the duration of stay after a surgery, complications and duration of a surgery. The models provide a higher precision than the state-of-the-art models [4][5][6][7]. Identification of risk factors using the results of the features importance analysis can support clinicians in the early analysis of complications and planning the preventive measures.…”

“…For example, the study [6] developed a prediction model for a 30-day morbidity after gynecological malignancy surgery. With a bootstrap-corrected concordance, index of the nomogram incorporating these three predictors was 0.656 (95% CI, 0.608-0.723).…”

Simple radiologic assessment of visceral obesity and prediction of surgical morbidity in high-risk endometrial cancer: a reliability and accuracy pilot study

“…Thus, efforts should focus on establishing a method to preoperatively identify those patients at risk. Several authors have attempted to describe predictors of complications and to validate risk scoring systems specifically in gynaecologic oncology surgery [6][7][8][9][10]34,[36][37][38][39] . But the studied populations were too heterogeneous, and yielded poor results, hindering their clinical application.…”

“…The prediction of surgical morbidity is fundamental in gynaecological oncology [6][7][8][9][10] . One of the key factors associated with surgical morbidity is obesity [11][12][13] .…”