American College of Surgeons NSQIP Risk Calculator Accuracy for Emergent and Elective Colorectal Operations

Lubitz, Andrea L.; Chan, Elaine; Zarif, Daniel; Ross, Howard M.; Philp, Matthew M.; Goldberg, Amy J.; Pitt, Henry A.

doi:10.1016/j.jamcollsurg.2017.07.1069

Cited by 47 publications

(38 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Online risk calculators like the National Surgical Quality Improvement Program Surgical Risk Calculator can reduce variability and increase the likelihood that patients will engage in prehabilitation, but they have time-consuming manual data acquisition and entry requirements, which hinders their clinical adoption. [13][14][15][16][17][18] Emerging technologies can circumvent this problem. The MySurgeryRisk platform autonomously draws data from multiple input sources and uses machine learning techniques to predict postoperative complications and mortality.…”

Section: Discussionmentioning

confidence: 99%

Added Value of Intraoperative Data for Predicting Postoperative Complications: The MySurgeryRisk PostOp Extension

Datta

Loftus

Ruppert

et al. 2020

Journal of Surgical Research

View full text Add to dashboard Cite

Background: Models that predict postoperative complications often ignore important intraoperative events and physiological changes. This study tested the hypothesis that accuracy, discrimination, and precision in predicting postoperative complications would improve when using both preoperative and intraoperative data input data compared with preoperative data alone. Methods: This retrospective cohort analysis included 43,943 adults undergoing 52,529 inpatient surgeries at a single institution during a 5-y period. Random forest machine learning models in the validated MySurgeryRisk platform made patient-level predictions for seven postoperative complications and mortality occurring during hospital admission using electronic health record data and patient neighborhood characteristics. For each outcome, one model trained with preoperative data alone; one model trained with both preoperative and intraoperative data. Models were compared by accuracy, discrimination (expressed as area under the receiver operating characteristic curve), precision (expressed as area under the precision-recall curve), and reclassification indices. Results: Machine learning models incorporating both preoperative and intraoperative data had greater accuracy, discrimination, and precision than models using preoperative data alone for predicting all seven postoperative complications (intensive care unit length of stay >48 h, mechanical ventilation >48 h, neurologic complications including delirium, cardiovascular complications, acute kidney injury, venous thromboembolism, and wound complications), and in-hospital mortality (accuracy: 88% versus 77%; area under the receiver operating characteristic curve: 0.93 versus 0.87; area under the precision-recall

show abstract

Section: Discussionmentioning

confidence: 99%

Added Value of Intraoperative Data for Predicting Postoperative Complications: The MySurgeryRisk PostOp Extension

Datta

Loftus

Ruppert

et al. 2020

Journal of Surgical Research

View full text Add to dashboard Cite

show abstract

“…Based on this program, Bilimoria and collaborators established the NSQIP Risk Calculator in 2013 [19]. This calculator proved to accurately predict outcomes, e.g., for Whipple procedures [20] and colorectal surgery [21] amongst others.…”

Section: Discussionmentioning

confidence: 99%

Experiences with the standardized classification of surgical complications (Clavien-Dindo) in general surgery patients

et al. 2018

View full text Add to dashboard Cite

SummaryBackgroundThe standardized Clavien-Dindo classification of surgical complications is applied as a simple and widely used tool to assess and report postoperative complications in general surgery. However, most documentation uses this classification to report surgery-related morbidity and mortality in a single field of surgery or even particular intervention. The aim of the present study was to present experiences with the Clavien-Dindo classification when applied to all patients on the general surgery ward of a tertiary referral care center.MethodsWe analyzed a period of 6 months of care on a ward with a broad range of general and visceral surgery. Discharge reports and patient charts were analyzed retrospectively and reported complications rated according to the most recent Clavien-Dindo classification version. The complexity of operations was assessed with the Austrian Chamber of Physicians accounting system.ResultsThe study included 517 patients with 817 admissions, of whom 463 had been operated upon. Complications emerged in 12.5%, of which 19% were rated as Clavien I, 20.7% as Clavien II, 13.8% as Clavien IIIa, 27.6% as Clavien IIIb, 8.6% as Clavien IVa, and 10.3% as Clavien V. No Clavien grade IVb complication occurred within the investigation. Patients having undergone more complex surgery or with higher scores experienced significantly longer lengths of hospital stay.ConclusionThe Clavien-Dindo classification can easily be used to document complication rates in general surgery, even though this collective was not included in the original validation studies of Clavien et al. and consisted of more heavily impaired patients.

show abstract

“…2 However, conversely, Lubitz et al found that in emergent colorectal surgery, the ACS risk calculator underestimated serious complications and length of stay and overestimated discharge to skilled nursing facility. 1 This was corroborated by Cologne et al's group in a high-volume minimally invasive colorectal surgery practice. 6 Thus, the ACS risk calculator is a valuable tool for allowing more informed consent; however, too many factors exist that impact the outcomes that cannot be measured by any specific model.…”

mentioning

confidence: 72%

“…Moreover, patients face their own challenges as their perspectives on informed consent are also influenced by multiple factors, which include age, sex, race, education level, native language, and socioeconomic status. 1 To that end, many surgeons now utilize a risk calculator to help provide patients with more objective data to help characterize and quantify their individual risk for developing postoperative complications. There are two main predictive models of postoperative risks in colorectal surgery: the American College of Surgeons (ACS) National Surgery Quality Improvement Program (NSQIP) risk calculator and Physiological and Operative Severity Score for the enUmeration of Mortality and morbidity (POSSUM), with its variants.…”

mentioning

confidence: 99%

Predicting and Preventing Postoperative Outcomes

Lee

Russ

2019

Clinics in Colon and Rectal Surgery

View full text Add to dashboard Cite

Complications after colorectal surgery are common. Given the frequency of postoperative complications and their implications on quality of life, it is important to know how to predict and prevent the complications that we encounter. This article aims to provide ways to predict and prevent postoperative complications in colorectal surgery. Here, we review the predictive models, American College of Surgeons National Surgery Quality Improvement Program risk calculator and Physiological and Operative Severity Score for the enUmeration of Mortality and morbidity on their practicality and usefulness. Additionally, this review summarizes nonmodifiable and modifiable risk factors in colorectal surgery, which are important for surgeons to understand to minimize and attempt to avoid postoperative complications as well as providing ways to optimize patients preoperatively. Thus, this review will provide information to surgeons to predict and prevent postoperative complications, how to optimize patients preoperatively and ultimately to help reduce their occurrence.

show abstract

American College of Surgeons NSQIP Risk Calculator Accuracy for Emergent and Elective Colorectal Operations

Cited by 47 publications

References 25 publications

Added Value of Intraoperative Data for Predicting Postoperative Complications: The MySurgeryRisk PostOp Extension

Added Value of Intraoperative Data for Predicting Postoperative Complications: The MySurgeryRisk PostOp Extension

Experiences with the standardized classification of surgical complications (Clavien-Dindo) in general surgery patients

Predicting and Preventing Postoperative Outcomes

Contact Info

Product

Resources

About