Postoperative bleeding risk prediction for patients undergoing colorectal surgery

Chen, David; Afzal, Naveed; Sohn, Sunghwan; Habermann, Elizabeth B.; Naessens, James M.; Larson, David W.; Liu, Hongfang

doi:10.1016/j.surg.2018.05.043

Cited by 33 publications

(35 citation statements)

References 41 publications

(42 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We review several limitations of deep learning tools illustrated with specific examples from prior work: prediction of postoperative bleeding following colorectal surgery (CRS-POB), 20 prediction of childhood asthma diagnosis, remission, and reoccurance (A-DRR), 21 prediction of time to first treatment for patients diagnosed with chronic lymphocytic leukemia (CLL-TFT), 22 prediction of ICU mortality (ICU-M) using a publically available dataset, 21,23 and finally prediction of opioid mis-use (Opioid). 24 Each study was approved by Mayo Clinic’s Institutional Review Board.…”

Section: Introductionmentioning

confidence: 99%

Deep learning and alternative learning strategies for retrospective real-world clinical data

et al. 2019

Self Cite

View full text Add to dashboard Cite

In recent years, there is increasing enthusiasm in the healthcare research community for artificial intelligence to provide big data analytics and augment decision making. One of the prime reasons for this is the enormous impact of deep learning for utilization of complex healthcare big data. Although deep learning is a powerful analytic tool for the complex data contained in electronic health records (EHRs), there are also limitations which can make the choice of deep learning inferior in some healthcare applications. In this paper, we give a brief overview of the limitations of deep learning illustrated through case studies done over the years aiming to promote the consideration of alternative analytic strategies for healthcare.

show abstract

Section: Introductionmentioning

confidence: 99%

Deep learning and alternative learning strategies for retrospective real-world clinical data

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…22e24 The remaining articles were either regarding gastrectomy 25 or liver surgery. 26 The outcomes of the articles describing colorectal surgery were anastomotic leakage, 13 surgical site infection, 14,16 postoperative bleeding, 15 a combination of surgical site infection, bleeding, and ileus, 18 or any postoperative complication. 17 The outcomes of the articles describing bariatric surgery were anastomotic leakage and venous thromboembolism, 20 morbidity and mortality, 21 or any severe postoperative complication.…”

Section: Resultsmentioning

confidence: 99%

The prediction of surgical complications using artificial intelligence in patients undergoing major abdominal surgery: A systematic review

Stam

Goedknegt

Ingwersen

et al. 2022

Surgery

View full text Add to dashboard Cite

“…The lack of sufficient protein affects the wound healing pathway, increasing f wound infection rates and wound dehiscence (9,32). In addition, because of the decreased production of coagulation factors, malnutrition leads to poor hemostasis and a markedly increased probability of postoperative bleeding (31). Impaired nutrition affects many immune system domains, including the complement system, opsonization, and white blood cell function, leading to increased nosocomial infections postoperatively (29,33).…”

Section: Discussionmentioning

confidence: 99%

Malnutrition as a risk factor of adverse postoperative outcomes in patients undergoing hepatic resection: analysis of US hospitals

et al. 2021

View full text Add to dashboard Cite

In patients with liver cancer or space-occupying cysts, they suffer from malnutrition due to compression of gastric and digestive structures, liver and cancer-mediated dysmetabolism, and impaired nutrient absorption. As proportion of these patients require removal of lesions through hepatic resection, it is important to evaluate the effects of malnutrition on post-hepatectomy outcomes. In our study approach, 2011-2017 National Inpatient Sample was used to isolate in-hospital hepatectomy cases, which were stratified using malnutrition (composite of malnutrition, sarcopenia, and weight loss/cachexia). The malnutrition-absent controls were matched to cases using nearest neighbor propensity score match method and compared to following endpoints: mortality, length of stay, hospitalization costs, and postoperative complications. There were 2531 patients in total who underwent hepatectomy with matched number of controls from the database; following the match, malnutrition cohort (compared to controls) were more likely to experience in-hospital death (6.60% vs 5.25% p<0.049, OR 1.27 95%CI 1.01-1.61), and were more likely to have higher length of stay (18.10d vs 9.32d p<0.001) and hospitalization costs ($278,780 vs $150,812 p<0.001). In terms of postoperative complications, malnutrition cohort was more likely to experience bleeding (6.52% vs 3.87% p<0.001 OR 1.73 95%CI1.34-2.24), infection (6.64% vs 2.49% p<0.001, OR 2.79 95%CI 2.07-3.74), wound complications (4.5% vs 1.38% p<0.001, OR 3.36 95%CI 2.29-4.93), and respiratory failure (9.40% vs 4.11% p<0.001 OR 2.42 95%CI 1.91-3.07). In multivariate, malnutrition was associated with higher mortality (p<0.028, aOR 1.3 95%CI 1.03-1.65). Thus, we conclude that malnutrition is an independent risk factor of postoperative mortality in patients undergoing hepatectomy.

show abstract

Postoperative bleeding risk prediction for patients undergoing colorectal surgery

Abstract: The study identified measures of functional capacity of patient as novel predictors of postoperative bleeding. The study found that risk of postoperative bleeding can be assessed, allowing for better use of human resources in addressing this important adverse event after surgery.

Cited by 33 publications

References 41 publications

Deep learning and alternative learning strategies for retrospective real-world clinical data

Deep learning and alternative learning strategies for retrospective real-world clinical data

The prediction of surgical complications using artificial intelligence in patients undergoing major abdominal surgery: A systematic review

Malnutrition as a risk factor of adverse postoperative outcomes in patients undergoing hepatic resection: analysis of US hospitals

Contact Info

Product

Resources

About