Dataset Information

Postoperative bleeding risk prediction for patients undergoing colorectal surgery.

ABSTRACT: BACKGROUND:There is limited consensus regarding risk factors for postoperative bleeding. The objective of this work was to investigate the capability of machine learning techniques in combination with practice-based longitudinal electronic medical record data for identifying potential new risk factors for postoperative bleeding and predicting patients at high risk of postoperative bleeding. METHODS:A retrospective study was conducted for patients who underwent colorectal surgery 1998-2015 at a single tertiary referral center. Various predictors were extracted from electronic medical record. The outcome of interest was the occurrence of postoperative bleeding within 7 days of surgery. Logistic regression and gradient boosting machine models were trained. Area under the receiver operating curve and area under the precision recall curve were used to evaluate the performance to different models. RESULTS:Of 13,399 cases undergoing colorectal resection, 1,680 (12.5%) experienced postoperative bleeding. A total of 299 variables were evaluated. Logistic regression and gradient boosting machine models returned an area under the receiver operating curve of 0.735 and 0.822 and area under the precision recall curve of 0.287 and 0.423, respectively. In addition to well-known risk factors for postoperative bleeding, nutrition (ranked third), weakness (ranked fifth), patient mobility (ranked sixth), and activity level (ranked eighth) were found to be novel predictors in the gradient boosting machine model based on permutation importance. CONCLUSION: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.

SUBMITTER: Chen D

PROVIDER: S-EPMC6263850 | biostudies-literature | 2018 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Postoperative bleeding risk prediction for patients undergoing colorectal surgery.

Chen David D Afzal Naveed N Sohn Sunghwan S Habermann Elizabeth B EB Naessens James M JM Larson David W DW Liu Hongfang H

Surgery 20180720 6

<h4>Background</h4>There is limited consensus regarding risk factors for postoperative bleeding. The objective of this work was to investigate the capability of machine learning techniques in combination with practice-based longitudinal electronic medical record data for identifying potential new risk factors for postoperative bleeding and predicting patients at high risk of postoperative bleeding.<h4>Methods</h4>A retrospective study was conducted for patients who underwent colorectal surgery 1 ...[more]

PMID: 30033185

Similar Datasets

Project description:BackgroundCardiovascular surgeries often require deep hypothermic circulatory arrest and cardiopulmonary bypass (CPB), which can disrupt blood clotting and lead to excessive bleeding. Traditional treatments involve transfusing blood and blood products, which can have adverse effects and place significant strain on the global blood supply. Research suggests that autologous platelet-rich plasmapheresis (aPRP) may reduce the need for transfusions by preserving blood components. However, the impact of aPRP on postoperative blood loss and clinical outcomes in cardiovascular surgery remains controversial. This study aimed to examine the effects of aPRP on postoperative blood loss and recovery in patients undergoing heart valve surgery.MethodsA total of 183 patients were divided into either aPRP or control groups. The aPRP group received aPRP before CPB, whereas the control group did not. The primary endpoint was postoperative bleeding between the groups. The secondary endpoints were postoperative bleeding risk factors and clinical outcome assessment. Logistic regression analysis with covariate adjustment was used to calculate these risk factors.ResultsA total of 76 patients (41.5%) in the aPRP group and 107 patients (58.5%) in the control group were included in the analysis. No significant difference was found in the occurrence of postoperative bleeding [odds ratio (OR) =0.53, 95% confidence interval (CI): 0.28-1.00, P=0.05], and the aPRP group had fewer complications than the controls (OR =0.28, 95% CI: 0.10-0.68, P=0.009). However, after adjusting for the New York Heart Association (NYHA) classification, diabetes, arrhythmology, mean activated clotting time (ACTmean), CPB, bleeding, thoracotomy, and body mass index (BMI), there was a significant difference in postoperative bleeding (adjusted OR =0.47, 95% CI: 0.22-0.98, P=0.04) and complications (adjusted OR =0.23, 95% CI: 0.07-0.64, P=0.008) between the two groups.ConclusionsPreoperative aPRP can improve postoperative outcomes and reduce complications in patients undergoing heart valve surgery.

Project description:BackgroundAntithrombotic drugs increase the risk of bleeding, especially in patients who need urgent surgery without an adequate wash-out period. This review aims to evaluate perioperative bleeding complications in patients on dual antiplatelet therapy (DAPT) or direct-acting oral anticoagulants (DOACs) undergoing high-bleeding risk cardiovascular surgery and to present currently available potential solutions to mitigate antithrombotic therapy-related bleeding complications.MethodsAs a first step, we searched for relevant articles, over the last 10 years, in Medline (PubMed) and abstracted clinical information based on pre-defined criteria for bleeding complications. In the next step, an additional search evaluating potential solutions to mitigate bleeding complications was performed. The literature screening and selection process followed the principles derived from the PRISMA statement.ResultsFrom all reviewed studies, a total of 19 articles could be included evaluating the risk for bleeding in cardiac surgery related to DAPT or DOACs and 10 papers evaluating antithrombotic drug reversal or removal in the setting of cardiovascular surgery. Reported bleeding rates ranged between 18% and 41%. The variability of the reported data is remarkable. Idarucizumab is reported to provide optimal perioperative hemostasis in up to 93% of patients. It has been observed that andexanet alfa causes unresponsiveness to the anticoagulant effects of heparin. Antithrombotic removal by intraoperative hemoadsorption is found to be associated with a significant decrease in re-thoracotomy rate, overall procedure duration, administered transfusion volumes, chest-tube drainage, and length of hospitalization.DiscussionBleeding complications in patients treated with DAPT or DOACs in cardiac surgery are high. New costly reversal agents are available but have not been sufficiently tested in the cardio-surgical setting so far. Interestingly, bleeding-related complications seem to be effectively reduced by applying innovative intraoperative hemoadsorption techniques. Expected results from the ongoing trials should provide better insights concerning the efficacy and safety of several potential solutions. Currently, the variability of reports and the deficit of high-quality studies in this specific setting represent the major limitation for the unbiased conclusion of this review.

Project description:BackgroundThe risk of postoperative cognitive dysfunction(POCD) in laparoscopic surgery should not be overlooked. Intravenous lidocaine can reduce perioperative inflammatory response in patients undergoing laparoscopic surgery, while the effect of intraoperative intravenous lidocaine on postoperative cognitive function in patients undergoing laparoscopic colorectal cancer surgery has not been well studied. We investigated whether intraoperative lidocaine improves postoperative cognitive function after laparoscopic radical resection for colorectal cancer.MethodsWe conducted a prospective, randomized double blinded controlled trial to investigate the effect of intravenous lidocaine on rapid postoperative recovery in patients undergoing laparoscopic radical resection of colorectal cancer. The patients were randomly assigned to receive either intravenous lidocaine or saline. The primary outcome was cognitive dysfunction defined by a decrease from pre- to postoperative ≥ 2 of the Mini-Mental State Examination (MMSE) score, at the 3rd and the 7th postoperative days. Secondary outcomes were the MMSE raw score and parameters of the patients' postoperative recovery such as agitation and length of stay in the post-anaesthesia care unit (PACU), length of hospital stay, markers of inflammation (white blood cell count and CRP), and incidence of complications.ResultsSeventy-three patients in the lidocaine group and 77 patients in the control group completed the trial. The rate of cognitive dysfunction was lower in the lidocaine group than that in the control group, both at the 3rd (18.57% vs. 63.64% for each group respectively; RR = 0.26, 95%CI = 0.19-0.32; p < 0.0001) and at the 7th postoperative day (12.33% vs. 53.25% for each group respectively; RR = 0.28, 95%CI = 0.22-0.35; P < 0.001). The postoperative MMSE scores were also higher in the lidocaine group than in the control group both at the 3rd (median 25 vs. 24 respectively) and at the 7th postoperative day (26 vs. 24 respectively). Also, patients in the lidocaine group displayed a lower white blood cell count than the control group at the 1st postoperative day (8.5 ± 2.7 vs. 10.4 ± 3.3; p < 0. 001). No differences were evidenced for the other secondary outcomes.ConclusionsIntraoperative intravenous lidocaine can significantly improve postoperative cognitive function in patients undergoing laparoscopic radical resection of colorectal cancer.Trial registrationChinese Clinical Trial Registry (16/1/2022, registration number: ChiCTR2200055683).

Project description:Oxidative stress plays an important role in the development of colorectal cancer (CRC). This study is aimed at developing and validating a novel scoring system, based on oxidative stress indexes, for prognostic prediction in CRC patients. A retrospective analysis of 1422 CRC patients who underwent surgical resection between January 2013 and December 2017 was performed. These patients were randomly assigned to the training set (n = 1022) or the validation set (n = 400). Cox regression model was used to analyze the laboratory parameters. The CRC-Integrated Oxidative Stress Score (CIOSS) was developed from albumin (ALB), direct bilirubin (DBIL), and blood urea nitrogen (BUN), which were significantly associated with survival in CRC patients. Furthermore, a survival nomogram was generated by combining the CIOSS with other beneficial clinical characteristics. The CIOSS generated was as follows: 0.074 × albumin (g/L), -0.094 × bilirubin (μmol/L), and -0.099 × blood urea nitrogen (mmol/L), based on the multivariable Cox regression analysis. Using 50% (0.1025) and 85% (0.481) of CIOSS as cutoff values, three prognostically distinct groups were formed. Patients with high CIOSS experienced worse overall survival (OS) (hazard ratio [HR] = 4.33; 95% confidence interval [CI], 2.80-6.68; P < 0.001) and worse disease-free survival (DFS) (HR = 3.02; 95% CI, 1.96-4.64; P < 0.001) compared to those with low CIOSS. This predictive nomogram had good calibration and discrimination. ROC analyses showed that the CIOSS possessed excellent performance (AUC = 0.818) in predicting DFS. The AUC of the OS nomogram based on CIOSS, TNM stage, T stage, and chemotherapy was 0.812, while that of the DFS nomogram based on CIOSS, T stage, and TNM stage was 0.855. Decision curve analysis showed that these two prediction models were clinically useful. CIOSS is a CRC-specific prognostic index based on the combination of available oxidative stress indexes. High CIOSS is a powerful indicator of poor prognosis. The CIOSS also showed better predictive performance compared to TNM stage in CRC patients.

Dataset Information

Postoperative bleeding risk prediction for patients undergoing colorectal surgery.

Publications

Postoperative bleeding risk prediction for patients undergoing colorectal surgery.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets