Predicting short-term thromboembolic risk following Roux-en-Y gastric bypass using supervised machine learning

BACKGROUND Roux-en-Y gastric bypass(RYGB)is a widely recognized bariatric procedure that is particularly beneficial for patients with class III obesity.It aids in significant weight loss and improves obesity-related medical conditions.Despite its effectiveness,postoperative care still has challenges.Clinical evidence shows that venous thromboembolism(VTE)is a leading cause of 30-d morbidity and mortality after RYGB.Therefore,a clear unmet need exists for a tailored risk assessment tool for VTE in RYGB candidates.AIM To develop and internally validate a scoring system determining the individualized risk of 30-d VTE in patients undergoing RYGB.METHODS Using the 2016–2021 Metabolic and Bariatric Surgery Accreditation Quality Improvement Program,data from 6526 patients(body mass index≥40 kg/m^(2))who underwent RYGB were analyzed.A backward elimination multivariate analysis identified predictors of VTE characterized by pulmonary embolism and/or deep venous thrombosis within 30 d of RYGB.The resultant risk scores were derived from the coefficients of statistically significant variables.The performance of the model was evaluated using receiver operating curves through 5-fold cross-validation.RESULTS Of the 26 initial variables,six predictors were identified.These included a history of chronic obstructive pulmonary disease with a regression coefficient(Coef)of 2.54(P<0.001),length of stay(Coef 0.08,P<0.001),prior deep venous thrombosis(Coef 1.61,P<0.001),hemoglobin A1c>7%(Coef 1.19,P<0.001),venous stasis history(Coef 1.43,P<0.001),and preoperative anticoagulation use(Coef 1.24,P<0.001).These variables were weighted according to their regression coefficients in an algorithm that was generated for the model predicting 30-d VTE risk post-RYGB.The risk model's area under the curve(AUC)was 0.79[95%confidence interval(CI):0.63-0.81],showing good discriminatory power,achieving a sensitivity of 0.60 and a specificity of 0.91.Without training,the same model performed satisfactorily in patients with laparoscopic sleeve gastrectomy with an AUC of 0.63(95%CI:0.62-0.64)and endoscopic sleeve gastroplasty with an AUC of 0.76(95%CI:0.75-0.78).CONCLUSION This simple risk model uses only six variables to assist clinicians in the preoperative risk stratification of RYGB patients,offering insights into factors that heighten the risk of VTE events.

Impact of COVID-19 on liver transplant recipients: A nationwide cohort study evaluating hospitalization, transplant rejection, and inpatient mortality

BACKGROUND The coronavirus disease 2019(COVID-19)pandemic has posed a major public health concern worldwide.Patients with comorbid conditions are at risk of adverse outcomes following COVID-19.Solid organ transplant recipients with concurrent immunosuppression and comorbidities are more susceptible to a severe COVID-19 infection.It could lead to higher rates of inpatient complications and mortality in this patient population.However,studies on COVID-19 outcomes in liver transplant(LT)recipients have yielded inconsistent findings.AIM To evaluate the impact of the COVID-19 pandemic on hospital-related outcomes among LT recipients in the United States.METHODS We conducted a retrospective cohort study using the 2019–2020 National Inpatient Sample database.Patients with primary LT hospitalizations and a secondary COVID-19 diagnosis were identified using the International Classi-fication of Diseases,Tenth Revision coding system.The primary outcomes included trends in LT hospitalizations before and during the COVID-19 pandemic.Secondary outcomes included comparative trends in inpatient mortality and transplant rejection in LT recipients.RESULTS A total of 15720 hospitalized LT recipients were included.Approximately 0.8%of patients had a secondary diagnosis of COVID-19 infection.In both cohorts,the median admission age was 57 years.The linear trends for LT hospitalizations did not differ significantly before and during the pandemic(P=0.84).The frequency of in-hospital mortality for LT recipients increased from 1.7%to 4.4%between January 2019 and December 2020.Compared to the pre-pandemic period,a higher association was noted between LT recipients and in-hospital mortality during the pandemic,with an odds ratio(OR)of 1.69[95%confidence interval(CI):1.55-1.84),P<0.001].The frequency of transplant rejections among hospitalized LT recipients increased from 0.2%to 3.6%between January 2019 and December 2020.LT hospitalizations during the COVID-19 pandemic had a higher association with transplant rejection than before the pandemic[OR:1.53(95%CI:1.26-1.85),P<0.001].CONCLUSION The hospitalization rates for LT recipients were comparable before and during the pandemic.Inpatient mortality and transplant rejection rates for hospitalized LT recipients were increased during the COVID-19 pandemic.

Association between acute peripancreatic fluid collections and early readmission in acute pancreatitis:A propensity-matched analysis

BACKGROUND Patients with acute pancreatitis(AP)frequently experience hospital readmissions,posing a significant burden to healthcare systems.Acute peripancreatic fluid collection(APFC)may negatively impact the clinical course of AP.It could worsen symptoms and potentially lead to additional complications.However,clinical evidence regarding the specific association between APFC and early readmission in AP remains scarce.Understanding the link between APFC and readmission may help improve clinical care for AP patients and reduce healthcare costs.AIM To evaluate the association between APFC and 30-day readmission in patients with AP.METHODS This retrospective cohort study is based on the Nationwide Readmission Database for 2016-2019.Patients with a primary diagnosis of AP were identified.Participants were categorized into those with and without APFC.A 1:1 propensity score matching for age,gender,and Elixhauser comorbidities was performed.The primary outcome was early readmission rates.Secondary outcomes included the incidence of inpatient complications and healthcare utilization.Unadjusted analyses used Mann-Whitney U andχ2 tests,while Cox regression models assessed 30-day readmission risks and reported them as adjusted hazard ratios(aHR).Kaplan-Meier curves and log-rank tests verified readmission risks.RESULTS A total of 673059 patients with the principal diagnosis of AP were included.Of these,5.1%had APFC on initial admission.After propensity score matching,each cohort consisted of 33914 patients.Those with APFC showed a higher incidence of inpatient complications,including septic shock(3.1%vs 1.3%,P<0.001),portal venous thrombosis(4.4%vs 0.8%,P<0.001),and mechanical ventilation(1.8%vs 0.9%,P<0.001).The length of stay(LOS)was longer for APFC patients[4(3-7)vs 3(2-5)days,P<0.001],as were hospital charges($29451 vs$24418,P<0.001).For 30-day readmissions,APFC patients had a higher rate(15.7%vs 6.5%,P<0.001)and a longer median readmission LOS(4 vs 3 days,P<0.001).The APFC group also had higher readmission charges($28282 vs$22865,P<0.001).The presence of APFC increased the risk of readmission twofold(aHR 2.52,95%confidence interval:2.40-2.65,P<0.001).The independent risk factors for 30-day readmission included female gender,Elixhauser Comorbidity Index≥3,chronic pulmonary diseases,chronic renal disease,protein-calorie malnutrition,substance use disorder,depression,portal and splenic venous thrombosis,and certain endoscopic procedures.CONCLUSION Developing APFC during index hospitalization for AP is linked to higher readmission rates,more inpatient complications,longer LOS,and increased healthcare costs.Knowing predictors of readmission can help target high-risk patients,reducing healthcare burdens.