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.

Role of fecal microbiota transplant in management of hepatic encephalopathy: Current trends and future directions

Fecal microbiota transplantation(FMT)offers a potential treatment avenue for hepatic encephalopathy(HE)by leveraging beneficial bacterial displacement to restore a balanced gut microbiome.The prevalence of HE varies with liver disease severity and comorbidities.HE pathogenesis involves ammonia toxicity,gut-brain communication disruption,and inflammation.FMT aims to restore gut microbiota balance,addressing these factors.FMT's efficacy has been explored in various conditions,including HE.Studies suggest that FMT can modulate gut microbiota,reduce ammonia levels,and alleviate inflammation.FMT has shown promise in alcohol-associated,hepatitis B and C-associated,and non-alcoholic fatty liver disease.Benefits include improved liver function,cognitive function,and the slowing of disease progression.However,larger,controlled studies are needed to validate its effectiveness in these contexts.Studies have shown cognitive improvements through FMT,with potential benefits in cirrhotic patients.Notably,trials have demonstrated reduced serious adverse events and cognitive enhancements in FMT arms compared to the standard of care.Although evidence is promising,challenges remain:Limited patient numbers,varied dosages,administration routes,and donor profiles.Further large-scale,controlled trials are essential to establish standardized guidelines and ensure FMT's clinical applications and efficacy.While FMT holds potential for HE management,ongoing research is needed to address these challenges,optimize protocols,and expand its availability as a therapeutic option for diverse hepatic conditions.

Impact of metabolic dysfunction-associated steatotic liver disease on COVID-19 hospitalizations:A propensity-matched analysis of the United States

BACKGROUND Metabolic dysfunction-associated steatotic liver disease(MASLD),formally known as nonalcoholic fatty liver disease,is the most common chronic liver disease in the United States.Patients with MASLD have been reported to be at a higher risk of developing severe coronavirus disease 2019(COVID-19)and death.However,most studies are single-center studies,and nationwide data in the AIM To study the influence of MASLD on COVID-19 hospitalizations during the initial phase of the pandemic.METHODS We retrospectively analyzed the 2020 National Inpatient Sample(NIS)database to identify primary COVID-19 hospitalizations based on an underlying diagnosis of MASLD.A matched comparison cohort of COVID-19 hospit-alizations without MASLD was identified from NIS after 1:N propensity score matching based on gender,race,and comorbidities,including hypertension,heart failure,diabetes,and cirrhosis.The primary outcomes included inpatient mortality,length of stay,and hospitalization costs.Secondary outcomes included the prevalence of systemic complications.RESULTS A total of 2210 hospitalizations with MASLD were matched to 2210 hospitalizations without MASLD,with a good comorbidity balance.Overall,there was a higher prevalence of severe disease with more intensive care unit admissions(9.5%vs 7.2%,P=0.007),mechanical ventilation(7.2%vs 5.7%,P=0.03),and septic shock(5.2%vs 2.7%,P<0.001)in the MASLD cohort than in the non-MASLD cohort.However,there was no difference in mortality(8.6%vs 10%,P=0.49),length of stay(5 d vs 5 d,P=0.25),and hospitalization costs(42081.5$vs 38614$,P=0.15)between the MASLD and non-MASLD cohorts.CONCLUSION The presence of MAFLD with or without liver cirrhosis was not associated with increased mortality in COVID-19 hospitalizations;however,there was an increased incidence of severe COVID-19 infection.This data(2020)predates the availability of COVID-19 vaccines,and many MASLD patients have since been vaccinated.It will be interesting to see if these trends are present in the subsequent years of the 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.