Predicting major adverse cardiovascular events after orthotopic liver transplantation using a supervised machine learning model:A cohort study

BACKGROUND Liver transplant(LT)patients have become older and sicker.The rate of post-LT major adverse cardiovascular events(MACE)has increased,and this in turn raises 30-d post-LT mortality.Noninvasive cardiac stress testing loses accuracy when applied to pre-LT cirrhotic patients.AIM To assess the feasibility and accuracy of a machine learning model used to predict post-LT MACE in a regional cohort.METHODS This retrospective cohort study involved 575 LT patients from a Southern Brazilian academic center.We developed a predictive model for post-LT MACE(defined as a composite outcome of stroke,new-onset heart failure,severe arrhythmia,and myocardial infarction)using the extreme gradient boosting(XGBoost)machine learning model.We addressed missing data(below 20%)for relevant variables using the k-nearest neighbor imputation method,calculating the mean from the ten nearest neighbors for each case.The modeling dataset included 83 features,encompassing patient and laboratory data,cirrhosis complications,and pre-LT cardiac assessments.Model performance was assessed using the area under the receiver operating characteristic curve(AUROC).We also employed Shapley additive explanations(SHAP)to interpret feature impacts.The dataset was split into training(75%)and testing(25%)sets.Calibration was evaluated using the Brier score.We followed Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis guidelines for reporting.Scikit-learn and SHAP in Python 3 were used for all analyses.The supplementary material includes code for model development and a user-friendly online MACE prediction calculator.RESULTS Of the 537 included patients,23(4.46%)developed in-hospital MACE,with a mean age at transplantation of 52.9 years.The majority,66.1%,were male.The XGBoost model achieved an impressive AUROC of 0.89 during the training stage.This model exhibited accuracy,precision,recall,and F1-score values of 0.84,0.85,0.80,and 0.79,respectively.Calibration,as assessed by the Brier score,indicated excellent model calibration with a score of 0.07.Furthermore,SHAP values highlighted the significance of certain variables in predicting postoperative MACE,with negative noninvasive cardiac stress testing,use of nonselective beta-blockers,direct bilirubin levels,blood type O,and dynamic alterations on myocardial perfusion scintigraphy being the most influential factors at the cohort-wide level.These results highlight the predictive capability of our XGBoost model in assessing the risk of post-LT MACE,making it a valuable tool for clinical practice.CONCLUSION Our study successfully assessed the feasibility and accuracy of the XGBoost machine learning model in predicting post-LT MACE,using both cardiovascular and hepatic variables.The model demonstrated impressive performance,aligning with literature findings,and exhibited excellent calibration.Notably,our cautious approach to prevent overfitting and data leakage suggests the stability of results when applied to prospective data,reinforcing the model’s value as a reliable tool for predicting post-LT MACE in clinical practice.

Comprehensive analysis of sodium polystyrene sulfonate-induced colitis:A systematic review

BACKGROUND Sodium polystyrene sulfonate(SPS)is commonly prescribed for the management of hyperkalemia,a critical electrolyte imbalance contributing to over 800000 annual visits to emergency departments.AIM To conduct a systematic review of documented cases of SPS-induced colitis and assess its associated prognosis.METHODS Following the PRISMA-P guidelines,our study employed Medical Subject Headings and Health Sciences Descriptors,skillfully combined using Boolean operators,to conduct comprehensive searches across various electronic databases,including Scopus,Web of Science,MEDLINE(PubMed),BIREME(Biblioteca Regional de Medicina),LILACS(Latin American and Caribbean Health Sciences Literature),SciELO(Scientific Electronic Library Online),Embase,and Opengray.eu.Language criteria were confined to English,Spanish,and Portuguese,with no limitations on the publication date.Additionally,we manually scrutinized the reference lists of retrieved studies.To present our findings,we utilized simple descriptive analysis.RESULTS Our search strategy yielded a total of 442 references.After rigorous evaluation,we included 51 references,encompassing 59 documented cases of colitis.Predominant clinical presentations included abdominal pain,observed in 35(60.3%)cases,and bloating,reported in 18(31%)cases.The most frequently affected sites of inflammation were the cecum,rectum,and small intestine,accounting for 31%,25.8%,and 22.4%of cases,respectively.Colonoscopy findings were described in 28(48.2%)cases,and 29(50%)of patients required surgical intervention.Among the subset of patients for whom outcome data was available,39(67.2%)experienced favorable outcomes,while 12(20.6%)unfortunately succumbed to the condition.The mean time required for resolution was 36.7 d,with a range spanning from 1 to 120 d.CONCLUSION SPS demonstrates the capacity to effectively lower serum potassium levels within 24 h.However,this benefit is not without the risk of bowel injury.Our study highlights the absence of high-quality data pertaining to the incidence of adverse events associated with SPS usage,making it challenging to determine whether the potential risks outweigh the benefits.However,a significant mortality rate related to SPS-induced colitis was noted.Future investigations should prioritize randomized controlled trials with a sufficiently large patient cohort to ascertain the true utility and safety profile of this medication.

Post-COVID-19 cholangiopathy:Systematic review

BACKGROUND The coronavirus disease 2019(COVID-19)pandemic has had a profound impact on global health,primarily characterized by severe respiratory illness.However,emerging evidence suggests that COVID-19 can also lead to secondary sclerosing cholangitis(SC),referred to as post-COVID-19 cholangiopathy.AIM To synthesize currently reported cases to assess the current state of knowledge on post-COVID-19 cholangiopathy.METHODS Medical Subject Headings and Health Sciences Descriptors were used to retrieve relevant studies,which were combined using Boolean operators.Searches were conducted on electronic databases including Scopus,Web of Science,and MEDLINE(PubMed).Studies published in English,Spanish,or Portuguese were included,with no restrictions on the publication date.Additionally,the reference lists of retrieved studies were manually searched.Simple descriptive analyses were used to summarize the results.Then the data were extracted and assessed based on Reference Citation Analysis(https://www.referencecitationanalysis.com/).RESULTS The initial search yielded a total of 192 articles.After screening,85 articles were excluded due to duplication,leaving 107 articles for further review.Of these,63 full-length articles met the inclusion criteria and were included in the analyses.Most of the patients were male and exhibited elevated liver function tests(93.8%).Magnetic resonance imaging revealed duct thickening with contrast enhancement(47.7%),as well as beading of the intrahepatic ducts(45.7%)with peribiliary contrast enhancement on diffusion(28.7%).Liver biopsy results confirmed SC in most cases(74.4%).Sixteen patients underwent liver transplantation,with three CONCLUSION Post-COVID-19 cholangiopathy is a serious condition that is expected to become increasingly concerning in the coming years,particularly considering long COVID syndromes.Although liver transplantation has been proposed as a potential treatment option,more research is necessary to establish its efficacy and explore other potential treatments.

Herb-induced liver injury: Systematic review and meta-analysis

BACKGROUND The use of herbal supplements and alternative medicines has been increasing in the last decades.Despite popular belief that the consumption of natural products is harmless,herbs might cause injury to various organs,particularly to the liver,which is responsible for their metabolism in the form of herb-induced liver injury(HILI).AIM To identify herbal products associated with HILI and describe the type of lesion associated with each product.METHODS Studies were retrieved using Medical Subject Headings Descriptors combined with Boolean operators.Searches were run on the electronic databases Scopus,Web of Science,MEDLINE,BIREME,LILACS,Cochrane Library for Systematic Reviews,SciELO,Embase,and Opengray.eu.Languages were restricted to English,Spanish,and Portuguese.There was no date of publication restrictions.The reference lists of the studies retrieved were searched manually.To access causality,the Maria and Victorino System of Causality Assessment in Drug Induced Liver Injury was used.Simple descriptive analysis were used to summarize the results.RESULTS The search strategy retrieved 5918 references.In the final analysis,446 references were included,with a total of 936 cases reported.We found 79 types of herbs or herbal compounds related to HILI.He-Shou-Wu,Green tea extract,Herbalife,kava kava,Greater celandine,multiple herbs,germander,hydroxycut,skullcap,kratom,Gynura segetum,garcinia cambogia,ma huang,chaparral,senna,and aloe vera were the most common supplements with HILI reported.Most of these patients had complete clinical recovery(82.8%).However,liver transplantation was necessary for 6.6%of these cases.Also,chronic liver disease and death were observed in 1.5%and 10.4%of the cases,respectively.CONCLUSION HILI is normally associated with a good prognosis,once the implied product is withdrawn.Nevertheless,it is paramount to raise awareness in the medical and non-medical community of the risks of the indiscriminate use of herbal products.

Primary sclerosing cholangitis and autoimmune hepatitis overlap syndrome associated with inflammatory bowel disease:A case report and systematic review

BACKGROUND A previously healthy 22-year-old woman presented with abdominal pain and jaundice.She had a reagent antinuclear factor(1:640,with a homogeneous nuclear pattern)and hypergammaglobulinemia(2.16 g/dL).Anti-smooth muscle,antimitochondrial and anti-liver-kidney microsomal antibody type 1 antibodies were negative.Magnetic resonance cholangiography showed a cirrhotic liver with multiple focal areas of strictures of the intrahepatic bile ducts,with associated dilations.Liver biopsy demonstrated periportal necroinflammatory activity,plasmocyte infiltration and advanced fibrosis.Colonoscopy showed ulcerative pancolitis and mild activity(Mayo score 1),with a spared rectum.Treatment with corticosteroids,azathioprine,ursodeoxycholic acid and mesalamine was initiated,with improvement in laboratory tests.The patient was referred for a liver transplantation evaluation.AIM To report the case of a female patient with autoimmune hepatitis and primary sclerosing cholangitis(PSC)overlap syndrome associated with ulcerative colitis and to systematically review the available cases of autoimmune hepatitis and PSC overlap syndrome.METHODS In accordance with preferred reporting items for systematic reviews and metaanalysis protocols guidelines,retrieval of studies was based on medical subject headings and health sciences descriptors,which were combined using Boolean operators.Searches were run on the electronic databases Scopus,Web of Science,MEDLINE(PubMed),Biblioteca Regional de Medicina,Latin American and Caribbean Health Sciences Literature,Cochrane Library for Systematic Reviews and Opengray.eu.Languages were restricted to English,Spanish and Portuguese.There was no date of publication restrictions.The reference lists of the studies retrieved were searched manually.RESULTS The search strategy retrieved 3349 references.In the final analysis,44 references were included,with a total of 109 cases reported.The most common clinical finding was jaundice and 43.5%of cases were associated with inflammatory bowel disease.Of these,27.6%were cases of Crohn’s disease,68%of ulcerative colitis,and 6.4%of indeterminate colitis.Most patients were treated with steroids.All-cause mortality was 3.7%.CONCLUSION PSC and autoimmune hepatitis overlap syndrome is generally associated with inflammatory bowel disease and has low mortality and good response to treatment.

Deep learning applied to the imaging diagnosis of hepatocellular carcinoma

Each year,hepatocellular carcinoma is diagnosed in more than half a million people worldwide.It is the fifth most common cancer in men and the seventh most common cancer in women.Its diagnosis is currently made using imaging techniques,such as computed tomography and magnetic resonance imaging.For most cirrhotic patients,these methods are enough for diagnosis,foregoing the necessity of a liver biopsy.In order to improve outcomes and bypass obstacles,many companies and clinical centers have been trying to develop deep learning systems that could be able to diagnose and classify liver nodules in the cirrhotic liver,in which the neural networks are one of the most efficient approaches to accurately diagnose liver nodules.Despite the advances in deep learning systems for the diagnosis of imaging techniques,there are many issues that need better development in order to make such technologies more useful in daily practice.