Predicting Short-term Survival after Liver Transplantation using Machine Learning

Background. High levels of IGF-1 have been reported in patients with initial poor function of the graft after liver transplantation (LT). Correlation with other clinical variables or early survival has not been extensively investigated.Aim. To evaluate the GH/IGF-1 profile as a function of liver recovery and patients’ early survival after LT.Methods. 30 transplanted patients (23 survivors and 7 nonsurvivors), were retrospectively enrolled in the study. GH and IGF-1 serum levels were assessed at baseline, graft reperfusion, and 1, 7, 15, 30 , 90, and 360 days after LT. Individual biochemical variables were also recorded.Results. After grafting, IGF-1 in blood linearly correlated with cholesterol(r=0.6, P=0.001). IGF-1 levels from day 15 after surgery were statistically higher in survivors as compared to nonsurvivors. ROC curves analysis identified an IGF-1 cut-off >90 μg/L, from day 15 after surgery, as a good predictor of survival (sensitivity 86%, specificity 95%, andP<0.001).Conclusions. After LT, GH levels correlate with the extent of cytolysis, while IGF-1 is an indicator of liver synthetic function recovery. IGF-1 levels >90 μg/L (day 15–30) seem to be an indicator of short-term survival.

Download Full-text

Lack of relationship between preoperative measures of the severity of cirrhosis and short-term survival after liver transplantation

Liver Transplantation and Surgery ◽

10.1002/lt.500030509 ◽

1997 ◽

Vol 3 (5) ◽

pp. 532-537 ◽

Cited By ~ 26

Author(s):

M Deschenes ◽

J P Villeneuve ◽

M Dagenais ◽

D Fenyves ◽

R Lapointe ◽

...

Keyword(s):

Liver Transplantation ◽

Short Term ◽

Term Survival ◽

Short Term Survival

Download Full-text

Absence of relationship between the severity of cirrhosis and short-term survival following liver transplantation Liver Unit, H�pital Saint-Luc, Universit� de Montr�al, Montr�al, Canada

Hepatology ◽

10.1016/0270-9139(95)94289-0 ◽

1995 ◽

Vol 22 (4) ◽

pp. A141

Keyword(s):

Liver Transplantation ◽

Short Term ◽

Term Survival ◽

Liver Unit ◽

Short Term Survival

Download Full-text

Predicting Short-Term Survival after Gross Total or Near Total Resection in Glioblastomas by Machine Learning-Based Radiomic Analysis of Preoperative MRI

Cancers ◽

10.3390/cancers13205047 ◽

2021 ◽

Vol 13 (20) ◽

pp. 5047

Author(s):

Santiago Cepeda ◽

Angel Pérez-Nuñez ◽

Sergio García-García ◽

Daniel García-Pérez ◽

Ignacio Arrese ◽

...

Keyword(s):

Machine Learning ◽

Test Data ◽

Tumor Resection ◽

Area Under The Curve ◽

Risk Groups ◽

Feature Reduction ◽

Short Term ◽

Data Set ◽

Term Survival ◽

Short Term Survival

Radiomics, in combination with artificial intelligence, has emerged as a powerful tool for the development of predictive models in neuro-oncology. Our study aims to find an answer to a clinically relevant question: is there a radiomic profile that can identify glioblastoma (GBM) patients with short-term survival after complete tumor resection? A retrospective study of GBM patients who underwent surgery was conducted in two institutions between January 2019 and January 2020, along with cases from public databases. Cases with gross total or near total tumor resection were included. Preoperative structural multiparametric magnetic resonance imaging (mpMRI) sequences were pre-processed, and a total of 15,720 radiomic features were extracted. After feature reduction, machine learning-based classifiers were used to predict early mortality (<6 months). Additionally, a survival analysis was performed using the random survival forest (RSF) algorithm. A total of 203 patients were enrolled in this study. In the classification task, the naive Bayes classifier obtained the best results in the test data set, with an area under the curve (AUC) of 0.769 and classification accuracy of 80%. The RSF model allowed the stratification of patients into low- and high-risk groups. In the test data set, this model obtained values of C-Index = 0.61, IBS = 0.123 and integrated AUC at six months of 0.761. In this study, we developed a reliable predictive model of short-term survival in GBM by applying open-source and user-friendly computational means. These new tools will assist clinicians in adapting our therapeutic approach considering individual patient characteristics.

Download Full-text

Predicting short-term survival after total resection in glioblastomas by machine learning-based radiomic analysis of preoperative MRI

10.21203/rs.3.rs-640526/v2 ◽

2021 ◽

Author(s):

Santiago Cepeda ◽

Angel Perez-Nuñez ◽

Sergio Garcia-Garcia ◽

Daniel Garcia-Perez ◽

Ignacio Arrese ◽

...

Keyword(s):

Artificial Intelligence ◽

Machine Learning ◽

Predictive Models ◽

Tumor Resection ◽

Short Term ◽

Total Resection ◽

Complete Tumor Resection ◽

Term Survival ◽

Complete Tumor ◽

Short Term Survival

Abstract Background Radiomics, in combination with artificial intelligence, has emerged as a powerful tool for the development of predictive models in neuro-oncology. Our study aims to find an answer to a clinically relevant question: is there a radiomic profile that can identify glioblastoma (GBM) patients with short-term survival after complete tumor resection?

Download Full-text

Non-selective beta blocker use is associated with improved short-term survival in patients with cirrhosis referred for liver transplantation

BMC Gastroenterology ◽

10.1186/s12876-019-1155-1 ◽

2020 ◽

Vol 20 (1) ◽

Cited By ~ 2

Author(s):

Taiwo Ngwa ◽

Eric Orman ◽

Eduardo Vilar Gomez ◽

Raj Vuppalanchi ◽

Chandrashekhar Kubal ◽

...

Keyword(s):

Liver Transplantation ◽

Beta Blockers ◽

Kidney Injury ◽

Refractory Ascites ◽

Short Term ◽

Term Survival ◽

Bacterial Peritonitis ◽

Stage 1 ◽

Short Term Survival

Abstract Background Recent evidence cautions against the use of non-selective beta-blockers (NSBB) in patients with refractory ascites or spontaneous bacterial peritonitis while other data suggests a survival benefit in patients with advanced liver disease. The aim of this study was to describe the use and impact of NSBB in patients with cirrhosis referred for liver transplantation. Methods A single-center cohort of patients with cirrhosis, who were referred and evaluated for liver transplantation between January and June 2012 were studied for baseline characteristics and clinical outcomes. Patients were grouped according to the use of NSBB at initial evaluation, with the endpoint of 90-day mortality. Results Sixty-five (38%) of 170 consecutive patients evaluated for liver transplantation were taking NSBB. Patients taking NSBB had higher MELD and Child Pugh score. NSBB use was associated with lower 90-day mortality (6% vs. 15%) with a risk adjusted hazard ratio of 0.27 (95%CI .09–0.88, p = .03). Patients taking NSBB developed acute kidney injury (AKI) within 90 days more frequently than patients not taking NSBB (22% vs 11%), p = 0.048). However, this was related to increased stage 1 AKI episodes, all of which resolved. Twelve (27%) of 45 patients with > 90 day follow up discontinued NSBB, most commonly for hypotension and AKI, had increased subsequent MELD and mortality. Conclusions NSBB use in patients with cirrhosis undergoing liver transplant evaluation is associated with better short-term survival. Nevertheless, ongoing tolerance of NSBB in this population is dynamic and may select a subset of patients with better hemodynamic reserve.

Download Full-text

Sa1649 Non-Selective Beta Blocker Use is Associated With Improved Short-term Survival in Patients Referred for Liver Transplantation

Gastroenterology ◽

10.1016/s0016-5085(16)33663-0 ◽

2016 ◽

Vol 150 (4) ◽

pp. S1085-S1086

Author(s):

Taiwo N. Ngwa ◽

Eric Orman ◽

Raj Vuppalanchi ◽

Paul Y. Kwo ◽

Naga P. Chalasani ◽

...

Keyword(s):

Liver Transplantation ◽

Beta Blocker ◽

Short Term ◽

Term Survival ◽

Short Term Survival

Download Full-text

Factors determining short-term survival after adult liver transplantation

Journal of Hepatology ◽

10.1016/s0168-8278(02)80658-4 ◽

2002 ◽

Vol 36 ◽

pp. 186

Author(s):

Rahul Deshpande ◽

Mohamed Rela ◽

Julia Wendon

Keyword(s):

Liver Transplantation ◽

Adult Liver ◽

Short Term ◽

Term Survival ◽

Short Term Survival

Download Full-text

Alcoholic Hepatitis and Liver Transplantation

Journal of Renal and Hepatic Disorders ◽

10.15586/jrenhep.2017.8 ◽

2017 ◽

Vol 1 (1) ◽

pp. 3-4

Author(s):

Gianni Testino ◽

Silvia Leone

Keyword(s):

Liver Transplantation ◽

Liver Disease ◽

Alcoholic Liver Disease ◽

Alcoholic Hepatitis ◽

Short Term ◽

Term Survival ◽

Alcohol Relapse ◽

Severe Alcoholic Hepatitis ◽

Long Time ◽

Short Term Survival

Some authors affirm that early liver transplant (LT) provides excellent short-term survival in patients with severe alcoholic hepatitis (SAH) (1–4) and similar rates of alcohol relapse compared to patients with 6 months of abstinence. We agree with the choice of not excluding patients who manifest their decompensation with bleeding and infections (common complications of SAH) and patients with psychiatric comorbidities. Data from the literature have stated for a long time that the approach to patients with alcoholic liver disease (ALD) should be changed with no ethical or technical preconceptions. The reasons in favor of this change are as follows:

Download Full-text