A novel prognostic model to predict outcome of artificial liver support system treatment.
Ontology highlight
ABSTRACT:
SUBMITTER: Shang J
PROVIDER: S-EPMC8021558 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Artificial liver support system (ALSS) therapy is widely used in patients with hepatitis B virus-related acute-on-chronic liver failure (HBV-ACLF). We aimed to develop a predictive score to identify the subgroups who may benefit from plasma exchange (PE)-centered ALSS therapy. A total of 601 patients were retrospectively enrolled and randomly divided into a derivation cohort of 303 patients and a validation cohort of 298 patients for logistic regression analysis, respectively. Five baseline variables, including liver cirrhosis, total bilirubin, international normalized ratio of prothrombin time, infection and hepatic encephalopathy, were found independently associated with 3-month mortality. A predictive PALS model and the simplified PALS score were developed. The predicative value of PALS score (AUROC = 0.818) to 3-month prognosis was as capable as PALS model (AUROC = 0.839), R score (AUROC = 0.824) and Yue-Meng' score (AUROC = 0.810) (all p > 0.05), and superior to CART model (AUROC = 0.760) and MELD score (AUROC = 0.765) (all p < 0.05). The PALS score had significant linear correlation with 3-month mortality (R2 = 0.970, p = 0.000). PALS score of 0-2 had both sensitivity and negative predictive value of > 90% for 3-month mortality, while PALS score of 6-9 had both specificity and positive predictive value of > 90%. Patients with PALS score of 3-5 who received 3-5 sessions of ALSS therapy had much lower 3-month mortality than those who received 1-2 sessions (32.8% vs. 59.2%, p < 0.05). The more severe patients with PALS score of 6-9 could still benefit from ≥ 6 sessions of ALSS therapy compared to ≤ 2 sessions (63.6% vs. 97.0%, p < 0.05). The PALS score could predict prognosis reliably and conveniently. It could identify the subgroups who could benefit from PE-centered ALSS therapy, and suggest the reasonable sessions.Trial registration: Chinese Clinical Trial Registry, ChiCTR2000032055. Registered 19th April 2020, http://www.chictr.org.cn/showproj.aspx?proj=52471 .
| S-EPMC7809456 | biostudies-literature
Project description:AimTo determine the prognostic risk factors of patients with hepatitis B virus related acute-on-chronic liver failure (HBV-ACLF) treated with plasma exchange (PE)-based artificial liver support system (ALSS), and create a prognostic predictive model.MethodsA total of 304 HBV-ACLF patients who received PE-based ALSS were retrospectively analyzed. Potential prognostic factors on admission associated with survival were investigated. Of note, 101 additional patients were analyzed to validate the performance of the prognostic models.ResultsAccording to 28-day survival, a total of 207 patients who survived and 97 non-survivors were identified in the derivation group. Overall, 268 (88.2%) ACLF cases were caused by reactivation of HBV. Cox proportional hazards regression model revealed that age, total bilirubin, ln (alpha-fetoprotein [AFP]), encephalopathy (HE) score, sodium level, and international normalized ratio (INR) were independent risk factors of short-term prognosis. We built a model named ALSS-prognosis model (APM) to predict the 28-day survival of HBV-ACLF patients with ALSS; the model APM showed potentially better predictive performance for both the derivation and validation groups than MELD, MELD-Na, and CLIF-C ACLF score.ConclusionsLow AFP was found to be an independent risk factor for high mortality in HBV-ACLF patients treated with PE-based ALSS. We generated a new model containing AFP, namely APM, which showed potentially better prediction performance than MELD, MELD-Na, and CLIF-C ACLF score for short-term outcomes, and could aid physicians in making optimal therapeutic decisions.
| S-EPMC7217207 | biostudies-literature
Project description:Background and objectivesThe prognosis of liver failure treated with non-bioartificial liver support systems is poor. Detecting its risk factors and developing relevant prognostic models still represent the top priority to lower its death risk.MethodsAll 215 patients with liver failure treated with non-bioartificial liver support system were retrospectively analyzed. Potential prognostic factors were investigated, and the Nomogram and the Random Survival Forests (RSF) models were constructed, respectively. Notably, we evaluated the performance of models and calculated the risk scores to divide patients into low-risk and high-risk groups.ResultsIn the training set, multifactorial Cox regression analysis showed that etiology, hepatic encephalopathy, total bilirubin, serum alkaline phosphatase, platelets, and MELD score were independent factors of short-term prognosis. The RSF model (AUC: 0.863, 0.792) performed better in prediction than the Nomogram model (AUC: 0.816, 0.756) and MELD (AUC: 0.658, 0.700) in the training and validation groups. On top of that, patients in the low-risk group had a significantly better prognosis than those in the high-risk group.ConclusionWe constructed the RSF model with etiology, hepatic encephalopathy, total bilirubin, serum alkaline phosphatase, platelets, and MELD score, which showed better prognostic power than the Nomogram model and MELD score and could help physicians make optimal treatment decisions.
| S-EPMC10965676 | biostudies-literature
Project description:Artificial liver support systems (ALSS) are widely used to treat patients with hepatitis B virus-related acute-on-chronic liver failure (HBV-ACLF). The aims of the present study were to investigate the subgroups of patients with HBV-ACLF who may benefit from ALSS therapy, and the relevant patient-specific factors. 489 ALSS-treated HBV-ACLF patients were enrolled, and served as derivation and validation cohorts for classification and regression tree (CART) analysis. CART analysis identified three factors prognostic of survival: hepatic encephalopathy (HE), prothrombin time (PT), and total bilirubin (TBil) level; and two distinct risk groups: low (28-day mortality 10.2-39.5%) and high risk (63.8-91.1%). The CART model showed that patients lacking HE and with a PT ≤ 27.8 s and a TBil level ≤455 μmol/L experienced less 28-day mortality after ALSS therapy. For HBV-ACLF patients with HE and a PT > 27.8 s, mortality remained high after such therapy. Patients lacking HE with a PT ≤ 27.8 s and TBil level ≤ 455 μmol/L may benefit markedly from ALSS therapy. For HBV-ACLF patients at high risk, unnecessary ALSS therapy should be avoided. The CART model is a novel user-friendly tool for screening HBV-ACLF patient eligibility for ALSS therapy, and will aid clinicians via ACLF risk stratification and therapeutic guidance.
| S-EPMC6848208 | biostudies-literature
Project description:The artificial liver support system (ALSS) offers the potential to improve the prognosis of patients with acute-on-chronic liver failure (ACLF). However, the literature has been inconsistent on its survival benefits. We aimed to conduct a time series-based meta-analysis of randomized clinical trials (RCTs) and observational studies which examined differences in mortality in ACLF patients treated with ALSS or not.MEDLINE, EMBASE, OVID, and COCHRANE library database were systemically searched up to December 2014. Quality of included studies was evaluated using the Jadad score. The outcome measure was mortality at different follow-up endpoints. Odds ratios (ORs) and survival curve data were pooled for analysis.Ten studies, 7 RCTs, and 3 controlled cohorts were enrolled, involving a total of 1682 ACLF patients, among whom 842 were treated with ALSS. ALSS was found to reduce the risk of short-term (1-month and 3-month) mortality for patients with ACLF by nearly 30%. Randomized trials and observational studies provided good internal and external validity respectively. The combined Kaplan-Meier curves showed a consistent pattern of findings. Meta-analysis also suggested that ALSS might reduce medium-term (6-month and 1-year) mortality risk by 30% and long-term (3-year) mortality risk by 50% in ACLF patients.ALSS therapy could reduce short-term mortality in patients with ACLF. Meanwhile, its impacts on medium- and long-term survival seem to be promising but remained inconclusive. Clinical utility of this system for survival benefit may be implied.
| S-EPMC4998263 | biostudies-literature
Project description:BackgroundHBV-related acute-on-chronic liver failure (HBV-ACLF) is the most common type of liver failure with high mortality. Artificial liver support system (ALSS) is an important mean to reduce the mortality of HBV-ACLF but lacking index to assess its effectiveness. The cytokines are closely related to the prognosis of HBV-ACLF patients with ALSS treatment, however, which is not fully understood.MethodsOne hundred forty-two patients with HBV-ACLF and 25 healthy donors were enrolled. The cytokine profile of peripheral blood was determined in the patients before and after ALSS treatment, and their relationship with effectiveness of ALSS treatment in HBV-ACLF was analyzed.ResultsSerum IL-28A levels were markedly lower in ALSS-effective patients than those in non-effective patients pre-ALSS treatment. Similarly, serum IL-6 was significantly lower in ALSS-effective patients. Furthermore, for patients with effective treatment, serum IL-28A levels were positively related with IL-6 levels post-ALSS (r = 0.2413, p = 0.0383). The ROC curve analysis showed that serum levels of IL-28A (AUC = 0.6959 when alone or 0.8795 when combined with total bilirubin, platelet count and INR, both p < 0.0001) and IL-6 (AUC = 0.6704, p = 0.0005) were useful indices for separating effective from non-effective ALSS treatment of HBV-ACLF patients. Multivariate logistic regression analysis demonstrated that lower level of IL-28A was independently associated with higher effective rate of ALSS treatments.ConclusionsLower level of IL-28A is a predictive biomarker for ALSS in effective treatment of HBV-ACLF patients and IL-28A may be potential target for the treatment of HBV-ACLF.
| S-EPMC9756982 | biostudies-literature
Project description:Background: Sepsis, post-liver transplantation, is a frequent challenge that impacts patient outcomes. We aimed to develop an artificial intelligence method to predict the onset of post-operative sepsis earlier. Methods: This pilot study aimed to identify "physiomarkers" in continuous minute-by-minute physiologic data streams, such as heart rate, respiratory rate, oxygen saturation (SpO2), and blood pressure, to predict the onset of sepsis. The model was derived from a cohort of 5,748 transplant and non-transplant patients across intensive care units (ICUs) over 36 months, with 92 post-liver transplant patients who developed sepsis. Results: Using an alert timestamp generated with the Third International Consensus Definition of Sepsis (Sepsis-3) definition as a reference point, we studied up to 24 h of continuous physiologic data prior to the event, totaling to 8.35 million data points. One hundred fifty-five features were generated using signal processing and statistical methods. Feature selection identified 52 highly ranked features, many of which included blood pressures. An eXtreme Gradient Boost (XGB) classifier was then trained on the ranked features by 5-fold cross validation on all patients (n = 5,748). We identified that the average sensitivity, specificity, positive predictive value (PPV), and area under the receiver-operator curve (AUC) of the model after 100 iterations was 0.94 ± 0.02, 0.9 ± 0.02, 0.89 ± 0.01, respectively, and 0.97 ± 0.01 for predicting sepsis 12 h before meeting criteria. Conclusion: The data suggest that machine learning/deep learning can be applied to continuous streaming data in the transplant ICU to monitor patients and possibly predict sepsis.
| S-EPMC8450439 | biostudies-literature
Project description:Hepatorenal syndrome (HRS) could occur when patients get decompensated liver cirrhosis. Meanwhile, hepatitis B virus (HBV) infection raises the risk of mortality of the end-stage liver diseases. As the artificial liver support system (ALSS) has been applied in liver failure, whether ALSS could benefit HBV-derived HRS remains uncertain. We retrospectively enlisted eligible HRS patients and compared the baseline characteristics and prognosis between HBV-derived HRS and non-HBV-derived HRS. Furthermore, propensity score matching (PSM) and Cox regression analyses were used to assess the beneficial effect of ALSS on HBV-derived HRS. In addition, a stratified analysis was carried out according to the degree of acute kidney injury (AKI) and the number of organ failures to observe in which populations ALSS can obtain the most excellent therapeutic effect. 669 patients were diagnosed as HRS, including 298 HBV negative and 371 HBV positive. Baseline characteristics were different between patients with HBV positive and HBV negative. HBV-derived HRS has higher 28-day mortality, though without a statistical difference. After PSM, 50 patients treated with ALSS and 150 patients treated with standard medical treatment (SMT) constituted a new cohort for the following analysis. We found that ALSS could significantly benefit HRS patients (P = 0.025). Moreover, the median survival time of patients treated with ALSS was longer than those treated with SMT. INR, neutrophil percentage, and treatment with ALSS were independent predictive factors for short-term mortality in HBV-derived HRS. The stratified analysis showed that ALSS could reduce the 28-day mortality of patients with HBV-derived HRS, especially those in AKI stage 3 and with organ failure ≥ 2. Additionally, serum bilirubin was significantly lower after ALSS, and the alteration of INR and creatinine were independent predictive elements for the mortality of HBV-derived HRS. HBV-derived HRS is more severe than non-HBV-derived HRS and has a worse prognosis. ALSS could reduce the short-term mortality of patients with HBV-derived HRS, especially those in AKI stage 3 and with organ failure ≥ 2. INR and the change of creatinine and INR could predict the prognosis of HBV-derived HRS. ChiCTR2200060123.
| S-EPMC9177308 | biostudies-literature
Project description:Convolutional neural networks (CNNs) may improve response prediction in diffuse large B-cell lymphoma (DLBCL). The aim of this study was to investigate the feasibility of a CNN using maximum intensity projection (MIP) images from 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography (PET) baseline scans to predict the probability of time-to-progression (TTP) within 2 years and compare it with the International Prognostic Index (IPI), i.e. a clinically used score. 296 DLBCL 18F-FDG PET/CT baseline scans collected from a prospective clinical trial (HOVON-84) were analysed. Cross-validation was performed using coronal and sagittal MIPs. An external dataset (340 DLBCL patients) was used to validate the model. Association between the probabilities, metabolic tumour volume and Dmaxbulk was assessed. Probabilities for PET scans with synthetically removed tumors were also assessed. The CNN provided a 2-year TTP prediction with an area under the curve (AUC) of 0.74, outperforming the IPI-based model (AUC = 0.68). Furthermore, high probabilities (> 0.6) of the original MIPs were considerably decreased after removing the tumours (< 0.4, generally). These findings suggest that MIP-based CNNs are able to predict treatment outcome in DLBCL.
| S-EPMC10423266 | biostudies-literature
Project description:BACKGROUND Hepatocellular carcinoma (HCC) is a malignant tumor which is famous for its high heterogeneity and complex pathogenesis. Angiogenesis is an important driver of tumor progression and immune-suppressive microenvironment formation. MATERIAL AND METHODS A training set was acquired from the TCGA-LIHC cohort. An angiogenesis-active subtype was identified by consensus clustering analysis. The tumor subtype's immune microenvironment pattern was analyzed using quanTIseq. DEGs-mediated biology function was analyzed by enrichment analysis based on GO and KEGG. A prognostic model was constructed using LASSO Cox regression analysis and validated by 2 external datasets derived from GEO and ICGC. Quantitative real-time PCR assay was conducted to analyze CDCA8's expression status in the HCC line and normal liver cell line. RESULTS In HCC, patients with the angiogenesis-active subtype had a poor prognosis. Angiogenesis can shape the tumor microenvironment into high-M2 microphage infiltration and activity pattern. Here, we identified an angiogenesis-active HCC subtype and constructed an angiogenesis feature-based prognostic model to predict patient outcome. The external validation sets were enrolled to verify the accuracy of this model. CONCLUSIONS Our research demonstrated angiogenesis can confer the tumor immune-suppressive characteristic. We provide a robust method to evaluate the HCC's angiogenesis potential and help identify the angiogenesis-active subtype. Validation in the external validation cohort further confirmed the accuracy of our prognostic model.
| S-EPMC8679551 | biostudies-literature