Deep Reinforcement Learning for Autonomous Driving with an Auxiliary Actor Discriminator.

In the research of robot systems, path planning and obstacle avoidance are important research directions, especially in unknown dynamic environments where flexibility and rapid decision makings are required. In this paper, a state attention network (SAN) was developed to extract features to represent the interaction between an intelligent robot and its obstacles. An auxiliary actor discriminator (AAD) was developed to calculate the probability of a collision. Goal-directed and gap-based navigation strategies were proposed to guide robotic exploration. The proposed policy was trained through simulated scenarios and updated by the Soft Actor-Critic (SAC) algorithm. The robot executed the action depending on the AAD output. Heuristic knowledge (HK) was developed to prevent blind exploration of the robot. Compared to other methods, adopting our approach in robot systems can help robots converge towards an optimal action strategy. Furthermore, it enables them to explore paths in unknown environments with fewer moving steps (showing a decrease of 33.9%) and achieve higher average rewards (showning an increase of 29.15%).

Diagnosis of Autism Spectrum Disorder (ASD) Using Recursive Feature Elimination-Graph Neural Network (RFE-GNN) and Phenotypic Feature Extractor (PFE).

Autism spectrum disorder (ASD) poses as a multifaceted neurodevelopmental condition, significantly impacting children's social, behavioral, and communicative capacities. Despite extensive research, the precise etiological origins of ASD remain elusive, with observable connections to brain activity. In this study, we propose a novel framework for ASD detection, extracting the characteristics of functional magnetic resonance imaging (fMRI) data and phenotypic data, respectively. Specifically, we employ recursive feature elimination (RFE) for feature selection of fMRI data and subsequently apply graph neural networks (GNN) to extract informative features from the chosen data. Moreover, we devise a phenotypic feature extractor (PFE) to extract phenotypic features effectively. We then, synergistically fuse the features and validate them on the ABIDE dataset, achieving 78.7% and 80.6% accuracy, respectively, thereby showcasing competitive performance compared to state-of-the-art methods. The proposed framework provides a promising direction for the development of effective diagnostic tools for ASD.

Clinical evaluation of radiation-induced sinusitis by MRI-based scoring system in nasopharyngeal carcinoma patients.

OBJECTIVE: To explore the application of magnetic resonance imaging (MRI) in the evaluation of radiation-induced sinusitis (RIS), MRI-based scoring system was used to evaluate the development regularity, characteristics and influencing factors of RIS in nasopharyngeal carcinoma (NPC) patients. PATIENTS AND METHODS: A retrospective analysis was performed by collecting the clinical and MRI data of 346 NPC patients to analyze the characteristics and prognosis of RIS. The predictive model was constructed according to the influencing factors of RIS. RESULTS: (1) In the 2-year follow-up after radiotherapy (RT), there was significant change in L-M score in both groups of NPC patients (sinusitis before RT group: p = 0.000 vs. non-sinusitis before RT group: p = 0.000). After 6 months of RT, the L-M scores of the two groups tended to plateau (sinusitis before RT group: p = 0.311 vs. non-sinusitis before RT group: p = 0.469). (2) The prevalence of sinusitis in two groups of NPC patients (without or with sinusitis before RT) was 83% vs. 93%, 91% vs. 99%, 94% vs. 98% at 1, 6 and 24 months after RT, respectively. (3) In the patients without sinusitis before RT, the incidence of sinusitis in maxillary and anterior/posterior ethmoid, sphenoid and frontal sinuses was 87.1%, 90.0%/87.1%, 49.5%, 11.8% respectively, 1 month after RT. (4) A regression model was established according to the univariate and multivariate analysis of the factors related to RIS (smoking history: p = 0.000, time after RT: p = 0.008 and TNM staging: p = 0.040). CONCLUSION: (1) RIS is a common complication in NPC patients after RT. This disorder progressed within 6 months after RT, stabilized and persisted within 6 months to 2 years. There is a high incidence of maxillary sinus and ethmoid sinus inflammation in NPC patients after RT. (2) Smoking history, time after RT and TNM staging were significant independent risk factors for RIS. (3) The intervention of the risk factors in the model may prevent or reduce the occurrence of RIS in NPC patients.

Quantification of 10 B vitamins in mouse colon by LC-MS/MS: Application on breast cancer mice treated with doxorubicin.

B vitamins play important roles in various physiological processes, including cell metabolism and DNA synthesis. The intestine is critical for the absorption and utilization of B vitamins, but few analytical methods for detecting intestinal B vitamins are currently available. In this study, we developed a novel liquid chromatography-tandem mass spectrometry (LC-MS/MS) method for the simultaneous quantification of 10 B vitamins in mouse colon tissue, including thiamin (B1), riboflavin (B2), nicotinic acid (B3), niacinamide (B3-AM), pantothenic acid (B5), pyridoxine (B6), pyridoxal 5'-phosphate (B6-5P), biotin (B7), folic acid (B9), and cyanocobalamin (B12). The method was thoroughly validated following the U.S. Food and Drug Administration (FDA) guidelines and yielded good results in terms of linearity (r2 > 0.9928), lower limit of quantification (40-600 ng/g), accuracy (88.9-119.80 %) and precision (relative standard deviation ≤ 19.71 %), recovery (87.95-113.79 %), matrix effect (91.26-113.78 %), and stability (85.65-114.05 %). Furthermore, we applied our method to profile B vitamins in the colons of mice with breast cancer after doxorubicin chemotherapy treatment, which revealed that the doxorubicin treatment led to significant colon damage and accumulation of several B vitamins including B1, B2 and B5. We also confirmed the capability of this method for quantifying B vitamins in other intestinal tissues like the ileum, jejunum, and duodenum. The newly developed method is simple, specific, and useful for targeted profiling of B vitamins in mouse colon, with a potential for future studies on the role of these micronutrients in healthy and diseased states.

TRIM21 ubiquitylates GPX4 and promotes ferroptosis to aggravate ischemia/reperfusion-induced acute kidney injury.

AIMS: This study aims to verify the molecular mechanism that Tripartite motif containing 21 (TRIM21) promotes ubiquitination degradation of glutathione peroxidase 4 (GPX4) by regulating ferroptosis, and to discuss the feasibility of TRIM21 as a new therapeutic target for acute kidney injury (AKI). MATERIALS AND METHODS: Ischemia-reperfusion (I/R)-AKI model was constructed using Trim21+/+ and Trim21-/- mice, and the expression of markers associated with kidney injury and ferroptosis were evaluated. HK-2 cells were treated by RSL3 and Erastin, and a hypoxia/reoxygenation (H/R) model was constructed to simulate I/R injury in vivo. KEY FINDINGS: In vivo, TRIM21 is highly expressed in I/R kidney tissues. Loss of TRIM21 alleviated I/R-AKI and improved renal function. The upregulation of GPX4, a key ferroptosis regulator, and the mild mitochondrial damage suggested that loss of TRIM21 had a negative regulation of ferroptosis. In vitro, TRIM21 was highly expressed in H/R models, and overexpression of TRIM21 in HK-2 cells increased ROS production, promoted intracellular iron accumulation, and boosted cellular sensitivity to RSL3 and Erastin. Mechanistically, we confirmed that GPX4 is a substrate of TRIM21 and can be degraded by TRIM21-mediated ubiquitination, suggesting that inhibiting TRIM21 attenuates ferroptosis. A JAK2 inhibitor Fedratinib downregulated TRIM21 expression and reduced damage both in vivo and in vitro, which is correlated with the upregulation of GPX4. SIGNIFICANCE: Our study showed that loss of TRIM21 could alleviate ferroptosis induced by I/R, revealed the mechanism of ubiquitination degradation of GPX4 by TRIM21 and suggested TRIM21 is a potential target for the treatment of AKI.

Intensive Care and Organ Support Related Mortality in Patients With COVID-19: A Systematic Review and Meta-Analysis.

To perform a systematic review and meta-analysis to generate estimates of mortality in patients with COVID-19 that required hospitalization, ICU admission, and organ support. DATA SOURCES: A systematic search of PubMed, Embase, and the Cochrane databases was conducted up to December 31, 2021. STUDY SELECTION: Previously peer-reviewed observational studies that reported ICU, mechanical ventilation (MV), renal replacement therapy (RRT) or extracorporeal membrane oxygenation (ECMO)-related mortality among greater than or equal to 100 individual patients. DATA EXTRACTION: Random-effects meta-analysis was used to generate pooled estimates of case fatality rates (CFRs) for in-hospital, ICU, MV, RRT, and ECMO-related mortality. ICU-related mortality was additionally analyzed by the study country of origin. Sensitivity analyses of CFR were assessed based on completeness of follow-up data, by year, and when only studies judged to be of high quality were included. DATA SYNTHESIS: One hundred fifty-seven studies evaluating 948,309 patients were included. The CFR for in-hospital mortality, ICU mortality, MV, RRT, and ECMO were 25.9% (95% CI: 24.0-27.8%), 37.3% (95% CI: 34.6-40.1%), 51.6% (95% CI: 46.1-57.0%), 66.1% (95% CI: 59.7-72.2%), and 58.0% (95% CI: 46.9-68.9%), respectively. MV (52.7%, 95% CI: 47.5-58.0% vs 31.3%, 95% CI: 16.1-48.9%; p = 0.023) and RRT-related mortality (66.7%, 95% CI: 60.1-73.0% vs 50.3%, 95% CI: 42.4-58.2%; p = 0.003) decreased from 2020 to 2021. CONCLUSIONS: We present updated estimates of CFR for patients hospitalized and requiring intensive care for the management of COVID-19. Although mortality remain high and varies considerably worldwide, we found the CFR in patients supported with MV significantly improved since 2020.

Abalone visceral peptides containing Cys and Tyr exhibit strong in vitro antioxidant activity and cytoprotective effects against oxidative damage.

The in vitro antioxidation and cytoprotection of abalone visceral peptides against oxidative damage were investigated. Results show that the DPPH· scavenging activities of the 16 chemically synthesized peptides were significantly and positively correlated with their reducing power. Their scavenging activities against ABTS·+ were positively correlated with their ability to inhibit linoleic acid oxidation. Only Cys containing peptides exhibited good DPPH· scavenging activity, while only Tyr containing peptides showed significant ABTS·+ scavenging activity. In the cytoprotection assay, all four representative peptides significantly increased the viability of H2O2-damaged LO2 cells and the activities of GSH-Px, CAT, and SOD, and all decreased MDA levels and LDH leakage, in which the Cys-containing peptides were more effective at increasing the activities of antioxidant enzymes, while the Tyr-containing peptides were more effective at decreasing MDA levels and LDH leakage. Abalone visceral peptides containing both Cys and Tyr exhibit strong in vitro and cellular antioxidation.

Entacapone alleviates acute kidney injury by inhibiting ferroptosis.

Acute kidney injury (AKI) is a common clinical problem and an efficacious treatment is lacking. Ferroptosis, a newly discovered type of programmed cell death, has been reported to alleviate renal tubular injury in ischemia/reperfusion-induced acute kidney injury (I/R-AKI). Entacapone is a specific inhibitor of catechol-O-methyltransferase, which is used as an adjuvant drug against Parkinson's disease. We demonstrated that entacapone prevents renal I/R injury by inhibiting ferroptosis. Compared with a sham group, entacapone treatment mitigated I/R-induced pathological alterations, improved renal function, and inhibited ferroptosis. In HK-2 cells, entacapone treatment significantly reduced the lipid peroxidation and iron accumulation induced by the ferroptosis inducers erastin and RSL3, and significantly regulated expression of ferroptosis-related proteins. Entacapone upregulates p62 expression and affects the p62-KEAP1-NRF2 pathway, thereby upregulating nuclear translocation of NRF2. This action results in increased expression of the downstream SLC7A11, and significant suppression of oxidative stress and ferroptosis. Our results identify entacapone as a ferroptosis inhibitor that enhances antioxidant capacity. Entacapone may serve as a novel strategy to improve treatment of, and recovery from, I/R-AKI.

Real-world study on HBsAg loss of combination therapy in HBeAg-negative chronic hepatitis B patients.

Combination therapy with pegylated interferon (PEG-IFN) and nucleos(t)ide analogues (NAs) can enhance hepatitis B surface antigen (HBsAg) clearance. However, the specific treatment strategy and the patients who would benefit the most are unclear. Therefore, we assessed the HBsAg loss rate of add-on PEG-IFN and explored the factors associated with HBsAg loss in chronic hepatitis B (CHB) patients. This was a real-world cohort study of adults with CHB. Hepatitis B e antigen (HBeAg)-negative NAs-treated patients with baseline HBsAg ≤1500 IU/ml and HBV DNA < the lower limit of detection, or 100 IU/ml, received 48 weeks of add-on PEG-IFN. The primary outcome of the study was the rate of HBsAg loss at 48 weeks of combination treatment. Using multivariable logistic regression analysis, we determined factors associated with HBsAg loss. HBsAg loss in 2579 patients (mean age: 41.2 years; 80.9% male) was 36.7% (947 patients) at 48 weeks. HBsAg loss was highest in patients from south-central and southwestern China (40.0%). Factors independently associated with HBsAg loss included: increasing age (odds ratio = 0.961); being male (0.543); baseline HBsAg level (0.216); HBsAg decrease at 12 weeks (between 0.5 and 1.0 log10 IU/ml [2.405] and >1.0 log10 IU/ml [7.370]); alanine aminotransferase (ALT) increase at 12 weeks (1.365); haemoglobin (HGB) decrease at 12 weeks (1.558). There was no difference in the primary outcomes associated with the combination regimen. In conclusion, HBsAg loss by combination therapy was higher in patients from southern China than those from the north. An increased chance of HBsAg loss was associated with baseline characteristics and dynamic changes in clinical indicators.

BK Channel Deficiency in Osteoblasts Reduces Bone Formation via the Wnt/ß-Catenin Pathway.

Global knockout of the BK channel has been proven to affect bone formation; however, whether it directly affects osteoblast differentiation and the mechanism are elusive. In the current study, we further investigated the role of BK channels in bone development and explored whether BK channels impacted the differentiation and proliferation of osteoblasts via the canonical Wnt signaling pathway. Our findings demonstrated that knockout of Kcnma1 disrupted the osteogenesis of osteoblasts and inhibited the stabilization of ß-catenin. Western blot analysis showed that the protein levels of Axin1 and USP7 increased when Kcnma1 was deficient. Together, this study confirmed that BK ablation decreased bone mass via the Wnt/ß-catenin signaling pathway. Our findings also showed that USP7 might have the ability to stabilize the activity of Axin1, which would increase the degradation of ß-catenin in osteoblasts.

A novel essential protein identification method based on PPI networks and gene expression data.

BACKGROUND: Some proposed methods for identifying essential proteins have better results by using biological information. Gene expression data is generally used to identify essential proteins. However, gene expression data is prone to fluctuations, which may affect the accuracy of essential protein identification. Therefore, we propose an essential protein identification method based on gene expression and the PPI network data to calculate the similarity of "active" and "inactive" state of gene expression in a cluster of the PPI network. Our experiments show that the method can improve the accuracy in predicting essential proteins. RESULTS: In this paper, we propose a new measure named JDC, which is based on the PPI network data and gene expression data. The JDC method offers a dynamic threshold method to binarize gene expression data. After that, it combines the degree centrality and Jaccard similarity index to calculate the JDC score for each protein in the PPI network. We benchmark the JDC method on four organisms respectively, and evaluate our method by using ROC analysis, modular analysis, jackknife analysis, overlapping analysis, top analysis, and accuracy analysis. The results show that the performance of JDC is better than DC, IC, EC, SC, BC, CC, NC, PeC, and WDC. We compare JDC with both NF-PIN and TS-PIN methods, which predict essential proteins through active PPI networks constructed from dynamic gene expression. CONCLUSIONS: We demonstrate that the new centrality measure, JDC, is more efficient than state-of-the-art prediction methods with same input. The main ideas behind JDC are as follows: (1) Essential proteins are generally densely connected clusters in the PPI network. (2) Binarizing gene expression data can screen out fluctuations in gene expression profiles. (3) The essentiality of the protein depends on the similarity of "active" and "inactive" state of gene expression in a cluster of the PPI network.

An annotated dataset of tongue images supporting geriatric disease diagnosis.

Hospitalized geriatric patients are a highly heterogeneous group often with variable diseases and conditions. Physicians, and geriatricians especially, are devoted to seeking non-invasive testing tools to support a timely, accurate diagnosis. Chinese tongue diagnosis, mainly based on the color and texture of the tongue, offers a unique solution. To develop a non-invasive assessment tool using machine learning in supporting a timely, accurate diagnosis in the elderly, we created an annotated dataset of 15% of 688 (=100) tongue images collected from hospitalized geriatric patients in a tertiary hospital in Shanghai, China. Images were captured via a light-field camera using CIELAB color space (to simulate human visual perception) and then were manually labeled by a panel of subject matter experts after chart reviewing patients' clinical information documented in the hospital's information system. We expect that the dataset can assist in implementing a systematic means of conducting Chinese tongue diagnosis, predicting geriatric syndromes using tongue appearance, and even developing an mHealth application to provide individualized health suggestions for the elderly.

The influx/efflux mechanisms of d-peptide ligand of nAChRs across the blood-brain barrier and its therapeutic value in treating glioma.

A d-peptide ligand of the nicotine acetylcholine receptors (nAChRs), termed DCDX, enables drug delivery to the brain when incorporated into liposomes and has shown promise as a nanocarrier for treating brain diseases. However, few reports have described the mechanisms whereby DCDX-modified liposomes traverse the blood-brain barrier (BBB). Here, we studied the molecular mechanisms enabling DCDX (and its associated liposomes) to cross an in vitro BBB using a simulated cerebral endothelium monolayer formed by brain capillary endothelial cells (bEnd.3 cells). We also examined the mechanisms whereby DCDX-modified liposomes cross the BBB in vivo using the brain efflux-index method. Transport of DCDX and its modified liposomes was dominantly mediated via the lipid raft/caveolae endocytic pathway. Both the endoplasmic reticulum (ER) and Golgi complex participated in delivering DCDX-modified liposomes to the plasma membrane (PM). DCDX-modified liposomes also participated in the endosome/lysosome pathway (with high-efficiency BBB crossing observed in vitro), while competing for the ER/Golgi/PM pathway. In addition, nAChR α7 did not promote the transportation of DCDX-modified liposomes in vivo or in vitro, as assessed with α7-knockout mice and by performing α-bungarotoxin (α-Bgt) binding-competition experiments. P-glycoprotein (P-gp) was identified as the main efflux transporter across the BBB, in vivo and in vitro. Using a xenograft nude mouse model of human glioblastoma multiforme, blocking the efflux function of P-gp with verapamil enhanced the therapeutic efficiency of DCDX-modified liposomes that were formulated with doxorubicin against glioblastoma. The findings of this study reveal novel mechanisms underlying crossing of the BBB by DCDX-modified liposomes, suggesting that DCDX-modified liposomes can potentially serve as a powerful therapeutic tool for treating glioma.

Saikosaponin B2 attenuates kidney fibrosis via inhibiting the Hedgehog Pathway.

BACKGROUND: Renal interstitial fibrosis is a common pathway through which chronic kidney disease progresses to end-stage renal disease. There are currently no effective drugs available to treat kidney fibrosis, so traditional medicine is likely to be a candidate. The therapeutic potential of saikosaponin B2 (SSB2), a biologically active ingredient of Radix Bupleuri, on renal fibrosis has not been reported. METHODS: A unilateral ureteral obstruction (UUO) model was conducted to induce renal interstitial fibrosis in mice. SSB2's effect was valuated by histological staining and exploring the changes in expression of relative proteins and mRNAs. A conditional medium containing sonic hedgehog variant protein stimulating normal rat kidney interstitial fibroblast cells (NRK-49F) was used in an in vitro model to determine the possible mechanism. The molecular target of SSB2 was verified using several mutation plasmids. RESULTS: SSB2 administration reduced kidney injury and alleviated interstitial fibrosis by decreasing excessive accumulation of extracellular matrix components in UUO mice. It could also reduce the expression of α-SMA, fibronectin and Gli1, a crucial molecule of the hedgehog (Hh) signaling pathway both in vivo and in vitro. In NIH-3T3 cells simulated by conditional medium containing sonic hedgehog variant protein, SSB2 showed the ability to decrease the expression of Gli1 and Ptch1 mRNA. Using a dual-luciferase reporter assay, SSB2 suppressed the Gli-luciferase reporter activity in NIH-3T3 cells, and the IC50 was 0.49 µM, but had no effect on the TNF-α/NF-κB and Wnt/ß-catenin signaling pathways, indicating the inhibition selectivity on the Hh signaling pathway. Furthermore, SSB2 failed to inhibit the Hh pathway activity evoked by ectopic expression of Gli2ΔN and Smo D473H, suggesting that SSB2 might potentially act on smoothened receptors. CONCLUSION: SSB2 could attenuate renal fibrosis and decrease fibroblast activation by inhibiting the Hh signaling pathway.

Correction: Testing the decoy effect to increase interest in colorectal cancer screening.

[This corrects the article DOI: 10.1371/journal.pone.0213668.].

Medication Use for Childhood Pneumonia at a Children's Hospital in Shanghai, China: Analysis of Pattern Mining Algorithms.

BACKGROUND: Pattern mining utilizes multiple algorithms to explore objective and sometimes unexpected patterns in real-world data. This technique could be applied to electronic medical record data mining; however, it first requires a careful clinical assessment and validation. OBJECTIVE: The aim of this study was to examine the use of pattern mining techniques on a large clinical dataset to detect treatment and medication use patterns for childhood pneumonia. METHODS: We applied 3 pattern mining algorithms to 680,138 medication administration records from 30,512 childhood inpatients with diagnosis of pneumonia during a 6-year period at a children's hospital in China. Patients' ages ranged from 0 to 17 years, where 37.53% (11,453/30,512) were 0 to 3 months old, 86.55% (26,408/30,512) were under 5 years, 60.37% (18,419/30,512) were male, and 60.10% (18,338/30,512) had a hospital stay of 9 to 15 days. We used the FP-Growth, PrefixSpan, and USpan pattern mining algorithms. The first 2 are more traditional methods of pattern mining and mine a complete set of frequent medication use patterns. PrefixSpan also incorporates an administration sequence. The newer USpan method considers medication utility, defined by the dose, frequency, and timing of use of the 652 individual medications in the dataset. Together, these 3 methods identified the top 10 patterns from 6 age groups, forming a total of 180 distinct medication combinations. These medications encompassed the top 40 (73.66%, 500,982/680,138) most frequently used medications. These patterns were then evaluated by subject matter experts to summarize 5 medication use and 2 treatment patterns. RESULTS: We identified 5 medication use patterns: (1) antiasthmatics and expectorants and corticosteroids, (2) antibiotics and (antiasthmatics or expectorants or corticosteroids), (3) third-generation cephalosporin antibiotics with (or followed by) traditional antibiotics, (4) antibiotics and (medications for enteritis or skin diseases), and (5) (antiasthmatics or expectorants or corticosteroids) and (medications for enteritis or skin diseases). We also identified 2 frequent treatment patterns: (1) 42.89% (291,701/680,138) of specific medication administration records were of intravenous therapy with antibiotics, diluents, and nutritional supplements and (2) 11.53% (78,390/680,138) were of various combinations of inhalation of antiasthmatics, expectorants, or corticosteroids. Fleiss kappa for the subject experts' evaluation was 0.693, indicating moderate agreement. CONCLUSIONS: Utilizing a pattern mining approach, we summarized 5 medication use patterns and 2 treatment patterns. These warrant further investigation.

Testing the decoy effect to increase interest in colorectal cancer screening.

Literature on consumer choice has demonstrated that the inclusion of an inferior alternative choice (decoy) can increase interest in a target product or action. In two online studies, we tested the impact of decoys on the probability of previous non-intenders to have a screening test which could significantly lower their chances of dying of colorectal cancer. We find that the presence of a decoy increased the probability to choose screening at the target hospital (over no screening) from 39% to 54% and 37% to 59% depending on how many hospital attributes were communicated and how strongly the decoy was dominated by the target. We also show that the presence of the decoy was associated with lower levels of reported decisional complexity while not undermining information seeking and knowledge acquisition. These findings offer a 'proof of principle' that decoys have the potential to increase screening uptake without negatively influencing informed choice.

XGBFEMF: An XGBoost-Based Framework for Essential Protein Prediction.

Essential proteins as a vital part of maintaining the cells' life play an important role in the study of biology and drug design. With the generation of large amounts of biological data related to essential proteins, an increasing number of computational methods have been proposed. Different from the methods which adopt a single machine learning method or an ensemble machine learning method, this paper proposes a predicting framework named by XGBFEMF for identifying essential proteins, which includes a SUB-EXPAND-SHRINK method for constructing the composite features with original features and obtaining the better subset of features for essential protein prediction, and also includes a model fusion method for getting a more effective prediction model. We carry out experiments on Yeast data to assess the performance of the XGBFEMF with ROC analysis, accuracy analysis, and top analysis. Meanwhile, we set up experiments on E. coli data for the validation of performance. The test results show that the XGBFEMF framework can effectively improve many essential indicators. In addition, we analyze each step in the XGBFEMF framework; our results show that both each step of the SUB-EXPAND-SHRINK method as well as the step of multi-model fusion can improve prediction performance.

Initial combination anti-viral therapy with lamivudine and adefovir dipivoxil decreases short-term fatality rate of hepatitis-B-virus-related acute-on-chronic liver failure.

BACKGROUND: Acute-on-chronic liver failure (ACLF) is a common serious hepatitis B virus (HBV)-related disease and has a poor prognosis. Until recently, initial combination antiviral treatment in ACLF patients was rarely reported. This study evaluated the effect of initial combination treatment with lamivudine and adefovir dipivoxil on the prognosis of HBV-related ACLF. METHODS: In this retrospective study, 131 eligible ACLF patients, including 61 treated with 100 mg lamivudine and 10 mg adefovir dipivoxil daily and 70 not treated with any nucleoside analogs (NAs), were selected and assigned into the NA and non-NA groups. All the patients received standard medicinal therapy. At weeks 0-4 and 12, serum markers for hepatic and renal functions were measured in all patients and accumulated fatality rates were calculated. Statistical analyses, including Student's t test, χ(2) test and unconditional logistic regression analysis, were performed using SPSS version 17.0 software. RESULTS: Clinical data indicated that improvement of hepatic function was better in the NA than in the non-NA group. The accumulated fatality rate in the NA group was lower than in the non-NA group at weeks 2-4 and 12, and these differences were significant. Univariate analysis showed that age, prothrombin activity, model of end-stage liver disease (MELD) score, and treatment without NAs were risk factors for short-term survival of ACLF. Further research by unconditional logistic regression analysis identified that older age, high MELD score and treatment without NAs were independent risk factors for short-term survival of ACLF. CONCLUSIONS: Initial combination antiviral treatment is effective in decreasing short-term fatality of HBV-related ACLF.