Variation pattern in the macromolecular (cellulose, hemicelluloses, lignin) composition of cell walls in Pinus tabulaeformis tree trunks at different ages as revealed using multiple techniques.

The plant cell wall is a complex, heterogeneous structure primarily composed of cellulose, hemicelluloses, and lignin. Exploring the variations in these three macromolecules over time is crucial for understanding wood formation to enhance chemical processing and utilization. Here, we comprehensively analyzed the chemical composition of cell walls in the trunks of Pinus tabulaeformis using multiple techniques. In situ analysis showed that macromolecules accumulated gradually in the cell wall as the plant aged, and the distribution pattern of lignin was opposite that of polysaccharides, and both showed heterogenous distribution patterns. In addition, gel permeation chromatography (GPC) results revealed that the molecular weights of hemicelluloses decreased while that of lignin increased with age. Two-dimensional heteronuclear single quantum coherence nuclear magnetic resonance (2D-HSQC NMR) analysis indicated that hemicelluloses mainly comprised galactoglucomannan and arabinoglucuronoxylan, and the lignin types were mainly comprised guaiacyl (G) and p-hydroxyphenyl (H) units with three main linkage types: ß-O-4, ß-ß, and ß-5. Furthermore, the C-O bond (ß-O-4) signals of lignin decreased while the C-C bonds (ß-ß and ß-5) signals increased over time. Taken together, these findings shed light on wood formation in P. tabulaeformis and lay the foundation for enhancing the processing and use of wood and timber products.

[Non-targeted metabolomics of spleen and liver metabolism in mice treated with Pruni Semen processed with different methods].

Ultra performance liquid chromatography-quadrupole time-of-flight mass spectrometry(UPLC-Q-TOF-MS) was employed to investigate the impacts of Pruni Semen processed with different methods(raw and fried) on the liver and spleen metabolism in mice. A total of 24 male mice were randomly assigned to three groups: raw Pruni Semen group, fried Pruni Semen group, and control(deionized water) group. Mice in the three groups were orally administrated with 0.01 g·mL~(-1) Pruni Semen decoction or deionized water for one week. After that, the liver and spleen tissues were collected, and liquid chromatography-mass spectrometry(LC-MS)-based metabolomic analysis was carried out to investigate the impact of Pruni Semen on the liver and spleen metabolism in mice. Compared with thte control group, the raw Pruni Semen group showed up-regulation of 11 metabolites and down-regulation of 57 metabolites in the spleen(P<0.05), as well as up-regulation of 15 metabolites and down-regulation of 58 metabolites in the liver(P<0.05). The fried Pruni Semen group showed up-regulation of 31 metabolites and down-regulation of 10 metabolites in the spleen(P<0.05), along with up-regulation of 26 metabolites and down-regulation of 61 metabolites in the liver(P<0.05). The differential metabolites identified in the raw Pruni Semen group were primarily associated with alanine, aspartate, and glutamate metabolism, purine metabolism, amino sugar and nucleotide sugar metabolism, and D-glutamine and D-glutamate metabolism. The differential metabolites identified in the fried Pruni Semen group predominantly involved riboflavin metabolism, amino sugar and nucleotide sugar metabolism, purine metabolism, alanine, aspartate, and glutamate metabolism, D-glutamine and D-glutamate metabolism, and glutathione metabolism. The findings suggest that both raw and fried Pruni Semen have the potential to modulate the metabolism of the liver and spleen in mice by influencing the glutamine and glutamate metabolism.

Causal relationship between immune cells and telomere length: mendelian randomization analysis.

BACKGROUND: The causal relationship between immune cells and telomere length remains controversial. METHODS: Data on the immune cells were obtained from a previous study with 3,757 participants. Data on telomere length were obtained from the OpenGWAS database. Genome-Wide Association Study (GWAS) data were obtained and screened for eligible instrumental variables (IVs) using the TwoSampleMR package and the Phenoscanner database. To investigate the genetic causality between immune cells and telomere length, Mendelian randomization (MR) analysis and Bayesian weighted Mendelian randomization (BWMR) analysis were used. RESULTS: MR analysis showed that there is indeed a genetic causal relationship between immune cells and telomere length. A total of 16 immune cells were successfully validated. A positive correlation was found between telomere length and immune cells such as CD28 + CD45RA + CD8br %CD8br (OR = 1.002, 95%CI: 1.000-1.003). A negative correlation was found between telomere length and immune cells such as Transitional AC (OR = 0.991, 95%CI: 0.984-0.997) (P < 0.05). Reverse MR analysis similarly confirmed that telomere length can affect four types of immune cells, including CD25 on IgD + CD24- (OR = 1.291, 95%CI: 1.060-1.571), at the genetic level. CONCLUSION: There is indeed a mutual genetic causality between immune cells and telomere length, which will provide theoretical basis and support for more subsequent clinical studies.

Modulatory Role of Biochar Properties and Environmental Risk of Heavy Metals by Co-Pyrolysis of Fenton Sludge and Biochemical Sludge.

Recent studies have reported that Fenton sludge and biochemical sludge contain high concentrations of toxic substances and heavy metals (HMs), whereas improper treatment can pose serious threats to environmental safety. Pyrolysis is considered an efficient technology to replace conventional sludge treatment. This study investigated the pyrolysis and kinetic processes of Fenton sludge and biochemical sludge, revealed the physicochemical properties of sludge biochar, and highlighted the role of co-pyrolysis in sludge immobilization of HMs and environmental risks. Results showed that Fenton sludge and biochemical sludge underwent three stages of weight loss during individual pyrolysis and co-pyrolysis, especially co-pyrolysis, which increased the rate of sludge pyrolysis and reduced the decomposition temperature. The kinetic reaction indicated that the activation energies of Fenton sludge, biochemical sludge, and mixed sludge were 11.59 kJ/mol, 8.50 kJ/mol, and 7.11 kJ/mol, respectively. Notably, co-pyrolysis reduced the activation energy of reactions and changed the specific surface area and functional group properties of the biochar produced from sludge. Meanwhile, co-pyrolysis effectively immobilized Cu, Pb, and Zn, increased the proportion of metals in oxidizable and residual states, and mitigated the environmental risks of HMs in sludge. This study provided new insights into the co-pyrolysis properties of sludge biochar and the risk assessment of HMs.

Cuproptosis-Related Genes MTF1 and LIPT1 as Novel Prognostic Biomarker in Acute Myeloid Leukemia.

Acute myeloid leukemia (AML) is a life-threatening hematologic malignant disease with high morbidity and mortality in both adults and children. Cuproptosis, a novel mode of cell death, plays an important role in tumor development, but the functional mechanisms of cuproptosis-related genes (CRGs) in AML are unclear. The differential expression of CRGs between tumors such as AML and normal tissues in UCSC XENA, TCGA and GTEx was verified using R (version: 3.6.3). Lasso regression, Cox regression and Nomogram were used to screen for prognostic biomarkers of AML and to construct corresponding prognostic models. Kaplan-Meier analysis, ROC analysis, clinical correlation analysis, immune infiltration analysis and enrichment analysis were used to further investigate the correlation and functional mechanisms of CRGs with AML. The ceRNA regulatory network was used to identify the mRNA-miRNA-lncRNA regulatory axis. Cuproptosis-related genes LIPT1, MTF1, GLS and CDKN2A were highly expressed in AML, while FDX1, LIAS, DLD, DLAT, PDHA1, SLC31A1 and ATP7B were lowly expressed in AML. Lasso regression, Cox regression, Nomogram and calibration curve finally identified MTF1 and LIPT1 as two novel prognostic biomarkers of AML and constructed the corresponding prognostic models. In addition, all 12 CRGs had predictive power for AML, with MTF1, LIAS, SLC31A1 and CDKN2A showing more reliable results. Further analysis showed that ATP7B was closely associated with mutation types such as FLT3, NPM1, RAS and IDH1 R140 in AML, while the expression of MTF1, LIAS and ATP7B in AML was closely associated with immune infiltration. Gene Ontology (GO), Kyoto Encyclopedia of Genes and Genomes (KEGG) and Gene Set Enrichment Analysis (GSEA) revealed that biological functions such as metal ion transmembrane transporter activity, haptoglobin binding and oxygen carrier activity, pathways such as interferon alpha response, coagulation, UV response DN, apoptosis, hypoxia and heme metabolism all play a role in the development of AML. The ceRNA regulatory network revealed that 6 lncRNAs such as MALAT1, interfere with MTF1 expression through 6 miRNAs such as hsa-miR-32-5p, which in turn affect the development and progression of AML. In addition, APTO-253 has the potential to become an AML-targeted drug. The cuproptosis-related genes MTF1 and LIPT1 can be used as prognostic biomarkers in AML. A total of six lncRNAs, including MALAT1, are involved in the expression and regulation of MTF1 in AML through six miRNAs such as hsa-miR-32-5p.

Antibody-antibiotic conjugate targeted therapy for orthopedic implant-associated intracellular S. aureus infections.

INTRODUCTION: Treating orthopedic implant-associated infections, especially those caused by Staphylococcus aureus (S. aureus), remains a significant challenge. S. aureus has the ability to invade host cells, enabling it to evade both antibiotics and immune responses during infection, which may result in clinical treatment failures. Therefore, it is critical to identify the host cell type of implant-associated intracellular S. aureus infections and to develop a strategy for highly targeted delivery of antibiotics to the host cells. OBJECTIVES: Introduced an antibody-antibiotic conjugate (AAC) for the targeted elimination of intracellular S. aureus. METHODS: The AAC comprises of a human monoclonal antibody (M0662) directly recognizes the surface antigen of S. aureus, Staphylococcus protein A, which is conjugated with vancomycin through cathepsin-sensitive linkers that are cleavable in the proteolytic environment of the intracellular phagolysosome. AAC, vancomycin and vancomycin combined with AAC were used in vitro intracellular infection and mice implant infection models. We then tested the effect of AAC in vivo and in vivo by fluorescence imaging, in vivo imaging, bacterial quantitative analysis and bacterial biofilm imaging. RESULTS: In vitro, it was observed that AAC captured extracellular S. aureus and co-entered the cells, and subsequently released vancomycin to induce rapid elimination of intracellular S. aureus. In the implant infection model, AAC significantly improved the bactericidal effect of vancomycin. Scanning electron microscopy showed that the application of AAC effectively blocked the formation of bacterial biofilm. Further histochemical and micro-CT analysis showed AAC significantly reduced the level of bone marrow density (BMD) and bone volume fraction (BV/TV) reduction caused by bacterial infection in the distal femur of mice compared to vancomycin treatment alone. CONCLUSIONS: The application of AAC in an implant infection model showed that it significantly improved the bactericidal effects of vancomycin and effectively blocked the formation of bacterial biofilms, without apparent toxicity to the host.

Interventions to treat patients with blood blister-like aneurysms of the internal carotid artery: a protocol for a network meta-analysis.

INTRODUCTION: Blood blister-like aneurysm (BBA) is a special type of intracranial aneurysm with relatively low morbidity and high mortality. Various microsurgical techniques and endovascular approaches have been reported, but the optimal management remains controversial. For a better understanding of the treatment of BBA patients, a network meta-analysis that comprehensively compares the effects of different therapies is necessary. METHODS AND ANALYSIS: This protocol has been reported following the Preferred Reporting Items for Systematic Review and Meta-Analysis Protocols. Related studies in the following databases will be searched until November 2022: PubMed, Embase, Scopus, Web of Science, Cochrane Library, China National Knowledge Infrastructure (CNKI), VIP and Wanfang. Randomised controlled trials (RCTs) and non-randomised studies comparing at least two different interventions in BBA patients will be included. Quality assessment will be conducted using Cochrane Collaboration's tool or Newcastle-Ottawa Scale based on their study designs. The primary outcome is the composite of the incidences of intraoperative bleeding, postoperative bleeding and postoperative recurrence. The secondary outcome is an unfavourable functional outcome. Pairwise and network meta-analyses will be conducted using STATA V.14 (StataCorp, College Station, Texas, USA). Mean ranks and the surface under the cumulative ranking curve will be used to evaluate every intervention. Statistical inconsistency assessment, subgroup analysis, sensitivity analysis and publication bias assessment will be performed. ETHICS AND DISSEMINATION: Ethics approval is not necessary because this study will be based on publications. The results of this study will be published in a peer-reviewed journal. PROSPERO REGISTRATION NUMBER: CRD42022383699.

Mendelian randomization analysis to analyze the genetic causality between different levels of obesity and different allergic diseases.

BACKGROUND: The causal relationship between obesity and different allergic diseases remains controversial. METHODS: The Two Sample MR package and Phenoscanner database were used to obtain and filter Genome-Wide Association Study (GWAS) data from the Open GWAS database. Mendelian randomization (MR) analysis was used to study the causal relationship between different levels of obesity and different allergic diseases. The data sets related to obesity and asthma were obtained from the Gene Expression Omnibus (GEO) database. Differentially expressed genes (DEGs) were screened by the limma package. Cluster Profiler and GO plot packages were used for enrichment analysis to verify the results of MR analysis. RESULTS: Two-sample MR analysis showed a causal relationship between obesity and childhood allergy (age < 16), allergic asthma and atopic dermatitis (P < 0.05). In addition, there was also a causal relationship between allergic asthma and obesity (P < 0.05), while there was no genetic causal relationship between obesity and allergic rhinitis, eczema, lactose intolerance and so on (P > 0.05). Subgroup analysis revealed a causal relationship between both class 1 and class 2 obesity and childhood allergy (age < 16) (P < 0.05). Obesity class 1 was associated with allergic asthma, while obesity class 3 was associated with atopic dermatitis (P < 0.05). Bioinformatics analysis shows that there were common DEGs between obesity and allergic asthma. CONCLUSION: Obesity is a risk factor for childhood allergy (age < 16), allergic asthma and atopic dermatitis, while allergic asthma is also a risk factor for obesity. Class 1 and class 2 obesity are both causally associated with childhood allergy (age < 16). In addition, there is a causal relationship between milder obesity and allergic asthma, while heavier obesity is causally related to atopic dermatitis.

Rapid and sensitive detection of aqueous ammonia harnessing nanocomposite functionalized tilted fiber Bragg grating.

A high sensitive aqueous ammonia sensor based on tilted fiber Bragg grating (TFBG) had been reported. The sensors were fabricated by a 10 ° TFBG coated by a membrane receptor named as Polyaniline/Graphene oxide on the surface of the fiber. The correlative concentrations of aqueous ammonia were demodulated by global monitoring of the envelope area of cladding modes in the transmitted spectrum of the TFBG. Tests have shown that the proposed sensor can provide a linear and rapid response of aqueous ammonia within 22 seconds, in a concentration range from 1-12 ppm. Moreover, the limit of detection can even reach 0.08 ppm, through the theoretical analysis of our experimental results. The proposed sensor has good performance, is easy to manufacture and of small size, making it a good choice for real-time, in-situ, label-free detection of aqueous ammonia in the future.

Interventions of river network structures on urban aquatic microplastic footprint from a connectivity perspective.

Microplastic footprint in urban river networks can be disturbed by multiple urbanization features, and regional river structures are generally overlooked. In this research, we analyzed the distribution of microplastics and potential impact pattern of river structures on it in a typical urban river network in Nanjing, China. Surface waters of the river network were jointly detected by multiple methods, and the Renkonen similarity index was used to study spatial variabilities of microplastics characteristics. Microplastics were ubiquitous and abundant, showing five (>50 µm) and six (20∼50 µm) hotspots, and heterogeneities in the shape and type of microplastics larger than 100 µm were prominent, presumably influenced by river network scale and connectivity. River structure parameters associated with network connectivity were obtained by combining graph theory and an entropy-based set-pair analysis model. Aiming at the action pathway of river structures, by using correlation and partial least squares regression analysis, we found that river node (confluences and sluices) ratio, river frequency, river network density, and water system circularity were significantly positively correlated with microplastic abundance, and confluences with poor connectivity had a greater indirect intervention intensity on the microplastic distribution. The land use characteristics dominated the fitting of microplastic abundance, which was about 1.2 times better than river structures, and the comprehensive land use intensity and river network connectivity were the critical factors, respectively. Potential ecological risks of microplastics were evaluated, resulting in relatively severe levels. This study proposed targeted measures to control urban microplastic pollution by combining the perspective of river network characteristics. To summarize, our exploration of microplastic footprint based on urban river network structures from the perspective of river network connectivity provides new insights into microplastic management.

Comparison of surgical strategies in patients with chronic subdural haematoma: a protocol for a network meta-analysis.

INTRODUCTION: Chronic subdural haematoma (CSDH) is one of the most common neurosurgical emergencies, especially in the elderly population. Surgery is the mainstay of treatment for CSDH. Some studies have suggested that some specific surgical strategies can have potential benefits for patients with CSDH; however, the best surgical method is still controversial. For a better understanding of surgical treatment for these patients, it is necessary to conduct a network meta-analysis to comprehensively compare the effects of medical treatment and different surgical methods. METHODS AND ANALYSIS: This protocol has been reported following the Preferred Reporting Items for Systematic Review and Meta-Analysis Protocols. Related studies published up to April 2023 will be searched in the following databases: PubMed, Embase, Scopus, Web of Science, the Cochrane Library, China National Knowledge Infrastructure, VIP and Wanfang. Randomised controlled trials and non-randomised prospective studies comparing at least two different interventions for patients with CSDH will be included. Quality assessment will be conducted using Cochrane Collaboration's tool or the Newcastle-Ottawa Scale based on study design. The primary outcome will be the recurrence rates, and the secondary outcome will be the functional outcome at the end of follow-up. Pairwise and network meta-analyses will be conducted using STATA V.14 (StataCorp, College Station, Texas, USA). Mean ranks and the surface under the cumulative ranking curve will be used to evaluate each intervention. Statistical inconsistency assessment, subgroup analysis, sensitivity analysis and publication bias assessment will be performed. ETHICS AND DISSEMINATION: Ethics approval is not necessary because this study will be based on publications. The results of this study will be published in a peer-reviewed journal. PROSPERO REGISTRATION NUMBER: CRD42022376829.

Single-photon ionization induced C-C or C-N bond formation in pyrrole clusters.

The formation of photodimers of nitrogen heterocyclic compounds (NHCs) can partially explain the DNA damage due to radiation. Pyrrole and its derivatives, as major components of DNA, are used to understand the phenomena at the molecular level. With the aid of vacuum ultraviolet (VUV)-infrared (IR) spectroscopy and theoretical calculations, herein, we explore the possibility of the formation of a new C-C or C-N bond in pyrrole (py) clusters in a supersonic jet after single-photon ionization. Both neutral (py)2 and (py)3 clusters are stabilized by multiple interactions, such as N-H⋯π hydrogen bonds and π⋯π interactions. With 118 nm light ionization of the (py)2, we elucidate that the two py are more inclined to be stabilized by a newly formed C-C or C-N covalent bond, besides the π-stacked parallel structure of (py)2+. The (py)3+ with a C-C or C-N covalent bonded (py)2+ core mainly contributes to the IR spectrum of (py)3+. The present results are helpful to elucidate the mechanism of DNA damage at a molecular level.

Parathlasia gen. nov. (Hemiptera, Cicadellidae, Ledrinae, Ledrini), a new leafhopper genus from Guizhou, China.

Parathlasia gen. nov., a new leafhopper genus and species of Ledrini, P.guizhouensis sp. nov., from Guizhou, China are described. Morphological differences between the new genus to other related Chinese genera are discussed. A key to distinguish Parathlasia from other similar genera is given.

Lateral ventricle ectopic schwannoma: Case report and literature review.

Background: Cases of lateral ventricular ectopic schwannomas (LVES) are extremely rare, with only 23 cases reported thus far. This study aimed to obtain a better understanding of the disease. Methods: We reported a rare case of LVES, in which the patient was admitted to our hospital, and reviewed the relevant literature on LVES to summarize and analyze the clinical manifestations, pathologies, imaging features and progress. Results: Of the 23 patients, LVES was more common in men (74%, 17/23) than in women and was mostly located on the right side (78%, 18/23). The average age at clinical presentation was 28 years, with an age range between 8 and 68 years. Moreover, most cases were histologically benign, except in one case of malignancy. In all the benign cases, there were 2 cases of subtotal resection, but no recurrence was found during follow-up. Conclusions: The origin of LVES could be the tumor transformation of autonomic nerve tissue in the perivascular choroid plexus. For lateral ventricle tumors,which are rare benign lesions with good prognosis after surgical resection, LVES should be considered in the differential diagnosis. Moreover, whether LVES could be considered for gamma knife treatment, similar to a small acoustic neuromas,requires further investigation.

Simultaneous measurement of axial strain and temperature based on a twin-core single-hole fiber with the optical Vernier effect.

An ultrasensitive optical fiber sensor based on the optical Vernier effect is proposed for the simultaneous measurement of axial strain and temperature. The sensor structure comprises two cascaded Mach-Zehnder interferometers (MZIs) with different free space ranges. The single MZI is built up by fusion splicing a segment of ∼3 mm twin-core single-hole fiber (TCSHF) between two pieces of ∼5 mm none core fibers (NCF). When acting separately, each MZI can respond linearly to the axial strain change with a sensitivity of ∼ 0.6 pm/µÎµ and temperature with a sensitivity of ∼34 pm/°C. When the two MZIs are cascaded in series, the sensitivities are amplified about 30 times because of the optical Vernier effect. Experimental results demonstrate that the cascaded structure exhibits a high axial strain sensitivity of ∼ 17 pm/µÎµ in the range of 0 to 2000 µÎµ and temperature sensitivity of ∼1.16 nm/°C in the range of 30 to 70 °C. Moreover, the cascaded structure can simultaneously measure the axial strain and temperature change in the acceptable error ranges.

A high neutrophil-to-platelet ratio is associated with hematoma expansion in patients with spontaneous intracerebral hemorrhage: a retrospective study.

BACKGROUND: Early hematoma expansion (HE) occurs in 20 to 40% of spontaneous intracerebral hemorrhage (ICH) patients and is a primary determinant of early deterioration and poor prognosis. Previous studies have shown that inflammation is a major pathological feature of ICH, and the neutrophil-to-platelet ratio (NPR) is a marker of systemic inflammation. Therefore, we aimed to assess the association between the NPR and HE in ICH patients. METHODS: We retrospectively collected and analyzed data from ICH patients who received treatment at our institution from January 2018 to November 2019. The NPR was calculated from the admission blood test. Brain computed tomography (CT) scans were performed at admission and repeated within 24 h. Hematoma growth was defined as relative growth > 33% or absolute growth > 6 ml. RESULTS: A total of 317 patients were enrolled in our study. Multivariate logistic regression analysis indicated that the NPR was an independent predictor of HE [odds ratio (OR) = 1.742; 95% CI: 1.508-2.012, p < 0.001]. Receiver operating characteristic (ROC) curve analysis revealed that the NPR could predict HE, with an area under the curve of 0.838 (95% CI, 0.788-0.888, p < 0.001). The best predictive cut-off of the NPR for HE was 5.47 (sensitivity, 75.3%; specificity, 77.6%). CONCLUSIONS: A high NPR was associated with an increased risk of HE in patients with ICH.

New insights into the decrease in Cd2+ bioavailability in sediments by microplastics: Role of geochemical properties.

Microplastics (MPs) are considered to influence the bioavailability of heavy metals through direct adsorption, but this neglects the distribution of heavy metal chemical speciation indirectly influenced by MPs by altering geochemical properties. The present study aims to explore the link between the fractionation distribution of cadmium (Cd2+) and changes in geochemical properties in sediments induced by polyethylene terephthalate microplastics (PET-MPs). The PET-MPs reduced the acid-soluble fraction of Cd2+ in sediments and increased its organically bound fraction. In addition, the concentration of bioavailable Cd2+ in the sediment decreased by 4.09-25.96 % with increasing PET-MPs doses and aging. Whereas the thermal aging of PET-MPs led to a decrease in the molar ratio of oxygen-containing functional groups and the BET surface area, which is not favorable for improving the adsorption capacity of PET-MPs. On the other hand, the correlation analysis demonstrated the key role of PET-MPs in increasing the content of sediment organic matter and its humification level, which indirectly led to a decrease in Cd2+ bioavailability. The microbial analysis demonstrated that PET-MPs increase the relative abundances of Chloroflexi, hexokinase, and 6-phosphofructose kinase in sediments, thereby increasing the humification level of sediment organic matter. The present study provides a new perspective for understanding the environmental risks of MPs-altered heavy metals.

Machine learning algorithms for integrating clinical features to predict intracranial hemorrhage in patients with acute leukemia.

BACKGROUND: Intracranial hemorrhage (ICH) in acute leukemia (AL) patients leads to high morbidity and mortality, treatment approaches for ICH are generally ineffective. Thus, early identification of which subjects are at high risk of ICH is of key importance. Currently, machine learning can achieve well predictive capability through constructing algorithms that simultaneously exploit the information coming from clinical features. METHODS: After rigid data preprocessing, 42 different clinical features from 948 AL patients were used to train different machine learning algorithms. We used the feature selection algorithms to select the top 10 features from 42 clinical features. To test the performance of the machine learning algorithms, we calculated area under the curve (AUC) values from receiver operating characteristic (ROC) curves along with 95% confidence intervals (CIs) by cross-validation. RESULTS: With the 42 features, RF exhibited the best predictive power. After feature selection, the top 10 features were international normalized ratio (INR), prothrombin time (PT), creatinine (Cr), indirect bilirubin (IBIL), albumin (ALB), monocyte (MONO), platelet (PLT), lactic dehydrogenase (LDH), fibrinogen (FIB) and prealbumin (PA). Among the top 10 features, INR, PT, Cr, IBIL and ALB had high predictive performance with an AUC higher than 0.8 respectively. CONCLUSIONS: The RF algorithm exhibited a higher cross-validated performance compared with the classical algorithms, and the selected important risk features should help in individualizing aggressive treatment in AL patients to prevent ICH. Efforts that will be made to test and optimize in independent samples will warrant the application of such algorithm and predictors in the future.