Targeting DNA junction sites by bis-intercalators induces topological changes with potent antitumor effects.

Targeting inter-duplex junctions in catenated DNA with bidirectional bis-intercalators is a potential strategy for enhancing anticancer effects. In this study, we used d(CGTATACG)2, which forms a tetraplex base-pair junction that resembles the DNA-DNA contact structure, as a model target for two alkyl-linked diaminoacridine bis-intercalators, DA4 and DA5. Cross-linking of the junction site by the bis-intercalators induced substantial structural changes in the DNA, transforming it from a B-form helical end-to-end junction to an over-wounded side-by-side inter-duplex conformation with A-DNA characteristics and curvature. These structural perturbations facilitated the angled intercalation of DA4 and DA5 with propeller geometry into two adjacent duplexes. The addition of a single carbon to the DA5 linker caused a bend that aligned its chromophores with CpG sites, enabling continuous stacking and specific water-mediated interactions at the inter-duplex contacts. Furthermore, we have shown that the different topological changes induced by DA4 and DA5 lead to the inhibition of topoisomerase 2 activities, which may account for their antitumor effects. Thus, this study lays the foundations for bis-intercalators targeting biologically relevant DNA-DNA contact structures for anticancer drug development.

Zbtb16 increases susceptibility of atrial fibrillation in type 2 diabetic mice via Txnip-Trx2 signaling.

Atrial fibrillation (AF) is the most prevalent sustained cardiac arrhythmia, and recent epidemiological studies suggested type 2 diabetes mellitus (T2DM) is an independent risk factor for the development of AF. Zinc finger and BTB (broad-complex, tram-track and bric-a-brac) domain containing 16 (Zbtb16) serve as transcriptional factors to regulate many biological processes. However, the potential effects of Zbtb16 in AF under T2DM condition remain unclear. Here, we reported that db/db mice displayed higher AF vulnerability and Zbtb16 was identified as the most significantly enriched gene by RNA sequencing (RNA-seq) analysis in atrium. In addition, thioredoxin interacting protein (Txnip) was distinguished as the key downstream gene of Zbtb16 by Cleavage Under Targets and Tagmentation (CUT&Tag) assay. Mechanistically, increased Txnip combined with thioredoxin 2 (Trx2) in mitochondrion induced excess reactive oxygen species (ROS) release, calcium/calmodulin-dependent protein kinase II (CaMKII) overactivation, and spontaneous Ca2+ waves (SCWs) occurrence, which could be inhibited through atrial-specific knockdown (KD) of Zbtb16 or Txnip by adeno-associated virus 9 (AAV9) or Mito-TEMPO treatment. High glucose (HG)-treated HL-1 cells were used to mimic the setting of diabetic in vitro. Zbtb16-Txnip-Trx2 signaling-induced excess ROS release and CaMKII activation were also verified in HL-1 cells under HG condition. Furthermore, atrial-specific Zbtb16 or Txnip-KD reduced incidence and duration of AF in db/db mice. Altogether, we demonstrated that interrupting Zbtb16-Txnip-Trx2 signaling in atrium could decrease AF susceptibility via reducing ROS release and CaMKII activation in the setting of T2DM.

From Monomers to Hexamers: A Theoretical Probability of the Neighbor Density Approach to Dissect Protein Oligomerization in Cells.

Deciphering the oligomeric state of proteins within cells is pivotal to understanding their role in intricate cellular processes. With the recent advances in single-molecule localization microscopy, previous efforts have harnessed protein location density approaches, coupled with simulations, to extract membrane protein oligomeric states in cells, highlighting the value of such techniques. However, a comprehensive theoretical approach that can be universally applied across different proteins (e.g., membrane and cytosolic proteins) remains elusive. Here, we introduce the theoretical probability of neighbor density (PND) as a robust tool to discern protein oligomeric states in cellular environments. Utilizing our approach, the theoretical PND was validated against simulated data for both membrane and cytosolic proteins, consistently aligning with experimental baselines for membrane proteins. This congruence was maintained even when adjusting for protein concentrations or exploring proteins of various oligomeric states. The strength of our method lies not only in its precision but also in its adaptability, accommodating diverse cellular protein scenarios without compromising the accuracy. The development and validation of the theoretical PND facilitate accurate protein oligomeric state determination and bolster our understanding of protein-mediated cellular functions.

Banff-based histologic chronicity index is associated with graft failure but has poor interobserver reproducibility.

BACKGROUND: Antibody-mediated rejection (AMR) often leads to chronic kidney allograft damage and is a critical cause of allograft failure. The Banff classification, used to diagnose AMR, has become complex and challenging for clinicians. A Banff-based histologic chronicity index (CI) was recently proposed as a simplified prognostic indicator. Its reliability and reproducibility have not been externally validated. METHODS: This study investigated 71 kidney allograft biopsies diagnosed with AMR. Interobserver reproducibility of the recently proposed CI and its components (cg, cv, ct, and ci) were assessed. The association between CI and allograft failure was analyzed, and CI cut-off values were evaluated by Cox proportional hazards regression and Kaplan-Meier estimator with log-rank test. RESULTS: The study confirmed the association of CI with allograft failure, but also revealed that the assessment of CI varied between pathologists, impacting its reproducibility as a prognostic tool. Only 49 (69.0%) of the biopsies showed complete agreement on the proposed cut-off value of CI < 4 or CI ≥ 4. Furthermore, this cut-off did not reliably stratify allograft failure. Notably, the cg score, which carries significant weight in the CI calculation, had the lowest agreement between observers (kappa = .281). CONCLUSIONS: While a simplified prognostic indicator for AMR is needed, this study highlights the limitations of CI, particularly its poor interobserver reproducibility. Our findings suggest that clinicians should interpret CI cautiously and consider establishing their own cut-off values. This study underscores the need to address interobserver reproducibility before CI can be widely adopted for AMR management.

Hepatic and Extrahepatic Characteristics of Autoimmune Hepatitis: A 23-year Hospital-Based Cohort Study.

BACKGROUND: The characteristics of autoimmune hepatitis (AIH) in Asia mostly remain elusive. METHODS: A cohort study of liver biopsy-proven AIH patients was conducted in a tertiary care cancer of Taiwan. RESULTS: From 1999 to 2022, of 13,766 patients who underwent liver biopsy, 150 patients with AIH were enrolled. The female-to-male ratio was 2.26. At baseline, the mean age was 51.09 years, mean alanine aminotransferase level was 494.11 U/L, and 17 (11.3%) had cirrhosis. All except one patient had AIH type 1. The females were older and had higher baseline cirrhosis rates than did the males. The 23-year cumulative incidences of cirrhosis, hepatocellular carcinoma (HCC), mortality/liver transplantation, autoimmune diseases and extrahepatic cancer were 64.2%, 13.3%, 23.4%, 30.7% and 21.2%, respectively. The 1-year, 2-year, 3-year, 5-year, 10-year and 20-year postimmunosuppressive therapy relapse rates were 60%, 78.2%, 81.8%, 89.1%, 94.5% and 100%, respectively. Baseline associations were as follows: alkaline phosphatase (Alk-p) levels with postimmunosuppressive therapy flare [hazard ratio (HR): 1.003; 95% CI HR: 1.000-1.005]; age with HCC (1.072; 1.010-1.138) and all-cause cancer (1.041;1.005-1.079); cirrhosis with mortality/liver transplantation (11.933;1.984-71.787); and antinuclear antibody (ANA) titers with mortality/liver transplantation (1.001;1.000-1.003), cirrhosis (1.001;1.000-1.002), and autoimmune diseases (1.001; 1.000-1.002). CONCLUSION: In an Asian country endemic for viral hepatitis, the female-to-male and baseline cirrhosis rates of AIH patients were lower than expected, while over 60% of the patients eventually developed cirrhosis. The high posttherapy relapse rate warrants cautious monitoring, particularly for patients with high baseline Alk-p levels. Baseline age, cirrhosis status and ANA titers are crucial for outcomes.

Exploring the key elements for the successful management of primary otolaryngologic clinics in Taiwan.

AIM: This study aims to investigate the key elements for successful operation and management of primary otolaryngologic clinics in Taiwan amidst a declining birth rate and increasing competition among clinics. It employs the Innovation Through Tradition (ITT) theory as a theoretical framework to develop an operational model for effective management strategies. METHODS: This research utilized the triangulation method to identify key elements crucial for the operation and management of primary otolaryngologic clinics. Five key elements were identified, namely service attitude, medication efficacy, diagnostic and treatment procedures, treatment costs, and operating hours. Outpatient satisfaction was analyzed using Donabedian's structure-process-outcomes model to assess the impact of these elements on patient experience. RESULTS: Analysis revealed that service attitude significantly influences outpatient visits, indicating its paramount importance in clinic management. Patient satisfaction was highest in the service outcome dimension, emphasizing the significance of effective treatment outcomes. However, satisfaction was lowest in the service structure dimension, indicating potential areas for improvement in clinic infrastructure and organization. CONCLUSION: Understanding these key elements and enhancing outpatient satisfaction can drive improvements in the quality of medical services, contributing to the overall success of primary otolaryngologic clinics.

Radiomics analysis for the prediction of locoregional recurrence of locally advanced oropharyngeal cancer and hypopharyngeal cancer.

PURPOSE: By radiomic analysis of the postcontrast CT images, this study aimed to predict locoregional recurrence (LR) of locally advanced oropharyngeal cancer (OPC) and hypopharyngeal cancer (HPC). METHODS: A total of 192 patients with stage III-IV OPC or HPC from two independent cohort were randomly split into a training cohort with 153 cases and a testing cohort with 39 cases. Only primary tumor mass was manually segmented. Radiomic features were extracted using PyRadiomics, and then the support vector machine was used to build the radiomic model with fivefold cross-validation process in the training data set. For each case, a radiomics score was generated to indicate the probability of LR. RESULTS: There were 94 patients with LR assigned in the progression group and 98 patients without LR assigned in the stable group. There was no significant difference of TNM staging, treatment strategies and common risk factors between these two groups. For the training data set, the radiomics model to predict LR showed 83.7% accuracy and 0.832 (95% CI 0.72, 0.87) area under the ROC curve (AUC). For the test data set, the accuracy and AUC slightly declined to 79.5% and 0.770 (95% CI 0.64, 0.80), respectively. The sensitivity/specificity of training and test data set for LR prediction were 77.6%/89.6%, and 66.7%/90.5%, respectively. CONCLUSIONS: The image-based radiomic approach could provide a reliable LR prediction model in locally advanced OPC and HPC. Early identification of those prone to post-treatment recurrence would be helpful for appropriate adjustments to treatment strategies and post-treatment surveillance.

From Molecules to Classrooms: A Comprehensive Guide to Single-Molecule Localization Microscopy.

Single-molecule localization microscopy (SMLM) has revolutionized our ability to visualize cellular structures, offering unprecedented detail. However, the intricate biophysical principles that underlie SMLM can be daunting for newcomers, particularly undergraduate and graduate students. To address this challenge, we introduce the fundamental concepts of SMLM, providing a solid theoretical foundation. In addition, we have developed an intuitive graphical interface APP that simplifies these core concepts, making them more accessible for students. This APP clarifies how super-resolved images are fitted and highlights the crucial factors determining image quality. Our approach deepens students' understanding of SMLM by combining theoretical instruction with practical learning. This development equips them with the skills to carry out single-molecule super-resolved experiments and explore the microscopic world beyond the diffraction limit.

Factors associated with postoperative efficacy evaluation in patients with morbid obesity.

The global obesity problem is becoming increasingly serious, with eight of the top ten causes of death in Taiwan in 2020 being related to obesity. Morbid obesity poses a significant threat to one's health and well-being. In recent years, bariatric surgery has emerged as a more effective treatment option for patients with morbid obesity. However, the procedure is not without risks. This study aims to examine the factors that impact the postoperative efficacy evaluation of patients with morbid obesity. This study uses a retrospective cross-sectional design, with medical records being collected retrospectively. The data was collected from patients who underwent bariatric surgery between July 1, 2017 and June 30, 2020 at a hospital in southern Taiwan. A total of 663 patients were included in the study and were observed for 1 year after the surgery. The independent variables included demographic variables, perceived symptoms variables, perceived lifestyle variables, and surgery-related variables, while the dependent variables included weight loss outcomes and complications. The prognostic factors affecting the postoperative efficacy evaluation of patients with pathological obesity were determined using multiple regression analysis and binary regression analysis. The study found that 65.6% of the participants were female, with an average age of 36.8 years. The results of the multiple regression and binary logistic regression showed that gender, age, BMI, diabetes, and smoking habit were the predictors of postoperative weight loss. Hypertension, diabetes, liver disease, kidney disease, smoking habit, drinking habit, and operation time were the predictors of postoperative complications. The study found that the presence of the aforementioned 12 significant factors can affect the success of weight loss after surgery and the incidence of postoperative complications. This information can serve as a reference for clinical care institutions and patients to improve the postoperative efficacy evaluation.

Developing the procedure-enhanced model of ginger-infused sesame oil based on its flavor and functional properties.

Ginger-infused sesame oil enriches the nutrition and provides enhanced flavor for the foods. An original processing procedure and module for evaluation were established in this study, using different raw materials (Guangdong and Chu ginger) and treatments (ginger powder, extract, and both). The quality, functionality, and flavor of the infused oils were evaluated. Ginger-infused sesame oil contained 0.58-3.22 µg/g of 6-gingerol, 0.21-0.88 µg/g of 6-shogaol. The number range of volatile compounds from 48 to 55 identified by gas chromatography-mass spectrometry varies depending on different process procedures. Agglomerative hierarchical clustering analysis revealed the flavor profiles were clustered by different varieties, while gingerol and phytosterol was by different treatments. In conclusion, sesame oil was an appropriate carrier for gingerol and phytosterol, which are characterized by higher antioxidant capacities (p < 0.05). These results show the benefits of developing infused oil products with enhanced functional and sensory properties.

Heparin-Binding Protein Promotes Acute Lung Injury in Sepsis Mice by Blocking the Aryl Hydrocarbon Receptor Signaling Pathway.

Purpose: This study aimed to explore the therapeutic effect and potential mechanism of heparin-binding protein (HBP) reduction on sepsis-related acute lung injury. Methods: We utilized a murine model of sepsis-induced by intraperitoneal injection of lipopolysaccharides (LPS) in C57BL/6J mice divided into four groups: Control, LPS, Anti-HBP, and ceftriaxone (CEF). Following sepsis induction, Anti-HBP or CEF treatments were administered, and survival rates were monitored for 48 h. We then used reverse-transcription quantitative PCR to analyze the expression levels of HBP in lung tissues, immunohistochemistry for protein localization, and Western blotting for protein quantification. Pulmonary inflammation was assessed using enzyme-linked immunosorbent assays of proinflammatory cytokines (tumor necrosis factor-α, interleukin [IL]-1ß, IL-6, and interferon-γ). The activation state of the aryl hydrocarbon receptor (AhR) signaling pathway was determined via Western blotting, evaluating both cytoplasmic and nuclear localization of AhR and the expression of cytochrome P450 1A1 protein by its target gene. Results: Anti-HBP specifically reduced HBP levels. The survival rate of mice in the Anti-HBP and CEF groups was much higher than that in the LPS group. The severity of lung injury and pulmonary inflammatory response in the Anti-HBP and CEF groups was significantly lower than that in the LPS group. AhR signaling pathway activation was observed in the Anti-HBP and CEF groups. Additionally, there was no significant difference in the above indices between the Anti-HBP and CEF groups. Conclusion: HBP downregulation in lung tissues significantly improved LPS-induced lung injury and the pulmonary inflammatory response, thereby prolonging the survival of sepsis mice, suggesting activation of the AhR signaling pathway. Moreover, the effect of lowering the HBP level was equivalent to that of the classical antibiotic CEF. Trial Registration: Not applicable.

Presentation of glomerulocystic disease in a young onset diabetes: A case report.

RATIONALE: This case report presents a challenging medical scenario involving a young adult male who exhibited an unusual combination of symptoms, including abrupt weight loss, declining renal function, proteinuria, and concurrent onset of diabetes mellitus. Remarkably, the patient had no previous medical history or family history of similar conditions, necessitating a comprehensive investigation. PATIENT CONCERNS: On March 10, 2021, a 25-year-old male sought medical attention due to the aforementioned symptoms. Initial assessments revealed stage 5 chronic kidney disease, with elevated blood urea nitrogen (BUN) and serum creatinine (Cr) levels, as well as significant proteinuria. The only notable physical finding was obesity, and renal ultrasound showed normal-sized kidneys without cysts. DIAGNOSIS: A treatment plan was initiated to stabilize creatinine levels, including medications such as Glimepiride, Glyxambi, Bisoprolol, Amlodipine, and Valsartan. However, despite diligent medication management, proteinuria persisted, prompting further evaluation. A renal biopsy was performed on April 12th, 2023, leading to the diagnosis of glomerulocystic kidney disease with early-stage changes indicative of diabetic nephropathy. INTERVENTIONS: The patient continues to receive ongoing care and follow-up at our outpatient clinic to optimize therapeutic interventions and elucidate the underlying etiology of this complex clinical scenario. OUTCOMES: Ongoing investigations and therapeutic interventions are crucial to understand the underlying cause and optimize patient care in this intricate clinical scenario. LESSONS: This case underscores the complexity of diagnosing and managing a young adult presenting with concurrent renal dysfunction, proteinuria, and diabetes mellitus in the absence of prior underlying conditions. It highlights the importance of comprehensive evaluation and ongoing care in such challenging cases.

Integrating OpenPose and SVM for Quantitative Postural Analysis in Young Adults: A Temporal-Spatial Approach.

Noninvasive tracking devices are widely used to monitor real-time posture. Yet significant potential exists to enhance postural control quantification through walking videos. This study advances computational science by integrating OpenPose with a Support Vector Machine (SVM) to perform highly accurate and robust postural analysis, marking a substantial improvement over traditional methods which often rely on invasive sensors. Utilizing OpenPose-based deep learning, we generated Dynamic Joint Nodes Plots (DJNP) and iso-block postural identity images for 35 young adults in controlled walking experiments. Through Temporal and Spatial Regression (TSR) models, key features were extracted for SVM classification, enabling the distinction between various walking behaviors. This approach resulted in an overall accuracy of 0.990 and a Kappa index of 0.985. Cutting points for the ratio of top angles (TAR) and the ratio of bottom angles (BAR) effectively differentiated between left and right skews with AUC values of 0.772 and 0.775, respectively. These results demonstrate the efficacy of integrating OpenPose with SVM, providing more precise, real-time analysis without invasive sensors. Future work will focus on expanding this method to a broader demographic, including individuals with gait abnormalities, to validate its effectiveness across diverse clinical conditions. Furthermore, we plan to explore the integration of alternative machine learning models, such as deep neural networks, enhancing the system's robustness and adaptability for complex dynamic environments. This research opens new avenues for clinical applications, particularly in rehabilitation and sports science, promising to revolutionize noninvasive postural analysis.

Efficacy evaluation of a bivalent subunit vaccine against classical swine fever virus and porcine circovirus type 2.

Classical swine fever virus (CSFV) and porcine circovirus type 2 (PCV2) are two of the most devastating and economically significant pathogens affecting pig populations worldwide. Administration of a combination of vaccines against swine pathogens has been demonstrated to be as efficacious as the administration of single vaccines. In this study, we developed and tested a novel bivalent subunit vaccine against CSFV and PCV2. The safety and efficacy of this vaccine were demonstrated in mice and specific pathogen-free (SPF) piglets. In addition to investigating the serological responses after immunization, challenge studies with both viruses were also conducted. The results showed that this CSFV/PCV2 bivalent vaccine elicited a high level of neutralizing antibodies against both viruses and provided protection in challenge studies. In conclusion, the CSFV/PCV2 bivalent vaccine is safe and effective against CSFV or PCV2 challenge.

[Comparison of the Prognostic Value of C-Reactive Protein to Albumin Ratio and Glasgow Prognostic Score in Patients with Diffuse Large B-Cell Lymphoma].

OBJECTIVE: To compare the prognostic value of two predictive models based on C-reactive protein (CRP) and albumin (ALB), namely the CRP to ALB ratio (CAR) and the Glasgow prognostic score (GPS), in newly diagnosed patients with diffuse large B-cell lymphoma (DLBCL). METHODS: The data of newly diagnosed DLBCL patients admitted to our center from May 2014 to January 2022 were reviewed. A total of 111 patients who completed at least 4 cycles of R-CHOP or R-CHOP-like chemotherapy with detailed clinical, laboratory data and follow-up information were included. The receiver operating characteristic (ROC) curve was performed to evaluate the predictive value of pre-treatment CAR on disease progression and survival. Furthermore, the association between CAR and baseline clinical, laboratory characteristics of patients was evaluated, and progression-free survival (PFS) and overall survival (OS) were compared between different CAR and GPS subgroups. Finally, the univariate and multivariate COX propor-tional hazard regression models were used to analyze the factors affecting disease outcomes. RESULTS: ROC curve showed that the area under the curve (AUC) of CAR predicting PFS and OS in DLBCL patients was 0.687 (P =0.002) and 0.695 (P =0.005), respectively, with the optimal cut-off value of 0.11 for both predicting PFS and OS. Compared with the lower CAR (<0.11) group, the higher CAR (≥0.11) group had more clinical risk factors, including age >60 years (P =0.025), ECOG score ≥2 (P =0.004), Lugano stage III-IV (P < 0.001), non-germinal center B-cell-like (non-GCB) subtype (P =0.035), elevated lactate dehydrogenase (LDH) ( P < 0.001), extranodal involved site >1 (P =0.004) and IPI score >2 (P < 0.001). The interim response evaluation of patients showed that the overall response rate (ORR) and complete response rate (CRR) in the lower CAR group were both significantly better than those in the higher CAR group (ORR: 96.9% vs 80.0%, P =0.035; CRR: 63.6% vs 32.5%, P =0.008). With a median follow-up of 24 months, patients with lower CAR had significantly longer median PFS and OS than those with higher CAR (median PFS: not reached vs 67 months, P =0.0026; median OS: not reached vs 67 months, P =0.002), while there was no statistical difference in PFS (P =0.11) and OS (P =0.11) in patients with GPS of 0, 1, and 2. Multivariate Cox regression analysis indicated that only sex (male) and IPI score >2 were independent risk factors for both PFS and OS. CONCLUSION: CAR is significantly correlated with disease progression and survival in DLBCL patients; And compared with GPS, CAR has more advantages in predicting disease outcomes in DLBCL patients.

Advancements and Practical Considerations for Biophysical Research: Navigating the Challenges and Future of Super-resolution Microscopy.

The introduction of super-resolution microscopy (SRM) has significantly advanced our understanding of cellular and molecular dynamics, offering a detailed view previously beyond our reach. Implementing SRM in biophysical research, however, presents numerous challenges. This review addresses the crucial aspects of utilizing SRM effectively, from selecting appropriate fluorophores and preparing samples to analyzing complex data sets. We explore recent technological advancements and methodological improvements that enhance the capabilities of SRM. Emphasizing the integration of SRM with other analytical methods, we aim to overcome inherent limitations and expand the scope of biological insights achievable. By providing a comprehensive guide for choosing the most suitable SRM methods based on specific research objectives, we aim to empower researchers to explore complex biological processes with enhanced precision and clarity, thereby advancing the frontiers of biophysical research.

Correlation of Disease Severity, Proinflammatory Cytokines, and Reduced Brain Gray Matter Volumes in Patients with Atopic Dermatitis.

Background: Atopic dermatitis (AD) is a chronic inflammatory skin disease. However, few studies have investigated brain changes associated with chronic inflammation. We hypothesized that chronic inflammation might be related to brain structural alterations in patients with AD. Objectives: To investigate the association between disease severity (Eczema Area and Severity Index [EASI]), proinflammatory cytokines, and differences in brain gray matter (GM) volume in patients with AD. Methods: Nineteen patients with AD and 19 age- and sex-matched healthy subjects were enrolled. All participants underwent clinical assessment and brain magnetic resonance imaging. Voxel-based morphometry was performed to analyze GM volume differences. Results: Patients with AD exhibited significantly decreased GM volume in many brain regions, such as bilateral precentral gyrus, right frontal pole, and right middle temporal gyrus (P < 0.001), compared with healthy subjects. Notably, in patients with AD, the GM volume in right middle temporal gyrus was negatively associated with both EASI score and proinflammatory cytokines (sIL-2R [soluble interleukin 2 receptor] and TNF-α receptor-1), whereas the GM volume in left precentral gyrus was negatively associated with both EASI score and proinflammatory cytokines (sIL-2R and CRP). Conclusion: Patients with AD demonstrated significant brain GM volume reduction in many brain regions, which is related to disease severity and proinflammatory cytokines.

Machine-learning models are superior to severity scoring systems for the prediction of the mortality of critically ill patients in a tertiary medical center.

BACKGROUND: Intensive care unit (ICU) mortality prediction helps to guide therapeutic decision making for critically ill patients. Several scoring systems based on statistical techniques have been developed for this purpose. In this study, we developed a machine-learning model to predict patient mortality in the very early stage of ICU admission. METHODS: This study was performed with data from all patients admitted to the intensive care units of a tertiary medical center in Taiwan from 2009 to 2018. The patients' comorbidities, co-medications, vital signs, and laboratory data on the day of ICU admission were obtained from electronic medical records. We constructed random forest and extreme gradient boosting (XGBoost) models to predict ICU mortality, and compared their performance with that of traditional scoring systems. RESULTS: Data from 12,377 patients was allocated to training (n = 9901) and testing (n = 2476) datasets. The median patient age was 70.0 years; 9210 (74.41%) patients were under mechanical ventilation in the ICU. The areas under receiver operating characteristic curves for the random forest and XGBoost models (0.876 and 0.880, respectively) were larger than those for the Acute Physiology and Chronic Health Evaluation II score (0.738), Sequential Organ Failure Assessment score (0.747), and Simplified Acute Physiology Score II (0.743). The fraction of inspired oxygen on ICU admission was the most important predictive feature across all models. CONCLUSION: The XGBoost model most accurately predicted ICU mortality and was superior to traditional scoring systems. Our results highlight the utility of machine learning for ICU mortality prediction in the Asian population.